CN114756114A - Energy-saving method and equipment for wearable equipment - Google Patents

Energy-saving method and equipment for wearable equipment Download PDF

Info

Publication number
CN114756114A
CN114756114A CN202210362067.4A CN202210362067A CN114756114A CN 114756114 A CN114756114 A CN 114756114A CN 202210362067 A CN202210362067 A CN 202210362067A CN 114756114 A CN114756114 A CN 114756114A
Authority
CN
China
Prior art keywords
data
physiological data
user
state
frequency
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210362067.4A
Other languages
Chinese (zh)
Other versions
CN114756114B (en
Inventor
郭少勇
陈钰
熊翱
杨少杰
才智
姚辉
彭凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xingyaoneng Beijing Technology Co ltd
Beijing University of Posts and Telecommunications
Original Assignee
Xingyaoneng Beijing Technology Co ltd
Beijing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xingyaoneng Beijing Technology Co ltd, Beijing University of Posts and Telecommunications filed Critical Xingyaoneng Beijing Technology Co ltd
Priority to CN202210362067.4A priority Critical patent/CN114756114B/en
Publication of CN114756114A publication Critical patent/CN114756114A/en
Application granted granted Critical
Publication of CN114756114B publication Critical patent/CN114756114B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3206—Monitoring of events, devices or parameters that trigger a change in power modality
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • 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
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/325—Power saving in peripheral device
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • 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
    • A61B5/103—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
    • A61B5/1123—Discriminating type of movement, e.g. walking or running
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Artificial Intelligence (AREA)
  • Remote Sensing (AREA)
  • Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Physiology (AREA)
  • Mathematical Physics (AREA)
  • Cardiology (AREA)
  • Veterinary Medicine (AREA)
  • Public Health (AREA)
  • Mathematical Optimization (AREA)
  • Animal Behavior & Ethology (AREA)
  • Mathematical Analysis (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Computational Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Probability & Statistics with Applications (AREA)
  • Operations Research (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)

Abstract

The invention provides a wearable device energy-saving method and wearable device, wherein a Gaussian distribution probability density function is obtained, a set probability threshold value used for judging whether physiological data are normal or abnormal is obtained, first physiological data of a user at the current moment are collected, a probability value corresponding to the first physiological data is calculated according to the Gaussian distribution probability density function, the probability value is compared with the set probability threshold value, whether the physiological data of the user are in a normal state or an abnormal state is judged, a heart rate sensor is instructed to perform low-frequency sampling in the normal state, and high-frequency sampling is performed in the abnormal state; and inputting the first physiological data into a preset classification algorithm, acquiring the activity state of the user at the current moment, and instructing the GPS positioning module to sample at different frequencies in a static state, a conventional state with low displacement and a motion state with high displacement. The monitoring device has the advantages that the monitoring device can monitor the health function and performance of a human body, reduce the power consumption of the device, prolong the endurance time and reduce the charging times.

Description

Energy-saving method and equipment for wearable equipment
Technical Field
The invention relates to the field of wearable equipment, in particular to an energy-saving method and equipment for the wearable equipment.
Background
With the rapid development of 5G and the Internet of things, the objects connected by 5G are expanded from people to everything, and more Internet of things terminals enter the production and life of people. The wearable equipment with small volume and strong function brings great convenience to the life of people, and is therefore popular. The high-precision induction sensor is arranged in the exercise health monitoring device, vital sign signals such as heart rate, blood oxygen and electrocardio of a human body are collected, the exercise health monitoring device is applied to the aspects of exercise health monitoring, daily health monitoring, sleep monitoring and the like of the human body, the exercise health monitoring device mainly has the functions of step counting, heart rate detection, sleep quality monitoring, sedentary reminding and the like, and the functions greatly enrich the lives of people. With the continuous improvement of the performance of wearable devices, the problem of power consumption of the devices is also more severe. Wearable devices need to collect data, process data and transmit data when operating, and the operation of these functions needs to consume a large amount of electric energy. And wearable equipment adopts battery powered usually, because the volume restriction of equipment, the battery capacity of placing is limited to a series of problems such as have resulted in that equipment energy is limited, duration is short, force the user to frequently charge, and then produce not good use and experience, also can't realize long-time health monitoring simultaneously.
