WO2007138930A1 - 疲労推定装置及びそれを搭載した電子機器 - Google Patents
疲労推定装置及びそれを搭載した電子機器 Download PDFInfo
- Publication number
- WO2007138930A1 WO2007138930A1 PCT/JP2007/060443 JP2007060443W WO2007138930A1 WO 2007138930 A1 WO2007138930 A1 WO 2007138930A1 JP 2007060443 W JP2007060443 W JP 2007060443W WO 2007138930 A1 WO2007138930 A1 WO 2007138930A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- fatigue
- level
- activity
- estimation
- user
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
Definitions
- the present invention relates to an apparatus and a method for realizing estimation of a fatigue level from body movement of a subject.
- the estimation of psychosomatic diseases can be realized to some extent by measuring hormones in the brain or using a device for measuring blood flow. It can also be realized by conducting various tests and questionnaires.
- the estimation of fatigue can be realized by, for example, the ATMT method (Advanced Trial Making Test method).
- ATMT method Advanced Trial Making Test method
- numbers appearing on the display are touched in order, and the level of fatigue is measured from the time required at that time.
- Questionnaires are often used as a method of estimating psychosomatic disorders including fatigue.
- Patent Document 1 Japanese Patent Laid-Open No. 7-178073 (published July 18, 1995)
- the present invention has been made in view of the above-described conventional problems, and is a fatigue estimation device, a fatigue warning device, an electronic device, a fatigue estimation method, and a fatigue level that can be estimated inexpensively and easily. It is an object to provide a fatigue estimation program and a computer-readable recording medium.
- the fatigue estimation apparatus of the present invention includes activity level detection means for continuously detecting the frequency of user activity as the activity level, and is detected by the activity level detection means.
- the activity level is output to a fatigue level estimation means for estimating the user's fatigue level based on the activity level.
- the activity level of the user can be automatically detected by the activity level detection means.
- the fatigue level estimation means estimates the user's fatigue level based on the activity level.
- the fatigue level is automatically determined based on the activity level automatically detected by the activity level detection means. Bell is estimated.
- the activity level of the user is automatically detected by the activity level detection unit, and the fatigue level is automatically detected from the detected activity level by the fatigue level estimation unit. Estimated. Therefore, the user's fatigue level can be easily estimated.
- the user's fatigue level can be estimated with a simple configuration of the activity level detection means and the fatigue level estimation means, the user's fatigue level can be estimated at low cost.
- FIG. 1 is a block diagram showing a configuration according to an embodiment of the present invention.
- FIG. 2 (a) is a graph showing typical body movement data when a person is tired.
- [2 (b)] is a graph showing typical body movement data when a person is tired.
- [2] (c)] is a graph showing body movement data of a patient with chronic fatigue syndrome.
- [2 (d)] is a graph showing the difference of the body motion data shown in FIG. 2 (c).
- [3 (a)] is a graph showing typical body movement data when a person is not tired.
- [3 (b)] This is a graph showing typical body movement data when a person is not tired.
- [3 (c)] This is a graph showing typical body movement data when a person does not feel tired.
- [3 (d)] This is a graph showing body motion data obtained by removing the trend from the body motion data shown in FIG. 3 (c).
- [4 (a)] is a diagram showing a state in which a person moves small when awakened.
- [4 (b)] is a diagram showing a state where a person is stationary when fatigued.
- FIG. 4 (c) is a diagram showing a state in which a person is freely active.
- [4 (d)] is a diagram showing a state in which a person is freely active.
- FIG. 5 is a diagram showing data after passing a one-axis output that can also obtain the force of an acceleration sensor attached to the wrist through a no-pass filter in order to see a change in acceleration.
- FIG. 6 (a) A table comparing five samples with respect to the skewness and average of body motion data and the fatigue level.
- FIG. 6 (b) This is a diagram showing the correlation between the estimated fatigue level and the numerical value that quantitatively shows the actual fatigue level obtained as a result of the questionnaire.
- FIG. 7 is a diagram showing a sigmoid function and an arctangent function.
- FIG. 8 (a) A diagram showing a result of measuring a 3-axis output of acceleration sensor force attached to the wrist for a certain period of time.
- FIG. 8 (b) is a diagram showing the output after passing the vector sum of the three-axis output through a no-pass filter.
- FIG. 9 (b) is a flowchart showing a specific process for calculating a fatigue level.
- ⁇ 10 (a)] is a diagram showing an example of the appearance of a mobile phone equipped with the fatigue warning device of the present invention.
- ⁇ 10 (b)] is a diagram showing an example of the appearance of a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 10 (c) is a diagram showing an example of the appearance of a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 11 (a) is a diagram showing a state in which the wristwatch equipped with the body motion detection unit in FIG. 1 is attached to the arm.
- FIG. 11 (b) is a diagram showing an image in which the product of the present invention is usually used.
- FIG. 12 (a) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 12 (b) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 12 (c) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 12 (d) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 12 (e) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- FIG. 12 (£) is a diagram showing a warning message displayed on a mobile phone equipped with the fatigue warning device of the present invention.
- Fig. 2 (a) and Fig. 2 (b) show typical body movement data when a person is tired.
- Figures 3 (a) to 3 (c) show typical body movement data when a person does not feel tired. Both The horizontal axis shows the elapsed time, and the vertical axis shows the body movement data obtained from the acceleration sensor force attached to the wrist.
- the body movement data is data that quantitatively indicates the frequency of human activity (activity), and a specific measurement method will be described later.
- body movement data with a low value compared to the surroundings only for a short time there is often no tendency to obtain body movement data with a low value compared to the surroundings only for a short time.
- body movement data with a lower value than the surroundings may be obtained for a short time, or body movement data with a higher value than the surroundings may be obtained for a short time.
- Body movement data may be widely distributed.
- the human fatigue level can be estimated from the body motion data. More specifically, the fatigue level can be estimated by detecting relatively low body motion data.
- FIG. Figure 5 shows the data after passing through a high-pass filter to see the change in acceleration for a single axis output that can also obtain the acceleration sensor force attached to the wrist!
- the body motion data shown in Fig. 2 (a), Fig. 3 (a), etc. has a threshold value of the output sensor (acceleration data) force 0.01G after passing the high-pass filter shown in Fig. 5.
- This data records the number of passes per unit time.
- the output of the acceleration sensor has passed the threshold value four times, so the body motion data is measured as 4.
- the body motion data measured in this way is generally called zero crossing data, and is used for sleep / wake detection, life rhythm analysis, and the like.
- the data shown in FIG. 5 is a force that allows the output of the acceleration sensor to pass through the noise-pass filter in order to efficiently see changes in the body motion data. Absent. For example, by subtracting the moving average value related to the output value of the acceleration sensor from the output value of the acceleration sensor itself, the change in the body motion data can be seen efficiently.
- the difference in human activity indicated by the body movement data shown in Fig. 2 (a), Fig. 3 (a), and Fig. 3 (c) can be estimated by taking the method described below.
- the trend of body motion data is removed.
- the trend can be removed as described below, for example.
- “Trend” means the tendency of long-term fluctuations in body movement data.
- the body motion data is further divided into shorter times, and the regression curve of the body motion data is obtained by calculating the first order approximation of the data of each section using the least square method.
- the trend of body movement data can be grasped from this regression curve.
- the data y (t) can be expressed as follows.
- t is the time of each data.
- the body movement data shown in Fig. 2 (b) is obtained from the body movement data shown in Fig. 2 (a), and the body movement data shown in Fig. 3 (a).
- the body motion data shown in Fig. 3 (b) is obtained from Fig. 3 (b), and the body motion data shown in Fig. 3 (d) is obtained from the body motion data shown in Fig. 3 (c).
- the skewness of the body movement data from which the trend at the time of fatigue is removed is negative 0.0118, whereas the skewness of the body movement data from which the trend at the time of non-fatigue is removed is larger than that. Indicates a positive value. That is, it can be said that the skewness is greatly related to fatigue.
- the fact that the degree of distortion is small means that the data is prominently low in value and prominently larger than the large value.
- the fact that the degree of distortion decreases when the fatigue level is high agrees well with the tendency of fatigue shown by the body motion data in Fig. 2 (a), Fig. 3 (a), and Fig. 3 (c). ing.
