KR20060122814A - System for monitoring and managing body weight and other physiological conditions including iterative and personalized planning, intervention and reporting capability - Google Patents

Abstract

A nutrition and activity management system is disclosed that monitors energy expenditure of an individual through the use of a body-mounted sensing apparatus (10). The apparatus is particularly adapted for continuous wear. The system is also adaptable or applicable to measuring a number of other physiological parameters and reporting the same and derivations of such parameters. A weight management embodiment is directed to achieving an optimum or pre-selected energy balance between calories consumed and energy expended by the user. An adaptable computerized nutritional tracking system is utilized to obtain data regarding food consumed. Relevant and predictive feedback is provided to the user regarding the mutual effect of the user's energy expenditure, food consumption and other measured or derived or manually input physiological contextual parameters upon progress toward said goal.

Description

SYSTEM FOR MONITORING AND MANAGING BODY WEIGHT AND OTHER PHYSIOLOGICAL CONDITIONS INCLUDING ITERATIVE AND PERSONALIZED PLANNING, INTERVENTION AND REPORTING CAPABILITY}

The present invention relates to a weight control system. More specifically, the system can be used as part of a behavior modification program for calorie control, weight control or general fitness. In particular, the invention according to one aspect relates to an apparatus used in connection with a software program for monitoring calorie consumption and / or calorie consumption of an individual. The invention also relates to a method of tracking to a weight target.

Studies show that many important health problems in society are caused, in whole or in part, by unhealthy lifestyles. Increasingly, our society requires people to go to a fast-paced, fulfilling lifestyle that prevents people from finding bad eating habits, high stress levels, lack of exercise, bad sleep habits, and time to concentrate and relax. Recognizing this, people are increasingly interested in creating a healthier lifestyle.

Traditional medicines implemented in the form of HMOs or similar instruments do not have a reward mechanism, training, or time to express the needs of individuals interested in a healthier lifestyle. Many attempts have been made to meet individual needs, including the spread of fitness programs and exercise equipment, diet plans, self-help booklets, alternative therapies, and, most recently, the overabundance of health information websites on the Internet. . Each of these attempts is aimed at recharging and empowering individuals. However, each of these attempts only addresses in part the needs of individuals seeking a healthier lifestyle and ignores many of the real barriers that most individuals face when trying to adopt a healthier lifestyle. These barriers include the fact that an individual is sometimes left alone (or her) in implementing a plan to find motivation, achieving a healthier lifestyle, monitoring progress, and brainstorming solutions when problems arise; The fact that exercise programs are directed at only one aspect of a healthier lifestyle and do not come collectively; And sometimes not recommended for the specific characteristics of the individual or his or her living environment.

In weight loss, in particular, many medical and other commercial methods have been developed to assist individuals to reduce excess weight and maintain appropriate weight levels through various diet, exercise, and behavior modification techniques. A weight monitor is an example of a weight loss behavior modification system in which a person manages weight loss by a point system using commercially available food. Every food item is assigned a specific number of points based on serving the size and content of fat, fiber and calories. Fatty foods are assigned a higher number of points. High fiber foods receive a lower number of points. Healthier foods are usually assigned a lower number of points, leading users to eat these food items.

The user is assigned a main point range that represents the total amount of food that must be consumed daily. Instead of keeping the user away from forbidden food, the user is encouraged to enjoy all foods as long as they fit within the user's point budget. The program is based on calorie reduction, potion control and modification of current eating habits. Exercise activities are also assigned points that are subtracted from points accumulated by the user's daily calorie intake.

Weight monitors allow users to create a balance between exercise and healthy eating in their lives. However, because only calorie values of food are specifically tracked, the program tends to fail to inform the user about nutritional changes that the user must make to maintain weight loss. Calories are not the only measure you need to control when deciding what food items to consume. Items containing the same calorie amount may not be nutritionally identical. It is important to note that the weight monitor program essentially deals with calorie intake and not calorie consumption.

Similarly, Jenny Craig is also a weight loss program. Usually, individuals are assigned a personal consultant who monitors the weight loss progress. In addition, the individual will receive a preselected menu based on food guide parameters for balanced nutrition. The menu includes a Jenny Craig brand food item that is delivered to any other location selected by the individual or to the individual's home. The Jenny Craig program presents potion control because the food item to be consumed is preconfigured and supplied by Jenny Craig. However, such close diet monitoring can be problematic once the diet is over because the diet plan does not teach the value of a new diet or exercise. Instead it focuses on short-term weight loss goals.

The integration of computer and diet tracking systems has created new and new automated approaches for weight loss. Useful methods can be tailored to meet specific physiological specific and weight loss goals of an individual.

The subject of Balancelog and US Application Publication No. 20020133378, developed by HealthTech, Inc., is a software program that provides a system for daily tracking and monitoring calorie intake and consumption. The user personalizes the program based on metabolic rate in addition to weight and nutritional goals. In addition to tracking progress, a user can create both exercise and nutritional plans. However, the balance log system has a plurality of limitations.

First, the user must know the resting metabolic rate, the number of calories burned at rest. The user can measure their resting metabolic rate. However, more accurate metabolic rate can be measured by appointment at the metabolic measurement site. A typical individual, particularly an individual beginning a weight and nutritional management plan, may feel uncomfortable with these needs. The system can provide an estimated resting metabolic rate based on a wide range of poppullation averages if more accurate measurements cannot be made. However, this resting metabolic rate can vary widely among individuals with similar physiological properties. Thus, the estimate cannot be accurate and affects the future projection of the individual's progress.

Second, the system is limited by user interaction and compliance. All aspects of the Balancelog system are passive. Every item you eat and any exercise you do should be logged in the system. If the user fails this, the reported progress will not be accurate. The manual data entry required by this balancelog assumes that the user will be closest to a data input device, such as a personal digital assistant or a personal computer, to enter daily activities and consumed meals. However, the user may not be consistently or reliably close to their data entry device immediately after an exercise or eating activity. They may be exercising in a fitness center or may be away from these devices. Similarly, users may not eat certain meals at home, so they cannot log orthogonal information after consuming a meal. Thus, the user must keep a record of all food consumed and all activities performed so that these items can later be entered into the balancelog system.

In addition, the balancelog system does not provide a probability of estimation. The user must select the food consumed and the corresponding portion size of the food item. If there is a time lapse between the meal and the input time and the user cannot remember the meal, the data cannot be entered correctly and the system will be less accurate. Likewise, if the user does not remember the details of the athletic activity, the data may not be accurate.

Finally, the balancelog system calculates energy consumption based only on information entered by the user. The user can log only athletic activity, such as running on a treadmill for 30 minutes on a particular day. This logging process does not take into account the individual's actual energy consumption, but instead relies on an average or lookup table based on general population data that may not be particularly accurate for any particular individual. The program also ignores the user's daily activities, such as climbing stairs or riding a bus. These daily activities need to be considered by the user in order to accurately calculate their total energy consumption.

Similarly, a software product developed by Whitday, Sizer Software, is another system that allows users to track both nutritional and athletic activity to plan weight loss and monitor progress. Whitday software helps the user control the diet through the entry of food items consumed. This software also tracks athletic activity and calorie consumption through data manually entered by the user. Whitday software also allows the user to track and graph body measurements for further motivation to relate to athletic activity. Whitday also focuses on other aspects of weight loss. The system prompts the user for information about daily feelings about the analysis of triggers that may affect the user's weight loss progression.

Whitday has the same limitations as the balance log. Whitday relies on user input for its calculations and weight loss progress analysis. As a result, the information may be less accurate and compliant because the user may not enter a meal or activity. In addition, the analysis of energy consumption depends on the user's input and does not take into account the user's daily activities.

Overall, if an individual consumes less calories than the number of calories burned, the user may not experience pure weight loss. Although the above described methods provide a plurality of methods for calculating calories burned, they do not provide an efficient method for calculating calories burned. In addition, they are highly dependent on precise data entry requirements. Therefore, what is needed in the art is a management system that can accurately and automatically monitor the daily activity and energy consumption of a user in order to reduce the repetitive nature and high dependency of manual entry of information.

A nutrition and activity management system is disclosed that can help an individual meet weight loss and achieve an optimal energy balance of calories burned versus burned calories. The system can be automated and applicable or applicable to measuring the number of different physiological parameters, reporting the same and deriving these parameters. In a preferred embodiment, the weight management system is adapted to achieve the optimal energy balance necessary for progression to weight loss-specific goals. Most programs, such as the programs described above, provide a method of tracking calories and food consumption but only half of them. Without accurate estimation of energy consumption, an optimal energy balance cannot be obtained. In other embodiments, the system may provide additional or alternative information regarding limitations on sal data such as limitations on physiological activity, such as for pregnant or recovering users, or blood sugar levels for diabetics.

The disclosed management system provides a more accurate estimate of the user's total energy consumption. The other programs described above can only track energy expenditure through the user's manual history with respect to specific physical activity over a particular period of time. The management system employs an apparatus on the body that continuously monitors the heat emitted by the user's body in addition to motion, skin temperature and conductivity. Since autonomy is worn continuously, data is collected during any physical activity performed by the user, including athletic activity daily life activity. The device is designed for ease and ease of use so that long-term wear does not harm the wearer's lifestyle activities. It should be particularly noted that this device is designed for continuous and long term wear. However, continuation is intended to mean almost continuous as this device can be removed for a short period of time for hygienic purposes or for another minimum non-use. Long term wear was usually considered to be for a substantial portion of each day of wear over one day. The data collected by the device is updated in the software platform to measure the number of calories burned, the number of steps taken and the duration of physical activity.

The disclosed management system also provides an easier process for entering and tracking calorie consumption. Estimation of calorie consumption provided by the management system is too time consuming and inconvenient for current manual nutrition tracking methods, so lower levels of compliance, inaccuracies in data collection, and incorrect estimates of higher percentage calorie intake It is based on the recognition that ultimately it will lead to. Most users are too busy to log everything they eat for each meal and tend to forget how much they have eaten. Thus, in addition to the manual entry of the food item consumed, the user can select one of a plurality of other methods of calorie entry, which may include an estimate for a particular meal based on the average of the meal, the repetition of the previous meal, and the fast calorie estimation tool. Can be. Users are guided through complex tasks that remember what they ate to increase compliance and reduce discrepancies between self-reported calorie intake and actual calorie intake.

The combination of information collected from the device and the information entered by the user is used to provide feedback information about the user's progress and recommendations for reaching the dietary target amount. Because of the accuracy of the information, the user may change their lifestyle in advance to meet weight loss targets, such as exercising to adjust for more calories or adjusting diet. The system can predict data indicative of a person's physiological parameters, including other detected and derived physiological or contextual information, as well as energy consumption and calorie intake for any given relevant time. Thereafter, the user may be informed about their actual or predicted progress regarding the optimal energy balance or other target for that day.

An apparatus is disclosed for monitoring a specially identified human condition parameter comprising at least one sensor adapted to be worn on an individual's body. The preferred embodiment uses a combination of sensors to provide more accurately sensed data, where the outputs of the plurality of sensors are used for derivation of additional data. Sensors used by the device include breathing sensors, temperature sensors, heat flux sensors, body conductivity sensors, body resistance sensors, body potential sensors, brain activity sensors, blood pressure sensors, body impedance sensors, body motion sensors, oxygen consumption sensors And a physiological sensor selected from the group consisting of a body chemistry sensor, a body position sensor, a body pressure sensor, a light absorption sensor, a body sound sensor, a piezoelectric sensor, an electrochemical sensor, a strain gauge and a light sensor. The sensor is adapted to generate data indicative of at least one of the first parameter of the individual and the second parameter of the individual, the first parameter being a physiological parameter. The apparatus also includes a processor to receive at least a portion of the data representing the first parameter and the second parameter. The processor is adapted to generate derivation data from at least a portion of the data representing the first parameter and the second parameter, the derivation data comprising a third parameter of the individual. The third parameter is a personal state parameter that cannot be detected directly by the at least one sensor.

In an alternative embodiment, an apparatus for monitoring human condition parameters is disclosed that includes at least two sensors adapted to be worn on the body of an individual selected from the group consisting of physiological sensors and contextual sensors. The sensor is adapted to generate data indicative of at least one of the first parameter of the individual and the second parameter of the individual, wherein the first parameter is a physiological parameter. The apparatus also includes a processor for receiving at least a portion of data representing at least one of the first parameter and the second parameter, the processor generating derived data from the data representing at least one of the first parameter and the second parameter. It is applied to make. This derivation data may include a third parameter of the individual, such as ovulation, sleep, burned calories, basal metabolic rate, basal temperature, physical activity level, stress level, relaxation level, oxygen consumption rate, ascent time, zone time, Recovery time, and nutritional activity. The third parameter is a personal state parameter that cannot be detected directly by any of the at least two sensors.

In another embodiment of the device, at least two sensors may be both physiological sensors or one may be a physiological sensor and one contextual sensor. The device includes a housing adapted to be worn on an individual's body, which housing supports the sensor or at least one of the sensors is positioned separately from the housing. The housing may further include a flexible body that supports the housing having first and second members adapted to be wound around a portion of the individual's body. The flexible body can support one or more sensors. The apparatus may further comprise wrapping means connected to the housing for maintaining contact between the housing and the body of the individual, which wrapping means may support one or more sensors.

Another embodiment of the apparatus may further comprise a central monitoring unit remote from at least two sensors comprising a data storage device. The data storage device receives the derived data from the processor and stores the reason data in retrievable therein. The apparatus also includes means for transmitting information to the recipient based on the derived data from the central monitoring unit, which recipient may comprise an individual or a third party authorized by the individual. The processor may be supported by a housing adapted to be worn on an individual's body or may alternatively be part of a central monitoring unit.

Weight loss oriented software programs are designed to reduce the repetitive nature of data entry in measuring calorie consumption in addition to automating the tracking of an individual's energy consumption through the use of the device and providing relevant feedback on the user's weight loss goals. Is disclosed. The software program is based on an energy balance equation with two components: energy intake and energy consumption. The difference between these two values is the energy balance. When this value is negative, weight loss was achieved because less calories were consumed than amount consumed. A positive energy balance will most likely have no weight loss or have gained weight.

The weight loss oriented software program may include an energy intake tracking subsystem, an energy consumption tracking subsystem, a weight tracking subsystem and an energy balance and feedback subsystem.

This energy intake tracking subsystem includes a food database that includes an extensive list of commonly-branded and self-populated non-popular foods useful in widely consumed food, regional and international food chains, and nutritional information for each item. It is preferable. The user also has the ability to enter individual preferences or therapies that become part of the food in the database.

The energy consumption subsystem includes a data retrieval process to retrieve data from the device. The system uses the data collected by the device to determine the overall energy consumption. The user has the option to manually enter data for related activities during times when the device was not useful. The system tracks and recognizes specific activity-related nutrition parameters or patterns and provides the user with a menu for selection of such identification values, as disclosed herein and incorporated in co-pending US patent application Ser. No. 10 / 682,293. The function to add is provided. In addition, the system may directly employ this identified activity or nutritional information as needed, without input from the user.

The energy balance and feedback subsystem provides feedback on behavioral strategies to achieve energy balance in advance. The feedback and coaching engines analyze the data generated by the system to provide the user with various choices depending on the user's progress.

The management system is disclosed to include a device for continuously monitoring a user's energy consumption and a software platform for manual entry of the user's information about physical activity and calories burned. This manual entry may be input by a user entering their own food, a second party entering food for a user such as an assistant in a assisted everyday situation, or a third party receiving information from a voice, phone, or other transmission mechanism. Is achieved by the party. Alternatively, food intake may be automatically collected through measurements derived from one or more physiological parameters or a monitoring system that captures what food has been removed from a storage appliance such as a refrigerator or what food is inserted into a food preparation appliance such as an oven. Can be.

The system can be further applied to obtain an individual's life activity data, and the information sent from the central monitoring unit is also based on the life activity data. The central monitoring unit may also be adapted to generate and provide feedback regarding information that an individual has followed the proposed routine. The feedback may be generated from at least some of data representing at least one of the first parameter and the second parameter, derived data, and life activity data. The central monitoring unit may also be adapted to generate and provide feedback to the recipient regarding the management of at least one aspect of the individual's health and lifestyle. Such feedback may be generated from at least one of data representing the first parameter, data representing the second parameter, and derived data. Feedback may include suggestions for modifying the individual's behavior.

The system may be further adapted to include a body weight and body fat composition tracking subsystem to interpret data received from the data collected by the device by a second device or device, such as a drive input, a transceiver enabled weight measurement device. .

The system may also be further adapted to include a meal planning subsystem that allows a user to personalize a meal plan based on personal fitness and weight loss goals. Appropriate foods are recommended to the user based on answers provided in general and medical questions. These inquiries are used as inputs to the meal plan generation system to ensure that foods that take into account the particular health conditions or preferences of the user are guaranteed. The system may be provided with the ability to recommend alternative choices based on the food category and the change value of the food and will match calorie content between the alternatives. The system may be further adapted to generate a list of food or diet intake recommendation aids based on answers to queries provided to the user.

The system can also provide the user with the option to save or print a report of the summary data. This summary data may provide detailed information on daily energy intake, daily energy consumption, weight change, body fat composition changes, and nutritional information if the user has locked the food consumed regularly. In addition, a report may be provided that includes information for a particular time period, such as seven days, thirty days, and ninety days, and information since the start of system use.

The system may also include an athletic planning subsystem that provides recommendations to the user for cardiovascular and resistance training. This recommendation may be based on fitness targets submitted by queries to the system.

The system may also provide feedback to the user in the form of periodic or intermittent status reports. The status report can be a warning located in a box on the screen's position to attract the user's attention and is usually set to off. Status reports and images may be generated by generating key strings based on the current view and status of the user and provide the user with information about their weight loss goal progression. This information may include suggestions for meeting the user's calorie balance for that day.

Although this description specifically refers to weight loss, it should be understood that this system may also apply equally to weight maintenance or weight gain.

Further features and advantages of the present invention will become apparent upon consideration of the following detailed description of the invention, with reference to the following drawings, in which like parts are referred to by like reference.

1 illustrates an embodiment of a system for monitoring physiological data and lifestyle in an electronic network in accordance with the present invention;

2 is a block diagram of one embodiment of the sensor device shown in FIG. 1;

3 is a block diagram of one embodiment of the central monitoring unit shown in FIG. 1;

4 is a block diagram of an alternative embodiment of the central monitoring unit shown in FIG. 1;

5 illustrates a preferred embodiment of a health manager web page in accordance with an aspect of the present invention;

6 illustrates a preferred embodiment of a nutritional webpage in accordance with an aspect of the present invention;

7 is a block diagram showing the configuration of a management system for a specific user according to an aspect of the present invention;

8 is a block diagram of a preferred embodiment of a weight tracking system according to one aspect of the present invention;

9 is a block diagram of a preferred embodiment of an update information wizard interface in accordance with an aspect of the present invention;

10 illustrates a preferred embodiment of an activity level web page in accordance with an aspect of the present invention;

11 illustrates a preferred embodiment of a mind centering web page in accordance with an aspect of the present invention;

12 illustrates a preferred embodiment of a sleeping webpage in accordance with an aspect of the present invention;

13 illustrates a preferred embodiment of a daily activities web page in accordance with an aspect of the present invention;

14 illustrates a preferred embodiment of a health index web page in accordance with an aspect of the present invention;

15 is a diagram of a preferred embodiment of a weight manager interface, in accordance with an aspect of the present invention;

16 is a logic diagram illustrating generation of an intermittent status report in accordance with an aspect of the present invention;

17 is a logic diagram illustrating generation of an intermittent status report based on an energy expenditure value according to one aspect of the present invention;

18 is a logic diagram illustrating the generation of an intermittent state report based on calorie intake in addition to state state determination in accordance with an aspect of the present invention;

19 is a logic diagram illustrating calculation of state state determination in accordance with an aspect of the present invention;

20 is a front view of a specific embodiment of the sensor device shown in FIG. 1;

21 is a rear view of a specific embodiment of the sensor device shown in FIG. 1;

22 is a side view of a specific embodiment of the sensor device shown in FIG. 1;

FIG. 23 is a bottom view of a specific embodiment of the sensor device shown in FIG. 1;

24 and 25 are front perspective views of a specific embodiment of the sensor device shown in FIG. 1;

FIG. 26 is an exploded side perspective view of a specific embodiment of the sensor device shown in FIG. 1;

Fig. 27 is a side view of the sensor vise shown in Figs. 20 to 26 inserted in the battery recharging unit;

FIG. 28 is a block diagram showing all components mounted on or connected to a printed circuit board forming part of the sensor device shown in FIGS. 20 to 26;

29 is a block diagram showing the format of an algorithm developed in accordance with an aspect of the present invention, and

30 is a block diagram illustrating an exemplary algorithm for predicting energy consumption in accordance with the present invention.

In accordance with the present invention, in general, data relating to an individual's physiological state, lifestyle, and specific contextual parameters are collected and preferably transmitted in real time or subsequently to a point remote from the individual, where: The data is preferably stored for later manipulation or display through an electronic network such as the Internet. Contextual parameters are used to mean parameters relating to an individual's environment, ambient conditions, and location, including but not limited to air quality, sound quality, ambient temperature, global positioning, and the like. . Referring to FIG. 1, a sensor device 10 adapted to be located in proximity to at least a portion of the human body is located at a user location 5. Preferably, the sensor device 10 is worn on his or her body by an individual user as part of a garment, such as, for example, a fit to body or part of an arm band. Sensor device 10 includes one or more sensors adapted to generate a signal in response to a physiological characteristic of an individual, and a microprocessor. Proximity as used herein means a distance such that the sensor of the sensor device 10 is separated from the body of the individual by the material or the sensor's ability is not disturbed.