Therefore, the wearable device is ensured to realize basic functions, the use requirements of users are met, meanwhile, how to effectively manage and control the power consumption of the device and improve the endurance capacity are achieved, and the problem to be solved urgently is formed.
Disclosure of Invention
In view of this, the present embodiment provides an energy saving method and device for a wearable device, so as to solve one or more defects in the prior art, and overcome a series of problems of large power consumption, short endurance time, poor use experience caused by forcing a user to frequently charge, and the like.
The technical scheme of the invention is as follows:
in one aspect, the present invention provides a wearable device energy saving method, which runs on a processor of a wearable device, and includes:
acquiring a Gaussian distribution probability density function of physiological data of healthy users, and a set probability threshold value for judging the normality and the abnormality of the physiological data, wherein the physiological data of the healthy users at least comprises acceleration data and heart rate data, and the Gaussian distribution probability density function is calculated based on the physiological data of a plurality of healthy users in different activity states;
acquiring first physiological data of a user at the current moment, and calculating a probability value corresponding to the first physiological data according to the Gaussian distribution probability density function, wherein the first physiological data at least comprises first acceleration data and first heart rate data;
comparing the probability value with the set probability threshold: if the probability value is larger than the set probability threshold value, judging that the first physiological data at the current moment is normal, and instructing a heart rate sensor to perform work sampling at a first frequency; if the probability value is smaller than the set probability threshold value, judging that the first physiological data at the current moment are abnormal, and instructing the heart rate sensor to perform working sampling at a second frequency for at least a first set duration; wherein the first frequency is less than the second frequency;
inputting the first physiological data into a preset classification algorithm to obtain an activity state of the user at the current moment, wherein the activity state at least comprises: a rest state without displacement, a normal state with low displacement and a motion state with high displacement;
if the user is in a static state at the current moment, instructing the GPS positioning module to sleep and not work; if the current time of the user is in a conventional state, the GPS positioning module is instructed to acquire positioning data at a third frequency; if the user is in a motion state at the current moment, instructing the GPS positioning module to acquire positioning data at a fourth frequency, wherein the third frequency is smaller than the fourth frequency; after the three states are judged, the GPS positioning module works for at least a second set time.
Preferably, the gaussian probability distribution density function of the physiological data of the healthy user is obtained by the following steps:
acquiring physiological data containing acceleration data and heart rate data of a plurality of age-group healthy users in different activity states as first sample data;
and performing distribution analysis on the first sample data by utilizing binary Gaussian distribution, and fitting to obtain the distribution probability of the acceleration and the heart rate so as to obtain a Gaussian distribution probability density function of the physiological data of the healthy user.
Preferably, before the step of inputting the first physiological data into a preset classification algorithm to obtain the activity state of the user at the current moment, the method further includes:
acquiring physiological data of a plurality of age-group healthy users in different activity states, wherein the physiological data comprises acceleration data and heart rate data, and marking the activity state category to which each data sample belongs to obtain second sample data;
training by using the second sample data to obtain a decision tree as the preset classification algorithm; the decision tree is one of ID3, C4.5, or CART.
Preferably, the preset classification algorithm is obtained based on support vector machine, generative confrontation network or convolutional neural network training.
Preferably, before acquiring a gaussian distribution probability density function of physiological data of a healthy user and a set probability threshold for determining normality and abnormality of the physiological data, the method further includes:
acquiring a cross validation set, wherein the cross validation set comprises normal physiological data obtained based on healthy users and abnormal physiological data obtained based on unhealthy users;
and calculating the probability of the normal physiological data and the abnormal physiological data by using the Gaussian distribution probability density function, and determining a set probability threshold value for judging the normality and the abnormality of the physiological data.