- Fig. 6 (a) shows a table comparing five samples regarding the skewness and average of body motion data and the fatigue level.
- the “actual fatigue level” shown in FIG. 6 (a) is information that quantitatively indicates the fatigue level obtained as a result of the questionnaire and can also be expressed as actual fatigue level information.
- Figure 6 (b) shows the correlation between the fatigue level estimated by the above formula and the numerical value that quantitatively shows the actual fatigue level obtained as a result of the above questionnaire.
- Figure 6 (c) shows the correlation between the output value obtained by inputting the estimated fatigue level into the sigmoid function and the numerical value that quantitatively shows the actual fatigue level.
- the fatigue level can be estimated with higher accuracy by using the following calculation formula.
- Fatigue 0.732 X Mean + 58.321 X Skew-4.028 X Mean X Skew + 33.370 where Mean indicates the average value of the body motion data, and Skew indicates the skewness of the body motion data with the trend removed. .
- the fatigue level can be estimated by a simple calculation formula. Therefore, the fatigue level can be estimated with a small load, but by combining statistical analysis methods, fatigue can be accurately performed. The level can be estimated. Also, statistical analysis methods are not limited to methods using average and skewness.
- the fatigue level can be estimated with higher accuracy by using the standard deviation or kurtosis of the body motion data.
- Fatigue 3.436 X mean + 16.392 X sd + (-62.426) X skew
- kurtosis The kurtosis of Zero Crossing Data in the past 30 minutes after removing the trend
- coefficients of the calculation formulas mentioned here and the statistical values to be used are merely examples, and it is needless to say that there is a possibility that they may vary depending on the measurement device, the subject, and the body part to be measured.
- the body motion data used for fatigue estimation does not necessarily need to be continuous.
- FIG. 2 (c) is a diagram showing body movement data of a patient with chronic fatigue syndrome.
- the inventors' earnest attention is that the body movement data of patients with chronic fatigue syndrome show relatively more rapid decline and slower and more powerful rise compared to normal subjects. The results of the study were found.
- FIG. 2 (d) is a graph showing the difference between the body motion data shown in FIG. 2 (c), and the long-term fluctuation component of the body motion data shown in FIG. 2 (c) is removed. It is assumed that the data shows.
- the difference value when the body motion data falls abruptly, the difference value shows a negative value for a short time, and when the body motion data rises slowly, the difference value shows a small positive value for a long time. Indicates the value.
- Such characteristics of body motion data can also be grasped by statistically analyzing the difference values of the body motion data. For example, if the body movement data shows a rapid decline and a gradual rise, the degree of distortion of the body movement data becomes small.
- the fatigue level can be estimated by the above formulas. However, if the above formula is maintained, the estimated fatigue level may be below the minimum value ⁇ or the maximum value may exceed 100. For example, among the five samples shown in FIG. 6 (a), the estimated fatigue level when the actual fatigue level is 0 is 0.306, which is below 0.
- a shaping process may be performed so that the fatigue level falls within a predetermined range (in the present embodiment, between 0 and 100).
- the sigmoid function has a slope that becomes closer to 50 near 50 and becomes gentler as it goes away from 50, and can be kept from 0 to 100 for any value. Has characteristics.
- the sigmoid function has the steepest slope near 50 and the highest sensitivity, so that a subtle change in characteristics near 50 can be clarified.
- the force also has a positive slope throughout, so the magnitude of the value does not reverse.
- the fatigue level is 0 as described above.
- the fatigue level can be corrected to a positive value close to 0, that is, 7.48.
- the fatigue level calculated as 30.07 and 50.17 is 26.96 and 50.22, respectively, as shown in Fig. 6 (a). And it is not much different from the previous value using the sigmoid function.
- Functions other than the sigmoid function may be used according to the purpose of use. If one is selected other than the sigmoid function, the arctangent function shown by the broken line in Fig. 7 can be listed. When the sigmoid function shown in Fig. 7 is used, values of 100 or more and 0 or less approach 100 or 0, respectively, but arc tangent is required to clarify the difference in fatigue level even when the value is 100 or 0 or less. It is better to use a function.
- the portion for increasing the sensitivity need not be limited to about 50, and the portion for which the sensitivity is to be increased may be changed according to the application.
- the alternate long and short dash line in FIG. 7 indicates the following sigmoid function. According to this sigmoid function, the sensitivity around 80 to 90 is enhanced.
- Body motion data used to estimate fatigue levels need not be limited to zero crossing data, and there is no need to set a single threshold.
- the output data (acceleration data) of the acceleration sensor force shown in Fig. 8 (a) or Fig. 8 (b) may be used as it is.
- Fig. 8 (a) shows the measurement of the triaxial output from the acceleration sensor attached to the wrist for a certain period of time.
- the vertical axis is acceleration in units of 1G. If there is no movement, the vector sum of the 3-axis output is 1G, which is the same as the Earth's gravitational acceleration.
- FIG. 8 (b) is a diagram showing an output after passing the vector sum of the three-axis outputs through a noise pass filter. Normally, if there is no movement, the acceleration data shown in Fig. 8 (b) is a constant value of 0. A value other than 0 is output according to the wrist movement.
- Estimating the fatigue level using the acceleration data shown in Fig. 8 (a) or Fig. 8 (b) can be realized, for example, by taking the following method.
- a plurality of threshold values are provided in the calorie velocity data shown in FIGS. 8 (a) and 8 (b), for example, in increments of 0.05G.
- the elapsed time from the time when acceleration data changes from a value exceeding the threshold value to a value below the threshold value to the time when the acceleration data changes from a value below the threshold value to a value exceeding the threshold value. (The part indicated by the arrow in the figure) is calculated. Then, for example, mean and variance are analyzed as statistics of this elapsed time.
- the activity status changes depending on whether or not the subject is fatigued, and this change is due to the appearance of relatively low body motion data in continuously measured body motion data.
- the method of discriminating changes in body motion data is not limited to a statistical method, but can also be performed by DFA (Detrend Fluctiation Analysis) to vWTMM (Wavelet Transform Modulus Maxima) to evaluate the fractal. In some cases, changes in body motion data can be identified. However, using these methods increases the amount of computation, so when assessing fatigue level with a mobile device, etc., a method of estimating the fatigue level from about two statistical values (for example, average and skewness) Judging from accuracy and calculation amount, it is most suitable. Therefore, in the following, an example of a fatigue warning device equipped with a function to estimate the fatigue level using two statistical values, average and skewness, will be described.
- the fatigue estimation device 1 of the present embodiment includes a body motion detection unit (activity detection means) 2 and a fatigue detection unit (fatigue level estimation means) 3.
- the fatigue warning device 10 of the present embodiment includes a fatigue estimation device 1, a fatigue warning determination unit (fatigue warning determination unit) 11, a fatigue presentation unit (fatigue presentation unit) 12, Is included.
- the body motion detection unit 2 detects the movement of the user's body (body motion) and has a wristwatch type shape that can be attached to the wrist.
- the body motion detection unit 2 includes an acceleration sensor (activity detection means) 4, a first data accumulation unit (activity detection means) 5, and a data transmission unit (activity detection means) 6. .
- the acceleration sensor 4 senses wrist acceleration.
- the acceleration sensor 4 The acceleration data obtained by the above is accumulated in the first data accumulation unit 5 for a certain period of time. Then, the data stored in the first data storage unit 5 is transmitted to the fatigue detection unit 3 via the data transmission unit 6. By accumulating acceleration data in the first data accumulation unit 5 in this way, even if the transmission of acceleration data by the data transmission unit 6 is interrupted for a short time, the acceleration data corresponding to the interruption time is stored in the first data accumulation unit 5.
- the acceleration data can be transmitted from the data transmission unit 6 to the fatigue detection unit 3 without interruption.
- the fatigue detection unit 3 is preferably realized by a portable small device and provided inside the mobile phone.
- the fatigue detection unit 3 includes a data reception unit (fatigue level estimation unit) 7, a second data storage unit (fatigue level estimation unit) 8, and a fatigue level calculation unit (fatigue level estimation unit) 9. .
- the data receiving unit 7 receives acceleration data transmitted from the data transmitting unit 6 of the body motion detecting unit 2.
- the acceleration data received by the data receiving unit 7 is accumulated in the second data accumulating unit 8.