The sensor device 10 includes individual heart rate, pulse rate, beat-to-bit variability, EKG or ECG, respiratory rate, skin temperature, internal body temperature, heat flux from the body, electrical skin response or GSR, EMG, EEG, EOG It generates data indicating various physiological parameters of the individual such as blood pressure, body fat, hydration level, activity level, oxygen consumption, glucose or blood sugar level, body location, pressure on muscle or bone, and UV radiation exposure and absorption. In some cases, the data indicative of various physiological parameters is a signal or signals generated by one or more sensors, and in some other cases by the microprocessor based on the signal or signals generated by one or more sensors. The data is calculated. Methods of generating data indicative of various physiological parameters and sensors used therein are known. Table 1 provides some examples of such known methods and shows the corresponding parameters, the methods used, the sensor devices used, and the signals generated. Table 1 also provides an indication of whether further processing is needed based on the generated signal to generate data.

parameter Way sensor signal Additional processing Heart rate EKG 2 electrodes DC voltage Yes Pulse rate BVP LED emitter and light sensor Change in resistance Yes Bit-to-bit variability Heart rate 2 electrodes DC voltage Yes EKG Skin surface potential 3-10 electrodes DC voltage No * (depends on location) Respiration rate Chest volume change Strain gauge Change in resistance Yes Skin temperature Surface temperature detection Thermistor Change in resistance Yes Internal temperature Esophageal or Intestinal Detection Thermistor Change in resistance Yes Heat flux Heat flux Thermopile DC voltage Yes Electric skin reaction Skin conductivity 2 electrodes Change in resistance no EMG Skin surface potential 3 electrodes DC voltage no EEG Skin surface potential Multi-electrode DC voltage Yes EOG Eye movement Thin film piezoelectric sensors DC voltage Yes Blood pressure Non-Intrusive Korotcuff Sound Electronic pulse meter Change in resistance Yes Body fat Body impedance 2 active electrodes Impedance change Yes activity Body movements Accelerometer DC voltage, capacitance change Yes Oxygen consumption Oxygen suction Electrochemistry DC voltage change Yes Glucose levels Non-invasive Electrochemistry DC voltage change Yes Body position (eg, lying, standing, sitting) N / A Mercury switch array DC voltage change Yes Muscle pressure N / A Thin film piezoelectric sensor DC voltage change Yes UV radiation absorption N / A UV Reactive Photocells DC voltage change Yes

 The types of data described in Table 1 are intended as examples of data ties that may be generated by the sensor device 10. It will be appreciated that other types of data relating to other parameters may also be generated by the sensor device 10 without departing from the scope of the present invention.

The microprocessor of the sensor device 10 may be programmed to summarize and analyze the data. For example, the microprocessor may be programmed to calculate the average, minimum, or maximum heart rate or respiratory rate for a defined time period, such as 10 minutes. The sensor device 10 may derive information about an individual's physiological state based on data indicative of one or more physiological parameters. The microprocessor of the sensor device 10 is programmed to derive such information based on data indicative of one or more physiological parameters and using known methods. Table 2 provides examples of the types of information that can be derived, and shows some types of data that can be used for this.

Information derived Data used ovulation Skin temperature, body temperature, oxygen consumption  Sleep Initiation / Wake Up Beat to beat variability, heart rate, pulse rate, respiration rate, skin temperature, body temperature, heat flux, electric skin reaction, EMG, EEG, EOG, blood pressure, oxygen consumption Calories Burned Heart rate, pulse rate, respiration rate, heat flux, activity, oxygen consumption Basal metabolic rate Heart rate, pulse rate, respiration rate, heat flux, activity, oxygen consumption Base temperature Skin temperature, body temperature Activity level Heart rate, pulse rate, respiration rate, heat flux, activity, oxygen consumption  Stress level EKG, beat-to-beat variability, heart rate, pulse rate, respiration rate, skin temperature, heat flux, electrical skin reaction, EMG, EEG, blood pressure, activity, oxygen consumption  Relaxation level EKG, beat-to-beat variability, heart rate, pulse rate, respiration rate, skin temperature, heat flux, electrical skin reaction, EMG, EEG, blood pressure, activity, oxygen consumption Oxygen consumption rate EKG, heart rate, pulse rate, respiration rate, heat flux, blood pressure, activity, oxygen consumption Time from ascent or rest rate to ascent to 85% of the maximum stroke Heart rate, pulse rate, heat flux, oxygen consumption Time in zone or heart rate was above 85% of target maximum Heart rate, pulse rate, heat flux, oxygen consumption Recovery time or the time it takes for the heart rate to return to rest after the heart rate is at or above 85% of the target maximum Heart rate, pulse rate, heat flux, oxygen consumption

In addition, the sensor device 10 may also generate data indicative of various contextual parameters relating to the environment surrounding the individual. For example, sensor device 10 may generate data indicative of air quality, sound level / quality, light quality, or ambient temperature, or even satellite location of an individual close to the individual. The sensor device 10 may include one or more sensors for generating a signal in response to a contextual characteristic relating to the environment surrounding the individual, which signal is finally used to generate the data types described above. Such sensors are also known, such as methods for generating contextual parameter data such as air quality, sound level / quality, ambient temperature, and satellite position.

2 is a block diagram illustrating an embodiment of a sensor device 10. The sensor device 10 includes at least one sensor 12 and a microprocessor 20. Depending on the nature of the signal generated by the sensor 12, the signal passes through one or more amplifiers 14, conditioning circuits 16, and analog-to-digital converters 18 before being sent to the microprocessor 20. May be sent to. For example, when sensor 12 generates an analog signal that needs to be amplified and filtered, it is sent to amplifier 14 and then to conditioning circuit 16, which may be, for example, a bandpass filter. The amplified and conditioned analog signal is then sent to an analog-to-digital converter 18, where it is converted into a digital signal. The digital signal is sent to the microprocessor 20. Alternatively, if sensor 12 generates a digital signal, this signal may be sent directly to microprocessor 20.

 Digital signals or digital signals indicative of certain physiological and / or contextual characteristics of the individual user are used by the microprocessor 20 to calculate and generate data indicative of the physiological and / or contextual parameters of the individual user. . The microprocessor 20 is programmed to extract information related to the personal physiological state of at least one aspect. Microprocessor 20 may also include other types of processors or processing devices, such as microcontrollers, or other devices that may be programmed to perform the functions described above.

Optionally, the central processing unit can provide motion control or, at a minimum, the selection of the audio player device 21. As will be apparent to those skilled in the art, the audio player 21 has a type of playing or storing and playing separately stored audio media. The device may control the output of the audio player 21 or simply provide a user interface, as described in more detail below, so that the mobile device can control the audio player 21.

 Data indicative of physiological and / or contextual parameters is, in accordance with one embodiment of the present invention, transmitted to a memory 22, such as a flash memory, where it is stored until uploaded in a manner described below. Although memory 22 is shown as a separate device in FIG. 2, it can be appreciated that it may be part of microprocessor 20. The sensor device 10 also includes an input / output circuit 24 adapted to output some data signal and receive as an input in the manner described herein. Thus, the memory 22 of the sensor device 10 will build up storage of data related to the body and / or environment of the individual user over time. The data is periodically uploaded from the sensor device 10 and remotely stored in a database for subsequent processing and representation to the user, preferably via a global or local electronic network such as the Internet, as shown in FIG. Is sent to the central monitoring unit 30. The upload of data may be an automatic process initiated by the sensor device 10 by the occurrence of an event, such as by the sensor device 10 of the heartbeat periodically or below a certain level, to an individual user or the user. Authorized third parties can be initiated on some periodic schedule, such as 10 pm daily. Alternatively, instead of storing the data in the memory 22, the sensor device 10 may continuously upload the data in real time.

Uploading from the sense device 10 to the central monitoring unit 30 for storage can be done in a variety of ways. In one embodiment, the data collected by the sensor device 10 is first transmitted to the personal computer 35 shown in FIG. 1 by a physical connection 40 which is a serial connection such as, for example, an RS232 or USB port. Is uploaded. Physical connections can be made using cradles (not shown) that are electronically coupled to the personal computer 35 into which the sensor device 10 can be inserted, as is common with many commercial personal digital assistants. Upload of data can be initiated by pressing a button on the cradle and can be initiated automatically upon insertion of the sensor device 10. Data collected by sensor device 10 may be uploaded by primary transmission to a personal computer by short-range wireless transmission, such as infrared or RF transmission, as indicated by 45.

When data is received at the personal computer 35, it is additionally compressed and encrypted in one of a variety of known ways and transmitted to the central monitoring unit 30 via a local or global electronic network, preferably the Internet. Personal computer 35 may be any computing device capable of connecting to and receiving data from an electronic network, such as, for example, a personal digital assistant such as Palm's Palm VII or Research In Motion's BlackBerry two-way pager. .

Alternatively, data collected by the sensor device 10 may be selectively encrypted and compressed by the microprocessor 20 and then long distance to the local telco site 55 using a wireless protocol such as email or ASCII or binary data. It may be sent to a wireless device 50 such as a two-way pager or cellular phone for wireless transmission. Local telco site 55 includes a tower 60 that receives wireless transmissions from wireless device 50 and a computer 65 connected to the tower. According to a preferred embodiment, the computer 65 is used for accessing an associated electronic network such as the Internet and for transmitting the received data in the form of a wireless transmission to the central monitoring unit 30 via the Internet. Although the wireless device 50 is shown as a separate device connected to the sensor device 10 in FIG. 1, a device having the same or similar function or the wireless device may be embedded as part of the sensor device 10.

The sensor device 10 may be equipped with buttons used to time events such as bedtime, wake up time, and meal time. This time designation is stored in the sensor device 10 and uploaded to the central monitoring unit 30 along with the other data described above. The time designation is uploaded to the central monitoring unit 30 and then digitally recorded voice message which can be translated into text or other information format that can be used by the central monitoring unit 30 using voice recognition technology. It may include. In an alternative embodiment, it should be noted that this time stamped event may be detected automatically.

In addition to using the sensor device 10 to automatically collect physiological data related to an individual user, a sensing device similar to the sensor device 10 in which a kiosk weighs an individual, or places a hand or other body part, for example. Or collect the data by scanning the individual body using laser technology or an iStat blood analyzer or the like. The kiosk is provided with access to the above-described processing capabilities and associated electronic networks, and thus can be adapted to transmit the collected data to the central monitoring unit 30 via the electronic network. A desktop sensing device similar to sensor device 10 may also be provided, on which a hand or other body part is placed. For example, such a desktop sensing device may be a blood pressure monitor in which an individual places his or her arms inside. The individual may wear a ring with a sensor device 10 implemented therein. A base (not shown) may be provided that is adapted to engage the ring. The desktop sensing device or the aforementioned base may be connected to a computer such as a personal computer 35 via a physical or short-range wireless connection such that the collected data is sent to the central monitoring unit 30 via the associated electronic network in the above-described method. Can be uploaded. For example, a mobile device such as a personal digital assistant may be provided with a sensor device 10 implemented therein. Such sensor device 10 collects data when the mobile device is located in close proximity with an individual body, such as holding the device in the palm of the hand, and collects the data to the central monitoring unit 30 by any of the methods described herein. Can be applied to upload the data.

One alternative embodiment includes the integration of a third device that does not need to be carried on the body and collects additional data belonging to a physiological state. Examples include portable blood analyzers, glucose monitors, scales, blood pressure cuffs, pulse oximeters, CPAP machines, portable oxygen machines, home thermostats, treadmills, cell phones and GPS locators. The system may collect data therefrom in the case of a treadmill or CPAP, control such a device, collect the data and integrate it into a stream for real-time or future derivation of new parameters. One example of this is a pulse oximeter on a user's finger, which may help measure the pulse to provide a surrogate reading of blood pressure. In addition, the user can use one of these other devices to achieve baseline reading to calibrate the device.

In addition, in addition to collecting data by automatically sensing such data in the manner described above, an individual may manually provide data related to various life activities, which are finally transmitted and stored to the central monitoring unit 30. The individual user can access a website maintained by the central monitoring unit 30 and can freely enter text by answering the questions presented by the website or by clicking through a dialog box provided by the website. You can directly enter information related to the activity. The central monitoring unit 30 may also receive an e-mail message, such as a personal computer 35 or a personal digital assistant, pager, or cellular phone, containing an e-mail message that is proposed to derive information related to life activity. It can be applied to transmit periodically to another device. The individual can provide the central monitoring unit 30 with data related to the vital activity by replying with the relevant data to the appropriate e-mail message. The central monitoring unit 30 may be adapted to make a telephone call to the individual user with questions that may be presented to the individual user. The user can answer the question by entering information using a telephone keypad, or a voice that requires conventional speech recognition technology used by the central monitoring unit 30 to receive and process the answer. The telephone call can be initiated by the user, in which case the user can talk directly to another person or enter information by using a keypad or by voice / voice recognition technology. The central monitoring unit 30 may be provided with access to a source of information controlled by the user, for example from a user's electronic calendar provided to an Outlook product sold by Microsoft in Redmond, Washington. Can be collected automatically. Data related to vital activities are meals, sleep, exercise, mental concentration or rest, and / or an individual's daily habits, patterns, and / or activities. Thus, a sample question includes: What did you have for lunch today? When did you fall asleep last night? What time did you get up this morning? How long did you run the treadmill today?

The feedback to the user in visual form, in the form of a sound signal, or directly through the sensor device 10, for example via an LED or LCD, or by configuring the sensor device 10 at least partially in thermochromic plastic, or It can be provided in the form of tactile feedback such as vibration. Such feedback can be an indication or warning to eat, to take supplements such as medicines or vitamins, to engage in activities such as exercise or meditation, or to drink water when dehydration is detected. In addition, an indication or alert may be issued when certain physiological parameters, such as ovulation, are detected, when the calorie level consumed during exercise is achieved, or when a high heart rate or respiratory rate occurs.

As will be apparent to those skilled in the art, it is possible to "download" data from the central monitoring unit 30 to the sensor device 10. The flow of data in the download process is substantially the inverse of the process described above in connection with the upload of data from the sensor device 10. Thus, the firmware of the microprocessor 20 of the sensor device 10 downloads new firmware from the central monitoring unit 30 to the sensor device 10 for parameters such as sampling rate and timing of the sensor device 10. It can be updated or changed remotely, ie the microprocessor can be reprogrammed. In addition, the suggestion / alarm provided from the sensor device 10 may be set by the user using a website maintained by the central monitoring unit 30 and substantially downloaded to the sensor device 10.

Referring to FIG. 3, a block diagram of the central monitoring unit 30 is shown. The central monitoring unit 30 receives a request for data or incoming and outgoing traffic to a router 75 whose main function is to direct or view the request and the traffic for viewing or processing on a website maintained by the central monitoring restoring 30. And connected CSU / DSU 70. The router 75 is connected to the firewall 80. The main function of the firewall 80 is to protect the rest of the central monitoring unit 30 from unauthorized or malicious intrusion. Switch 85 connected to firewall 80 is used to direct data flow between middleware servers 95a through 95c and database server 110. The load balancer is provided to distribute a load of incoming requests between identically configured middleware servers 95a through 95c. A load balancer, in which the F5 server Aaron sold by Foundry Networks, San Jose, CA, may be a suitable example, utilizes each middleware server 95a-95c to properly distribute tasks among the middleware servers 95a-95c. Analyze the likelihood and amount of system resources used within the middleware servers 95a to 95c.

The central monitoring unit 30 includes a network storage device 100, such as a storage area network (SAN), which acts as a central repository for data. In particular, network storage device 100 includes a database that stores all the data collected for each individual user in the manner described above. An example of a suitable network storage device 100 is a Symetrics product sold by EMC Corporation of Hopkinton, Massachusetts. Although only one network storage device is shown in FIG. 3, multiple network storage devices of various capacities may be used depending on the data storage capacity of the central monitoring unit 30. The central monitoring unit 30 also includes a database server 110 connected to the network storage device 100. Database server 110 consists of two main components: a high-capacity multiprocessor server and an enterprise type such as 8 / 8i devices sold by Oracle Corporation in Redwood City, California, or 5067 components from Microsoft in Washington, Redmond. Includes a software server. The primary function of the database server 110 is to provide access by request for data stored in the network storage device 100 and to fill the network storage device 100 with new data. The network storage device 100 is connected to a controller 115, which typically includes a desktop personal computer, for managing data stored in the network storage device 100.

A middleware server 95a to 95c, which may be a suitable example of a 22OR dual processor sold by Sun Microsystems, Palo Alto, California, may be a web site or a home page of a website maintained by a central monitoring unit 30, respectively. It includes software for generating and managing. As is known, a web page means a block of data available on the World Wide Web that includes a file described in Hypertext Markup Language (HTML), and a website is a web page on the Internet that runs a World Wide Web server process. Which means computer. A corporate or home page is a web page that is opened or presented by members of the public who visit the site using a suitable uniform resource indicator (URL). As is known, URLs are in the form of addresses used on the World Wide Web and provide a standardized way of specifying the location of objects such as web pages on the Internet. The middleware servers 95a to 95c each include software for generating and maintaining web pages of the web site of the central monitoring unit 30 which are registered and accessed only by individuals who are members of the central monitoring unit 30. Member users are individuals who wish to store their data in the central monitoring unit 30. Access by such member users is controlled using passwords for security purposes. Preferred embodiments of the web page are described in detail below and are generated using collected data stored in a database of the network storage device 100.

Middleware servers 95a-95c also include software that requests data from network storage device 100 via database server 110 and writes data to the network storage device. An individual user may initiate a session with the central monitoring unit 30 to enter data into the database of the network storage device 100, view his or her data stored in the database of the network storage device 100, or both. When the user visits the home web page of the central monitoring unit 30 using a browser program such as Internet Explorer distributed by Microsoft in Redmond, Washington, and logs in as a registered user. The load balancer 90 assigns the user one of the middleware servers 95a through 95c, which is specified as the selected middleware server. The user will preferably be assigned to the selected middleware server for each full session. The selected middleware server authenticates the user using one of the known methods to ensure that it is a true user authorized to access information in the database. Member users can grant access to their data to third parties such as health care managers or personal trainers. Each authorized third party may be given a separate password and may view the data of the member user using a conventional browser. Thus, it is possible for both the user and the third party to be the recipient of the data.

Once the user is authenticated, the selected middleware server requests the individual user's data from the network storage device 100 through the database server 110 for a predetermined period of time. The predetermined time period is preferably 30 days. The requested data is temporarily stored in the cache memory by the selected middleware server as long as it is received from the network storage device 100. The cached data is used by the selected middleware server as a basis that can be presented back to the user through the user's browser in the form of a web page. Each middleware server 95a-95c is provided with suitable software for generating such web pages, including software for performing and manipulating calculations that utilize the data to make the format suitable for presenting the data to the user. When the user ends his session, the data is discarded from the cache. When the user initiates a new session, the process of acquiring and caching data for the user as described above is repeated. The cache system thus ideally needs only one call to the network storage device 100 per session, thereby reducing the traffic that the database server 110 must handle. If a request from a user during a particular session requires data that is outside a predetermined time period of cached data already retrieved, a separate call to network storage device 100 would have to be performed by the selected middleware server. However, the predetermined time period may be chosen such that additional calls are minimized. Cached data can be stored in cache memory so that it can be used again when a user starts a new session. Thus, eliminating the need to initiate a new call to network storage device 100.

As described in connection with Table 2, the microprocessor of the sensor device 10 may be programmed to extract information related to an individual physiological state based on data indicative of one or more physiological parameters. The central monitoring unit 30, and preferably the middleware servers 95a to 95c, can be similarly programmed to extract the information based on data indicating one or more physiological parameters.

It is also conceivable that the user may enter additional data during the session, such as information related to the user's eating and sleeping habits, for example. This additional data is preferably stored in the cache by the selected middleware server for the duration of the user's session. When the user ends the session, additional new data stored in the cache is sent by the selected middleware server to the database server 110 for accumulation in the network storage device 100. Or, in addition to being stored in the cache for potential use during the session, input data is immediately sent to the database server 110 for accumulation in the network storage device 100 as part of the write-through cache system, as is known. Can be sent.

Data collected by the sensor device 10 shown in FIG. 1 is periodically uploaded to the central monitoring unit 30. Via long distance wireless transmission or personal computer 35, the connection to the central monitoring unit 30 is via an electronic network, preferably the Internet. In particular, a connection is made to the load balancer 90 through the CSU / DSU 70, the router 75, the firewall 80, and the switch 85. The load balancer 90 then selects one of the middleware servers 95a through 95c (hereinafter referred to as the selected middleware server) that handles the upload of data. The selected middleware server authenticates the user using one of the known methods. Once authenticated, the data is uploaded to the selected middleware server, as described above, and finally sent to the database server 110 for accumulation in the network storage device 100.

Referring to FIG. 4, another embodiment of a central monitoring unit 30 is shown. In addition to the elements shown and described in connection with FIG. 3, the central monitoring unit 30 of FIG. 4 includes a mirror network storage device 120 which is an extra backup of the network storage device 100. Mirror network storage device 120 is coupled to controller 122. Data from network storage device 100 is periodically copied to mirror network storage device 120 for the purpose of data redundancy.

A third party, such as an insurance company or research institute, can access any information stored in mirror network storage device 120, for example, for a fee. Preferably, in order to maintain the confidentiality of the individual user providing the data to the central monitoring unit 30, such third institution is not provided with access to the user's personal database records, but in the form of an aggregate mirror network storage device. Only access to data stored within 120 is provided. The third institution may access the information stored in the mirror network storage device 120 through an internship using a conventional browser program. Requests from third parties may come through the CSU / DSU 70, the router 75, the firewall 80, and the switch 85. In the embodiment of FIG. 4, a separate load balancer 130 is provided for distributing tasks related to the access and representation of mirror drive array 120 among identically configured middleware servers 135a through 135c. Middleware servers 135a through 135c each include software that allows a third party to form a query for information from mirror network storage device 120 via a separate database server 125 using a browser. The middleware servers 135a to 135c also include software for representing to the third institution information obtained from the mirror network storage device 120 via the Internet in the form of a web page. In addition, the third party may select from a series of prepared reports that allow information to be packaged along a subject line, such as various exemplary categories.

As will be apparent to those skilled in the art, instead of giving the third institution access to the backup data stored in the mirror network storage device 120, the third authority may be given access to the data stored in the network storage device 100. . In addition, instead of providing the load balancer 130 and middleware servers 135a to 135c, the same functionality may be provided by the load balancer and middleware servers 95a and 95c even if performance is reduced to some extent.

When an individual user first becomes a registered user or member, the user conducts a detailed investigation. The purpose of the survey is as follows: to identify unique characteristics / environments for individual users that need to be reviewed to maximize the likelihood of implementing and maintaining a healthy lifestyle proposed by the central monitoring unit 30; Collecting basic data used to facilitate any graphical data output and calculation, such as health index pistons, and to set initial targets for individual users; Identifying unique user characteristics and circumstances that help the central monitoring unit 30 customize the form of content provided to the user in the daily prescription of the health manager; And identifying unique user characteristics and circumstances that can guide the health manager to review possible barriers to healthy light style through the health manager's troubleshooting capabilities.