Preferably, the method further comprises:
during the period that the heart rate sensor works and samples at a first frequency, if the first physiological data is judged to be abnormal at the current moment, the heart rate sensor is immediately instructed to be converted from the first frequency to a second frequency to work and sample, and the work and the sampling lasts for at least the first set time.
Preferably, the active state comprises at least: lying still, sitting still, standing still, sitting for working, walking, going upstairs and downstairs, jumping and running.
The static state includes at least: the normal state at least comprises the following steps: sit to work, walk, go upstairs and downstairs, the motion state includes at least: jumping and running;
in another aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described above.
In another aspect, the present invention further provides a wearable device, which is characterized by at least comprising:
the acceleration sensor is used for acquiring acceleration data of a user;
the heart rate sensor is used for collecting heart rate data of a user;
the GPS positioning module is used for recording user displacement change data;
a processor for executing the wearable device energy saving method.
The invention has the beneficial effects that:
the energy-saving method and the energy-saving equipment for the wearable equipment acquire a Gaussian distribution probability density function and a set probability threshold value for judging whether physiological data are normal or abnormal, acquire first physiological data of a user at the current moment, calculate a probability value corresponding to the first physiological data according to the Gaussian distribution probability density function, compare the probability value with the set probability threshold value, judge whether the physiological data of the user are in a normal state or an abnormal state, instruct a heart rate sensor to perform low-frequency sampling in the normal state and perform high-frequency sampling in the abnormal state; and inputting the first physiological data into a preset classification algorithm, acquiring the activity state of the user at the current moment, and instructing the GPS positioning module to sample at different frequencies in a static state, a conventional state with low displacement and a motion state with high displacement. According to the method, the use requirements and the daily activity rule of the user are researched, the low-power-consumption running design is carried out on the sampling frequency and the working mode of the high-power-consumption sensor in the wearable device by combining the daily activity rule of the user, the health monitoring effect is guaranteed, self-adaption energy saving is achieved, the power consumption of the whole device is reduced by reducing the power consumption of the sensor, and the health condition of the user can be really monitored for a long time.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
It will be appreciated by those skilled in the art that the objects and advantages that can be achieved with the present invention are not limited to the specific details set forth above, and that these and other objects that can be achieved with the present invention will be more clearly understood from the detailed description that follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a schematic flow chart of an energy saving method for a wearable device according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of a gaussian probability distribution density function for acquiring physiological data of a healthy user according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating the effect of an anomaly detection algorithm according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the following embodiments and the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures and/or processing steps closely related to the scheme according to the present invention are shown in the drawings, and other details not so relevant to the present invention are omitted.
It should be emphasized that the term "comprises/comprising" when used herein, is taken to specify the presence of stated features, elements, steps or components, but does not preclude the presence or addition of one or more other features, elements, steps or components.
It is also noted herein that the term "coupled," if not specifically stated, may refer herein to not only a direct connection, but also an indirect connection in which an intermediate is present.
In order to overcome a series of problems that wearable equipment is large in power consumption and short in endurance time, users are forced to charge frequently, poor using experience is caused, and the like, the invention provides the energy-saving method and the energy-saving equipment for the wearable equipment.
The invention provides a wearable device energy-saving method, which runs on a processor of a wearable device and comprises the following steps S101-S105 as shown in figure 1:
it should be emphasized that, in the present embodiment, the steps S101 to S105 are not limited to a sequence order of the steps, but it should be understood that the steps may be executed according to the sequence mentioned in the embodiment, may also be executed in a sequence different from the sequence in the embodiment, or several steps may be executed at the same time:
step S101: the method comprises the steps of obtaining a Gaussian distribution probability density function of physiological data of healthy users and a set probability threshold value for judging the normality and the abnormality of the physiological data, wherein the physiological data of the healthy users at least comprise acceleration data and heart rate data, and the Gaussian distribution probability density function is obtained by calculation based on the physiological data of the healthy users in different activity states.