- the fatigue level calculation unit 9 calculates the fatigue level (Fatigue) using the acceleration data stored in the second data storage unit 8 and the calculation formula described above.
- the fatigue warning determination unit 11 determines whether or not to issue a warning to the user based on the fatigue level (Fatigue) calculated by the fatigue level calculation unit 9. The determination process in the fatigue warning determination unit 11 will be described later.
- the fatigue warning determination unit 11 determines that it is necessary to issue a warning to the user, the information is sent to the fatigue presentation unit 12, and the fatigue level is set to the user as described later. Corresponding warnings and messages are communicated.
- the configuration shown in FIG. 1 is merely an example for realizing the present invention, and may be another configuration.
- the body motion detection unit 2, the fatigue warning determination unit 11, and the fatigue presentation unit 12 are separated from each other. This is to prevent the burden on the user as much as possible. This is to reduce the size of the body motion detection unit 2 and increase the size of the fatigue presentation unit 12 so that as much information as possible can be transmitted to the user.
- the body motion detection unit 2, the fatigue warning determination unit 11 and the fatigue presentation unit 12 may be integrated.
- the first data storage unit 5, the data transmission unit 6, and the data reception unit 7 may be omitted.
- the fatigue warning determination unit 11 and the fatigue presentation unit 12 and the fatigue level calculation unit 9 the fatigue detection unit 3
- the fatigue warning determination unit 11 and the fatigue presentation unit 12 can be realized by separate devices.
- a configuration may be adopted in which the fatigue presentation unit 12 is omitted, and the fatigue level and risk level are transmitted to a medical institution or user administrator via a network.
- the fatigue level is estimated from the activity of a part of the body (wrist), but a similar sensor is worn not only on the wrist but also on the whole body to determine the fatigue level. It is of course possible to estimate. Since the wrist is often moved, it is suitable for measuring body movement data. However, it often moves due to external factors such as riding on a vehicle. In that case, the accuracy of estimating the fatigue level decreases.
- the wrist essentially does not move when sleeping, but may move according to the shaking of the vehicle when riding, and the fatigue level is estimated based on the acceleration caused by the shaking. It doesn't make sense.
- the acceleration of the whole body for example, the waist, legs, trunk, head, etc.
- the vibration caused by the movement of the vehicle It is better to cancel the vibration with the acceleration force of the whole body.
- the fatigue level cannot be estimated from the wrist acceleration! /
- the second and third candidates such as the waist, legs, trunk, or head
- the fatigue level It is also possible to estimate the fatigue level.
- health care workers are concerned about infections when they wash their hands and need to remove their wristwatches and wash their hands up to their wrists. In some situations, they may not wear their wrist watches for a while. In that case, it is possible to correctly estimate the fatigue without interruption by measuring the activity at the part other than the wrist and estimating the activity / power fatigue level.
- the force using the acceleration sensor 4 as the sensor of the body motion detection unit 2 is a method for detecting the tendency of the body motion data during fatigue described with reference to FIGS. 2, 3, and 4. Is not limited to the method using an acceleration sensor.
- the position information output from the position information sensor attached to the user's body is received using, for example, UWB (Ultra Wide Band) communication means.
- UWB Ultra Wide Band
- the user's position information can be detected quickly.
- the fatigue level may be estimated in the same procedure as when using the acceleration sensor.
- body motion data is measured by the acceleration sensor 4 in that the fatigue level can be easily estimated with higher accuracy.
- FIG. 9 (a) shows a flowchart relating to a fatigue estimation method realized by the fatigue estimation device 1 or the fatigue warning device 10 described above.
- acceleration sensor 4 First, measurement of acceleration data is started by the acceleration sensor 4 (Sl). Thereafter, the acceleration sensor 4 continues to acquire the acceleration data (S2), and determines whether or not the force has passed a certain time (for example, 30 minutes) from the start of the acceleration data measurement. In this way, the acceleration data force measured by the acceleration sensor 4 is accumulated in the first data accumulating unit 5 until a certain time has elapsed since the start of measurement.
- a certain time for example, 30 minutes
- the acceleration data stored in the first data storage unit 5 is stored in the second data storage unit 8 via the data transmission unit 6 and the data reception unit 7 as described above.
- the level calculation unit 9 calculates the fatigue level based on the above-described calculation formula using the acceleration data stored in the second data storage unit 8 (S4).
- FIG. 9 (b) shows a processing flow for calculating the fatigue level.
- the fatigue level calculation unit 9 acquires acceleration data stored in the second data storage unit 8 (S 11), and removes the influence of gravity from this acceleration data using a high-pass filter (S 12 ).
- the fatigue level calculation unit 9 counts the number of times that the acceleration data from which the influence of gravity has been removed in S12 passes a predetermined threshold (S13), so that zero crossing data, that is, the body Get dynamic data.
- the fatigue level calculation unit 9 calculates a mean value (Mean) of body motion data (S 1
- the fatigue level calculator 9 calculates the fatigue level Fatigue based on the following equation using the mean value calculated in S 14a and the skewness Skew calculated in S 14c (S15).
- Fatigue 0.732 X Mean + 58.321 X Skew-4.028 X Mean X Skew + 33.370
- the fatigue warning determination unit 11 sets the calculated fatigue level Fatigue to a constant value (for example, 7
- the fatigue presentation unit 12 displays a warning that the user is tired on a predetermined screen (S7). In addition, if “No” is determined in either S5 or S6, the fatigue presentation unit 12 does not issue the above warning.
- the next fatigue level cannot be estimated until the acceleration data necessary for estimating the fatigue level is accumulated in the second data accumulation unit 8. Yes.
- the fatigue level at an arbitrary time can be estimated to some extent.
- the fatigue level may be output according to the user's request.
- the number of fatigue levels referred to by the user is large and the fatigue levels are similar, the tendency to determine whether the fatigue is accumulated or whether the fatigue has recovered May not be accurately communicated.
- the specification is such that no warning is issued until a certain time (2 hours) elapses after the warning is once issued. This is because once a fatigue warning is issued, the user is likely to take measures to recover from fatigue (such as a break). Also, fatigue is not expected to recover immediately after taking a break, and repeated fatigue warnings before fatigue recovers do not make much sense.
- a coefficient in an arithmetic expression for obtaining a fatigue level and an algorithm for estimating the fatigue level can be dynamically calibrated and corrected to improve the estimation accuracy of the fatigue level. It is even better to ask the patient's subjective symptoms and correlate with the estimated fatigue level.
- the process of associating the inquiry result with the fatigue level can be specifically realized as follows. First, when the fatigue level is estimated intermittently or continuously, the estimated fatigue level is recorded in the second data storage unit 8 together with the time information at that time.
- the fatigue presentation unit 12 displays a screen for determining the degree of subjective symptoms. And Acquires the degree of subjective symptoms of fatigue input by the user via the operation input unit (not shown) in the fatigue warning device 10, and provides information (actual fatigue level information) about the acquired subjective symptoms. Then, it is stored in the second data storage unit 8 together with the time information at that time.
- the estimated fatigue level information related to the estimated fatigue level and the actual fatigue level information can be correlated with respect to time.
- FIG. 10 and FIG. 11 show examples of wearing the fatigue estimation device and fatigue warning device according to the present embodiment.
- FIG. 10 (a) to FIG. 10 (c) are examples of the appearance of a mobile phone equipped with the fatigue warning device described with reference to FIG.
- this will be referred to as “mobile phone with product of the present invention”
- product of the present invention for distinction.
- the contents of the description of the mobile phone with the product of the present invention it was understood that all the contents except the description about the phone were described as the description of the configuration of the product of the present invention.
- the cellular phone 201 with a product of the present invention is of a folding type, and includes a main body 202 and a lid 203.
- the mobile phone 201 with the present invention it is generally different from the mobile phone that is generally distributed except that the fatigue estimation device 1 and the fatigue warning device 10 of the present embodiment are installed.
- the main body 202 has a cell phone operation key array, and the display unit 203a of the lid unit 203 displays various functions of the cell phone. Do.
- a fatigue warning for the user can be given by the screen display on the display unit 203a.
- the fatigue warning can be confirmed with almost the same operation as when receiving a call or receiving / sending mail. That is, from the state shown in FIG. 10 (a) to the state shown in FIG. 10 (c) through the state shown in FIG. 10 (b).