In alternative embodiments, particularly for weight loss or management applications, as described more fully herein, a user may carry the sensor device 10 in the long term or continuously to observe changes in certain health or weight related parameters. You can choose to. Alternatively, the user may choose to carry only the sensor device 10 for a short time, an initial period, to baseline or initially calculate typical daily calorie intake and energy expenditure. This information may provide a basis for diet and / or exercise planning, menu selections, meal plans, and the sensor device 10 for a while within a time frame in which progress is achieved for completion of any associated weight loss or change goals. Can be checked periodically by reusing. .

Specific information investigated includes: key personal temperament including activity level, regularity of meals, bedtime and habits, initial response to the situation, adaptability, patience, threshold of response, intensity of response, and mood ; User level of independent functions such as self-organization and management, sociality, memory, academic achievement; The user's ability to focus and maintain attention, including the user's level such as stimulation, recognition rate, complaint filtering ability, insomnia, self-monitoring, etc .; Current health conditions, including current weight, height, blood pressure, recent visits, gynecological visits, and other physician / health consultations, current and supplement medications, allergies, and current signs and / or health related behaviors; User's medical history, such as illness / surgery, family history, social stress such as divorce or unemployment that require adjustment by an individual; Beliefs, values, and ideas about users' health priorities, their ability to change their behaviors that can stress their lives, and how to manage them; Daily routines for the user's level of awareness, sympathy, authority, self-esteem, the user's current meals, sleep, exercise, rest, and actions to complete a routine; And the user's awareness of the temperament traits of two main characters, e.

In a weight loss or management application, an individual user is first registered or a member of a software platform, and a body monitoring device is issued that collects data from the user. The user can further personalize the device by entering certain information into the software platform. Such information may include first name, date of birth, height, weight, gender, waistline measurements, body type, smoking status, lifestyle, typical activities, routine bedtime, and wake up time. After the user connects the apparatus to a personal computer or other similar device by any of the above connecting means, the apparatus is updated with this information. The user may also have the option of setting a reminder, which may be a reminder for taking vitamins, engaging in physical activity, or uploading data at a particular time. After the configuration process is complete, the program indicates how the device should be attached to the body and how the user removes the device from the personal computer to place the device in a suitable location on the body for the collection of data. Alternatively, some of this personalization may occur during the initial trial carry period.

In a more general embodiment, each member user can access a set of customized web pages for the user, referred to as a health manager, through the home web page of the central monitoring unit 30. The health manager web page is shown in FIG. 5. The health manager web page is the main workspace for member users. The health manager web page may include various types and types of data generated from the data it collects or generates, that is, one or more: by the sensor device 10, where the central monitoring unit 30 is generally referred to as analytic state data. Data indicating various physiological parameters generated; Data derived from data indicative of various physiological parameters; Data indicative of various contextual parameters generated by the sensor device 10; And data entered into the health, fitness and lifestyle indicators calculated by the user. For example, the amount and calories of any vitamins of protein, fat, carbohydrates can be calculated based on data entered by the user with respect to the food he ingested. As another example, skin temperature, heart rate, respiratory rate, heat flux and / or GSR can be used to provide the user with an indicator of his or her stress level over a period of time. As another example, skin temperature, heat flux, beat-to-beat heart variability, heart rate, pulse rate, respiratory rate, center temperature, calvanic skin response, EMG, EEG, EOG, blood pressure, oxygen consumption, ambient sound and vibration accelerometers Body movements or movements sensed by the device, such as can be used to provide the user with an indicator of his or her sleep pattern for a predetermined period of time.

The health index 155 is located on the health manager web page 150. Health index 155 is a graphical utility used to measure and provide feedback to member users of their success and how successful they have reached a healthy daily routine suggested by central monitoring unit 30. Health index 155 provides instructions for member users to track their progress. Health index 155 includes six categories related to the user's health and lifestyle: nutrition, activity level, mental concentration, sleep, daily activities and emotions. Nutrition categories relate to when, what, and how much you eat and drink. The activity level category relates to how much you move. Mental concentration is related to the quality and amount of time an individual engages in an activity that allows the body to achieve a state of profound rest while the mind is very concentrated. Sleep categories relate to the quality and quantity of an individual's sleep. Everyday activity categories relate to the day-to-day responsibilities and health risks of an individual. Finally, emotion categories relate to the general perception of how you feel on a particular day. Each category has an associated level indicator or piston that preferably indicates a range from bad to good for how it is performing in relation to that category.

When each member user completes the initial survey described above, a profile is created that provides the user with a summary of his or her associated characteristics and life environment. A plan and / or set of contents is provided in the form of a proposed health routine. Suggested health routines include a combination of specific suggestions to implement appropriate nutrition, exercise, mental concentration, sleep, and selected activities of daily life in the user's life. A typical schedule can be provided as a guide on how this proposed activity will be implemented in the user's life. The user will periodically re-examine and the above items will be adjusted accordingly.

The nutrition category is calculated from the data input by the user and the data detected by the sensor device 10. Data entered by the user includes the time and duration of breakfast, lunch, dinner, and some snacks, food intake, supplements such as vitamins ingested, water consumed during the associated preset time period, and other beverages. Based on this data and the data stored in relation to the known properties of the various foods, the central monitoring unit 30 calculates known nutritional food values such as calories and amounts of protein, fat, carbohydrates, vitamins and the like consumed.

The nutritional health index piston level is preferably determined in relation to the following suggested healthy daily routine: Intake of at least three meals: 6-11 servings of bread, pasta, cereals and rice, 2-4 servings of fruit, 3 Intake of -5 servings of vegetables, 2-3 servings of fish, meat, poultry, dried beans, eggs and peanuts, and 2-3 servings of milk, yogurt, and cheese; Drink more than 8 ounces of water. This routine may be adjusted based on information about the user such as gender, age, height, weight. Certain nutritional goals may be set in relation to the daily calories, fat, dietary fiber, fat, carbohydrates, and / or water consumption and percentage of total consumption by or for the user. The parameters utilized in the calculation of the relevant piston level include the number of meals per day, the amount of water and the type and amount of food consumed daily, as entered by the user.

Nutrition information is presented to the user through the nutrition web page 160 shown in FIG. Preferred nutrition web page 160 includes nutrition fact charts 165 and 170 showing actual and target nutrition facts as pie charts, respectively, and nutrition charts 175 and 180 showing actual and past nutritional intakes as pie charts, respectively. do. Nutrition fact charts 165 and 170 preferably show percent breakdown of items such as carbohydrates, proteins and fats, while nutrition charts 175 and 180 preferably show total and target calories, fat, carbohydrates, proteins and vitamins. The value is qualified by the same component. Web page 160 also provides timed meal and water consumption tracking 185 users direct access to nutrition related news items and articles, suggestions for improving and improving their daily routines with regard to nutrition and related advertisements on the network. A hyperlink 190 to allow, and a calendar 195 that can select between views having a variable and selectable time period. The items shown at 190 may be selected and individualized based on the information learned about the individual in the survey and the performance measured by the health index.

In a weight management embodiment, a user may also have access via a central monitoring unit 30 to a software platform called a weight manager, which may be included or independent of the health manager module. The weight manager may also be a web based application.

When the weight manager software platform is initialized, a registered user can log in to the weight manager. If users are not registered, they must complete the registration process before using another part of the software platform. The user starts the registration process by selecting a username and password and entering the device's serial number.

7 is a block diagram illustrating the steps used to construct a personalized weight manager. During the initial configuration of the weight manager, the user may personalize the system with specific information in the weight manager's user profile 100. The user may also return to the user profile 100 at any time during use of the system to modify the information. On the body parameter screen 1005, the user can display specific information including first name, date of birth, height, weight, sex, weightline measurements, left and right hand grips, body frame size, smoking status, physical activity level, bedtime and wake up time. You can enter On the reminder screen 1010, the user can select a time zone from a pull down menu as well as set a reminder. Once any information on the body parameter screen 1005 or reminder screen 1010 has been modified, armband update button 1015 allows the user to begin the upload process for armband configuration 1020.

On the weight target screen 1025, the user is given the option of the weight loss target amount. If the user selects this option, the user will be required to enter the following information to achieve this goal: current weight, target weight, target date to reach the target weight, target daily calorie intake and target daily calorie burn rate. . Thereafter, the system displays the body mass index at the user's current weight, the body mass index at the target weight, the weight loss per week required to reach the target weight by the target date, and the daily calorie balance at the input daily intake and continuous rate. Will be calculated. The screen may also display a risk factor bar showing the risk of certain conditions such as diabetes, heart disease, high blood pressure, stroke and premature death in the user's current weight compared to the risk at the target weight. The current and target risk factors of each disease state can be displayed side by side for the user. If the user has not entered any information for at least 5 days, the user is given a start over option 1030.

In addition, a user may select a plan that may include a low carb, high protein diet plan, or a diet and exercise plan associated with more health conditions, such as those prescribed by the American Heart Association or the American Diabetes Association, to provide a diet and exercise plan screen ( 1035) to achieve a diet exercise plan. In particular, it should be noted that all similar diets, including many not recorded here, are interchangeable for the purpose of this application. The user's diet plan is selected from a pull down menu. The user also enters the expected intake of fats, carbohydrates and proteins as a percentage of their total calorie intake. The user also selects a suitable exercise from the pull down menu or manually enters this exercise.

In accordance with one aspect of the present invention, the system generates individual daily meal plans to help users achieve their health fitness goals. The system uses a database of food and meals (combinations of food) to create a daily menu. The database of food and meals is used in connection with diet restrictions that restrict user preferences, health and fitness goals, lifestyles, body types and types of meals contained within menus. These individual constraints determine the individualized calorie range and nutritional breakdown for the user's meal plan. Meals are assigned to the menu with a top-priority strategy to be within the required error of optimal daily calorie and nutritional balance.

According to another aspect of the present invention, the system may use information about the daily energy consumption of the user to create a menu with calories that can compensate for the user's actual energy consumption during the day. For example, the lunch can be configured to be slightly more if the user normally exercise immediately after lunch. Feedback between the information collected from the armband and the menu can help the user achieve fitness and health goals more quickly.

The user logs the daily meal by selecting individual food items from the food data. The food database may include foods that are normally consumed, such as milk, bread, for example, brand name entries useful in grocery stores, such as Weight Watchers or Mrs. T's, as well as food useful in a particular local or country restaurant chain, For example, McDonald's and Burger King provide an extended risk for food. The name of the food, its calorie content and nutritional information are recorded in a database. Equivalent food may be found in the case of simple preparation. If the user does not provide detailed nutritional information, it may be replaced by a summary meal entry such as a large, medium or small meal. This provides a baseline nutrition input for the energy balance features described herein. Again, as explained more fully below, the accuracy of this estimation can be improved through the feedback of the system of monitoring and estimating the amount of calories actually consumed and correlating it into large, medium, and small categories.

To be more precise, the ability to add individual preferences is optional. There are two ways in which the user can add individual foods. The first method is to add the dishes or ingredients of larger complex dishes or meals to produce individual foods or meals. The second method is to enter data found on a bag of processed or packaged food. Each method configures additions to the user's food database for later retrieval. If the user wants to add their own individual food, the food database provides the user with the ability to name their own preferences and enter the ingredients and calories and nutrition contained. When entering an individual preference, the user must specify a name and at least one component. Once preferences are added to the database as individual foods, it is possible for them to be selected as the rest of the foods in the database. Individual food data may include calories, total fat, sodium content, total carbohydrate content, total protein content, fiber and cholesterol in each serving. This value can be estimated based on the input component.

Another aspect of the invention is the use of adaptive and inferential methods to make the food input process simpler. This method includes the steps of helping to accurately select the portion size of a meal or ingredient by automatically simply repeating the system for the user. One example of the first method is to inquire a user when a particular meal is entered. For example, when lasagna is entered, the user is asked about the details of the lasagna dish to help down the calorie content of the food. In addition, the portion size of the user can be compared to the typical portion size entered for a given meal, inquiring the user when their entry is out of range. Finally, the user is asked about foods that are widely related when a particular food is entered. For example, when a turkey sandwich is entered, the user may be prompted for the seasoning because it is very likely that some seasoning has been consumed. In general, such a suggestion can be made based on a conditional probability. For example, if the user has a beer, the system may suggest a pizza. Such proposals can be hardcoded or derived by extracting common patterns within a population database or a local, family, seasonal or individual subset.

In a similar nature, the user's pattern with the rest of the population and their relationship can also be used to drive other aspects of food entry interaction. For example, if a user has a combination of food that is often popular, the system suggests that the user make the combination a separate meal.

Another aspect of the present invention is that it is possible to design the order of foods in a frequent food list or database lookup, maximizing the probability that a user selects foods with a minimum of clicks. Instead of filling the page with blank meals, the system can infer meals using meal entry information history, physiological data, user's body parameters, general popular food entry data or in relation to a particular other user. For example, if the system has noticed that two or more users often have approximately the same meal in a regular pattern, the system can use one user's entry to prompt the second user. For example, if the wife has a cheeseburger, the system can prompt the husband for the same meal. For a group of six individuals who all appear to have a particular brand of sandwich as lunch on Tuesday, the system can be used to drive the prompting for another user using input from one person. In addition, in institutional settings such as hospitals or assisted living centers where a vast number of identical meals are being distributed, a single entry for each meal component may be used for all passengers / patients. Another aspect is the direct use of physiology to drive the suggestion that a sports drink may be prompted, for example if the system senses a vast amount of activity.

The food input screen is the front end to the food database. The user interface provides the ability to search the food database. Search can be interactive and text and phrase matchable to facilitate input. The user starts searching by entering at least three characters in the input box. The search shall be insensitive and out of order, irrespective of the words entered in the input box. The results of the food search can be grouped into categories such as My Food, Popular Food, or Other Food. In each group in the search results, the food must first be arranged into food starting with the search string and then alphabetically. After selecting the food item, the user selects the potion size of the selected food. Potion size size and measurements are dependent on the food selected, for example, as item, serving, gram, ounce. Meal information can also be edited after it is entered. Users can enter as many different daily meals as they choose, including breakfast, after breakfast snacks, lunch, after lunch stacks, dinner and after dinner stacks. The system can also automatically pop pool a user database of individual meals with entries from their selected meal plan. This will give the user a simple way to track what they have spent and a self-reported way of tracking compliance with the program.

8 is a block diagram illustrating a weight tracking subsystem 1040 that enables a user to record weight changes over time and receive feedback. The user enters an initial weight entry 1045 into the weight tracking subsystem 1040. The weight tracking subsystem 1040 calculates the percentage change in weight since the last time the user entered the weight (10500.) If the newly entered weight is 3% greater or lower than the latest weight, the user knows that the entered weight is correct. A weight verification page 1055 is displayed to confirm: If the entered weight is not 3% higher or lower than the latest weight, the weight tracking subsystem 1040 stores the entry as the current weight (1060). It should be particularly noted that 1040 may use body fat measurements and calculations in addition to or instead of weight entry 1045.

The current weight 1060 is compared with the target weight selected by the user via the weight loss comparison 1065. If a weight equal to or below the target weight is entered, a congratulatory page 1070 is displayed with a field for resetting the target weight. In a preferred embodiment, a comparison is made (1075) for all six entries between the current body weight x and (x-6) th body weight to determine interval weight loss. Based on the information provided by the user in the registration process for the weight loss goal, in addition to the user's input through the use of the system, the expected weight loss amount 1080 is calculated based on these nutritional and energy expenditure values. If the interval weight loss 1075 between two weights is more than 10 pounds from the preprogrammed expected weight loss 1080, the user moves to a weight mismatch error page 1085a that allows the user to contact technical support. If the difference between the two weights is more than four pounds, the user may be taken to a second weight mismatch error page 1085b that displays a list of potential reasons for mismatch.

Another aspect of the weight tracking subsystem is the estimation of the date when a user's weight should be equal to a target shaping value entered or later updated by the user during registration. The algorithm calculates the rate of weight change based on the sequence of recorded weight entries of the user. Kalman Smoother is applied to the sequence to eliminate the effects of noise due to daily weight changes and scale inaccuracies. The date that the user will reach their weight target value is predicted based on the rate of weight change.

The total energy consumption of the user can be estimated by using the device or by manually entering the type and duration of the activity. The device automates the estimation process to facilitate and simplify data entry. It is known that total metabolism is measured as total energy consumption (TEE) according to the following equation.

TEE = BMR + AE + TEF + AT

Here, BMR is the basis metabolism, which is the energy consumed by the body during a rest such as sleep; AE is active energy consumption, which is energy consumed during physical activity; TEF is a thermally effective amount of food, which is energy consumed during digestion and processing of ingested food; AT is adaptive thermogenesis, the mechanism by which the body modifies its metabolism to extreme temperatures. It is estimated that about 10% of the food consumed is needed to process food. TEF is therefore estimated to be 10% of the total calories consumed. Therefore, calorie consumption can be measured without the need to manually track or record food-related information by a reliable and practical way of measuring TEF. Specifically, once TEF is measured, it can be accurately estimated by dividing TEF by 0.1 (TEF = 0.1 * calories burned; calories burned = TEF / 0.1).

9 is a block diagram of an update information wizard interface 1090 that serializes a data retrieval process from a device to update energy consumption. The user is given at least three options to update energy consumption, including no armband data upload option 1095a, armband wearing oblivion data option 1095b, and armband data upload option 1095c.

When data is retrieved from the device, the system can provide a semi-automatic interface. The system is provided with the ability to communicate with devices wirelessly and with wired USB connections. The system prompts the user to select a communication mode before retrieving the data. The most common usage model is considered wireless search. If wireless search is used, the wired connection may be used primarily for field upgrades of firmware in the armband. Each device is associated with a particular user and the devices are individualized so that they cannot be interchanged between different users.

The system will use the data collected by the armband to estimate the total energy consumption. This value is calculated using an algorithm included in the software. The database includes estimates of energy consumption per minute, number of stems, amount of time the device has been worn, active energy consumption, in the preferred embodiment the user's habits, which are usually stored as non-physical active energy consumption per hour, while not wearing the device. Saves reported exercise, and time spent actively.

9 again, if the user selects the no armband data upload option 1095a or the armband wearing oblivion data option 1095b, the user may select the energy consumption estimation option 1100. If the user selects the armband data upload option 1095c, the user can initiate retrieval of data from the device. If the device is worn or not intermittently worn during the period, the system may provide the user with a manual activity entry option 1105 to manually enter the type of activity associated with the user during this period. Useful options include a top left option, a list of activities from the American College of Sports Medicine Metabolic Equivalent Table, and a list of activities previously entered during use of the device. For time, the options may be expressed in order from highest frequency to lowest frequency to facilitate data entry by placing the most frequent options at the top of the list. In addition, the system can observe patterns of activity based on time of day, day of week, and the like, and can suggest activities with high probability over a particularly missed period. If nothing is entered for the activity, the system will use the user's previously stored data to estimate the user's energy consumption. In a preferred embodiment, this is achieved using histogram estimation and analysis comprising an hourly data set each containing a running average value of the non-kinetic energy consumption recorded by the device.

In addition, the user can select an exercise calculator to estimate calories burned during any particular activity in the database. The user selects the appropriate activity from the time period and risk for the activity. The system calculates an approximate calorie burned by the user during that period, based on either or both of (i) a lookup table of mean estimation data or (ii) previous measurements for the user during that particular activity.

According to one aspect of the invention, the armband may detect when the user is in a physically active state and in the upper left state. During physical active time, the usage pattern is not updated. Instead users are required to report in their high active period. During the non-physical active time, the usage pattern is updated and then the collected information is used for the upper left time reported when the user is not wearing an armband.

Through either a software platform, a body monitor, or both, the system accurately refers to the mobile by collecting and analyzing data about the mobile over time, finding patterns, finding relationships, or correlating the data. Can improve its performance. For example, if the user gives the system distinct feedback, such as the time to stamp a particular activity, the system can directly improve the system's ability to identify the activity. As another example, the system may characterize an individual's habits over time to further improve the quality of the derived measurements. For example, knowing when a user tends to exercise, how long they tend to exercise, or knowing when they are not exercising can all be valuable inputs for predicting when physical activity is taking place. have.

It will be apparent to those skilled in the art that the features of the detected patterns and habits themselves are possible derived parameters. In addition, these patterns and habits allow the system to be intuitive when the sensor is not operating or when the device is not attached to the user's body. For example, if the user does not carry the device and the measured energy consumption is not useful, or if he neglects the meal input, as the data is mentioned more fully herein, the data may be indicative of previously observed meals, activities and habits. It can be estimated from the feature.

For a more general embodiment, the activity level category of the health index 155 helps to monitor when and how the user moves during the day and to utilize the data input by the user and the data detected by the sensor device 10. It is designed. The data entered by the user includes details related to the user's daily activities, such as working at a desk from 8 am to 5 pm and taking an aerobic course from 6 pm to 7 pm Include. Relevant data sensed by the sensor device 10 can be derived by the sensor device 60 or the central monitoring unit 30, movements detected by devices such as heart rate, vibration accelerometer, heat flux, respiratory rate Includes calories burned, gsr and hydration levels. Calories burned are multiplied by duration of the type of exercise input by the user; Multiplying the detected motion by the number of motions multiplied by the filter constant; The detected heat flux is calculated in various ways, including multiplying by the time multiplied by the filter constant.

The activity level health index piston level is preferably determined in relation to the proposed healthy daily routine, the daily routine comprising: a preset time period, preferably aerobic exercise for 20 minutes, a preset time period, preferably 1 hour Participating in a passionate lifestyle activity, while consuming at least a minimum target number of calories, preferably 205 calories, through aerobic exercise and / or lifestyle activities. The minimum number of calories may be set according to information about the user such as gender, age, height and / or weight. The parameters used in the calculation of the relevant piston level are the amount of time spent in aerobic exercise or passionate lifestyle activity as input detected by the user and / or by the sensor device 10 and the energy expenditure parameters previously calculated above. It includes the number of calories consumed.