Step S101 is a preparation step of the energy-saving method for the wearable device, when a human body performs different activities, the acceleration and the heart rate have corresponding numerical interval changes of upper and lower limits in corresponding activity states, the acceleration sensor and the heart rate sensor are used for collecting acceleration data and heart rate data of a plurality of healthy users in different activity states, and abnormal states of human body physiological data are identified through an abnormal detection algorithm. Specifically, a Gaussian distribution probability density function of acceleration data and heart rate data is constructed based on physiological data of a healthy user, and a set probability threshold value capable of distinguishing normality and abnormality of the physiological data is obtained through test by substituting a cross validation set containing abnormal data and normal data and is used for distinguishing whether the physiological data of the user is in an abnormal or normal state. For normal physiological data, the distribution is concentrated, so that the distribution probability is high, and for abnormal physiological data, the distribution is loose, so that the distribution probability is low, and therefore effective classification can be carried out by setting a set probability threshold.
Step S102: the method comprises the steps of collecting first physiological data of a user at the current moment, and calculating a probability value corresponding to the first physiological data according to a Gaussian distribution probability density function, wherein the first physiological data at least comprises first acceleration data and first heart rate data.
The collected first physiological data of the user at the current moment is represented by a two-dimensional vector formed by the acceleration data and the heart rate data at the current moment, and is used for depicting the motion state and the intensity of the user at the current moment. By substituting the gaussian distribution probability density function, the distribution probability of the first physiological data of the user at the current moment can be calculated, namely, the higher the corresponding probability value is, the more concentrated the normal data belongs to, and the lower the corresponding probability value is, the more loose the abnormal data belongs to, relative to the distribution probability in the normal or abnormal states.
Step S103: comparing the probability value with a set probability threshold: if the probability value is larger than the set probability threshold value, judging that the first physiological data at the current moment is normal, and instructing the heart rate sensor to perform work sampling at a first frequency; if the probability value is smaller than the set probability threshold value, judging that the first physiological data at the current moment are abnormal, and instructing the heart rate sensor to perform work sampling at a second frequency for at least a first set duration; wherein the first frequency is less than the second frequency.
The first frequency, the second frequency and the first set duration are set in a comprehensive consideration mode according to the self performance of the wearable device and the user requirements. For example, wearable equipment specially used for a health monitoring function needs to consider the performance of a product and set a working value which can meet the requirement of realizing the function of the equipment; for example, when an unhealthy user uses the wearable device, the user needs to set a working value that meets the user's needs in consideration of the health condition of the user and the use requirements of the product.
The set probability threshold value for determining the normality and abnormality of the physiological data acquired in step S101 is obtained by dividing based on a cross validation set including abnormal data and normal data, and the normal data and the abnormal data are divided by selecting a probability value as the set probability threshold value under the condition that the normal data and the abnormal data can be effectively distinguished.
When judging that the current first physiological data of user is normal, the user physiological function is in low risk state, consequently can set up wearable equipment and carry out sampling less frequently to greatly reduce the energy consumption of equipment, improve duration. When the current first physiological data of the user is judged to be abnormal, the user physiological function is determined to be in a high risk state, or monitoring data acquisition errors may exist, and the wearable device can be set to perform sampling at a high frequency so as to ensure effective monitoring and identification of the physiological hidden danger of the user. By adopting the mode that the sampling is afraid of frequency dynamic adjustment, the high-frequency sampling under an unnecessary state can be reduced, and the energy consumption of equipment is reduced.
Furthermore, in order to ensure effective identification of the high-risk physiological state of the user, the embodiment limits that the low-frequency sampling can be switched to only after the high-frequency sampling is continued for a first set time period under the condition that the abnormality is detected, and the high-frequency sampling and identification state is maintained no matter whether the first physiological data is recovered to be normal or not during the period, so that the physiological state of the user is recovered to be normal really and effectively, and then the low-frequency sampling is switched to improve the monitoring reliability of the device.