- the method of giving a fatigue warning using the cellular phone 201 with the present invention is not limited to the method described above.
- the lid 203 has a small display unit
- the fatigue state may be displayed on the display unit.
- the fatigue state can be confirmed without opening the cellular phone 201 with the product of the present invention.
- the fatigue state can be displayed in detail on a large screen rather than using a small display unit using the display unit 203a, the fatigue state can be accurately communicated to the user.
- the display unit 203a is not limited to the screen display, and the fatigue state can be transmitted to the user by sound or vibration, or a combination thereof, or the fatigue state can be presented to the user by various methods.
- a short beep may be sounded and a message prompting for a break may be displayed on the display unit 203a.
- a message confirmation process by the user is detected, such as detecting the opening of the lid 203 from the folded state of the cellular phone 201 with the present invention.
- fatigue warnings may be continued using beeps and vibrations. As a result, it is possible to reliably issue a warning to the user.
- Fig. 11 (a) is a diagram showing a state in which the wristwatch equipped with the body motion detection unit 2 in Fig. 1 is worn on the arm.
- a wristwatch equipped with the body motion detector 2 is not significantly different from a normal wristwatch at first glance, and the time can be confirmed.
- a wristwatch equipped with the body motion detection unit 2 is different from a normal wristwatch in that the acceleration sensor 4, the first data storage unit 5, and the data transmission unit 6 shown in FIG. Different.
- FIG. 11 (b) shows an image diagram in which the product of the present invention is usually used.
- the mobile phone 201 with the product of the present invention is put in a trouser pocket or the like and carried close to the user, and the body motion detector 2 is installed. Always wear the wristwatch 204 on your wrist.
- the cellular phone 201 with the product of the present invention and the wristwatch 204 communicate frequently. There must be a communication range between the two.
- the body motion detection unit 2 includes a first data storage unit 5. Therefore, while the first data storage unit 5 can store acceleration data, even if communication between the mobile phone 201 with the present invention and the wristwatch 204 is interrupted, user acceleration data can be acquired without interruption. Can do.
- These two configurations do not necessarily have to be separated.
- the functions related to the fatigue warning device of the present invention can be realized only by the mobile phone, and the advantage of reducing the number of parts can be obtained. It is done.
- the wrist acceleration is used, the user's fatigue level can be estimated with the highest accuracy. Therefore, in the present embodiment, a configuration in which the mobile phone 201 with the product of the present invention and the arm watch 204 are separated may be adopted.
- the mobile phone with the product of the present invention If the fatigue level calculated by the fatigue level calculation unit 9 is determined to be, for example, 70% or more by the fatigue warning determination unit 11, the mobile phone with the product of the present invention generates the same ringing tone as when a call is received. And a message prompting for a break is displayed on the display unit 203a as shown in FIG. 12 (a).
- a plurality of fatigue warning levels may be set. For example, if the fatigue warning calculation unit 11 determines that the fatigue level calculated by the fatigue level calculation unit 9 is 90% or more, a message with a higher degree of urgency is displayed as shown in Fig. 12 (b). May be.
- Fig. 12 (c) a message that suggests a break to the user according to the fatigue level is displayed before the closing time, so that the user can calm down and respond to the message. Later actions can also be judged.
- a graph showing the temporal transition of the fatigue level is displayed on the display unit 20.
- the user can confirm the time transition of his fatigue level.
- the person who reports the result of fatigue estimation is not necessary for the person who reports the result of fatigue estimation to be a person wearing the product of the present invention.
- the product of the present invention is not limited to being mounted only on a mobile phone. An example in which the result of fatigue estimation is transmitted to a person other than the wearer will be described below.
- FIG. 12 (e) An example in which the wearer of the present invention is a sports player and the result of fatigue estimation is transmitted to the manager of the player will be described with reference to FIG. 12 (e).
- the wearer of the present invention is a sports player and the result of fatigue estimation is transmitted to the manager of the player
- FIG. 12 (e) As shown in Fig. 12 (e), by displaying a message informing that the athlete is tired in Fig. 12 (e), the manager can directly ask the athlete whether he is tired or not. Players can be replaced at the right time without relying on experience or intuition.
- the fatigue presentation unit 12 need not be limited to the display unit of the mobile phone.
- a fatigue presentation unit 12 may be provided in an electronic device having a notification function, and the fatigue presentation unit 12 may be used to convey the result of fatigue estimation to the supervisor.
- the environment of use is a stadium, the effects of water and dust are unavoidable, and there may be cases where it is not appropriate to install the fatigue presentation section 12 on electronic equipment. In such a case, the result of fatigue estimation may be transmitted by voice.
- transmission means for transmitting fatigue level information indicating the fatigue level estimation result to the outside via a network as described later may be provided in the product of the present invention.
- a message indicating that the fatigue estimation result determined by the fatigue warning determination unit 11 is informed to the medical institution may be displayed on the display unit 203a.
- the display unit 203a may be displayed on the display unit 203a.
- the electronic device having the function of the present invention is not limited to a mobile phone, but may be an in-vehicle device.
- a personal computer with a function to estimate the fatigue level in the business, if it is determined that the user feels fatigue during the work, the user is encouraged to take a break from the fatigue presentation section 12 provided in the computer. Can avoid overwork problems it can.
- the fatigue presentation unit 12 provided in the in-vehicle device can inform the user of overdriving and the timing of breaks, preventing accidents in advance. be able to.
- the estimation of the fatigue level using the product of the present invention is not necessarily performed in real time.
- data indicating the result of estimating the fatigue level may be accumulated for a certain period, and the fatigue level may be estimated using, for example, a home PC based on the accumulated data.
- the change in fatigue level over time over a certain period in the past can be grasped afterwards.
- the program for executing the flowchart for estimating the fatigue level should be able to follow up the processing steps later so that the fatigue level can be estimated with higher accuracy in the future. desirable.
- the program for estimating the fatigue level can be updated by simply downloading the program using the original communication function of the mobile phone. This is suitable for adding processing steps later.
- Fatigue is a common symptom of various nervous system diseases such as depression and chronic fatigue syndrome. Moreover, in recent years, accidents associated with fatigue and diseases that cause overwork have become a problem. Therefore, if it is possible to easily detect fatigue at any time, it will be possible to detect neurological diseases as described above early and judge the degree of symptoms, and to prevent accidents associated with fatigue. It is significant.
- the fatigue level is calculated on the mobile phone side!
- body motion data may be acquired and stored using a mobile phone, and the acquired body motion data may be transmitted to a specified server, and the fatigue level may be calculated at the server or a workstation connected to the server. .
- the fatigue level may be displayed on the mobile phone, or the mobile phone power may issue a fatigue warning.
- the fatigue level calculated by the server may be sent to other than the user, such as a medical institution, a user administrator, a user's relative or friend.
- the fatigue estimation method executed by the fatigue estimation apparatus of the present embodiment can be recorded as a fatigue estimation program on a computer-readable recording medium in which a program executed by a computer is recorded.
- a portable recording medium on which a program for performing the fatigue estimation method of the present embodiment is recorded.
- a program reading device as an external storage device is provided, which is not shown in the figure because it is processed by a microcomputer, for example, a program medium such as ROM. It can also be a program medium that can be read by inserting a recording medium into it! /.
- V in case of misalignment, may be configured such that the program stored and accessed by the microprocessor is executed, and the program read out and read out is Alternatively, the program may be downloaded to a program storage area (not shown) of the microcomputer and executed. In this case, it is assumed that the download program is stored in the main unit in advance.
- the program medium is a recording medium configured to be separable from the main body, and includes a tape system such as a magnetic tape and a cassette tape, a magnetic disk such as a floppy (registered trademark) disk and a hard disk, and a CD— ROMZMOZMDZDVD and other optical disk systems, IC cards (including memory cards) Z optical cards and other card systems, mask ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electricaly Erasable Programmable Read Only Memory), flash It may be a medium that carries a fixed program including semiconductor memory such as ROM.
- the system configuration that can connect to a communication network including the Internet may be a medium that dynamically carries the program so as to download the communication network power program.
- the download program may be stored in advance in the receiver, or may be installed on another recording medium capability.
- the fatigue estimation apparatus of the present invention includes activity level detection means for continuously detecting the frequency of user activity as the activity level, and the activity detected by the activity level detection means.