 The information about the movement of the individual user includes an activity graph 205 in the form of a bar graph for monitoring the activity of the individual user in one of three categories: high, medium and low intensity for a preselected time unit. Presented to the user via the activity level web page 200 shown in FIG. An activity percentage chart 210 in the form of a pie chart may be provided to show the percentage of a preselected time period, such as a day, that the user spends in each category. Activity level web page 200 may include a calorie section 215 for displaying items such as burned total calories, burned daily target calories, total calorie intake, and aerobic activity duration. Finally, activity level web page 200 provides at least one hyperlink 220 to allow users to directly access suggestions and related news items and articles to refine and improve daily routines for activity levels and to be familiar with advertisements on the network. ). Activity level web page 200 can be viewed in a variety of formats and includes user-selectable graphs and charts, such as bar graphs or pie charts, as selectable by activity level check box 225. Activity level calendar 230 is provided for selection among views with variable and selectable time periods. The item indicated at 220 may be selected and tailored based on the performance of the individual as measured by the health index and the information learned about the individual in the survey.

 The mind centering category of the health index 155 assists the user in monitoring parameters over time involved in certain activities in order to allow the body to achieve a state in which the body is deeply relaxed while the mind is concentrated. Based on the data detected by 10 and the data input by the user. In particular, the user may enter the start and end times of a relaxation activity such as yoga or meditation. The quality of these activities as determined by the depth of mind centering events can be measured by monitoring parameters including skin temperature, respiratory rate, and heat flux detected by sensor device 10. The percentage change in the GSR can also be used as the percentage change induced by the sensor device 10 or by the central monitoring unit 30.

 The mind centering health index piston level is preferably calculated for the proposed health daily routine that includes daily participation in activities that allow the body to achieve deep rest while the mind is highly concentrated for at least 15 minutes. The parameters used in the calculation of the relevant piston level are GSR or heat flux as detected by the sensor device 10 compared to the baseline, which is an indication of the depth and quality of the mind centering activity, the percentage change in skin temperature, and the respiratory rate. , And the amount of time spent on mind centering activities.

 Information regarding self-contemplation and rest is presented to the user via the mind centering web page 250 shown in FIG. For each mind centering activity, the preferred mind centering web page 250, referred to as a session, compares the time spent during the session represented by 255, the target time represented by 260, the target and actual depth or focus of mind centering. 265, and a histogram 270 showing the overall stress level derived from skin temperature, heart rate, respiratory rate, heat flux, and / or GSR, and the like. In the comparison section 265, the outline of the human body representing the target focus is a solid line, and the outline of the human body representing the actual focus reaches a blurred line or solid line depending on the level of focus. The preferred mind centering web page 250 shows the total time spent on mind centering activities, indicated by 275, suggestions for users to refine and improve their daily routines for mind centering, direct access to relevant news items and articles, and familiarity with ads on the network. A hyperlink 280 to enable, and a calendar 285 for selection among views of the view having a variable selectable time period. The item indicated at 280 may be selected and tailored based on the individual's performance as measured by the health index and the information learned about the individual in the survey.

 The sleep categories of health index 155 help the user to monitor their sleep patterns and the quality of sleep. It helps the user to know about the relationship of sleep to heart rhythm and the importance of sleep in the user's healthy lifestyle, which is a normal daily routine in body function. The sleep category is based on the data detected by the sensor device 10 and the data input by the user. The data entered by the user during each relevant time interval includes the time the user went to bed and the time of occurrence and the quality of sleep quality. As shown in Table 2, data from sensor device 10 includes skin temperature, heat flux, bit-bit heart variability, heart rate, pulse rate, respiratory rate, core temperature, electrical skin response, EMG, EEG, EOG, blood pressure. , And oxygen consumption. Also relevant are body movements and movements detected by ambient sound and accelerometers. This data can be used to calculate or derive sleep start and wake time, sleep stop, and sleep quality and depth.

 Sleep health index piston levels are determined for a healthy daily routine that includes a minimum amount of sleep per night, eight hours, and predictable bedtime and wake up time. This particular parameter, which determines the piston level calculation, is derived from or graded by the user or derived from the amount of sleep per night and bedtime and wake-up times and other data entered by the user or detected by the sensor device 10. Include the quality of.

Information about sleep is presented to the user through the sleep web page 290 shown in FIG. Sleep web page 290, along with user sleep time indicator 300 and wake up time indicator 305, may display sleep duration indicator 295 based on data input by a user or data from sensor device 10. Include. The quality of the sleep grade 310 entered by the user may also be used and displayed. If the day time interval is displayed on the sleep web page 290, the sleep duration indicator 295 is calculated and displayed as a cumulative value, and the sleep time indicator 300 and the quality of sleep grade 310 are calculated and averaged. Is illustrated. The sleep web page 290 includes a user-selectable sleep graph 315 that calculates and displays one sleep related parameter for a preselected time interval. For illustrative purposes, FIG. 11 shows the heat flux during a day period that tends to be low during sleep and high during waking. From this information, an individual's biorhythm can be derived. The sleep graph 315 includes a graphical representation of data from the accelerometer included in the sensor device 10 that monitors the movement of the body. The sleep web page 290 is associated with at least one hyperlink 220 so that a user can directly access suggestions and related news items and articles to refine and improve their daily routines for sleep and be familiar with advertising on the network. Sleep calendar 325 for selecting a time interval. The item shown as 320 may be selected and tailored based on the performance of the individual as measured by the health index and the information learned about the individual in the survey.

 The categories of daily activities of health index 155 assist the user in monitoring certain health and safety related activities and risks and are based on data entered by the user. Categories of daily activities include: personal hygiene, which enables the user to monitor activities such as combing the hair, brushing teeth, and showering, tracking whether the user is taking a dispensed medicine, and allowing the user to take automatic safety measures such as using the seat belt. And health maintenance to monitor tobacco and alcohol consumption, time spent on hanging out with family and friends, and personal time to monitor mind centering activities; And four subcategories, such as accountability activities that allow users to monitor work and monetary activities such as family day pay.

 The daily activity activity health index level is preferably determined in relation to the following health index daily routine. For personal hygiene, routines require the user to shower and bathe daily, comb and brush their teeth, and maintain regular eating habits. For health maintenance, routines require the user to take medicine and vitamins and / or nutritional supplements, use seat belts, quit smoking and drink alcohol appropriately, and check daily health with a health manager. For personal time, routines allow users to spend at least one hour a day with family and / or friends, limit work hours to a maximum of nine hours a day, spend some time on daily leisure or play activities and participate in mind stimulation activities. Requires. For accountability activities, routines require users to do household chores, pay bills, work on time, and keep appointments. The piston level is calculated based on the degree to which the daily activity list determined by the information entered by the user is completed.

Information about these activities is presented to the user through the daily activity web page 330 shown in FIG. In the preferred daily activity web page 330, the activity chart 335, selectable for one or more subcategories, shows whether the user has done what is required by the daily routine. Color or shaded boxes indicate that the user has performed the requested activity, and empty, colorless, or shaded boxes indicate that the user has not performed the requested activity. Activity chart 335 may be generated and viewed at selectable time intervals. For illustrative purposes, FIG. 13 shows personal hygiene and personal time subcategories for a particular day. In addition, the daily activity web page 330 may include at least one daily activity hyperlink (e.g., to provide users with direct access to suggestions, related news items, and articles to refine and improve daily routines for daily activities, and to be familiar with advertising on the network). 340, and a daily activity calendar 345 for selecting an associated time interval. The item indicated as 340 may be selected and tailored based on the performance of the individual as measured by the health index and the information learned about the individual in the survey.

 The How You Feel category of the health index 155 enables to monitor perception of how to feel condition for a particular day, and in particular based on subjective rating information entered directly by the user. Users are rated on a scale of one to five on nine subject areas, including mental acuity, emotional and psychological well-being, energy levels, ability to withstand stress, appearance, physical well-being, self-control, motivation and other situational comfort. To provide. These grades are averaged and used to calculate the relevant piston level.

Referring to FIG. 14, a health index web page 350 is shown. Health index web page 350 allows to view the performance of the health index for a user selectable time interval that includes any number of consecutive or discontinuous days. Using the health index selector button 360, the user can select to view health index piston levels for one category, or compare the health index piston levels side by side for two or more categories. For example, a user may simply turn on sleep to see if their overall sleep rating improved over the previous month has improved over the previous month, in a similar way that users see their performance by their preferred stock. You may want Alternatively, sleep mill activity levels may be displayed simultaneously to compare and evaluate sleep grades and corresponding activity level grades to determine if any daily correlations exist. The nutritional grade may be expressed as a feeling of condition over a preselected time interval to determine if any correlation exists between daily eating habits and how they feel during that interval. For illustrative purposes, FIG. 14 illustrates a comparison between sleep and activity level piston levels for the week from June 10 to June 16. The health index web page 350 also displays the total number of days the user has logged in and used the health manager, the percentage of days the user has used the health manager since becoming a subscriber, and the time the user used the sensor device 10 to secure data. And a tracking calender 365 that displays statistics and access information such as percentages.

Referring again to FIG. 5, opening the health manager web page 150 includes a plurality of user selectable category summaries 156a-156f, each of which corresponds to a respective health index 155 category. Each of the category summaries 156a-156f represents a preselected filtered subset of data associated with the corresponding category. Activity level category summary 156b displays daily targets and actual calories burned. Mind centering category summary 156c indicates the actual depth of target and mind centering or focus. Sleep category summary 156d indicates target sleep, actual sleep, and sleep quality grade. The daily activity category summary 156e displays targets and actual scores based on the percentage of suggested daily activities completed. The condition status feeling category summary 156f represents the target and actual rating for that day.

Opening the health manager web page 150 may include hyperlinks to news items and articles, comments, and acknowledgments to users based on their disposition, such as poor nutritional habits, determined from an initial survey on a daily time interval. Daily dose section 157 that provides information to the user. A note on the daily dose 157, for example, suggests that drinking eight glasses of water a day reduces the risk of colon cancer by as much as 32%, with the suggestion to store and frequently fill one cup of water at work on the computer or at the desk. This is a practical explanation. Opening the health manager web page 150 may also include a problem solver section 158 that actively assesses the user's performance in each of the categories of health index 155 and suggests suggestions for improvement. For example, if the user detects below the user's sleep level, suggesting that there is a problem with sleep, the problem solver 158 provides a suggestion regarding how to improve sleep. The problem solver 158 also includes user query performance with regard to improving performance. Opening the health manager web page 150 also includes a daily data section 159 that launches an input dialog. The input dialog facilitates input by the user about the various data required by the health manager. As is known in the art, the data entry may be in a form selected from a predetermined list or a general free form text input. Finally, opening the health manager web page 150 provides information about vital signs such as the user's height, weight, body measurements, body mass index or BMI, and heart rate, blood pressure, or any identified physiological parameter. Body condition section 161.

Again, in weight management embodiments, energy balance is used to track and predict weight loss and progress. Energy Balance There are two components, energy intake and energy consumption, and the difference between these two values is energy balance. Your daily calorie intake is equal to the number of calories you consume in one day. Total energy consumption is the amount of calories burned by a user whether associated with any type of activity or resting. The goal of the system is to provide a way to track daily calorie intake and automatically and accurately monitor overall energy consumption, allowing the user to track their status and progress against these two parameters. The user is also provided with feedback regarding additional activities needed to achieve their energy balance. To achieve weight loss, the energy balance should be negative, meaning that fewer calories are consumed than consumed. Both energy balances have the potential to result in no weight gain or no weight loss. The management system automates the user's ability to track energy balance through an energy intake tracking subsystem, an energy consumption tracking subsystem, and an energy balance and feedback subsystem.

Again in FIG. 9, if the user has not entered any meal or food item consumed since the latest update, the user will be prompted to initiate the energy intake subsystem 1110 to log calorie intake for a suitable meal. . The energy intake subsystem may estimate the average daily calorie intake of the user using the change in the user's weight and / or body fat composition and the overall energy expenditure estimate. Values entered into this system include estimates of body fat composition or weight and energy expenditure of the user at regular intervals associated with the relevant time period. If the user has not updated their weight in the last 7 days they will be directed to the weight reminder page 1115. The energy expenditure estimate is based on a basic equivalent of 3500 kcal equal to a 1 lb change in body weight. In addition, the software program will attempt to smooth the estimate by taking into account the fluctuations in moisture contained in the body and the difference in how the user collects weight readings, for example, at different times of day or on different scales. .

The system can also be used to derive calorie intake from the user's energy expenditure and the amount of change in body weight inputted or detected by the system. This is accomplished by using the same basic calculations described here, but the net weight increase or decrease is used as the reference input. In the equation A + B = C, A is the caloyl intake, B is the energy expenditure, and C is the net weight increase or decrease. The system cannot determine specific information regarding the type of food item consumed by the user, but can calculate how much calorie intake for the user is given given the energy consumption and known physiological parameters measured during the relevant time period. The amount of change in body fat and water can be incorporated into this calculation to make it more accurate.

This calculation of daily calorie intake is described in the simplified method of calorie input by the user, as disclosed in co-pending US Patent Application No. 10 / 682,759, the disclosure of which is incorporated herein by reference. This can be done when tuning nutrition between meal options or entering nutrition information as a test for the accuracy of the data entry and even when the user's actual calorie consumption is entered. In turn, this inverse calculation can be used in an organ setting to determine whether or not the patient is consuming or provided the meal provided to the system.

Logging of food consumed is completely optional for the user. By using this feature, the user can get feedback on how much food the user has consumed compared to what the user actually consumed as measured by the energy intake estimation subsystem described above. If the user chooses to log food intake, a semi-automatic interface guides the user through the progress of the morning, after breakfast snack, lunch, after lunch snack, dinner, and after dinner snack. If the user does not need to enter any data, for example if the user has not eaten a snack after breakfast, an option may be provided to skip the input. In addition, instant feedback on the calorie content of the selected food may be provided.

For any of the six meal events, the software wants to log in for each of the following scenarios, namely the food the user ate and what they ate; The user ate but ate the same thing as the previous day; The user ate but could not remember what they ate; You can remember what you ate and what you ate, but you don't want to enter what you ate for each meal; The user skipped a meal; The user has not yet eaten; assuming one is true. The software prompts the user to apply this scenario for each meal in time since the latest meal was entered into the system. This ensures that no gaps exist in the data. The gap in the data leads to a miscalculation of calorie balance.

If the user wants to log a food item, the software responds by prompting the user to type the first few characters of the food in a dynamic search box that pulls the closest match from the food database into a drop-down list to scroll down to just below the input. do. Upon selection of the entry, the food appears in the list of consumed foods to the right of the drop down, where addition of information such as units of measure and serving size can be edited or deleted from the list of foods consumed. The total number of calories per meal is automatically calculated at the bottom of the list of foods consumed. This method is repeated until the meal is recalculated. If the food is not in the database, a drop-down box will appear with a suggestion that the user can add individual foods to their personal database.

If the user ate the same as the previous day, the user selects the appropriate day and the selected meal appears on the right. The user enters this into the system by hitting the Next button. This specifically exploits the tendency of a person to have a repetitive eating pattern, such as the same food, for the same meal for an increased time.

If a user cannot remember a meal, the software responds by providing a screen that calculates the average value of the total number of knives consumed for that meal for a particular number of days and provides that number to the user.

If the user has eaten but does not want to enter the food items consumed, the software allows the user to enter the number of calories consumed or by selecting expressions such as normal, less than normal, more than normal, more or very less. It can provide a screen for quickly estimating. Depending on the selection, the estimated calorie intake increases or decreases from those based on average values or average ranges. For example, on average, if a user consumes between 850 and 1000 kcal of calories at mealtime, specify that the estimate is higher than 1000kcal for the related meal he ate more than usual.

If the user has not yet eaten a particular meal they may choose to proceed to a weight management center. This means that the user eats at different points in the day but does not eat at all before another meal.

In order to minimize the time the user must spend entering meal information, the system may also provide an option to select from a list of frequently consumed foods. The user can select food items from a list of frequent foods and minimize the need to search a database for commonly consumed foods. Frequent food tools are designed to speed up the task of accurately remembering and entering food consumption. This is according to the observation that people tend to eat only 35-50 unique foods seasonally. People tend to eat a core set of their favorite breakfast foods, snacks, snacks, lunches and fast foods, depending on personal preferences and convenience issues such as where they can walk or exercise for lunch in the workplace. Frequent food tools operate by counting the number of times a particular food entry is selected from the database by the user for each of the six daily meal events. The total number of selections of a particular food entry is recorded, and the top foods with the most selections appear as frequent foods according to popularity. The system also recognizes other meal related parameters of the user, such as a meal plan or diet type, and speeds up data entry by raising more relevant foods or limiting the selection above the list.

15 is a diagram of a preferred embodiment of a weight manager interface 1120. The weight manager interface 1120 is provided with a multi-section with a navigation bar 1210 that includes a series of topic tabs 1122. The tabs can be programmatically customized, but usually section 1122b for writing and selecting reports, The navigation tab 1122c to the user's profile, the navigation tab 1122d to the armband sensor device update section, the navigation tab to the meal entry section 1122e and the message section 1122f are usually included. As shown in Figure 15, there is further provided an action section 1122a, titled Balance, which includes the main user functions of the weight manager interface 1120. The calendar section 1123 is provided to the user for any particular date or It provides the ability to select and view data from that date.Features section 1125 provides commentary as described herein. And a dashboard section 1126 provides a graphical output regarding the energy intake and consumption of the selected day, after all, the weight loss progress section 1135 is in time for any given date selected in the calendar section 1123. Provides a graphical output of body weight.

The feedback and coaching engine analyzes the data generated by the total energy consumption and daily calorie intake calculations, as described herein, to provide feedback to the user in the feedback section 1125. Feedback can present various choices depending on the current state of the user's progress. If the user is losing weight and is meeting the target daily calorie intake and overall energy expenditure target, the user is encouraged to continue the program without any adjustments. If the user does not lose weight according to a predetermined target amount, the user is further provided with the option of increasing the total energy consumption, reducing the daily calorie intake, increasing the total energy consumption and increasing the daily calorie intake. Possible energy balance targets or reset target targets are reached. The feedback may further include suggestions for meals and vitamin supplements. This feedback and coaching can also be incorporated into the intermittent status reports described below because both provide similar information.

If the user chooses to reduce the daily calorie intake, the user may be given the option to plan a new meal to meet their new daily calorie target. If the user also chooses to increase the total energy expenditure target, the user may be provided with a workout plan that leads them to a predetermined target amount. An overall energy consumption estimation calculator utility may also be useful to the user. The calculator utility allows the user to choose from a number of exercise options. If the user chooses to increase overall energy consumption and reduce daily calorie intake to reach a predetermined goal, the meal plan and exercise selection may be adjusted accordingly. Safety limits can be set for daily calorie intake and total energy consumption recommendations. For example, a current schedule of less than 1200 kcal per day and exercise recommendations of more than an hour per day cannot be recommended based on the safety limits presented.

In addition, a proposal may be provided to the user to achieve a predetermined target amount. These suggestions may include specific hints as to why the user may not see the expected results, as well as wearing the user's armband more often, visiting the gym frequently, parking away from the office, or eating more regularly. It can contain simple hints such as logging.

In an alternative embodiment, the recommendations given by the coaching engine are based on a broader set of inputs, including past past recommendation history and the user's physiology data. The feedback engine can optionally associate the user with a series of questions that allow the user to derive an underlying source for failure to reach a predetermined target amount. For example, the system may ask questions including whether the user had a visitor, whether the user was in church on the weekend, whether the user was too busy to exercise, or whether the user is eating out during the weekday. Asking these questions encourages the user and understands why the user could not achieve the predetermined goal.

Another aspect of this alternative embodiment of the feedback system is that the system can evaluate the results that gave feedback to the user. This is accomplished by tracking parameters that are the subject of feedback, such as context and estimated daily calorie intake or logged intake. This feature allows the system to monitor the nature of the compliance and modify the feedback accordingly, so that the system can be observed and not just based on the results. For example, if the system proposes to eat less, the system can measure how much less the user will eat next week and use this successful response as feedback to the system's effectiveness with respect to the user's flexibility with the original feedback or suggestion. Can be tuned.

Other examples of such delayed feedback for the system are whether the user is exercising more when the system suggests, when the user is carrying more cardiovascular exercise when prompted, and when the user is wearing the armband when suggested. This type of delayed feedback signal and its continuous adaptability to the system is identified as reinforcement learning as is known in the art. This learning system tunes the behavior of the system or agent based on the delayed feedback signal.

In an alternative embodiment, the system is tuned at three levels of characteristics through a reinforcement learning framework. First, the feedback is adapted for the entire population for a given situation, such as what is the correct feedback to give when the user is on the flat. Second, feedback is consumed by a person for three weeks, for example, what may be correct feedback in situation X for a person such as person Y or may differ from the character or tone or character of the feedback given to the man in the same state. Adapt to a group of people, such as what is the correct feedback for a woman when the target is not achieved. Finally, the system can also be adapted directly on the basis of an individual, such as what is the best feedback for a particular user who has not exercised sufficiently in a given week.

In another aspect of the invention, feedback provided to a user may be predictive in nature. In time, an individual may experience an untargeted or negative situation, such as weight gain, during a weight loss regimen. The situation can also be positive and neutral. Because of the continuous monitoring of the data through the use of the system, events surrounding the situation, i.e. immediately before and following the situation, can be analyzed to determine and classify the type of event. The sequence of parameters, readings or events can be recorded in a pattern that the system can store and review. The system can compare current data for this situation with previous data or patterns to predict whether similar situations have occurred previously and whether past episodes will occur recently. The system can then provide feedback regarding the situation, and for each occurrence, the system can tailor the feedback provided to the user based on the response detected or provided by the user. The system may further tailor the feedback based on the efficiency of the feedback. If the system is more personalized with respect to the user, the system may proactively present suggestions based on the user's detected response to the feedback. For example, in situations where a user reaches flat in weight management, the system may formulate a new proposal to allow the user to return to a state of progress.

The system also modifies the reinforcement learning framework for detected or undetected responses to the provided feedback. For example, if the system suggests that the user increase their energy consumption but the individual responds by wearing the armband more often, the system can modify the framework based on the user's sensitivity to feedback. This augmentation arises from any difference in behavior as well as from the user's direct interaction with the system even if the connection is not immediately apparent.

It should be particularly noted that predictive analysis of data regarding negative or neutral situations may be based on a user's personal history or pattern or on aggregated data of similar data from other users in a population. Population data may be based on data collected from a user of any embodiment of the system, including but not limited to weight management.