In some embodiments, the wearable device energy saving method further comprises: during the period that the heart rate sensor works and samples at the first frequency, if the first physiological data at the current moment is judged to be abnormal, the heart rate sensor is immediately instructed to be switched from the first frequency to the second frequency to work and sample, and the work and the sampling lasts for at least a first set time length.
The heart rate sensor always works in a first frequency and a second frequency in a switching mode during the running period of the equipment, and the abnormal data is judged to be required to be immediately converted into the second frequency for working sampling during the first frequency working sampling period; however, when the heart rate sensor works and samples at the second frequency within the first set time length, the heart rate sensor still works and adopts at the second frequency when judging normal data, and after the heart rate sensor continues to work for the first set time length and judges normal data, the heart rate sensor can be converted into the first frequency to work and sample, wherein the first set time length can be changed according to specific requirements.
Step S104: inputting the first physiological data into a preset classification algorithm to obtain the activity state of the user at the current moment, wherein the activity state at least comprises: a rest state without displacement, a normal state with a low displacement amount, and a motion state with a high displacement amount.
The first physiological data, namely the acceleration data and the heart rate data at the current moment, can be used in steps S102-S103 to realize self-adjustment of the work sampling frequency of the heart rate sensor, and can also be used in steps S104-S105 to realize self-adjustment of the work mode of the GPS positioning module to avoid the power consumption problem caused by repeated sampling data. The acquisition frequency of the first physiological data is set according to the performance of the equipment and the use requirement of a user.
Specifically, the activity state of the user is identified by a preset classification algorithm, so that the sampling frequency of the GPS positioning module is reduced in the activity state without displacement or with less displacement, and the sampling frequency of the GPS positioning module is increased in the activity state with more displacement. The preset classification algorithm may be obtained by performing pre-training in a machine learning manner, for example, a set of training sample sets is obtained, the training sample sets at least include physiological data (i.e., acceleration data and heart rate data) of a plurality of users in different activity states, the physiological data of each user in each state is used as a sample, and the activity state corresponding to each sample is added as a label. And training the universal classification model by adopting a training sample set to obtain a model capable of classifying and identifying the activity state of the user.
In this embodiment, the predetermined classification algorithm is obtained based on a support vector machine, a generative confrontation network, or a convolutional neural network training. The support vector machine, the generative confrontation network and the convolutional neural network all belong to deep learning algorithms, are a branch of machine learning, are loosely modeled according to a human brain neural pathway, do not need to manually select related characteristics, can realize automatically learning useful characteristics, and obtain a preset classification algorithm for training of the invention.
After the corresponding active state is identified, the state is further divided into a static state, a normal state and a motion state.
Step S105: if the user is in a static state at the current moment, the GPS positioning module is instructed to sleep and not work; if the current time of the user is in a conventional state, the GPS positioning module is instructed to acquire positioning data at a third frequency; if the user is in a motion state at the current moment, instructing the GPS positioning module to acquire positioning data at a fourth frequency, wherein the third frequency is smaller than the fourth frequency; after the three states are judged, the GPS positioning module works for at least a second set time.
The user usually keeps a certain period of time when carrying out an activity, for example, the sitting office state lasts for 1-3 hours, the sleeping state lasts for 6-8 hours, the activity state of the user is divided into a static state, a normal state and a motion state, certain stability is guaranteed, and meanwhile, the activity state of the user in one day can be covered.
In this embodiment, the active state at least includes: lying still, sitting still, standing still, sitting for working, walking, going upstairs and downstairs, jumping and running. The eight activity states comprehensively cover the daily life of the user in one day, and the physiological values acquired in different activity states have representativeness and accuracy.
In this embodiment, the static state at least includes: the normal state at least comprises the following steps: sit official working, walk, go upstairs and downstairs, the motion state includes at least: jumping and running.
The third frequency, the fourth frequency and the second set duration are set in a comprehensive consideration mode according to the self performance of the wearable device and the user requirements. For example, when the user is a child, in order to avoid the occurrence of a safety problem, a working value meeting the user requirement is set, and a detailed movement track and a current specific position are generated through the GPS positioning module.