- the mobility is output to a fatigue level estimation means that estimates the user's fatigue level based on this activity.
- the activity level of the user can be automatically detected by the activity level detection means.
- the fatigue level estimation means estimates the user's fatigue level based on the activity level.
- the fatigue level is automatically determined based on the activity level automatically detected by the activity level detection means. Bell is estimated.
- the activity level is automatically detected by the activity level detection means, and the fatigue level is automatically detected from the detected activity level by the fatigue level estimation means. Estimated. Therefore, the user's fatigue level can be easily estimated.
- the user's fatigue level can be estimated at a low cost because the user's own fatigue level can be estimated with a simple configuration of activity level detection means and fatigue level estimation means.
- the fatigue estimation device is characterized in that the fatigue level estimation means is such that the activity level showing a continuously high value is lower by a short time than the time showing the high value. It is preferable to estimate the fatigue level by judging the tendency to show the ⁇ value ⁇
- the activity level that continuously shows a high value tends to show a low value for a short time compared to the time that shows a high value.
- the fatigue level estimation means judges this tendency and estimates the fatigue level. Therefore, it is possible to accurately grasp the user's fatigue and accurately estimate the fatigue level.
- the fatigue level estimation means determine the tendency of the activity level by statistically analyzing the activity level.
- the tendency that appears in the activity level during fatigue can be accurately grasped by performing a statistical analysis of the activity level, for example, by calculating the skewness or average of the activity level. Therefore, if the activity is analyzed statistically, the user's fatigue level can be estimated more accurately. It can be done with certainty.
- the fatigue level estimation means removes a long-term fluctuation component of the activity and determines the tendency in the activity from which the fluctuation component is removed.
- the fatigue level estimation means removes the long-term fluctuation component of the activity level and judges the tendency in the activity level from which the fluctuation component has been removed, so that the fatigue of the chronic fatigue syndrome patient can also be grasped. it can.
- the fatigue level estimating means can remove long-term fluctuation components of the activity by differentiating the activity with respect to time.
- the long-term fluctuation component of the activity level may be removed by obtaining a difference value in the activity level.
- a regression curve of the activity level may be obtained, and the regression curve may be removed from the activity level as a long-term fluctuation component of the activity level!
- the fatigue level estimation means corrects a range that the fatigue level can take to a predetermined range.
- the range force that the fatigue level estimated by the fatigue level estimation means can take is corrected to a predetermined range. Therefore, the estimated fatigue level value is more appropriate by matching the predetermined range after this correction with the range that can be taken by the value that quantitatively indicates the level of fatigue that the user actually feels. Can be.
- the fatigue level estimation means is a function that changes the output value with sensitivity higher than the sensitivity to the input value, not near the specific value, with respect to the change in the input value near the specific value. It is preferable that the range that the fatigue level can take is set to a predetermined range using.
- the specific numerical value is a numerical value that clearly grasps the change in the fatigue level
- the input value of the function is the estimated fatigue level itself
- the output value of this function The change in the vicinity of the numerical value for which the change in the fatigue level should be clearly understood will change greatly. Therefore, if the output value of the function is determined, the fatigue level can be determined more accurately.
- An example of such a function is a sigmoid function.
- the activity level detection means preferably detects the activity level based on the acceleration of motion in a part of the whole body of the user! /.
- the activity detection means detects the activity as the number of times the acceleration has changed.
- the activity detection means detects the number of times the acceleration has changed as the number of times the acceleration passes a predetermined threshold value.
- the activity detection means may detect the acceleration based on a temporal change in position information of all or part of the user's body.
- the acceleration may be a three-dimensionally obtained acceleration of movement in all or part of the user's body.
- the acceleration may be an acceleration obtained in the one-dimensional direction of motion in the whole or a part of the user's body.
- one-dimensional motion refers to the X-axis' y-axis ⁇ ⁇ -axis when the user's motion is defined in the direction of the three axes X-axis * y-axis ⁇ ⁇ -axis.
- the user s direction to the axis It means exercise.
- To evaluate one-dimensional motion it is sufficient to use a single-axis output acceleration sensor.
- the acceleration is preferably an acceleration of the user's wrist movement.
- the activity level detection means is preferably provided in a wristwatch.
- the wrist acceleration can be accurately detected by providing the activity level detection means in the wrist watch. This makes it possible to accurately detect the activity and estimate the fatigue level more accurately.
- the activity level detection means may detect the activity level based on positional information of all or part of the user's body! /.
- the tendency for the user's body movement to decrease during fatigue can also be detected by judging the user's position information. In other words, if body movement decreases, the user's position will naturally not change much. Therefore, the user's fatigue can be detected by detecting the tendency that the position does not change based on the position information.
- the user's position can be determined, so that the user's position can be grasped together with the user's fatigue level.
- the activity level detection means may detect the activity level based on image information obtained by photographing all parts of the user's body! /.
- the actual fatigue level information related to the user's fatigue obtained as a result of the inquiry to the user is associated with the estimated fatigue level information related to the fatigue level estimated by the fatigue level estimation means. That is, the actual fatigue level information regarding the user's fatigue obtained as a result of the inquiry to the user is the most reliable information indicating the user's fatigue. Therefore, by associating this information with the estimated fatigue level information related to the fatigue level estimated by the fatigue level estimating means, the user's fatigue level can be determined more accurately, and an appropriate treatment can be performed.
- the fatigue level estimation means is preferably provided in a server separated from the fatigue estimation device.
- the process of estimating the fatigue level of the user based on the activity level executed in the fatigue level estimation means is realized in the server, so that the configuration of the fatigue estimation device itself can be made compact.
- the fatigue level estimated in the server can be sent to a person other than the user, even if the user himself / herself cannot cope with his / her fatigue, Can deal with fatigue.
- the fatigue warning device of the present invention determines the degree of fatigue level estimated by the fatigue estimation device having the above-described configuration and the fatigue level estimation means, and determines whether or not to issue a warning about user fatigue.
- the fatigue warning determination unit determines whether or not to issue a warning about the user's fatigue by the fatigue warning determination unit, and a fatigue warning is presented from the fatigue presentation unit based on the determination result.
- the user and others can easily know the user's fatigue level by judging the fatigue warning presented by the fatigue presentation means. This avoids troubles caused by fatigue.
- the fatigue presenting means is characterized by presenting the warning at every predetermined timing.
- the fatigue presentation unit may present the warning to a person other than the subject whose fatigue level is estimated by the fatigue level estimation unit.
- an electronic device of the present invention is characterized by including the fatigue estimation device having the above-described configuration or the fatigue warning device having the above-described configuration.
- the fatigue level can be estimated without a sense of incongruity in daily life.
- the electronic device preferably includes transmission means for transmitting estimated fatigue level information indicating the fatigue level estimated by the fatigue level estimation means to the outside.
- the user's fatigue level can be known at the transmission destination of the estimated fatigue level information. Therefore, even if one user cannot cope with his / her fatigue, the person who has confirmed the information at the destination of the estimated fatigue level information can cope with the fatigue.
- the electronic device is preferably a mobile phone. Since a mobile phone is generally carried by a user without leaving his / her body, the activity level can be accurately detected if the activity level detection means is provided in the mobile phone.
- the fatigue estimation method of the present invention solves the above-described problem, and activity level detection in which the frequency of user activity is continuously detected as activity level by activity level detection means provided in the fatigue estimation device. And a fatigue level output step for outputting the activity level detected in the activity level detection step to a fatigue level estimation means for estimating a user's fatigue level. . [0203] According to the fatigue estimation method, it is possible to obtain the same operational effects as the fatigue estimation device of the present invention.
- the fatigue estimation program of the present invention is a fatigue estimation program for executing the fatigue estimation method of the present invention to solve the above-described problem, and causes a computer to execute each of the above steps.
- the fatigue level can be estimated using any computer.
- the fatigue estimation program can be executed on any computer.
- the fatigue estimation device of the present invention continuously detects a user's activity status and based on the detected activity status! / It may be configured to detect fatigue.
- the fatigue estimation device configured as described above, it is preferable to detect fatigue based on a relatively low activity state during a continuous activity state. It is also preferable to obtain a relatively low activity status by removing long-term fluctuation components from a continuous activity status.
- a relatively low activity status may be obtained by statistically analyzing the detected activity status. As a method of removing long-term fluctuation components in this way, it is only necessary to obtain a minute or difference value of the activity status.