Moreover, as the user experiences multiple cases of similar situations, the system may begin to understand how an individual has reached this stage and whether a person has successfully attempted to correct the situation unsuccessfully. The system uses pattern matching to enhance its learning and adaptability, further modifying future feedback the next time this situation occurs. For example, it is not abnormal in weight management that the user experiences a congestion that slows the user's metabolism to preserve calories and the user cannot experience any progress to a predetermined goal. In addition, it may happen that a user deviates from a predetermined goal for a temporary and long period of time, such as a long weekend, vacation, business trip or constant weather conditions, and the system warns and avoids impending problems prior to congestion or such an event. Providing reminders can be provided.

In an alternative embodiment, when a user experiences a negative, positive or neutral situation that is likely to affect the progress achieved, the system may indicate the risk factors described above when they are affected by the situation. For example, if the user has experienced a negative situation causing weight gain, the system may determine that the risk for heart disease of the user is now rising. This elevated risk is represented in the risk factor for that condition and compared with the risk at the user's target level.

The description given for guiding a person through an automated process of behavior modification combined with augmentation of a series of physiological and / or contextual states of the individual body and their previous responses has been described for specific behavior modifications in weight management. It will be apparent to those skilled in the art that there is no need to limit the behavior modification goals. This process may be applied without limitation to sleep management, pregnancy health care, diabetes disease management, cardiovascular disease management, fitness management, infant health care, and stress management, with the same or other additional inputs or outputs into the system.

Equally, the system is applicable to diabetic patients using weight management tools, with rapid changes in insulin levels and blood glucose levels recorded in the data or with a series of or severe symptoms. In such embodiments, the input values, ie calories ingested, types of calories, activity and energy expenditure and weight may be the same as the weight embodiment. For insulin levels, management specifically tuned for body insulin levels, calorie intake, calorie burn, activity classification and weight management where the feedback of such a system is predicted may be used. The user input includes a glucometer reading similar to the weight scale of the weight loss embodiment. It should be noted that insulin levels are indirectly related to energy balance and thus weight management. Even for non-diabetes, low insulin levels reflect a limitation on energy consumption because the body cannot have its maximum potential.

In addition to physiological and contextual parameters, environmental parameters can also be monitored to determine impact on the user. Such parameters may include, but are not limited to, ozone, pollen counts, and humidity and may be useful in systems of asthma management.

There are many aspects of feedback that can be applied to different embodiments of such a system. For example, the medium of feedback can be modified. Based on the performance, the system may choose to contact the user via phone, email, fax, or website. The tone or format of the message can be modified by selecting a strong message that is itself delivered, for example, as a popup message. A message like "You are too lazy! I order you to exercise more with me there this week" or "You were doing very well, but if you can find more time to exercise this week, Will be closer to your target, ”a softer tone message can be delivered in the feedback center of the website.

The system may also include a remote feature that provides a summary of energy consumption, daily calorie intake, energy balance or nutritional information for any period of time. The user is provided with an interface to graphically view and analyze the number of their energy balances. The inputs to the energy balance calculation are the total calorie intake estimated using the total energy consumption and body weight or body fat change and total energy consumption estimates based on the use of the energy consumption tracking system. This information can be provided to the user in equation form and visually. Shortcuts are provided for commonly used summary periods such as daily, yesterday, last 7 days, last 30 days, and after start.

Reports can also be personalized in a variety of ways, including what the user has requested to see in the past or what the user has actually done. Reports can be personalized by third party specifications or by user selection. The workout tab may be left if the user has not exercised. The user may require viewing a diary of past feedback to see the type of feedback previously received. If the feedback is all about controlling daily calorie intake, the report may be more than nutritional. Those skilled in the art will appreciate that this report can be enhanced in any way that the feedback engine can be enhanced and viewed as an extension of the feedback engine.

Again in FIG. 15, balance tab 1122a illustrates the summary of the user's weight loss progress in various formats. For the balance section 1122a, the weight loss progress graph 1135 describes the user's weight loss progression from the date the user initiated using the entire weight loss system to the current date. Energy balance section 1136 provides details regarding the user's actual and target energy balance, including actual and target calories burned and burned actual and target calories. The energy balance graph 11370 is a graphical representation of this same information.The dashboard section 1126 also has a performance indicator section 1146 that allows the user to know the status of their energy balance relative to their target values. The information contained in the performance indicator section 1146 may be a graphical representation of the information in the feedback section 1125. Optionally, the system may include calorie, carbohydrate and fat content in the form of a list and chart of specific foods consumed during the relevant time period. Similarly, the indication may include a charted list of all activities performed during the relevant period along with relevant data such as duration of activity and calories burned. It can be used to log activity at a user selected level of detail, including exercise, beauty exercises, and the like.

In alternative embodiments, the system may also provide intermittent feedback to the user in the feedback section 1125 alone or in conjunction with the feedback and coaching engine. The feedback and coating engine is a more specific or alternative embodiment of the problem solver, as described above. Feedback may also be expressed in additional display boxes in the form of periodic or intermittent status reports 1140, as appropriate. Intermittent status report 1140 may also be requested by the user at any time. The status report can be an alert located in a box on the location of the screen and is usually installed to attract the user's attention. Status reports and images may be generated by generating key strings or parameter sets based on the user's current view and provide the user with information regarding their weight loss goal progression. This information usually includes a suggestion to meet the user's calorie balance target for that day.

An intermittent status report 1140 is generated on the balance tab 1122a of the weight manager interface 1120. The goal of the intermittent status report 1140 is to provide the user with instant command feedback for the selected view. The property file containing the key value pairs is searched to match the corresponding keys with images and messages that achieve specific selection criteria.

In the preferred embodiment, there are four possible views for intermittent status report 1140 today, a specific day, average (last 7 or 30 days), and after initiation.

User status is incorporated as part of the selection criteria for intermittent status report 1140. The user status is based on the actual and target values of daily calorie intake and energy expenditure as previously described. Targeted and predicted energy balances based on daily calorie intake and energy consumption are also used as additional comparison factors for user states 4 and 5. Possible user states are shown in Table 3.

condition Explanation Calculation One You will not reach your energy target and your daily calorie intake is below the budget. (Energy consumption <target energy consumption) and (daily calorie intake <= target daily calorie intake) where = has a tolerance of ± 50 calories. 2 The user will burn or burn more calories than the target, and the daily calorie intake is below the budget. (Energy consumption> = target energy consumption) and (daily calorie intake <= target daily calorie intake) where = has a tolerance of ± 50 calories. 3 The user did not exercise enough and ate too much. (Energy consumption <target energy consumption) and (daily calorie intake> target daily calorie intake) where = has a tolerance of ± 50 calories. 4 The user has exceeded the calorie intake target, but the energy consumption must compensate for it. (Energy consumption> = target energy consumption) and (daily calorie intake> target daily calorie intake) && (predicted energy balance> = target energy balance) where = has a tolerance of ± 50 calories. 5 The user has exceeded the calorie intake target, but the energy expenditure target will not make up for it. (Energy consumption> = target energy consumption) and (daily calorie intake> target daily calorie intake) && (predicted energy balance <target energy balance) where = has a tolerance of ± 50 calories.

The user's current energy balance is also used to determine some of the selection criteria.

String Calculation black (Energy consumption = daily calorie intake)> 40 equilibrium -40 <(energy consumption-daily calorie intake) <40 Red 40 <(Energy Consumption-Daily Calorie Intake)

The last part of the selection criteria depends on the type of view selected as described above. Specifically, today's view incorporates two parameters to predict the user's ability to correct energy balance defects by the end of the relevant period.

String Explanation Early Favorite activities take less than an hour to correct energy balance and are before 11 pm; Activities suitable for the user will correct the energy balance and remain within the relevant time period for its completion in sufficient time. Reit Your favorite activity takes more than an hour to correct the energy balance or after 11 pm; There is not enough time to complete an activity that will return a positive result for energy balance.

All other views use two types of information to estimate the validity of the target.

String Calculation Effective goal (State 2 or 4), there is a valid activity to make up for a difference in time that is 80%>% DCI or% EE> 120% and less than another hour based only on percent. Suspension Goal (State 2 or 4), there is no valid activity to make up for a difference in time that is 80%>% DCI or% EE> 120% or less than another hour based only on percent .

Here,% DCI or% EE represents the current percentage of daily calorie intake or energy consumption, as appropriate with respect to the user's goals.

Similar methods are used to determine the message under each horizontal bar chart as shown in FIG. 15. The next part of the selection criteria is the attainment state, which is determined by the current value of the daily calorie intake or energy consumption associated with the goal set by the user. The parameters are as follows:

String Calculation top Value> target value same Value = target value bottom Value <target value

In an alternative embodiment, the representation underlining the method for selecting feedback may be a decision tree, a planning system, a constraint fulfillment system, a frame based system, a case based system, a rule based system, a predictive calculus, a universal planning system or It may be a probabilistic network, but is not limited thereto. In an alternative embodiment, another aspect of the method is to apply a subsystem for selecting feedback. This can be done, for example, using a decision-theoretic adaptive probability system, a simple adaptive planning system, or a gradient descent method on a set of parameters.

In calculating the energy balance, the armband sensor device continuously measures the energy consumption of a person. During that day, the body continuously burns calories. The minimum rate at which the body consumes energy is called the resting metabolic rate, or RMR. For the average person, the daily RMR is about 1500 calories. This is more for more people.

Energy consumption is different from RMR because the person knows during the day how many calories have been burned by the time of rest and activity. When the user looks at the energy consumption information, two things can be seen. First, the calorie burning amount of the individual from midnight to the time recorded on the armband sensor device, and second, the user's RMR from the current time to the end of the day. The sum of these numbers is a prediction of the minimum amount of calories the user consumes during the day.

This estimate can be improved by applying a multiplicative factor to the RMR. Human lifestyles contribute significantly to the amount of energy they consume. People on the left who do not exercise burn only slightly more calories than consumed by their RMR. Constantly active athletes burn significantly more calories than RMR. This lifestyle impact on RMR can be estimated as a multiplication factor for RMR ranging from 1.1 of the top left person to 1.7 of the athlete. This multiplication factor may also be calculated from the average value of a person's wearing time based on the time of day or time of year or may be determined from information entered by a person into a date or time management program, as described above. Using these factors greatly improves the predictive nature of the estimated daily consumption for the individual.

The final factor predicting weight loss trend is the nutritional log. Nutrition logs allow people to keep track of what they are eating. It records the amount of calories consumed so far for that day.

By knowing the amount of calories consumed and the amount of calories burned by a person, the armband sensor device can calculate the energy balance of a person. Energy balance is the difference between burned and consumed calories. If a person burns more calories than they consume, they are in a weight loss trend. If people are consuming more calories than they are in a row, they are in a weight gain trend. The energy balance prediction is an estimate made at any time during that day of a person's actual daily energy balance for that day.

The proposal is provided in the form of an intermittent status report, which takes one of three general forms. First, a person may be in compliance to achieve a predetermined target value. This means that the energy balance prediction is within the allowable deviation approximating the daily target value. If the user's energy balance indicates that more calories can be burned during the day than more calories have been consumed, the user may be congratulated since he has exceeded a predetermined target value. Finally, the user may have burned more calories than planned to be continuous. In this case, the system can calculate how much more the user needs to burn to meet the target value. Using the predicted energy consumption associated with general activities such as walking, the system can also suggest a method for achieving the target value within a predetermined time period. For example, a person who needs to burn 100 more calories may be advised to take the activity to achieve a target value if the system recognizes that it can burn calories that require 30 minutes of walking.

Many people, especially during the working week, settle for routine. For example, a person can wake up at the same time each day, go to work, then go home and exercise before taking a break. Their eating pattern may also be similar from day to day. By detecting similarities that have worked in human behavior, armbands can make more accurate predictions of a person's energy balance and thus a person's weight loss trend.

There are a number of ways in which energy balance predictability can be improved by analyzing the user's historical data. First, the amount of rest for activity in a person's lifestyle can be used to improve the RMR estimate over the remaining time of the day. Second, the day can be divided into units of time to improve the estimate. For example, those who exercise normally in the morning and rest in the evening have a different daily profile than those who exercise in the evening. The energy consumption estimate may be adjusted based on time to better predict the energy balance of the individual. A person's activity may also vary with a daily or weekly schedule, time of year, or progress of progression to a predetermined target value. The energy expenditure estimate can thus be adjusted accordingly. Again, this information can be obtained from a time or date management program. Third, it is possible to predict how many calories a person normally burns by generating the average value of a person's daily energy consumption over a certain time.

Likewise, by detecting trends in a person's eating habits, one can estimate how many calories a person is expected to consume. For example, a person who eats a lot of breakfast but a few dinners has a different profile than a person who skips breakfast but eats a lot less during the day. These different eating habits can also be reflected in the user's energy balance to provide more accurate daily estimates.

The concept of energy balance is not limited to a single blade. This can also apply to multiple days, weeks, months or even years. For example, people often overeat at special events such as holidays, birthdays or anniversaries. Such abnormal consumption meal spurts may be spurless or contribute to organ patterns. The actual energy balance over time may indicate a weight loss or weight gain trend and may help an individual match his goal to actual exercise and eating habits.

Logic is provided in FIGS. 16-19 to calculate the intermittent status report 1140. 16 illustrates the calculation of an intermittent status report 1140 using information from both energy consumption and calorie intake values. If the intermittent status report state 1150 indicates that the intermittent status report 1140 is already ready for today, the intermittent status report program is an energy balance value 1155 that is the difference between energy consumption and daily calorie intake. Returns. An adjustment threshold, for example 40 calories, is selected as the target tolerance to place the user in one of three categories. If the difference between energy consumption and daily calorie intake is greater than +40 calories, the balance status indicator 1160 indicates that the user has significantly exceeded the daily energy balance target for that day. If the difference between these values is less than -40 calories, the balance status indicator 1160 indicates that the user failed to meet the daily energy balance target value. If the difference between these values is zero or nearly zero, as defined by the tolerance between ± 40 calorie differences, the balance state indicator 1160 indicates that the user has met the daily energy balance target. The program executes a time check (1165). As the current time is before or after the auxiliary time limit, the program determines whether it is first or later. In addition, the program may all be based on a previous intermittent status report 1040 for that day, within a time limit of the day based on time of day or together with suggestions for energy expenditure activity to assist in achieving the target value. Display an energy balance target intermittent status report 1170 indicating whether individuals within another period have time to meet their energy balance target values.

If the intermittent status report state 1150 determines that the intermittent status report 1040 is not ready for today, the program retrieves the energy balance value (1155) and determines whether the energy consumption is greater or less than the calorie intake value. do. According to the value of the difference between the energy expenditure value and the calorie intake value indicated by the balance state indicator (1160), the program performs a user state determination. The user state determination unit 1175 is an overall relationship between the target and actual daily calorie intake for the same period and the user's target and actual energy consumption during the relevant period. After the program determines the user's state, the program determines the target state 1180 of the user. If the state of the goal is within a certain percentage of completion, the program executes a time decision 1185 as to whether the user can still meet this goal in the time frame by performing a particular activity. The program displays the relevant energy balance target intermittent status report 1170 to the user. The content of the intermittent status report 1170 is determined by the results of these various decisions and selected from a suitable library of related.

17 illustrates the generation of an intermittent status report based only on energy consumption. If the intermittent status report state 1150 indicates that the intermittent status report 104 is ready for the day, the program calculates an energy consumption target progress 1190 that is the difference between the target energy consumption and the current energy consumption. If the energy consumption exceeds the target consumption, the program determines (1195) any required momentum that needs to be made available to the user to achieve the energy consumption target for that day. Similarly, if the current or predicted energy expenditure value is less than the target energy expenditure, the program determines 1195 any required amount of exercise to enable the user to achieve the daily goal. The energy expenditure intermittent status report 1200 will be generated based on the information including this proposed athletic activity.

If the intermittent status report 1040 has not been prepared for the relevant period of time, the intermittent status report status 1150 instructs the program to calculate the energy expenditure target progress 1190 using the target and the predicted energy expenditure values. Based on this value, the program determines (1195) any required amount of exercise that allows the user to achieve an energy expenditure goal. Energy consumption intermittent status report 1200a is generated based on this information, including any suggested athletic activity.

18 illustrates how the program generates an intermittent status report based solely on calorie intake. The calorie state 1205 is calculated, which is the difference between the target calorie intake and the predicted calorie intake. If the predicted calorie intake is greater than the target calorie intake, the user has exceeded the calorie budget. If the estimated calorie intake is less than the target calorie intake, the user has consumed fewer calories than the calorie budget. If this value is nearly zero or zero, the user has met their calorie budget. A calorie intake intermittent status report 1210 is generated based on this information.

Likewise, FIG. 18 illustrates how the program makes a user state state determination 1215 of a user's calorie intake. This calculation may be the same as the determination of the user's state of energy consumption. The user state state is determined by subtracting the difference between the predicted calorie intake and the target calorie intake. An adjustment threshold, for example 50, is selected as the target tolerance for placing the user in one of three categories. If the difference between the predicted calorie intake and the target calorie intake is greater than +50 calories, the state status determination result is one. If the difference between the predicted calorie intake and the target calorie intake is less than -50 calories, the state state determination result is -1. If the amount is greater than the predicted amount, the program returns a negative one. If the value is nearly zero or equal, as defined by the tolerance between ± 50 calorie differences, the state state determination result is zero.

Based on the user state state determination described above, FIG. 19 illustrates how the program ultimately makes user state decision 1175. The program makes a user state status decision 1215 of the user's calorie intake determination based on the calculation. After the program returns a value of 1,0, or -1, the program makes a user state status decision 1215 of the user's energy consumption. Based on the combination of these values, the user state decision 1175 is calculated.

As shown in FIGS. 20-25, certain embodiments of sensor device 10 are shown in the form of armbands adapted to be worn over an individual's arm or between a shoulder and an elbow. Although similar sensor devices are worn on other parts of the individual's body, these locations have the same function for single or multiple sensor measurements of the user's activity or state and for automatic detection and / or identification. For the purposes of this disclosure, the sensor device 10 of this particular embodiment shown in FIGS. 20-25 is conveniently referred to as the armband sensor device 10. Armband sensor device 400 includes a computer housing 405, a flexible wing body 410, and an elastic strap 415, as shown in FIG. 25. Computer housing 405 and flexible wing body 410 are preferably made of synthetic rubber or flexible urethane material, such as rubber or rubber-silicon blends by molding methods. The flexible wing body 410 includes first and second wings 418, each having a through hole 420 located near its end 425. First and second wings 418 are adapted to surround the wearer's upper arm.

Elastic strap 415 is used to detachably attach armband sensor device 10 to an upper arm of an individual. As can be seen in FIG. 25, the bottom surface 426 of the elastic strap 415 is provided with a velcro loop 416 along a portion thereof. Each end of the elastic strap 415 has a velcro hook patch 428 on the bottom surface 426 and a pull tab 429 on the top surface 430. Each pull tab 429 portion extends beyond the edge of each end 427.

 To wear the armband sensor device 400, a user inserts each end 427 of the elastic strap 415 into each through hole of the flexible wing body 410. The user is then positioned his arm through a loop created by the elastic strap 415, the flexible wing body 410 and the computer housing 405. By pulling each pull tab 429 and engaging the velcro hook patch 428 with the velcro loop 416 in a desired position along the bottom surface 426 of the elastic strap 415, the user can comfortably wear it. The elastic strap 415 can be adjusted. Since the velcro hook patch 428 can be engaged with the velcro loop 416 at the desired position along the bottom surface 426, the armband sensor device 400 can be adjusted to attach to arms of various sizes. In addition, the elastic strap 415 may be provided in various lengths to accommodate a variety of different sizes. As will be apparent to those skilled in the art, other means, including snaps, buttons or buckles, may be used to tighten and adjust the size of the elastic strap. It is also possible for the user to use two elastic straps that are secured by one of several means including velcro, snaps, buttons or buckles, or by only a single elastic strap attached to the wing 418.

Alternatively, instead of providing a through hole 420 in the wing 418, a loop having a capital letter D shape may be attached to the end 425 of the wing 418 by one of several conventional means. For example, a pin, not shown, can be inserted through end 425, where the pin engages each end of each loop. In this configuration, the D-shaped loop serves as a connection point for the elastic strap 415, which effectively creates a through hole between each end 425 of each wing 418 and each loop.

As shown in FIG. 26, which is an exploded view of the armband sensor device 400, the computer housing 405 includes a top 435 and a bottom 440. The computer housing 405 includes a printed circuit board or PCB 445, a rechargeable battery 450, preferably a lithium ion battery, model 12342 and 12343 motors sold by permanent MG motors, as used in pagers, A vibration motor 455 is included that provides tactile feedback to the wearer.

 The top 435 and bottom 440 of the computer housing 405 are hermetically mated along the groove 436 with which the O-ring 437 is mated, and the aperture 439 and bottom in the PCB 445. It may be attached to each other by a scoop, not shown, passing through the stiffener 438b and the scoop hole 438a of 440 and into the threaded receiving stiffener 451 of the top 435. Alternatively, top 435 and bottom 440 may be attached to each other with an adhesive or snap matched together. Preferably, the assembled computer housing 405 may be sufficiently waterproof to allow the armband sensor device 400 to be worn without adversely affecting its performance while swimming.

As can be seen in FIG. 21, the bottom portion 440 includes a raised platform 430 on its bottom side. A heat flux or flow rate sensor 460 is attached to the raised platform 430, which may be a good example of a micro-foil heat flux sensor sold by RdF Corporation of Hudson, New Hampshire. The heat flux sensor 460 functions as a magnetically generated thermopile transducer and includes a carrier made of a polyamide membrane. The bottom portion 440 includes a heat sink, not shown, made of a suitable metal material, such as aluminum, on its top side opposite the side on which the heat flux sensor 460 is fixed. The raised platform 430 also has a GSR sensor 465 that includes an electrode formed of a material such as conductive carbonized rubber, gold or stainless steel. Although two GSR sensors 465 are shown in FIG. 21, those skilled in the art will appreciate that the number of GSR sensors 465 and their position on the raised platform 430 are as long as the individual GSR sensors 465, i.e., the electrodes are insulated from each other. It will be appreciated that it may vary. By being secured to the raised platform 430, the heat flux sensor 460 and the GSR sensor 465 are adapted to contact the wearer when the armband sensor device 400 is worn. The bottom 440 of the computer housing 405 may be provided with a removable and replaceable soft foam fabric pad, not shown, on its surface that does not include the raised platform 430 and the scoop holes 438a. Can be. The soft foam fabric is intended to be in contact with the wearer's skin and makes the armband sensor device 400 more comfortable to wear.