Similarly, in order to ensure effective identification of the user motion state, the embodiment limits that the user must continue to sample at high frequency for a first set time period before switching to low frequency sampling in the conventional manner, and during this period, the state of high frequency sampling and identification is maintained no matter whether the first physiological data is recovered to be normal or not, so as to ensure that the physiological state of the user is really and effectively recovered to be normal, and then switching to low frequency sampling is performed, thereby improving the reliability of device monitoring.
Considering that the GPS positioning module is used to record the displacement change data of the user, the present embodiment classifies the set eight activities into three major activity states, and as mentioned above, the displacement change in the three activity states has obvious characteristics. When the user is in a static state, displacement change can not occur, the GPS positioning module does not work in a dormant state, energy conservation of the GPS positioning module is greatly achieved, meanwhile, the activity state of the user is divided into the three types, and the GPS positioning module has certain stability.
In the present embodiment, as shown in fig. 2, the gaussian probability distribution density function of the physiological data of the healthy user is obtained by the following steps S201 to S202:
step S201: acquiring physiological data containing acceleration data and heart rate data of a plurality of age-group healthy users in different activity states as first sample data;
the method comprises the following steps that a plurality of age-group healthy users serve as training samples, acceleration data and heart rate data form a two-dimensional vector, and a two-dimensional data training set is formed.
Step S202: and performing distribution analysis on the first sample data by utilizing binary Gaussian distribution, and fitting to obtain the distribution probability of the acceleration and the heart rate so as to obtain a Gaussian distribution probability density function of the physiological data of the healthy user.
The first sample data is a two-dimensional data training set composed of acceleration data and heart rate data, and when distribution analysis is carried out, feature correlation on two dimensions needs to be considered, abnormal values which obviously deviate from a normal range are prevented from being regarded as normal values when a planning range is carried out, so that a Gaussian distribution probability density function of physiological data of a healthy user obtained by utilizing binary Gaussian distribution is a product of two independent Gaussian distribution densities of the acceleration data and psychological data, namely the Gaussian distribution probability density function based on mathematical expectation and variance on the two dimensions of the acceleration data and the heart rate data.
In this embodiment, before the inputting the first physiological data into the preset classification algorithm to obtain the activity state of the user at the current time, the method further includes: and acquiring physiological data of a plurality of age-group healthy users in different activity states, wherein the physiological data comprises acceleration data and heart rate data, marking the activity state category to which each data sample belongs, and acquiring second sample data. Training by adopting second sample data to obtain a decision tree as the preset classification algorithm; the decision tree is one of ID3, C4.5, or CART.
The second sample data are marked with motion state classification labels and are divided into a training set and a cross validation set, the division ratio is 8:2, state classification is carried out based on decision tree learning, and compared with a Bayesian algorithm, the decision tree does not need any domain knowledge or parameter setting in the construction process.
In this embodiment, before the step S101, that is, before acquiring the gaussian distribution probability density function of the physiological data of the healthy user and before the set probability threshold for determining the normality and abnormality of the physiological data, the method further includes:
acquiring a cross validation set, wherein the cross validation set comprises normal physiological data obtained based on healthy users and abnormal physiological data obtained based on unhealthy users;
and calculating the probability of normal physiological data and abnormal physiological data by using the Gaussian distribution probability density function, and determining a set probability threshold value for judging the normality and the abnormality of the physiological data.
The cross validation set can extract data from the first sample data, and can also acquire physiological data again, but needs to include abnormal physiological data of unhealthy users. The abnormal detection algorithm based on Gaussian distribution is trained to obtain a Gaussian distribution density function, a set probability threshold is determined by using a cross validation set to obtain a Gaussian distribution probability model, abnormal physiological data are identified, and the set probability threshold is a constraint range of the Gaussian distribution probability model.