- the calculated fatigue level is processed within a predetermined range.
- the activity status is preferably acquired by acceleration of all or part of the body.
- the activity status may be acquired from position information of all or part of the body, or may be acquired from image information of all or part of the body.
- the activity status is preferably acquired based on the change in acceleration.
- the acceleration may be acquired based on a change in the position information.
- the change in acceleration may be obtained by counting the number of times the acceleration crosses a predetermined value.
- the acceleration is preferably a one-dimensional acceleration.
- the electronic apparatus of the present invention may have a configuration in which the fatigue estimation device having the above configuration is mounted.
- This electronic device is more preferable if it is a mobile phone that preferably has a communication function.
- a fatigue estimation program can be added later.
- the state estimation device of the present invention is preferably configured as a wristwatch having a function of acquiring a wrist activity state.
- the fatigue level can be estimated easily at low cost. Therefore, according to the present invention, it is possible to detect various symptoms caused by fatigue in recent years! Or prevent accidents associated with fatigue.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/302,768 US8926531B2 (en) | 2006-05-29 | 2007-05-22 | Fatigue estimation device and electronic apparatus having the fatigue estimation device mounted thereon |
JP2008517864A JP4819887B2 (ja) | 2006-05-29 | 2007-05-22 | 疲労推定装置及びそれを搭載した電子機器 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2006148987 | 2006-05-29 | ||
JP2006-148987 | 2006-05-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2007138930A1 true WO2007138930A1 (ja) | 2007-12-06 |
Family
ID=38778449
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2007/060443 WO2007138930A1 (ja) | 2006-05-29 | 2007-05-22 | 疲労推定装置及びそれを搭載した電子機器 |
Country Status (3)
Country | Link |
---|---|
US (1) | US8926531B2 (ja) |
JP (2) | JP4819887B2 (ja) |
WO (1) | WO2007138930A1 (ja) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090221937A1 (en) * | 2008-02-25 | 2009-09-03 | Shriners Hospitals For Children | Activity Monitoring |
JP2011183005A (ja) * | 2010-03-10 | 2011-09-22 | Nec Corp | 携帯端末 |
JP2012024449A (ja) * | 2010-07-27 | 2012-02-09 | Omron Healthcare Co Ltd | 歩行変化判定装置 |
JP2014121410A (ja) * | 2012-12-20 | 2014-07-03 | National Institute Of Advanced Industrial & Technology | 疲労判定装置、疲労判定方法、及びそのプログラム |
JP2015150150A (ja) * | 2014-02-13 | 2015-08-24 | 富士ゼロックス株式会社 | 情報提供装置及びプログラム |
CN106781281A (zh) * | 2016-12-28 | 2017-05-31 | 珠海市魅族科技有限公司 | 一种车辆的提示信息生成方法及车载终端 |
JP2017108977A (ja) * | 2015-12-17 | 2017-06-22 | 株式会社イトーキ | 業務支援システム |
EP2486516A4 (en) * | 2009-10-07 | 2018-03-28 | iOnRoad Technologies Ltd. | Automatic content analysis method and system |
US10147004B2 (en) | 2011-05-03 | 2018-12-04 | Ionroad Technologies Ltd. | Automatic image content analysis method and system |
JP2019524287A (ja) * | 2016-08-08 | 2019-09-05 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | 被験者の運動を支援するシステムおよび方法 |
US11197633B2 (en) | 2013-10-09 | 2021-12-14 | Resmed Sensor Technologies Limited | Fatigue monitoring and management system |
Families Citing this family (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9084550B1 (en) | 2007-10-18 | 2015-07-21 | Innovative Surgical Solutions, Llc | Minimally invasive nerve monitoring device and method |
US8343065B2 (en) * | 2007-10-18 | 2013-01-01 | Innovative Surgical Solutions, Llc | Neural event detection |
US8343079B2 (en) | 2007-10-18 | 2013-01-01 | Innovative Surgical Solutions, Llc | Neural monitoring sensor |
US8942797B2 (en) * | 2007-10-18 | 2015-01-27 | Innovative Surgical Solutions, Llc | Neural monitoring system |
US10572721B2 (en) | 2010-08-09 | 2020-02-25 | Nike, Inc. | Monitoring fitness using a mobile device |
US8810413B2 (en) * | 2010-10-15 | 2014-08-19 | Hewlett Packard Development Company, L.P. | User fatigue |
US9977874B2 (en) | 2011-11-07 | 2018-05-22 | Nike, Inc. | User interface for remote joint workout session |
US9283429B2 (en) | 2010-11-05 | 2016-03-15 | Nike, Inc. | Method and system for automated personal training |
US9457256B2 (en) | 2010-11-05 | 2016-10-04 | Nike, Inc. | Method and system for automated personal training that includes training programs |
CA2816589A1 (en) | 2010-11-05 | 2012-05-10 | Nike International Ltd. | Method and system for automated personal training |
US9223936B2 (en) | 2010-11-24 | 2015-12-29 | Nike, Inc. | Fatigue indices and uses thereof |
US9852271B2 (en) | 2010-12-13 | 2017-12-26 | Nike, Inc. | Processing data of a user performing an athletic activity to estimate energy expenditure |
US10420982B2 (en) | 2010-12-13 | 2019-09-24 | Nike, Inc. | Fitness training system with energy expenditure calculation that uses a form factor |
US9380978B2 (en) * | 2011-06-29 | 2016-07-05 | Bruce Reiner | Method and apparatus for real-time measurement and analysis of occupational stress and fatigue and performance outcome predictions |
US9811639B2 (en) | 2011-11-07 | 2017-11-07 | Nike, Inc. | User interface and fitness meters for remote joint workout session |
US9301711B2 (en) | 2011-11-10 | 2016-04-05 | Innovative Surgical Solutions, Llc | System and method for assessing neural health |
US8983593B2 (en) | 2011-11-10 | 2015-03-17 | Innovative Surgical Solutions, Llc | Method of assessing neural function |
DE102012000629A1 (de) | 2012-01-14 | 2013-07-18 | Volkswagen Aktiengesellschaft | Verfahren, Vorrichtung und Mobilgerät zur Müdigkeitserkennung eines Fahrers eines Fahrzeugs |
US8855822B2 (en) | 2012-03-23 | 2014-10-07 | Innovative Surgical Solutions, Llc | Robotic surgical system with mechanomyography feedback |
WO2013184679A1 (en) | 2012-06-04 | 2013-12-12 | Nike International Ltd. | Combinatory score having a fitness sub-score and an athleticism sub-score |
US9039630B2 (en) | 2012-08-22 | 2015-05-26 | Innovative Surgical Solutions, Llc | Method of detecting a sacral nerve |
US8892259B2 (en) | 2012-09-26 | 2014-11-18 | Innovative Surgical Solutions, LLC. | Robotic surgical system with mechanomyography feedback |
FI124068B (en) * | 2013-05-03 | 2014-02-28 | Jyvaeskylaen Yliopisto | Procedure for improving driving safety |
JP6131706B2 (ja) * | 2013-05-10 | 2017-05-24 | オムロンヘルスケア株式会社 | 歩行姿勢計およびプログラム |
US10478097B2 (en) | 2013-08-13 | 2019-11-19 | Innovative Surgical Solutions | Neural event detection |
US10478096B2 (en) | 2013-08-13 | 2019-11-19 | Innovative Surgical Solutions. | Neural event detection |