 Electrical connection between heat flux sensor 460, individual GSR sensor 465, and PCB 445 is accomplished in one of several known ways. By way of example, suitable wiring is molded to the bottom 440 of the computer housing 405 and electrically connected by soldering to the appropriate input position and heat flux sensor 460 and individual GSR sensors 465 on the PCB 445. . Alternatively, rather than molding a line to the bottom 440, a through hole is provided in the bottom 440 through which appropriate wiring can pass. The through hole is provided with an airtight waterproof seal to maintain the integrity of the computer housing 405.

Rather than being secured to the raised platform 430 as shown in FIG. 21, one or both of the heat flux sensor 460 and the individual GSR sensor 465 may be the skin of the wearer when the armband sensor device 400 is worn. Secured to the interior 466 of the flexible wing body 410 on the wing 418. In this configuration, the electrical connection between the heat flux sensor 460 and the individual GSR sensor 465 and the PCB 445 pass through one or more through-holes of the computer housing 405 and solder to the appropriate input location on the PCB 445. Is achieved by suitable wiring molded to the flexible wing body 410 which is electrically connected by it. The through hole is provided with an airtight waterproof seal to maintain the integrity of the computer housing 405. Alternatively, rather than providing a through hole in the computer housing 405 through which the wiring passes, the wiring is captured in the computer housing 405 during the overmolding process and finally soldered to the appropriate input location on the PCB 445 as described below. do.

As shown in FIGS. 20, 24, 25, and 26, the computer housing 405 includes buttons 470 connected and applied to activate the momentary switch 585 on the PCB 445. Button 470 is used to wake up armband sensor device 400 for use in indicating an event occurrence time or for requesting system state information such as battery level and memory capacity. When button 470 is pressed, momentary switch 585 closes the circuit and a signal is sent to processing unit 490 on PCB 445. Due to the time interval at which button 470 is pressed, the generated signal triggers one of the above events. The computer housing 405 also includes LEDs 475, which can be used to indicate battery level and memory capacity or to provide visual feedback to the wearer. Rather than LEDs 475, computer housing 405 may include a liquid crystal display, an LCD to provide the wearer with battery level, memory capacity or feedback information. Battery level, memory capacity or feedback information may be provided to the user tactilely or audibly.

 The armband sensor device 400 collects data when the heat flux sensor 460 and the individual GSR sensors 465 detect a particular condition indicating that the armband sensor device 400 has been placed in contact with the user's skin. It is adapted to be activated for use. The armband sensor device 400 may also be used alone or in combination with one another by the heat flux sensor 460, the individual GSR sensor 465, the accelerometer 495 or 550, or any other device that communicates with the armband sensor device 400. The armband sensor device 400 is adapted to be activated for use in the case of detecting a particular condition indicating that the armband sensor device 400 has been placed in contact with the user's skin. Otherwise, armband sensor device 400 is deactivated to conserve battery power.

 The computer housing 405 is adapted to be connected to the battery recharger unit 480 shown in FIG. 19 for the purpose of recharging the rechargeable battery 450. Computer housing 405 includes a recharger contact 485 shown in FIGS. 20, 23, 24 and 25 connected to rechargeable battery 450. Recharger contact 485 may be made of a material such as bronze, gold or stainless steel and is electrically connected and mated to an unshown electrical contact provided to battery recharger unit 480 when armband sensor device 400 is located. Is applied. The electrical contact provided to the battery recharger unit 480 is connected to the recharge circuit 481a provided inside the battery recharger unit 480. In this configuration, the recharge circuit 481a is connected to the wall outlet by way of wiring, including a suitable plug attached or attachable to the battery recharger unit 480. Alternatively, the electrical contact 480 is connected to a wire attached or attachable to the battery recharger unit 480 that is connected to the recharge circuit 481b external to the battery recharger unit 480. The wiring of this configuration may include a plug, not shown, adapted to plug into a conventional outlet.

 Inside the battery recharger unit 480 is provided an RF transceiver 483 provided in the computer housing 405 and adapted to receive or transmit signals from the RF transceiver 565 shown in FIG. 20. The RF transceiver 483 is adapted to be connected with an appropriate cable to a USB port of a device such as the personal computer 35 shown in FIG. 1 or a serial port such as an RS 232 port. Although RF transceivers 483 and 565 are shown in FIGS. 19 and 20, other types of wireless transceivers, such as infrared transceivers, may be used. Alternatively, the computer housing 405 may be further electrically connected and mated to an additional electrical contact (not shown) provided in the battery recharger unit 480 when the armband sensor device 400 is located. Contact is provided. Additional electrical contacts in the computer housing 405 are connected to the processing unit 490 and the additional electrical contacts provided to the battery recharger unit 480 may be connected to a USB port or RS 232 port of a device such as a personal computer 35. The cable is connected to the serial port. This configuration provides an alternative method of downloading data to or uploading data from the armband sensor device 400 over a physical connection.

20 is a schematic diagram showing the system structure of the armband sensor device 400, in particular the respective components connected to or on the PCB 445.

As shown in FIG. 26, the PCB 445 includes a processing unit 490, which may be a microprocessor, microcontroller, or other processing device that may be applied to perform the functions described below. The processing unit 490 is adapted to provide all the functions described in connection with the microprocessor 20 shown in FIG. A suitable example of processing unit 490 is Dragon Ball EZ, sold by Motorola, Schaumburg, Illinois. PCB 445 also has a two-axis accelerometer 495, a model ADXL210 accelerometer sold by Norwood, Inc., Analog Devices. The two-axis accelerometer 495 is positioned on the PCB 445 at an angle at which its sensing axis is offset by an angle of approximately 45 degrees from the longitudinal axis of the wearer's arm when the armband sensor device 400 is worn. Is mounted. The longitudinal axis of the wearer's arm refers to the axis defined by a straight line from the wearer's shoulder to the wearer's elbow. The signal of the two-axis accelerometer 495 passes through the buffer 500 and is input to an analog-to-digital converter 505 connected to the processing unit 490. The amplifier 510 provides an amplification and low pass function, for example, the model AD8544 sold by Norwood, Inc., an analog device company. The amplified and filtered signal output by the amplifier is input to an amplifier / offset 515 and filtered / conditioned circuit 520 to provide additional gain and remove any bias voltage, respectively, connected to the analog-to-digital converter 505. ) Is entered. The heat flux sensor 460 is connected to a vehicle input amplifier 525, such as a model INA amplifier sold by Tucson's Burr-Brown Corporation, Arizona, and the final amplified signal is filtered before being input to the analog-to-digital converter 505. Pass through circuit 530, buffer 535, and amplifier 540. Amplifier 540 is a battery monitor configured to provide additional gain and low pass filtering, such as the Model AD8544 sold by Norwood Analog Devices Inc., Mass., And monitor the remaining power level of rechargeable battery 450 ( 545). The battery monitor 545 includes a voltage divider with a low pass filter to supply an average battery voltage. When the user presses the button 470 to request a battery level, the processing unit 490 examines the output of the battery monitor 545 and sends the user through the LEDs 475, preferably the vibration motor 455 or Instructions are provided via ringer 575. LCDs can also be used.

PCB 445 may include a three-axis accelerometer 550 instead of or in addition to two-axis accelerometer 495. The three-axis accelerometer outputs a signal to the processing unit 490. Suitable examples of three-axis accelerometers include Scottsdale, I.M. PAM sold by the system. The three-axis accelerometer is tilted in the manner described for the two-axis accelerometer 495.

PCB 445 also includes an RF receiver 555 coupled to processing unit 490. RF receiver 555 is used to receive a signal output by another wirelessly transmittable device shown in FIG. 20 as a wireless device 558 positioned or worn near an individual wearing armband sensor device 400. Can be used. As an example, wireless device 558 may be a heart rate monitor mounted on a chest, such as a tempo product sold by Polar Electro of Oulu, Finland. Using the heart rate monitor, data indicative of the wearer's pulse rate may be collected by the armband sensor device 400. An antenna 560 and an RF transceiver 565 are connected to the processing unit 490 and upload data to and from the central processing unit 30. The RF transceiver 565 and the RF receiver 555 may employ Bluetooth technology as a wireless communication protocol. In addition, other forms of wireless transmission, such as infrared transmission, may also be used.

Vibration motor 455 is connected to processing unit 490 via vibrator driver 570 and provides tactile feedback to the wearer. Similarly, Ringer 575, a suitable example of which is a model SMT916A Ringer sold by Project Unlimited, Dayton, Ohio, is processed through Ringer driver 580, a suitable example of a model MMBTA14CTI Darlington transistor driver sold by Motorola, Schaumburg, Illinois. Connected to unit 490 and providing acoustic feedback to the wearer. Feedback may include, for example, congratulations, attention, and other threshold or event driven messages when the wearer reaches calorie levels consumed during exercise.

A momentary switch 585 is also provided on the PCB 445 and connected to the processing unit 490. Momentary switch 585 is also coupled to button 470 for actuating momentary switch 585. LED 475, which is used to provide various types of feedback information to the wearer, is connected to the processing unit 490 via an LED latch / driver 590.

An oscillator 595 is provided on the PCB 445 and supplies a system clock to the processing unit 490. A reset circuit 600 that can be accessed or triggered through the pinhole next to the computer housing 405 is connected to the processing unit 490 to enable the processing unit 490 to reset to its standard initial settings.

The rechargeable battery 450, the main power source of the armband sensor device 400, is connected to the processing unit 490 via a voltage regulator 605. Finally, the SRAM 610 on the PCB 445 provides a memory function for the armband sensor device 400 that stores data about the wearer of the armband sensor device 400. SRAM 610 and flash memory 615 are coupled to processing unit 490 and preferably each have a storage capacity of at least 512K.

In the manufacture and assembly of the armband sensor device 400, the top 435 of the computer housing 405 is first formed, preferably, as in a conventional molding process, and then the flexible wing body 410 is Overlay molded on the top of the top (435). That is, the top 435 is located in a suitably formed mold, ie, having a residual cavity formed according to the desired shape of the flexible wing body 410 when the top 435 is positioned, and the flexible wing body 410 Is molded to the top of the top 435. As a result, the flexible wing body 410 and the top 435 are joined or glued together to form a single unit. Alternatively, the top 435 of the computer housing 405 and the flexible wing body 410 may be formed together, such as by molding into a single mold. However, the single unit formed can then rotate so that the bottom of the top 435 faces upward, the contents of the computer housing 405 can be located on the top 435, and the top 435 and the bottom ( 440 may be attached to each other. As another alternative, the flexible wing body 410 may be formed separately, such as as in a conventional molding process, wherein the computer housing 405, and in particular the top 435 of the computer housing 405, is adhesive It may be attached to the flexible wing body 410 by one of several well known methods, such as by snap fitting, or screwing two pieces together. The remainder of the computer housing 405 will then be assembled as described above. Rather than assembling the rest of the computer housing 405 after the top 435 is attached to the flexible wing body 410, the computer housing 405 may be assembled first and then the flexible wing body 410. Will be attached.

In the various embodiments described above, specifically contemplated are methods in which activity or nutritional data is input or detected in the system for derivation of the data needed. As described in many embodiments, automatic detection of specific activity and / or nutritional intake can replace this manual input.

One aspect of the invention relates to a sophisticated algorithm development process that generates a wide range of algorithms for generating information relating to various variables from data received from a plurality of physiological contextual sensors on a sensor device 1201. Such variables include sleep, effective total value, energy consumption including calorie intake per day, sleeping, sleeping initiation, sleep disturbance, waking up, and sleeping, and exercise, sitting, moving, and lying down. Algorithms for generating values for such variables may include, for example, a two-axis accelerometer, a heat flux sensor, a GSR sensor, a skin temperature sensor, a vicinity of the body, for example. Based on data from the temperature sensor, and heart rate sensor.

Note that there are several types of algorithms that can be computed. By way of example, and not limitation, these include algorithms for predicting user characteristics, continuous measurement, persistent context, instantaneous events, and cumulative conditions. User characteristics include the wearer's permanent and semi-permanent parameters, including perspectives such as weight, height, and wearer identity. An example of continuous measurement is energy consumption, in which the number of calories of energy consumed by the wearer is continuously measured, eg every minute. A persistent context is an action that lasts for a period of time, such as sleeping, driving, or jogging. Momentary events are those that occur at fixed or very short time, such as a heart attack or depression. Cumulative conditions are those in which a person's condition can be inferred from its behavior over a particular previous period. For example, if a person did not sleep within 36 hours and did not eat within 10 hours, he would be tired. Table 3 below shows many examples of specific personal characteristics, continuous measurements, continuous measurements, momentary events, and cumulative conditions.

Personal characteristics Age, gender, weight, gender, athletic ability, conditioning, disease, height, immunity, activity level, individual detection, good hand, metabolic rate, body composition Continuous measurement Mood, heart rate change, breathing, energy expenditure, blood sugar level, ketosis level, heart rate, stress level, fatigue, alertness level, blood pressure, redness, strength, persistence, affinity, hourly step, calm level, body position and orientation , Cleanliness, mood or impact, accessibility, calorie intake, TEF, XEF, 'in the zone'-ness, active energy consumption, carbohydrate intake, fat intake, protein intake, hydration level, authenticity, sleep quality, sleep status, consciousness Levels, drug effects, medication predictions, water intake, alcohol intake, dizziness, pain, comfort, remaining processing power for new stimuli, proper use of armbands, interest in topic, relative effort, locating, blood alcohol level Continuous measurement Exercise, sleep, lying down, sitting, standing, walking, running, walking, viking, stop biking, road biking, lifting weights, aerobics exercise, aerobic exercise, strength training, mental concentration activity, intense emotional period, relaxation, Watching TV, sedentaryness, REM detector, meals, in the zone, disturbance, general activity detection, sleep stages, heat stress, heat stroke, teaching / learning affinity, bipolar compensation, (heart signal, activity level, user measured Abnormal events, surprises, highway driving or travel, air travel, helicopter trips, boring events, motion detection (football, baseball, soccer, etc.), studying, reading, addiction, drug effects A momentary event Deterioration, heart attack, seizures, sleep ventilation events, PVC, abnormal blood sugar, severe stress or disorientation, emergencies, cardiac arrhythmias, shock, vomiting, sudden blood loss, taking medication, swallowing Cumulative condition Alzheimer's, increased likelihood of debilitating or lowering, drowsiness, fatigue, presence of ketosis, ovulation, pregnancy, disease, pain, fever, edema, anemia, cold, high blood pressure, psychosis, severe dehydration, hypothermia, in the zone

It will be appreciated that the present invention can be used as a method of automatic journaling of the physiological context of the wearer. The system can automatically create a journal of what activity the user is participating in, what event has occurred, how the user's physiology has changed over time, and when the user has or is likely to experience certain conditions . For example, in addition to recording the user's hydration levels, energy expenditure levels, sleep levels, and alert levels throughout the day, the system may be exercising, driving, sleeping, at risk of cardiac stress, or eating. You can make a record of what you did. This detected condition can be used to trigger a specific delay or real time feedback event, as well as time or event stamp the data record to modify certain parameters of the representation or analysis of the data.

In accordance with the algorithm development process, a linear or nonlinear mathematical model or algorithm is constructed that maps data from a plurality of sensors to a desired variable. The process consists of several steps. First, data is collected by a subject wearing a sensor device 1201 that is as close as possible to the actual world situation (with respect to the parameter being measured) so that the subject is not at risk and at the same time the proposed algorithm This predictive variable can be reliably measured using highly accurate medical grade lab equipment. This first step provides the following two sets of data to be used as inputs to the algorithm development process: (i) raw data from sensor device 1201, and (ii) gold-standard labels measured with more accurate lab equipment. Data consisting of: For the case where the proposed algorithm is about context detection, such as moving by car, the sensor device 1201, gold-standard data by the subject himself or herself through information manually entered or manually recorded on the PC. Is provided. Both the collected data, that is, the raw data and the corresponding gold standard label data, are then organized into a database and divided into training and test sets.

Next, using data from the training set, a mathematical model is created that relates the raw data to the corresponding gold standard label data. Specifically, various machine learning techniques are used to generate two types of algorithms: 1) Algorithms known as feature detectors that produce highly correlated results with lab-measurement levels (eg, metabolic carts, Douglas bags). , Or VO2 level information from double label water), and 2) an algorithm known as a context detector that predicts various contexts useful for the overall algorithm (eg, running, exercising, lying down, sleeping, driving). Many well-known machine learning techniques can be used at this stage, including artificial neural networks, decision trees, memory-based methods, boosting, attribute selection via cross-validation, and stochastic search methods such as simulated annealing and advanced computations. have. After a suitable set of feature detectors and context detectors are obtained, some well-known machine learning methods are used to cross-validate the model using training data and to increase the quality of the model of the data. Techniques used at this stage include, but are not limited to, multilinear regression, local weighted regression, decision trees, artificial neural networks, stochastic search methods, support vector machines, and model trees.

In this step, the model predicts every minute, for example. The minute-to-minute effect is next considered by generating a holistic model that integrates the prediction every minute. Known or custom windowing and threshold optimization tools can be used at this stage to take advantage of the time continuity of the data. Finally, the performance of the model can be evaluated for test sets that have not yet been used in generating the algorithm. Thus, the performance of the model on the test set is a good estimate of the expected performance of the algorithm on other invisible data. Finally, the algorithm may live test new data for further validation.

Other examples of machine learning methods and / or non-linear functional types that may be used in the present invention include conditional, case statements, logical processing, probabilistic or logical inference, neural network processing, kernel-based methods, memory-based lookups (kNN, SOM), decisions List, decision tree prediction, support vector machine prediction, clustering, boosted method, cascade correlation, Boltzmann classifier, regression tree, case based listening, Gaussian, Bayesnet, dynamic Bayesian network, HMM, Kalman filter, Gaussian process Algorithm predictor (eg, learned by evolved computation or other program synthesis tool).

Although one may view the algorithm when taking raw sensor values or signals as input, performing computations, and then calculating the desired output, in one preferred embodiment, the algorithm is a series of derivatives applied to the raw sensor values ( derivation is useful. Each derivative produces a signal called a derived channel. In addition, the raw sensor value or signal is called the raw channel, rather than the derived channel. These derivatives, also called functions, may be simple or complex but are applied in a given order to primitive values and possibly to already derived channels. The first derivative, of course, only needs to take the raw sensor signal as input, but the subsequent derivative can take as input the previously derived channel. Note that the particular channel used to derive the desired derived channel can be easily determined from the order of the differential application. Also note that the input provided by the user on the I / O device or in a particular manner may be included as a raw signal that can be used by the algorithm. For example, a category selected to describe a meal may be used by the derivative to compute a calorie estimate for that meal. In one embodiment, the raw signal may first be summarized and efficiently stored into channels sufficient for later derivatives. These channels include derivatives such as sums, sums of differences, and means. Summarizing high rate data into a compressed channel is useful for both compression and storage of useful features, but note that it may be useful to store some or all segments of high rate data, depending on the exact details of the application. In one embodiment, these summary channels are then calibrated to give the appropriate scale and values in the correct units, taking into account small measurable manufacturing differences. For example, during the manufacturing process, if a particular temperature sensor is determined to have a minor offset, this offset is applied, resulting in an induced channel representing the temperature in degrees Celsius.

For the purposes of this description, the derivative or function is linear if expressed as a weighted combination of its inputs with a particular offset. For example, if G and H are two primitive or derived channels, then all derivatives of form A * G + B * H + C (where A, B and C are constants) are linear derivatives. The derivative is nonlinear with respect to the input unless it is expressed as a weighted sum of the constant offset and the input. An example of a nonlinear derivative is as follows: (G> 7) returns H * 9, otherwise (H * 3.5 + 912). The channel is derived linearly if all of the derivatives involved in computing it are linear and the channel is nonlinear if any of the derivatives used to produce it is nonlinear. The channel mediates the derivative nonlinearly by varying the computation performed in the derivative, while keeping all other inputs constant. According to a preferred embodiment of the present invention, the algorithm developed using this process will have the format conceptually shown in FIG. Specifically, the algorithm will take as input input demographic information about an individual as shown in box 1600 and a channel derived from sensor data collected by the sensor device from various sensors. The algorithm calculates at least one weight that is calculated from W ₁ to W _N , representing the probability that a predetermined portion of the collected data as collected for one minute is collected while the wearer is in each of several possible contexts. Context detector 1605. Such a context may include whether an individual was at rest or active. In addition, for each context, a regression algorithm 1610 is provided when continuous prediction is computed taking the raw or derived channel as input. Individual regressions can be any of various regression equations, including, for example, multivariate linear or polynomial regression, memory based methods, support vector machine regression, neural networks, Gaussian processes, arbitrary procedural functions, and the like. Or a method. Each regression is an estimate of the output of the parameter of interest in the algorithm, for example energy consumption. Finally, the output of each regression algorithm 1610 for each context, shown as weights W ₁ to W _N , and A ₁ to A _N , is determined by the algorithm, shown in box 1620. Combined in post-processor 1615 that outputs the parameter of interest that is being predicted or measured. In general, post-processor 1615 may be configured in any of a number of ways of combining separate context predictions, including a method of commits, a boost, a method of bowing, consistency checking, or context-based recombination.