The invention is illustrated in detail below with reference to an example:
using the public data set: PAMAP2_ Dataset physical Activity monitoring (2012), the data in this data set was derived from 9 testers, 8 males and 1 female, with an age range of 27.22 + -3.31 years and a BMI range of 25.11 + -2.62 kgm2. All testers were wearing devices at the dominant arm wrist for one day experimental activities, which were inertial measurement devices (colliwirlessimus) with a sampling rate of 100Hz and heart rate sensors (BM-CS5 srfrommbinovationgmbh) with a sampling rate of 9 Hz.
The data of the data set are sorted to obtain three-axis acceleration and heart rate data of 9 testers in 8 activities of lying, sitting, standing, sitting, working, walking, going upstairs and downstairs, jumping and running, the data set representing the daily activity rule of the human body can be obtained by integrating the activity data of 9 testers and taking the average value of the heart rate and the square average value of the three-axis acceleration, and in 8 activities, the activity data of 100 testers are sorted in each activity, and the total number of 900 (the activities of going upstairs and downstairs are 100 respectively) of the 9 testers (X is the activities of going upstairs and downstairsAcceleration of a vehicle，XHeart rate) A two-dimensional vector. The data in this data set may be equivalent to data from a basic physical link bracelet with health monitoring worn by a normal user.
700 data are extracted from a raw data set to serve as a training set, 200 data are extracted from the raw data, and 210 data in total are artificially constructed from 10 abnormal data to serve as a cross validation set. The mathematical expectation mu-6.300285713.967639 and variance were obtained by learning on a training set based on a binary gaussian distribution anomaly detection algorithm
Figure BDA0003585667570000091
Figure BDA0003585667570000092
And the optimal probability threshold epsilon is obtained by cross validation set to be 0.007171. The experimental effect diagram of the anomaly detection algorithm is shown in fig. 3, wherein the probability of the data which are centrally distributed and normal data is greater than epsilon, and the probability of the data which are loosely distributed and abnormal data is less than epsilon. The heart rate sensor energy-saving method comprises the following steps:
the wrist strap collects (X) during the initial operation and the operation of the deviceAcceleration of a vehicle，XHeart rate) The probability p of the data is calculated through the obtained Gaussian distribution function, if the probability p is larger than epsilon, the heart rate value at the moment is judged to be normal, and the heart rate sensor works and samples at the low frequency of 0.01 Hz; if p is smaller than epsilon, the heart rate value at the moment is judged to be abnormal, and the heart rate sensor works at a high frequency of 1Hz for sampling;
when the heart rate sensor samples at low frequency, if abnormal data are acquired, the abnormal data are immediately converted into high-frequency sampling; the heart rate sensor can maintain a high-frequency state for 3 minutes during high-frequency sampling, normal data collected within 3 minutes cannot be converted into low frequency data, and the normal data collected after 3 minutes can be converted into low-frequency sampling.
The low-frequency, high-frequency and high-frequency maintaining time described above is specified for convenience of description in this embodiment, and should be formulated in combination with specific equipment and user requirements in the actual application process.
Classifying 300 data of three activities of static lying, static sitting and static standing in the original data set into static states, wherein the classification label is 0; 400 data of three activities of working, walking and going upstairs and downstairs are classified into a conventional state, and the classification label is 1; 200 data of two activities of running and rope skipping are classified into motion states, the classification label is 2, and the labeled data set is divided into 630 training sets and 270 cross validation sets.
And learning by a C4.5 decision tree classification algorithm to obtain a human activity state classification model with the classification accuracy of 94.4%. The energy-saving method of the GPS positioning system is worked out by the classification model:
data (X) collected by the wristband terminalAcceleration of a vehicle，XHeart rate) And judging the current state of the user through a classification model, if the user is in a static state, the GPS does not work in a dormant state, if the user is in a normal state, the GPS works at low frequency, namely the positioning information is updated every 5 minutes, if the user is in a motion state, the GPS works at high frequency, namely the positioning information is updated every 30 seconds, after each state is judged, the duration is 10 minutes, and after 10 minutes, whether the state is changed is judged.