US9622684B2 (en) | 2013-09-20 | 2017-04-18 | Innovative Surgical Solutions, Llc | Neural locating system |
US20150119732A1 (en) * | 2013-10-24 | 2015-04-30 | JayBird LLC | System and method for providing an interpreted recovery score |
US20160058378A1 (en) * | 2013-10-24 | 2016-03-03 | JayBird LLC | System and method for providing an interpreted recovery score |
US9848828B2 (en) * | 2013-10-24 | 2017-12-26 | Logitech Europe, S.A. | System and method for identifying fatigue sources |
WO2016040281A1 (en) | 2014-09-09 | 2016-03-17 | Torvec, Inc. | Methods and apparatus for monitoring alertness of an individual utilizing a wearable device and providing notification |
US10535024B1 (en) | 2014-10-29 | 2020-01-14 | Square, Inc. | Determining employee shift changes |
KR102072788B1 (ko) | 2015-04-30 | 2020-03-12 | 삼성전자주식회사 | 휴대 장치 및 휴대 장치의 콘텐트 화면 변경방법 |
DE102015217365A1 (de) * | 2015-09-11 | 2017-03-16 | Continental Automotive Gmbh | Verfahren zum Ermitteln eines Gesamt-Aufmerksamkeitsgrads eines Fahrzeugführers, zugehörige Vorrichtung und Datenübergabeeinrichtung |
JP2019510550A (ja) | 2016-02-18 | 2019-04-18 | カーイージス テクノロジーズ,インコーポレイティド | 注意力予測システム及び方法 |
US10321833B2 (en) | 2016-10-05 | 2019-06-18 | Innovative Surgical Solutions. | Neural locating method |
KR102395293B1 (ko) | 2017-07-04 | 2022-05-09 | 현대자동차주식회사 | 무선통신시스템, 차량, 스마트 장치 및 무선통신시스템의 제어방법 |
KR102532412B1 (ko) * | 2018-02-13 | 2023-05-16 | 삼성전자주식회사 | 생체 정보에 기반한 건강 정보를 제공하기 위한 전자 장치 및 그 제어 방법 |
DE102018208060B3 (de) | 2018-05-23 | 2019-07-04 | Robert Bosch Gmbh | Verfahren und Vorrichtung zum Erkennen einer Müdigkeit eines Fahrers eines Fahrzeugs in einem Mobilgerät |
US10869616B2 (en) | 2018-06-01 | 2020-12-22 | DePuy Synthes Products, Inc. | Neural event detection |
US11903712B2 (en) * | 2018-06-08 | 2024-02-20 | International Business Machines Corporation | Physiological stress of a user of a virtual reality environment |
CN110680332B (zh) * | 2018-07-05 | 2024-08-02 | 博世汽车部件(苏州)有限公司 | 用于确定手指疲劳状态的装置和方法 |
US10870002B2 (en) | 2018-10-12 | 2020-12-22 | DePuy Synthes Products, Inc. | Neuromuscular sensing device with multi-sensor array |
US11399777B2 (en) | 2019-09-27 | 2022-08-02 | DePuy Synthes Products, Inc. | Intraoperative neural monitoring system and method |
TWI745812B (zh) * | 2019-12-25 | 2021-11-11 | 財團法人工業技術研究院 | 智慧即時運動疲勞偵測系統及方法、及智慧即時運動疲勞偵測裝置 |
EP4101376A4 (en) * | 2020-02-06 | 2023-06-21 | Takenaka Civil Engineering&Construction Co., Ltd. | POSTURE DETERMINING DEVICE AND POSTURE CONTROL DEVICE |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07295715A (ja) * | 1994-04-20 | 1995-11-10 | Mitsubishi Electric Corp | Vdt使用状況警告装置 |
WO2002094091A1 (fr) * | 2001-05-22 | 2002-11-28 | Kazuyoshi Sakamoto | Dispositif de controle de fatigue et procede d'evaluation de fatigue |
JP2005013385A (ja) * | 2003-06-25 | 2005-01-20 | Sony Corp | 生体情報適応制御装置、生体情報適応制御方法、プログラム、記録媒体 |
JP2005312868A (ja) * | 2004-04-30 | 2005-11-10 | Cci:Kk | 瞬きを用いた覚醒度計測法 |
JP2006271893A (ja) * | 2005-03-30 | 2006-10-12 | Toshiba Corp | 運動計測装置、運動計測方法および運動計測プログラム |
Family Cites Families (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4545385A (en) * | 1982-03-23 | 1985-10-08 | Siemens Aktiengesellschaft | Ultrasound examination device for scanning body parts |
US4943986A (en) * | 1988-10-27 | 1990-07-24 | Leonard Barbarisi | Mammography compression apparatus for prosthetically augmented breast |
EP0553246B1 (en) * | 1990-10-19 | 2000-09-13 | St. Louis University | Surgical probe locating system for head use |
US5409497A (en) * | 1991-03-11 | 1995-04-25 | Fischer Imaging Corporation | Orbital aiming device for mammo biopsy |
US5197489A (en) * | 1991-06-17 | 1993-03-30 | Precision Control Design, Inc. | Activity monitoring apparatus with configurable filters |
JPH07178073A (ja) | 1993-12-24 | 1995-07-18 | Shimadzu Corp | 体動解析装置 |
US5855554A (en) * | 1997-03-17 | 1999-01-05 | General Electric Company | Image guided breast lesion localization device |
US6176837B1 (en) * | 1998-04-17 | 2001-01-23 | Massachusetts Institute Of Technology | Motion tracking system |
US6675037B1 (en) * | 1999-09-29 | 2004-01-06 | Regents Of The University Of Minnesota | MRI-guided interventional mammary procedures |
US6254614B1 (en) * | 1999-10-18 | 2001-07-03 | Jerry M. Jesseph | Device and method for improved diagnosis and treatment of cancer |
US6449508B1 (en) * | 1999-10-21 | 2002-09-10 | Medtronic, Inc. | Accelerometer count calculation for activity signal for an implantable medical device |
US6513532B2 (en) * | 2000-01-19 | 2003-02-04 | Healthetech, Inc. | Diet and activity-monitoring device |
AU2001231117A1 (en) * | 2000-01-24 | 2001-07-31 | Ambulatory Monitoring, Inc. | System and method of monitoring and modifying human activity-based behavior |
FR2804596B1 (fr) * | 2000-02-04 | 2002-10-04 | Agronomique Inst Nat Rech | Procede d'analyse d'irregularites de locomotion humaine |
EP1195139A1 (en) * | 2000-10-05 | 2002-04-10 | Ecole Polytechnique Féderale de Lausanne (EPFL) | Body movement monitoring system and method |
SE0004298D0 (sv) * | 2000-11-23 | 2000-11-23 | Siemens Elema Ab | Röntgendiagnostikapparat |
US7171256B1 (en) * | 2001-11-21 | 2007-01-30 | Aurora Imaging Technology, Inc. | Breast magnetic resonace imaging system with curved breast paddles |
FI115605B (fi) * | 2001-12-21 | 2005-06-15 | Newtest Oy | Anturiyksikkö, laitejärjestely ja laitejärjestelyä hyödyntävä menetelmä kehoon kohdistuvien voimien mittaamiseksi ja arvioimiseksi |
JP3930399B2 (ja) * | 2002-08-21 | 2007-06-13 | 本田技研工業株式会社 | 歩行補助装置 |
US6883194B2 (en) * | 2002-11-08 | 2005-04-26 | Art Advanced Research And Technology Inc. | Method and apparatus for positioning a patient on a table for a medical procedure on a breast |
US7771360B2 (en) * | 2003-04-09 | 2010-08-10 | Techniscan, Inc. | Breast scanning system |
US7387611B2 (en) * | 2003-04-10 | 2008-06-17 | Matsushita Electric Industrial Co., Ltd. | Physical movement analyzer and physical movement analyzing method |
US20040210159A1 (en) * | 2003-04-15 | 2004-10-21 | Osman Kibar | Determining a psychological state of a subject |
US7828744B2 (en) * | 2003-04-23 | 2010-11-09 | Boston Scientific Scimed, Inc. | Method and assembly for breast immobilization |
US7330566B2 (en) * | 2003-05-15 | 2008-02-12 | Microsoft Corporation | Video-based gait recognition |
EP1651106A4 (en) * | 2003-07-09 | 2009-05-27 | Medical Technologies Unltd Inc | COMPLETE NEUROMUSCULAR PROFILER |
AU2003904336A0 (en) * | 2003-08-15 | 2003-08-28 | Medcare Systems Pty Ltd | An automated personal alarm monitor |
JP2005095307A (ja) * | 2003-09-24 | 2005-04-14 | Matsushita Electric Ind Co Ltd | 生体センサおよびこれを用いた支援システム |
JP2005095408A (ja) * | 2003-09-25 | 2005-04-14 | Matsushita Electric Ind Co Ltd | 生体状態判断装置及び支援システム |