Referring to FIG. 30, an exemplary algorithm for measuring an individual's energy consumption is conceptually illustrated. Such exemplary algorithms may include a sensor device 1201 having at least one accelerometer, heat flux sensor, and GSR sensor, or such sensor, as disclosed in co-pending US patent application Ser. No. 10 / 682,759, the specification of which is incorporated herein by reference. May be executed on I / O 1200 receiving data from a device. In this exemplary algorithm, the raw data from the sensor is calibrated and many values based on it, i. E. Derived channels, are generated. In particular, the following derived channels, shown at 1600 in FIG. 30, are computed from the raw signal and demographic information: (1) longitudinal accelerometer average (LAVE) based on accelerometer data; (2) the lateral accelerometer sum (TSAD) of the mean difference, based on the accelerometer data; (3) heat flux high gain average variance (HFvar) based on heat flux sensor data; (4) sum of absolute and lateral and longitudinal accelerometers or vector sum of SAD (VSAD), based on accelerometer data; (5) Galvanic Skin Response Low Gain (GSR) based on GSR data; And (6) basic metabolic rate (BMR) based on demographic information. The context detector 1605 consists of a naive Bayesian classifier that predicts whether the wearer is active or at rest using LAVE, TSAD, and HFvar derived channels. The output is probabilistic weights (W ₁ and W ₂ for two context breaks and activities). For the rest context, the regression algorithm 1610 is a linear regression that combines the channels derived from the accelerometer, heat flux sensor, demographic data of the user, and galvanic skin response sensor. The equation obtained through the algorithm design process is A * VSAD + B * HFvar + C * GSR + D * BMR + E, where A, B, C, D and E are constants. The regression algorithm 1610 for the activity context is the same except that the constants are different. Post-processor 1615 for this example is to add together the weighted results of each contextual regression. If A ₁ is the result of a rest regression and A ₂ is the result of an active regression, then the combination is the energy consumption shown at 1620 as W ₁ * A ₁ + W ₂ * A ₂ . In another example, an induced channel that calculates whether the wearer is monitoring (driving) during the period may also be input to the post-processor 1615. The process by which this derived monitoring channel is computed is algorithm (3). Thereafter, the post-processor 1615 in this case, when the wearer is predicted to be driving by the algorithm 3, the energy consumption is equal to a certain multiple (i.e. 1.3) at the base metabolic rate every minute. Can be constrained to be limited during that period.

This algorithm development process can be used to create an algorithm that allows the sensor device 1201 to detect and measure a variety of parameters, including the following: (i) unconsciousness, fatigue, shock, Including drowsiness, heat stress and dehydration; And (ii) an individual's readiness, health and / or metabolic conditions, such as in a military environment, including dehydration, malnutrition and sleep deprivation. In addition, algorithms may be developed for the purposes of filtering, signal cleanup and noise cancellation, etc., on signals measured by the sensor device as described herein. As will be appreciated, the actual algorithm of the function developed using this method will be highly dependent on the specification of the sensor device used, such as the particular sensor and its placement and the overall structure and geometry of the sensor device. Thus, an algorithm developed for one sensor device will not work well, if not at all, on sensor devices that are not substantially structurally identical to the sensor device used to generate the algorithm.

Another aspect of the invention relates to the ability of advanced algorithms to handle various kinds of uncertainty. Data uncertainty refers to sensor noise and possible sensor failures. Data uncertainty is when data is not completely reliable. In such conditions, for example, if the sensor, for example the accelerometer, has failed, the system will assume that the wearer is sleeping, resting or no movement is taking place. Under these conditions, it is difficult to conclude that the data are not good, or that the model that predicts and concludes is wrong. When an application contains both model and data uncertainty, it is very important to identify the relative magnitude of the uncertainty associated with the model and data. The intelligent system will notice that the sensor appears to be producing the wrong data, and switch to an alternative algorithm or, in some cases, intelligently fill the gap before predicting. Determining when a sensor has failed and when the data channel is no longer reliable is a trivial task, where a failed sensor sometimes produces a reading that may appear to match some of the other sensors so that the data It may be within the normal operating range of the sensor.

Clinical uncertainty refers to the fact that other sensors make seemingly contradictory conclusions. Clinical uncertainty is when the conclusions drawn from the data are not certain. For example, an accelerometer indicates that the wearer is motionless (according to the "rest"), the galvanic skin response sensor provides a very high response (according to the "active"), and the heat flux sensor It may indicate that the wearer is still dissipating substantial heat (a conclusion is reached). How should these differences be assessed? Low-end systems will either attempt to vote between the sensors or will incorporate various readings using an unfounded method. The present invention weights important joint probabilities and concludes an appropriate and most promising conclusion, which concludes that, in this example, a low-motion activity such as a stationary viking is currently or recently performed.

According to another aspect of the invention, a sensor device such as sensor device 400 automatically measures, records, and stores a parameter Y relating to a human state, preferably a human state that cannot be measured directly by the sensor. And / or to report. State parameter Y may include, but is not limited to, calories burned, energy expenditure, sleep state, hydration level, ketosis level, shock, insulin level, physical exhaustion and heat exhaustion, for example. The sensor device may observe a vector of live signals configured as the output of a particular sensor of one or more sensors, which may include all or a subset of these sensors. As discussed above, the same potential terminology problem of a particular signal, called a channel, can be derived from a vector of raw signal signals. The vector X of a particular channel of such live and / or derived channels, referred to herein as raw and derived channel X, is called any U, or any state, event and / or any of the state parameters Y of Y, or U, of interest. It will vary in any organic way that is level dependent or sensitive. Here there is a relationship between Y and U such that Y can be obtained from U. According to the invention, the first algorithm or function f1 is generated using a sensor device that takes raw and derived channels X as inputs, yields predicted values as outputs and is conditionally represented by symbol ∏, (i) state parameter Y Or indicator U, and (ii) some other state parameter Z of the individual. This algorithm or function f1 can be expressed as follows.

f1 (X) ∏ U + Z

or

f1 (X) ∏ Y + Z

According to a preferred embodiment, f1 is a method taken for the live and derived channel X derived from the data, specifically the signal collected by the sensor device, the correct answer, for example to generate an algorithm from the collected data, for example , Verifiable standard data associated with U or Y and Z measured simultaneously using high accuracy medical grade lab equipment, and algorithm development processes described elsewhere herein using various machine learning methods. The algorithm or function f1 is generated under the condition that either indicator U or state parameter Y is present in either case. As will be appreciated, the actual algorithms or functions developed using this method will be highly dependent on the details of the sensor devices used, such as the specific sensors and their arrangement and overall structure and geometry of the sensor device. Thus, algorithms developed with one sensor device may not operate at all, but at least not as well as at least known conversion parameters, in sensor devices that are not inherently structurally identical to the sensor device used to generate the algorithm. It cannot be converted to a device or sensor to sensor.

Next, a second algorithm or function f2 is generated using a sensor device that takes raw and derived channel X as input and outputs its predicted value as output, and in any case all output by f1 except Y or U Is conditionally dependent on and in either case is indicated by the symbol 의 of either Y or U and is conditionally independent. The idea may account for or filter out changes in live and derived channel X coming from a non-X or non-U related event by specific live and derived channel X from one or more sensors. This algorithm or function f2 can be expressed as Arie.

f2 (X) ∏ Z and (f2 (X) ㅛ Y or f2 (X) ㅛ U

Like f1, f2 is preferably developed using the algorithm development process described above. In either case, however, f2 is developed and validated under the condition that no U or Y is present. Thus, the gold standard data used to generate f2 is only data related to Z measured using high accuracy medical grade lab equipment.

Thus, according to this aspect of the present invention, two functions will be generated, one of which is f1 sensitive to U or Y and the other of f2 is insensitive to U or Y. As will be appreciated, in either case, there is a relationship between f1 and f2 that will yield U or Y. That is, a function f3 exists such that f3 (f1, f2) = U or f3 (f1, f2) = Y. For example, U or Y can be obtained by subtracting the data generated by two functions (U = f1-f2 or Y = f1-f2). If U rather than Y is determined from the relationship between f1 and f2, the next step includes obtaining Y from U based on the relationship between Y and U. For example, Y may be some fixed percentage of U that allows Y to be obtained by dividing U by some factor.

One skilled in the art may, in the present invention, more than two such functions, for example (f1, f2, f3, ... f_n-1), be combined by the last function f_n in the manner described above. In general, this aspect of the invention requires that a set of functions whose outputs vary from one another in a way that indicates the parameter of interest. It will also be understood that condition dependencies or independence as used herein will be defined for approximation rather than precision.

The method just described can be used to automatically measure and / or report a person's calorie consumption or intake using a sensor device, such as, for example, a daily calorie intake of a person known as DCI. Automatic measurement and reporting of calorie intake is difficult for other non-automatic methods, such as maintaining diaries and journals of food intake, to be maintained and calorie information for food items is not always reliable or readily available, as in the case of restaurants. Because it is beneficial.

It is known that total body metabolism is measured as total energy consumption (TEE) according to the following equation.

TEE = BMR + AE + TEF + AT

Here, BMR is the basic metabolic rate, which is the energy consumed by the body during a rest such as sleep, AE is the active energy consumption, which is the energy consumed during physical activity, and TEF is the energy consumed during the digestion and processing of food ingested It is the heat effective amount of food, and AT is the adaptive heat generation, the mechanism by which the body modifies its metabolism over extreme temperatures. It is estimated that about 10% of the value of the food consumed is used to process the food. Thus, TEF is estimated at 10% of total calories burned. Thus, a reliable and practical method of measuring TEF allows calorie consumption to be measured without the need to manually track or record food related information. Specifically, once TEF is measured, calorie consumption can be accurately estimated by dividing TEF by 0.1 (TEF = 0.1 * calories burned; calories burned = TEF / 0.1).

According to a specific embodiment of the invention with respect to the automatic measurement of state parameter Y as described above, as described above, the sensor device may be used to automatically measure and / or record calories consumed by an individual. In this embodiment, state parameter Y is calories consumed by the individual and indicator U is TEF. First, the sensor device is used to generate f1, which is an algorithm for predicting TEE. f1 is developed and validated for subjects who consumed food, that is, subjects who were performing activities and experiencing TEF effects. f1 is referred to as EE (notice) to indicate that it predicts energy consumption including meal effects. The verifiable standard data used to generate f1 is the VO @ machine. The function f1 for predicting TEE is conditionally dependent on item U of interest, which is TEF, and predicts item U. In addition, f1 is in this case conditionally dependent on Z, which is BMR + AE + AT and predicts Z. Next, the sensor device is used to generate f2, an algorithm for predicting all aspects of the TEE except TEF. f2 is developed and validated for patients who fasted for any period of time, preferably 4-6 hours, prior to collection of data to ensure that TEF was not present and was not a factor. Such a patient would be performing physical activity without any TEF effect. As a result, f2 is conditionally dependent and predictive on BME + AE + AT but not conditional independent on TEF. f2 is called EE (fasting) to indicate that this does not include the effect of eating and predicts energy consumption. Thus, f1 thus developed will be sensitive to TEF and f2 thus developed will be insensitive to TEF. As will be appreciated, in this embodiment, the relationship between f1 and f2, which in this case yields the indicator U which is TEF, is subtracted. That is, EE (notice)-EE (fasting) = TEF. Once developed, the sewage f1 and f2 can be programmed in software stored by the sensor device and executed by the processor of the sensor device. The data from which the generated and derived channel X can be derived can then be collected by the sensor device. The output of f1 and f2 using the collected data can then be subtracted to yield the TEF. Once the TEF is determined for the same time as one day, the calories consumed can be obtained during that period by dividing EF by 01 since the TEF is estimated to be 10% of the total calories consumed. The calorie consumption thus obtained may be stored, reported and / or used in place of the manually collected calorie consumption data used in the embodiments described elsewhere.

The sensor device may be a body motion sensor, such as an accelerometer adapted to generate data indicative of motion, a skin conductivity sensor, such as a GSR sensor, adapted to generate data indicative of resistance to the current of an individual's skin, or heat from the body. Generate data indicating the temperature of the skin of the individual and a body potential sensor such as a heat flux sensor adapted to generate data representing the representative data, an ECG sensor adapted to generate data representing the rate or other characteristics of the individual's heat bits It is desirable to be in communication with a temperature sensor that is adapted to do so. In this preferred embodiment, in addition to the skin information for the wearer, this signal constitutes a vector of signals from which live and derived channel X are derived. The vector of these signals includes data of motion, storage of the individual's skin for current, and heat flowing from the body.

As mentioned above, one can imagine the case where the set of additional state parameters Z is zero, as in the limited case of estimating TEF. This results in direct TEF measurements through a derivative process using the linear and nonlinear derivatives described above. In this variation, an algorithmic process is used to directly predict the TEF that should be provided as verifiable standard training data.

As an alternative to TEF, any effects of food on the body, such as, for example, drowsiness, urination or electrical effects, or any other signal of a meal such as bowel sound, have just been described to enable automatic estimation of calorie consumption. Used as indicator U in the method. In this alternative embodiment, the relationship between state parameters Y and U, calorie consumption, may be based on any known or developed scientific characteristic or equation or may be based on statistical modeling techniques.

In alternative embodiments, the DCI can be estimated by combining measurements of body weight taken at different times with estimates of energy consumption. It is known from the literature that weight changes (measured multiple times under the same conditions to filter the moisture content and the effects of the digestive process) are related to energy balance and calorie intake as follows: (calorie intake-energy consumption) / K = Weight gain in pounds, where K is a constant that is preferably 3500. Thus, if the aspect herein relates to a method and apparatus for measuring energy consumption that can take an input from a scale, a human calorie intake can be accurately estimated based on the following equation: calorie intake = energy consumption + (Weight gain in pounds * K). This method requires users to weigh their own weight regularly to obtain a measure of calorie intake and does not require them other efforts.

In addition, DCI can be estimated using algorithms that take sensor data and directly estimate calories consumed by the wearer by using the number of calories as a verifiable standard and using the set of raw and derived channels as training data. have. This is only one example of the algorithm process described above.

Another specific example in which the present invention may be used relates to detecting when a person is tired. Such detection can be performed in at least two ways. The first method uses a sensor device to provide an estimate of fatigue and uses the two function (f1 and f2) approaches described for TEF and calorie intake estimates to calculate the user's calorie intake, moisture level, sleep, stress and energy consumption. Accurately measuring a parameter, such as a level. The second method involves directly modeling fatigue using the direct differential approach described in conjunction with FIGS. 29 and 30. This example illustrates that the complex algorithm itself that predicts the physiological state of the wearer can be used as input to other more complex algorithms. One potential application for one such embodiment of the present invention is for first responders (e.g. firefighters, police officers, soldiers) whose wearers are quite susceptible to extreme conditions and performance considerations. In a pilot study, the assignee herein analyzed data from firefighters in training exercise and determined that reasonable measurements of heat stress were possible using a combination of calibrated sensor values. For example, if the heat flux is too low for a long time but the skin temperature continues to rise, the wearer is more likely to have problems. It will be appreciated that the algorithm can use both calibrated sensor values and complex derivation algorithms.

According to an alternative embodiment of the present application, the software that implements and determines U and / or Y from f1 and f2 is not placed on and executed by the sensor device itself, rather, such software is separate from the sensor device. Can be placed on and executed by the summing device. In this embodiment, this computing device receives the signals collected by the sensor device from which the set of live and derived channels X are derived, wired or wirelessly and determines U and / or Y from these signals as described above. This alternative embodiment may be an embodiment in which the state parameter Y determined by the computing device is calorie consumption and the indicator affects the body of food, such as TEF. The calculating device can display the determined calorie consumption data to the user. In addition, the sensor device may also generate calories burned data described elsewhere in communication with the computing device. The computing device may then generate and display information based on calorie consumption data and calorie consumption data, such as energy balance data, target related data, and weight loss or growth rate data.

The terminology and terminology used herein is for the purpose of description and not of limitation, and is not intended to be equivalent to the description and depicted features, and therefore, various modifications may be made within the scope of the present invention as claimed. Recognize that it is possible. While specific embodiments of the invention have been illustrated in the foregoing detailed description, it is to be understood that the invention is not intended to be limiting, and that numerous modifications, modifications, and substitutions are possible.

Claims (278)