US20060155175A1 (en) * | 2003-09-02 | 2006-07-13 | Matsushita Electric Industrial Co., Ltd. | Biological sensor and support system using the same |
US7379769B2 (en) * | 2003-09-30 | 2008-05-27 | Sunnybrook Health Sciences Center | Hybrid imaging method to monitor medical device delivery and patient support for use in the method |
US7771371B2 (en) * | 2004-08-11 | 2010-08-10 | Andante Medical Devices Ltd | Sports shoe with sensing and control |
US7297110B2 (en) * | 2004-08-27 | 2007-11-20 | Goyal Muna C | Systems and methods for remote monitoring of fear and distress responses |
US20060089538A1 (en) * | 2004-10-22 | 2006-04-27 | General Electric Company | Device, system and method for detection activity of persons |
JP2008011865A (ja) | 2004-10-27 | 2008-01-24 | Sharp Corp | 健康管理装置及びこれを機能させるためのプログラム |
KR100601981B1 (ko) * | 2005-01-14 | 2006-07-18 | 삼성전자주식회사 | 활동패턴 감시 방법 및 장치 |
US20060167387A1 (en) * | 2005-01-27 | 2006-07-27 | Horst Buchholz | Physical activity monitor |
US7427924B2 (en) * | 2005-02-11 | 2008-09-23 | Triodyne Inc. | System and method for monitoring driver fatigue |
US20060282021A1 (en) * | 2005-05-03 | 2006-12-14 | Devaul Richard W | Method and system for fall detection and motion analysis |
EP1893086B1 (en) * | 2005-05-24 | 2013-04-17 | St. Jude Medical AB | A method and a medical device for evaluating the prevalence of different postures of a patient and a computer readable medium for bringing a computer to performing the method |
WO2007117402A2 (en) * | 2006-04-01 | 2007-10-18 | U.S. Government As Represented By The Secretary Of The Army | Human biovibrations method |
US7558622B2 (en) * | 2006-05-24 | 2009-07-07 | Bao Tran | Mesh network stroke monitoring appliance |
US9763597B2 (en) * | 2007-05-03 | 2017-09-19 | Wisconsin Alumni Research Foundation | Local MRI breast coil and method of use |
US8152745B2 (en) * | 2008-02-25 | 2012-04-10 | Shriners Hospitals For Children | Activity monitoring |
-
2007
- 2007-05-22 WO PCT/JP2007/060443 patent/WO2007138930A1/ja active Search and Examination
- 2007-05-22 JP JP2008517864A patent/JP4819887B2/ja not_active Expired - Fee Related
- 2007-05-22 US US12/302,768 patent/US8926531B2/en active Active
-
2011
- 2011-07-19 JP JP2011158353A patent/JP5433905B2/ja not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07295715A (ja) * | 1994-04-20 | 1995-11-10 | Mitsubishi Electric Corp | Vdt使用状況警告装置 |
WO2002094091A1 (fr) * | 2001-05-22 | 2002-11-28 | Kazuyoshi Sakamoto | Dispositif de controle de fatigue et procede d'evaluation de fatigue |
JP2005013385A (ja) * | 2003-06-25 | 2005-01-20 | Sony Corp | 生体情報適応制御装置、生体情報適応制御方法、プログラム、記録媒体 |
JP2005312868A (ja) * | 2004-04-30 | 2005-11-10 | Cci:Kk | 瞬きを用いた覚醒度計測法 |
JP2006271893A (ja) * | 2005-03-30 | 2006-10-12 | Toshiba Corp | 運動計測装置、運動計測方法および運動計測プログラム |
Non-Patent Citations (1)
Title |
---|
OHASHI K. ET AL.: "Shintai Katsudo Choki Jikeiretsu no Kaiseki to Seishin Shogai Shinshinsho", DAI 18 KAI ANNUAL SYMPOSIUM ON BIOLOGICAL AND PHYSIOLOGICAL ENGINEERING, 6 October 2003 (2003-10-06), pages 265 - 268, XP003019811 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8152745B2 (en) * | 2008-02-25 | 2012-04-10 | Shriners Hospitals For Children | Activity monitoring |
US20090221937A1 (en) * | 2008-02-25 | 2009-09-03 | Shriners Hospitals For Children | Activity Monitoring |
US9970774B2 (en) | 2009-10-07 | 2018-05-15 | Ionroad Technologies Ltd. | Automatic content analysis method and system |
EP2486516A4 (en) * | 2009-10-07 | 2018-03-28 | iOnRoad Technologies Ltd. | Automatic content analysis method and system |
JP2011183005A (ja) * | 2010-03-10 | 2011-09-22 | Nec Corp | 携帯端末 |
JP2012024449A (ja) * | 2010-07-27 | 2012-02-09 | Omron Healthcare Co Ltd | 歩行変化判定装置 |
US10147004B2 (en) | 2011-05-03 | 2018-12-04 | Ionroad Technologies Ltd. | Automatic image content analysis method and system |
JP2014121410A (ja) * | 2012-12-20 | 2014-07-03 | National Institute Of Advanced Industrial & Technology | 疲労判定装置、疲労判定方法、及びそのプログラム |
US11197633B2 (en) | 2013-10-09 | 2021-12-14 | Resmed Sensor Technologies Limited | Fatigue monitoring and management system |
US12070325B2 (en) | 2013-10-09 | 2024-08-27 | Resmed Sensor Technologies Limited | Fatigue monitoring and management system |
JP2015150150A (ja) * | 2014-02-13 | 2015-08-24 | 富士ゼロックス株式会社 | 情報提供装置及びプログラム |
JP2017108977A (ja) * | 2015-12-17 | 2017-06-22 | 株式会社イトーキ | 業務支援システム |
JP2019524287A (ja) * | 2016-08-08 | 2019-09-05 | コーニンクレッカ フィリップス エヌ ヴェKoninklijke Philips N.V. | 被験者の運動を支援するシステムおよび方法 |
CN106781281A (zh) * | 2016-12-28 | 2017-05-31 | 珠海市魅族科技有限公司 | 一种车辆的提示信息生成方法及车载终端 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2007138930A1 (ja) | 2009-10-01 |
US8926531B2 (en) | 2015-01-06 |
JP4819887B2 (ja) | 2011-11-24 |
US20100137748A1 (en) | 2010-06-03 |
JP2011251137A (ja) | 2011-12-15 |
JP5433905B2 (ja) | 2014-03-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5433905B2 (ja) | 疲労推定装置及びそれを搭載した電子機器 | |
US11564623B2 (en) | Food intake monitor | |
US20200170548A1 (en) | Automated near-fall detector | |
CN107256329B (zh) | 用于检测用户的移动数据的整体式装置和非瞬时计算机可读介质 | |
CN102687152B (zh) | Copd恶化预测系统 | |
JP4617154B2 (ja) | 携帯電話、生活活動解析方法、プログラム、および記録媒体 | |
JP4633374B2 (ja) | 生体センサ装置 | |
JP2008011865A (ja) | 健康管理装置及びこれを機能させるためのプログラム | |
JP2008067892A (ja) | 生体解析装置及びプログラム | |
JP2019004924A (ja) | システム及び方法 | |
US11478189B2 (en) | Systems and methods for respiratory analysis | |
US20120101399A1 (en) | Respiratory Monitoring System | |
US20170325718A1 (en) | Neuropathic Diagnosis and Monitoring Using Earpiece Device, System, and Method | |
US20190069829A1 (en) | Method and apparatus for monitoring urination of a subject | |
WO2004026138A1 (ja) | 身体運動評価装置、及び身体運動評価システム | |
CN114080180A (zh) | 检测和测量打鼾 | |
Ahanathapillai et al. | Assistive technology to monitor activity, health and wellbeing in old age: The wrist wearable unit in the USEFIL project | |
TWI582728B (zh) | 疲勞警示系統 | |
JP4494843B2 (ja) | ペット管理システム | |
US20200210689A1 (en) | A system and a method for analyzing a behavior or an activity of an object | |
JP2000245718A (ja) | 精神状態評価装置 | |
EP3967225B1 (en) | Respiratory cessation detection system and storage medium | |
JP2015112152A (ja) | 体動検知通知装置及びシステム | |
KR102015444B1 (ko) | 배변징후 알림 웨어러블 장치 | |
WO2019193160A1 (en) | Method and apparatus for monitoring a subject |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 07743877 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2008517864 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 12302768 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 07743877 Country of ref document: EP Kind code of ref document: A1 |
|
DPE1 | Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101) |