A system for monitoring a person's physiological parameters and providing status information about the person's physiological parameters, (a) receive at least one of (i) detected and (ii) manually entered data related to a physiological parameter of the first person; (b) directly detecting at least a physiological parameter of at least a second human; And (c) a device adapted for placement on the body that provides status information about the interchanging effects on the physiological parameters of the first and second humans. The system of claim 1, wherein the apparatus is a sensor device for mounting on a body. The system of claim 2, wherein the sensor device is an armband sensor device for mounting on the upper arm of a body. The system of claim 2, wherein the sensor device further comprises at least one sensor for detecting at least one of the physiological parameters of the first and second humans. The sensor of claim 2, wherein the at least one sensor comprises: a sensor for measuring a GSR comprising at least two electrical contacts, a skin temperature sensor, an ambient temperature sensor, an accelerometer, an ambient light sensor, an ambient sound sensor, an EMG sensor, an ECG And at least one of a sensor, a cardiac parameter related sensor, a GPS sensor and a skin impedance sensor. The system of claim 2, wherein the sensor device further comprises at least one sensor for contextual parameters. 7. The system of claim 6, further comprising at least one sensor for detecting a physiological state parameter of the additional human. 8. The system of claim 7, wherein the physiological parameters of the first and second humans, the physiological parameters of the additional human, and the contextual parameters are used to derive data indicative of the nature of the wearer's activity. The system of claim 8, wherein data indicative of the physiological parameters of the first and second humans and the nature of the wearer's activity are correlated over time. 10. The system of claim 9, wherein the system provides output data comprising data indicative of the nature of the wearer's activity and the physiological parameters of the first and second humans in relation to time. The system of claim 1, wherein the physiological parameter of the first human being is daily calorie intake. 12. The system of claim 11, wherein the daily calorie intake is entered manually. The system of claim 12, wherein the daily calorie intake is entered manually by a user. 13. The system of claim 12, wherein the daily calorie intake is entered manually for a user by another individual. 13. The system of claim 12, wherein the daily calorie intake is entered manually by a person for a plurality of users. 12. The system of claim 11, further comprising a food database in which food items from which food items are selected for calculation of daily calorie intake are pre-populated. 17. The system of claim 16, wherein the food database is calibrated into individual items. 17. The system of claim 16, further comprising a prioritized list of food items from which food items can be selected. 19. The system of claim 18, wherein the list of food items is dynamically updated based on the frequency of selection. 19. The system of claim 18, wherein the list of food items is dynamically updated based on one of time, day of week, meal, season, and meal plan. 17. The system of claim 16, further comprising a database of menu plans, the proposed food comprising the proposed food for consumption. The system of claim 1, wherein the physiological parameter of the first human is blood glucose level. 2. The system of claim 1, further comprising a glucose meter in electronic communication with the system, wherein blood glucose levels are transmitted from the glucose meter to the system. The system of claim 1, wherein the physiological parameter of the second human is energy expenditure. 25. The system of claim 24, wherein said energy consumption is entered manually. 27. The system of claim 25, further comprising a database of activities associated with energy expenditure values, from which the user can select a suitable activity. The system of claim 1, wherein the system detects energy expenditure as the second physiological parameter. 28. The system of claim 27, wherein the energy consumption is detected by a sensor device adapted for mounting on the body. The method of claim 27, wherein the energy consumption is equation: TEE = BMR + AE + TEF + AT And BMR is basal metabolism, AE is active energy expenditure, TEF is heat effective amount of food and AT is adaptive heat generation amount. The system of claim 1, further comprising an additional detection device in electronic communication with the system, wherein at least one of the first and second human physiological parameters is obtained from the additional detection device. 31. The system of claim 30, wherein said additional detection device further comprises one of a weight scale and a glucometer, a blood pressure monitor and a pulse oximeter. The system of claim 1, further comprising a data input device for manual entry of data related to the physiological parameter of the human. The system of claim 1, further comprising a processor for calculating data indicative of at least one of the physiological parameters of the first and second persons of the user. 34. The system of claim 33, wherein the data indicative of at least one of the physiological parameters of the first and second humans is an energy balance. 10. The system of claim 1, further comprising display means for displaying information to a user. The system of claim 1, wherein the system is in electronic communication with an external computing device. 37. The system of claim 36, wherein the external computing device is in electronic communication via a data information network. 37. The system of claim 36, wherein the external computing device is provided with data from the system. 38. The system of claim 37, wherein the external computing device is in electronic communication with other devices, such as a plurality of systems. 40. The system of claim 39, wherein the system and the external computing device exchange data for the purpose of generating a database of aggregate data output from the system. 40. The system of claim 39, wherein the system, the external computing device, and other devices such as the system exchange data for the purpose of generating aggregate data output from all of the system. 37. The system of claim 36, wherein the external computing device exchanges data with the system for the purpose of modifying the operation of the system. In a system for monitoring and managing weight, A detection device mounted to the body for detecting data indicative of a condition parameter of a person selected from the group consisting of an individual's energy consumption and nutritional parameters; And (i) receiving at least one of manually entered and (ii) detected state parameter data of the person and manipulating the data to provide feedback on the mutual change effect in the person's state parameter with respect to each other; A monitoring unit in communication with the detection device. 44. The system of claim 43, wherein the detection device mounted to the body comprises at least one sensor for detecting at least one of the state parameters of the person. 45. The system of claim 44, wherein the detection device mounted to the body is an armband sensor device. 45. The system of claim 44, wherein said body mounted detection device further comprises at least one sensor for detecting contextual parameters. 47. The system of claim 46, further comprising at least one sensor for detecting a status parameter of an additional person. 48. The system of claim 47, wherein the condition parameter of the person, the condition parameter of the additional person, and the contextual parameter are used to derive data indicative of the nature of the wearer's activity. 49. The system of claim 48, wherein said human condition parameter data indicative of the nature of said wearer's activity is correlated over time. 50. The system of claim 49, wherein the system provides output data comprising data indicative of the nature of the wearer's activity and a state parameter of a time correlated person. 45. The method of claim 44, wherein the at least one sensor comprises: a sensor for measuring a GSR comprising at least two electrical contacts, a skin temperature sensor, an ambient temperature sensor, an accelerometer, an ambient light sensor, an ambient sound sensor, an EMG sensor, an ECG And at least one of a sensor, a cardiac parameter related sensor, a GPS sensor and a skin impedance sensor. 45. The system of claim 44, wherein said state parameter data of said person includes weight data for said individual. 53. The system of claim 52, wherein said weight data is used to calculate a change in weight of said individual. 54. The system of claim 53, wherein the change in body weight and the detected energy expenditure are used to calculate daily calorie intake. 44. The system of claim 43, wherein said state parameter of said first person is daily calorie intake. 56. The system of claim 55, wherein said daily calorie intake is entered manually. 59. The system of claim 56, wherein said daily calorie intake is entered manually by a user. 57. The system of claim 56, wherein said daily calorie intake is entered manually for a user by another individual. 59. The system of claim 56, wherein the daily calorie intake is manually entered for a plurality of users by a single person. 56. The system of claim 55, further comprising a food database in which food items from which food items are selected for calculation of daily calorie intake are pre-populated. 61. The system of claim 60, wherein the food database is calibrated into individual items. 61. The system of claim 60, further comprising a prioritized list of food items from which food items can be selected. 63. The system of claim 62, wherein the list of food items is dynamically updated based on the frequency of selection. 63. The system of claim 62, wherein the list of frequently consumed food items is dynamically updated based on one of time of day, day of week, meal, season, and meal plan. 63. The system of claim 62, further comprising a database of menu plans, the proposed food comprising the proposed food for consumption. 44. The system of claim 43, wherein one of the human state parameters is energy consumption. 67. The system of claim 66, wherein said energy consumption is entered manually. 68. The system of claim 67, further comprising a database of activities associated with energy expenditure values, from which the user can select a suitable activity. 44. The system of claim 43, wherein the system detects energy consumption as a human state parameter. 70. The system of claim 69, wherein the energy expenditure is detected by a sensor device adapted for mounting on the body. The method of claim 69, wherein the energy consumption is equation: TEE = BMR + AE + TEF + AT And BMR is basal metabolism, AE is active energy expenditure, TEF is heat effective amount of food and AT is adaptive heat generation amount. 44. The system of claim 43, further comprising an additional detection device in electronic communication with the system, wherein at least one of the first and second human physiological parameters is obtained from the additional detection device. 73. The system of claim 72, wherein said additional detection device further comprises a weight scale. 44. The system of claim 43, further comprising a data input device for manual input of data related to the state parameter of the person. 44. The system of claim 43, further comprising a processor for calculating data indicative of one of the state parameters of the first and second persons of the user. 76. The system of claim 75, wherein the data representative of at least one of the state parameters of the person is an energy balance. 44. The system of claim 43, further comprising a display for displaying information to a user. 44. The system of claim 43, wherein the system is in electronic communication with an external computing device. 79. The system of claim 78, wherein the external computing device is in electronic communication via a data information network. 79. The system of claim 78, wherein data from the system is provided to the external computing device. 80. The system of claim 79, wherein the external computing device is in electronic communication with a plurality of other systems. 84. The system of claim 81, wherein the system and the external computing device exchange data for the purpose of generating a database of aggregate data output from the system. 84. The system of claim 81, wherein the system, the external computing device and the other system exchange data for the purpose of generating aggregate data output from all of the system. 79. The system of claim 78, wherein the external computing device exchanges data with the system for the purpose of modifying the operation of the system. 44. The system of claim 43, further comprising a feedback and coaching engine, wherein the feedback and coaching engine analyzes the interchange effect of the physiological parameters of the person with respect to each other and provides one of the feedback and status information to the individual. System. 86. The system of claim 85, wherein one of the feedback and status information is in the form of a suggestion to the individual. 86. The system of claim 85, wherein said status information includes a status parameter of said person. 86. The system of claim 85, wherein the feedback and coaching engine provides an output that is modified based on at least one of a person's detected person's state parameter and the state information. A method of providing feedback regarding a physiological parameter of an individual of a person, the method comprising Placing a detection device on the body of the individual to detect a physiological condition parameter of a first person; Obtaining input data from at least one of (i) manually inputted data representing the physiological state parameters of the first and second persons and (ii) data detected from the detection device; And Manipulating the data to provide feedback about a mutual effect of the change in the human state parameter with respect to each other. 89. The method of claim 89, wherein the physiological state parameter of the first human is energy expenditure. 93. The method of claim 89, further comprising detecting a contextual parameter. 92. The method of claim 91, further comprising detecting a physiological state parameter of the additional human. 93. The method of claim 92, further comprising deriving data indicative of the nature of the wearer's activity from the physiological state parameters of the first and second persons, the physiological state parameters of the additional person, and the contextual parameters. How to. 95. The method of claim 93, wherein data indicative of the nature of the wearer's activity and the first and second human saree state parameters are correlated by time. 95. The method of claim 94, wherein output data is provided for the time related first and second physiological state parameters and data indicative of the nature of the wearer's activity. 90. The method of claim 89, wherein said physiological parameter of said first human is daily calorie intake. 98. The method of claim 96, wherein the daily calorie intake is entered manually. 98. The method of claim 97, wherein the daily calorie intake is manually input by a user. 98. The method of claim 96, wherein the daily calorie intake is manually entered for a user by another individual. 98. The method of claim 97, wherein the daily calorie intake is manually entered for a plurality of users by a single person. 98. The method of claim 97, further comprising a food database with pre-populated food items from which food items are selected for calculation of daily calorie intake. 102. The method of claim 101, wherein the database can be calibrated into individual items. 107. The method of claim 102, further comprising a prioritized list of food items from which food items can be selected. 107. The method of claim 103, wherein the list of food items is dynamically updated based on the frequency of selection. 107. The method of claim 103, wherein the list of food items is dynamically updated based on one of time, day of the week, meal, season, and meal plan. 102. The method of claim 101, further comprising a database of menu plans, the suggested food comprising for consumption. 90. The method of claim 89, wherein said physiological parameter of said first human is blood glucose level. 90. The method of claim 89, further comprising a glucose meter in electronic communication with the system, wherein blood glucose levels are transmitted from the glucose meter to the system. 90. The method of claim 89, further comprising a blood pressure gauge in electronic communication with the system, wherein the blood pressure is transmitted from the blood pressure gauge to the system. 90. The method of claim 89, further comprising a pulse oximeter in electronic communication with the system, wherein the pulse is transmitted from the pulse oximeter to the system. 89. The method of claim 89, wherein the physiological parameter of the second human is energy expenditure. 118. The method of claim 111, wherein the energy consumption is input manually. 118. The method of claim 112, further comprising a database of activities associated with energy expenditure values, from which the user can select a suitable activity. 93. The method of claim 89, wherein the system detects energy consumption as a human state parameter. 118. The method of claim 114, wherein the energy expenditure is detected by a sensor device adapted for mounting on the body. 119. The energy consumption of claim 114 wherein the energy consumption is: TEE = BMR + AE + TEF + AT Calculated according to BMR is basal metabolic rate, AE is active energy consumption, TEF is heat effective amount of food and AT is adaptive heat generation amount. 93. The method of claim 89, further comprising obtaining at least one of the physiological parameters of the first and second humans from a further detection device. 118. The method of claim 117, wherein the additional detection device further comprises one of a weight scale and a glucometer. 90. The method of claim 89, further comprising inducing energy balance from the physiological parameters of the human. 119. The method of claim 119, wherein the energy balance is derived from daily calorie intake and energy consumption. 119. The method of claim 119, wherein said energy balance is used to track and predict changes in human physiological parameters. 121. The method of claim 120, wherein said feedback is provided with respect to the mutual effects of daily calorie intake and energy expenditure on each other. 98. The method of claim 97, wherein the user can replace the summary entry based on the size of the meal. 98. The method of claim 97, wherein a combination of food items can be proposed. 98. The method of claim 97, wherein historical meal entry information is used to prompt the user to simplify manual entry of the current meal. 98. The method of claim 97, wherein said food database further comprises a search function. 93. The method of claim 89, wherein the feedback is generated by a feedback and coaching engine. 127. The method of claim 127, wherein the feedback is provided with respect to the mutual effects of nutritional and energy consumption parameters on each other. 93. The method of claim 89, wherein the feedback presents various selections or suggestions. 129. The method of claim 129, wherein the proposal comprises a meal and vitamin supplement. 89. The method of claim 89, wherein said feedback is in the form of an intermittent status report. 143. The method of claim 131, wherein the intermittent status report is presented in an additional display box or window. 143. The method of claim 131, wherein the intermittent status report can be generated by a key string or a parameter set. 143. The method of claim 131, wherein the intermittent status report includes information related to a user's preset target value. 90. The method of claim 89, wherein said feedback is required by a user. 89. The method of claim 89, wherein said feedback is requested periodically. 90. The method of claim 89, further comprising providing an individual response to the feedback. 93. The method of claim 89, further comprising: detecting the individual's response to the feedback; And modifying the feedback according to the response of the individual to optimize the feedback. 138. The method of claim 138, wherein the correction of the feedback relates to tones of future feedback. 138. The method of claim 138, wherein the modification of the feedback relates to the severity of future feedback. 138. The method of claim 138, wherein the modification of the feedback relates to the content of future feedback. 138. The method of claim 138, wherein the feedback parameter is one of context, estimated daily calorie intake and logged intake. 138. The method of claim 138, wherein the feedback is modified based on the overall population of a given situation, one of a specific group of individuals, and an individual. 138. The method of claim 138, wherein the modification of the feedback further comprises dynamically adjusting the feedback based on a delay enhancement cycle in which a response to the provided feedback is used to adjust continuous feedback to optimize the feedback. How to. 138. The method of claim 138, wherein the proposal is related to the detected nutritional parameters of the individual. 138. The method of claim 138, wherein the proposal is one of a combination of an increased total energy consumption, a reduced daily calorie intake, an increased total energy consumption, and a reduced daily calorie intake and a reset goal. 138. The method of claim 138, wherein the proposal includes an option to generate a new meal plan. 138. The method of claim 138, wherein the proposal includes an option to generate a new exercise plan. 138. The method of claim 138, wherein the proposal is one of hints to wear more detection devices, hints to visit more gyms, hints to log food items more regularly, and specific hints about an individual's condition. How to. 127. The method of claim 127, wherein the feedback and coaching engine provides a recommendation based on a user's physiological data and a history of the recommendation. 90. The method of claim 89, wherein a sequence of one of the negative, positive, and neutral human physiological state parameters is monitored. 151. The method of claim 151, wherein a sequence of one of the negative, positive, and neutral human state parameters is recorded as a pattern for future review. 152. The method of claim 152, wherein the recorded pattern is analyzed and matched and used to detect one of (i) present and (ii) future sequences of physiological state parameters of negative, positive and neutral humans. . 153. The method of claim 153, wherein the analysis and matching of the recorded pattern is based on one of (i) data from an individual's personal history and (ii) aggregate data of another individual. 153. The method of claim 153, wherein the feedback can be tailored to a particular sequence of negative, positive, and neutral human physiological state parameters. 90. The method of claim 89, wherein the medium of feedback is one of a telephone, an email, a mail, a facsimile, or a website. 89. The method of claim 89, wherein said feedback is in the form of an intermittent status report. 162. The method of claim 157, wherein the intermittent status report is presented in an additional display box or window. 162. The method of claim 157, wherein the intermittent status report can be generated by a key string or parameter set. 162. The method of claim 157, wherein the intermittent status report includes information related to the target amount of the individual. 90. The method of claim 89, wherein said feedback is requested by a user. 89. The method of claim 89, wherein said feedback is requested periodically. 162. The method of claim 157, wherein the intermittent status report is selected from the group consisting of: the day, a particular day, the average of a plurality of days, and after the start of the program. 162. The method of claim 157, wherein the intermittent status report is based on actual and target values of energy consumption and daily calorie intake. 162. The method of claim 157, wherein the intermittent status report provides a time-based suggestion. 162. The method of claim 157, wherein the intermittent status report is based on a percentage of daily calorie intake. 162. The method of claim 157, wherein the intermittent status report is based on a percentage of energy consumption. 166. The method of claim 157, further comprising selecting the intermittent status report, wherein the selecting logic is based on decision trees, planning systems, constraint satisfaction systems, frames based systems, cases based systems, rules based. A system, a predictive callus, a general planning system, and a stochastic network. 162. The method of claim 157, wherein the intermittent status report is based on energy balance. 171. The method of claim 169, wherein the energy balance value is calculated from energy consumption and daily calorie intake. 172. The method of claim 170, wherein the adjustment threshold is selected as a target tolerance to place the user in a particular category based on the current target status. 172. The method of claim 171, wherein the category is indicated by a balance status indicator. 172. The category of claim 171, wherein the category is one of wherein the user has met and exceeded the daily energy balance target amount, the user must meet the daily energy balance target amount and the user will not meet the daily energy balance target amount. Way. 172. The method of claim 171, wherein the secondary time is selected as a threshold to determine whether the time is one of early and late. 174. The method of claim 174, wherein the current time is compared with an auxiliary time in relation to the current target state. 175. The method of claim 175, wherein the intermittent status report is generated to indicate whether an individual can meet an energy balance target amount based on the time of day. 176. The method of claim 176, wherein the intermittent status report indicates a proposal for energy expenditure activity to help achieve an energy balance target. 178. The method of claim 177, wherein the intermittent status report suggests an activity based on a target status. 90. The method of claim 89, further comprising achieving a database of data output values. 179. The method of claim 179, wherein the database comprises a pattern of physiological data. 179. The method of claim 179, wherein the database comprises a pattern of contextual data. 179. The method of claim 179, wherein the database comprises a pattern of activity data derived from physiological and contextual data. 179. The method of claim 179, further comprising analyzing the data output values to achieve a data pattern. 184. The method of claim 183, further comprising storing the data pattern. 184. The method of claim 184, further comprising comparing the stored data pattern with the detected data to identify and categorize the detected data into additional data patterns. 184. The method of claim 184, further comprising: (i) comparing the stored data pattern with detected data to identify such detected data as similar to at least one of the stored data patterns; And (ii) predicting future detected data. 186. The method of claim 186, further comprising generating an output based on a prediction of the future detected data. 187. The method of claim 187 wherein the output is an alarm. 187. The method of claim 187, wherein the output is a report. 187. The method of claim 187, wherein the output is used as an input by another device. 90. The method of claim 89, further comprising a final step of using said feedback for the purpose of achieving initial assessment for a health modification plan. 192. The method of claim 191, further comprising the additional final step of using the feedback to assess an intermediate state of progression to the health modification plan. In the method of weight loss management, Establishing a weight correction target value; Continuously monitoring the user's energy consumption through the use of a detection device mounted on the user's body adapted to detect at least one of a person's physiology and contextual parameters from the wearer's body; Recording a weight entry of the user; Providing feedback including the user's energy expenditure to the user regarding the user's progress with respect to the weight loss target value; And Modifying a user's behavior based on the feedback. 199. The method of claim 193, further comprising obtaining a daily calorie intake of the user. 199. The method of claim 193, wherein the daily calorie intake is entered manually by a user. 199. The method of claim 195, further comprising a food database with pre-populated food items from which food items are selected for the calculation of daily calorie intake. 196. The method of claim 196, wherein the database can be calibrated into individual items. 199. The method of claim 195, further comprising a prioritized list of food items from which food items can be selected. 199. The method of claim 198, wherein the list of food items is dynamically updated based on the frequency of selection. 199. The method of claim 198, wherein the list of food items is dynamically updated based on one of time, day of the week, meal, season, and meal plan. 199. The method of claim 195, further comprising a database of menu plans, the proposed food comprising for consumption. 199. The method of claim 193, wherein the energy consumption is input manually. 202. The method of claim 202, further comprising a database of activities associated with energy expenditure values, from which the user can select a suitable activity. 199. The method of claim 193, wherein the energy expenditure is detected by a sensor device adapted for mounting on the body. 194. The energy consumption of claim 193 wherein the energy consumption is: TEE = BMR + AE + TEF + AT Calculated according to BMR is basal metabolic rate, AE is active energy consumption, TEF is heat effective amount of food and AT is adaptive heat generation amount. 199. The method of claim 193, wherein the weight input value is obtained from an additional detection device. 199. The method of claim 193, further comprising inducing energy balance from the physiological parameters of the human. 207. The method of claim 207, wherein the energy balance is derived from daily calorie intake and energy consumption. 207. The method of claim 207, wherein the energy balance is used to track and predict changes in weight loss progression. 208. The method of claim 208, wherein the feedback is provided with respect to the mutual effects of daily calorie intake and energy expenditure on each other. 194. The method of claim 194, wherein a user can replace a summary entry based on the size of the meal. 199. The method of claim 195, wherein a combination of food items can be proposed. 199. The method of claim 195, wherein historical meal entry information is used to prompt the user to simplify manual entry of the current meal. 196. The method of claim 196, wherein the food database further comprises a search function. 199. The method of claim 193, further comprising detecting physiological parameters of the additional human. 215. The method of claim 215, further comprising deriving data indicative of the nature of the wearer's activity from at least one physiological state parameter, the additional human's physiological state parameter, and the contextual parameter. 216. The method of claim 216, wherein data indicative of the nature of the wearer's activity and the physiological state parameter of the at least one person are correlated by time. 228. The method of claim 217, wherein the output data provides data indicative of the physiological state parameters of at least one person and time-correlated properties of the wearer's activity. 199. The method of claim 193, wherein the feedback is generated by a feedback and coaching engine. 219. The method of claim 219, wherein the feedback is provided with respect to the mutual effects of nutritional and energy consumption parameters on each other. 199. The method of claim 193, wherein the feedback presents various selections or suggestions. 226. The method of claim 221, wherein the proposal comprises a meal and vitamin supplement. 199. The method of claim 193, wherein the feedback is in the form of an intermittent status report. 234. The method of claim 223, wherein the intermittent status report is presented in an additional display box or window. 234. The method of claim 223, wherein the intermittent status report can be generated by a key string or a parameter set. 223. The method of claim 223, wherein the intermittent status report includes information related to a user's predetermined target value. 199. The method of claim 193, wherein the feedback is required by a user. 194. The method of claim 193, wherein the feedback is requested periodically. 199. The method of claim 193, further comprising providing an individual with a response to the feedback. 229. The method of claim 229, further comprising: detecting the individual's response to the feedback; And modifying the feedback according to the response of the individual to optimize the feedback. 234. The method of claim 230, wherein the correction of the feedback relates to tones of future feedback. 234. The method of claim 230, wherein the correction of the feedback relates to the security of future feedback. 234. The method of claim 230, wherein the correction of the feedback relates to the content of future feedback. 234. The method of claim 230, wherein the feedback parameter is one of context, estimated daily calorie intake and logged intake. 234. The method of claim 230, wherein the feedback is modified based on one of a total population, a particular group of individuals, and an individual for a given situation. 234. The method of claim 230, wherein modifying the feedback further comprises dynamically adjusting the feedback based on a delay enhancement cycle in which a response to the provided feedback is used to adjust continuous feedback to optimize the feedback. How to. 226. The method of claim 221, wherein the proposal is related to the detected nutritional parameters of the individual. 228. The method of claim 221, wherein the proposal is one of a combination of an increase in total energy consumption, a decrease in daily calorie intake, an increase in total energy consumption and a decrease in daily calorie intake and a reset target amount. 226. The method of claim 221, wherein the proposal includes an option to generate a new meal plan. 226. The method of claim 221, wherein the proposal includes an option to generate a new exercise plan. 228. The method of claim 221, wherein the proposal is one of a hint to wear more detection devices, a hint to visit more gyms, a hint to log food items more regularly, and a specific hint about a person's condition. How to. 219. The method of claim 219, wherein the feedback and coaching engine provides a recommendation based on a user's physiological data and a history of the recommendation. 194. The method of claim 193, wherein a sequence of one of the negative, positive, and neutral human physiological state parameters is monitored. 245. The method of claim 243, wherein the sequence of one of the negative, positive and neutral human state parameters is recorded as a pattern for future review. 244. The method of claim 244, wherein the recorded pattern is analyzed and matched and used to detect one of (i) present and (ii) future sequences of physiological state parameters of negative, positive and neutral humans. . 245. The method of claim 245, wherein analysis and matching of the recorded pattern is based on one of (i) data from a person's personal history and (ii) aggregate data of another person. 245. The method of claim 243, wherein the feedback can be tailored to a particular sequence of one of negative, positive, and neutral human physiological state parameters. 199. The method of claim 193, wherein the medium of feedback is one of a telephone, an email, a mail, a facsimile, or a website. 234. The method of claim 223, wherein the intermittent status report is selected from the group consisting of the day, a particular day, an average of a plurality of days, and after the start of the program. 223. The method of claim 223, wherein the intermittent status report is based on actual and target values of energy consumption and daily calorie intake. 226. The method of claim 223, wherein the intermittent status report provides a time-based suggestion. 237. The method of claim 223, wherein the intermittent status report is based on a percentage of daily calorie intake. 238. The method of claim 223, wherein the intermittent status report is based on a percentage of energy consumption. 235. The method of claim 223, further comprising selecting the intermittent status report, wherein the selecting logic includes a decision tree, a planning system, a constraint satisfaction system, a frame based system, a case based system, a rule based system. A predictive callus, a general planning system, and a stochastic network. 238. The method of claim 223, wherein the intermittent status report is based on energy balance. 255. The method of claim 255, wherein the energy balance value is calculated from energy consumption and daily calorie intake. 258. The method of claim 256, wherein the adjustment threshold is selected as a target tolerance for placing the user in a particular category based on the current target status. 270. The method of claim 257, wherein the category is indicated by a balance said indicator. 268. The category of claim 257, wherein the category is one of where the user has met and exceeded the daily energy balance target amount, the user must meet the daily energy balance target amount and the user will not meet the daily energy balance target amount. Way. 258. The method of claim 256, wherein a secondary time is selected as a threshold to determine whether the time is one of early and late. 260. The method of claim 260, wherein the current time is compared with an auxiliary time in relation to the current target state. 261. The method of claim 261, wherein the intermittent status report is generated to indicate whether an individual can meet an energy balance target amount based on the time of day. 262. The method of claim 262, wherein the intermittent status report indicates a proposal for energy expenditure activity to help achieve an energy balance target. 263. The method of claim 263, wherein the intermittent status report suggests an activity based on a target status. 194. The method of claim 193, further comprising achieving a database of data output values. 265. The method of claim 265, wherein the database comprises a pattern of physiological data. 265. The method of claim 265, wherein the database comprises a pattern of contextual data. 265. The method of claim 265, wherein the database comprises a pattern of activity data derived from physiological and contextual data. 265. The method of claim 265, further comprising analyzing the data output values to achieve a data pattern. 269. The method of claim 269, further comprising storing the data pattern. 270. The method of claim 270, further comprising comparing the stored data pattern with the detected data to categorize the detected data into additional data patterns. 278. The method of claim 271, further comprising: (i) comparing the stored data pattern with detected data to identify the detected data as being similar to at least one of the stored data patterns; And (ii) predicting future detected data. 272. The method of claim 272, further comprising generating an output based on a prediction of the future detected data. 278. The method of claim 273, wherein the output is an alarm. 278. The method of claim 273, wherein the output is a report. 278. The method of claim 273, wherein the output is used as an input by another device. 199. The method of claim 193, further comprising the final step of using the feedback for the purpose of achieving an initial assessment of the weight correction target amount. 277. The method of claim 277, further comprising the additional final step of using the feedback to assess an intermediate state of progression to the weight correction target amount.

Images