The energy-saving method of the heart rate sensor and the GPS positioning system, which is made by combining the selected data set, is applied to the activities of 9 testers in the data set in one day, and experiments prove that the energy-saving method provided by the invention can averagely save 80-90% of electric energy under the condition of no other energy-saving measures, so that the heart rate sensor can be in a low-frequency working mode in most of time, and the frequency of updating the positioning information by the GPS is greatly reduced.
In summary, according to the energy saving method and the energy saving device for the wearable device, the gaussian distribution probability density function is obtained, the set probability threshold for judging whether the physiological data is normal or abnormal is used, the first physiological data of the user at the current moment is collected, the probability value corresponding to the first physiological data is calculated according to the gaussian distribution probability density function, the probability value is compared with the set probability threshold, the normal or abnormal state of the physiological data of the user is judged, the heart rate sensor is instructed to sample at low frequency in the normal state, and sampling at high frequency in the abnormal state is judged; and inputting the first physiological data into a preset classification algorithm to obtain the activity state of the user at the current moment, and instructing the GPS positioning module to sample at different frequencies in a static state, a conventional state with low displacement and a motion state with high displacement. According to the method, the use requirements and the daily activity rule of the user are researched, the low-power-consumption operation design is carried out on the sampling frequency and the working mode of the high-power-consumption sensor in the wearable device in combination with the daily activity rule of the user, the health monitoring effect is guaranteed, self-adaption energy saving is achieved, the power consumption of the whole device is reduced by reducing the power consumption of the sensor, and the health condition of the user can be monitored for a long time.
Those of ordinary skill in the art will appreciate that the various illustrative components, systems, and methods described in connection with the embodiments disclosed herein may be implemented as hardware, software, or combinations of both. Whether this is done in hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments can be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Features that are described and/or illustrated with respect to one embodiment may be used in the same way or in a similar way in one or more other embodiments and/or in combination with or instead of the features of the other embodiments in the present invention.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A wearable device energy saving method running on a processor of a wearable device, comprising:
acquiring a Gaussian distribution probability density function of physiological data of healthy users, and a set probability threshold value for judging the normality and the abnormality of the physiological data, wherein the physiological data of the healthy users at least comprises acceleration data and heart rate data, and the Gaussian distribution probability density function is calculated based on the physiological data of a plurality of healthy users in different activity states;
acquiring first physiological data of a user at the current moment, and calculating a probability value corresponding to the first physiological data according to the Gaussian distribution probability density function, wherein the first physiological data at least comprises first acceleration data and first heart rate data;
comparing the probability value with the set probability threshold: if the probability value is larger than the set probability threshold value, judging that the first physiological data at the current moment are normal, and instructing a heart rate sensor to work and sample at a first frequency; if the probability value is smaller than the set probability threshold value, judging that the first physiological data at the current moment are abnormal, and instructing the heart rate sensor to perform working sampling at a second frequency for at least a first set duration; wherein the first frequency is less than the second frequency;
inputting the first physiological data into a preset classification algorithm to obtain an activity state of the user at the current moment, wherein the activity state at least comprises: a rest state without displacement, a normal state with a low displacement amount and a motion state with a high displacement amount;
if the user is in a static state at the current moment, the GPS positioning module is instructed to sleep and not work; if the current time of the user is in a conventional state, the GPS positioning module is instructed to acquire positioning data at a third frequency; if the user is in a motion state at the current moment, instructing the GPS positioning module to acquire positioning data at a fourth frequency, wherein the third frequency is smaller than the fourth frequency; after the three states are judged, the GPS positioning module works for at least a second set time.
2. The wearable device energy saving method of claim 1, wherein the Gaussian probability distribution density function of the physiological data of the healthy user is obtained by the following steps:
acquiring physiological data containing acceleration data and heart rate data of a plurality of age-group healthy users in different activity states as first sample data;
and performing distribution analysis on the first sample data by utilizing binary Gaussian distribution, and fitting to obtain the distribution probability of the acceleration and the heart rate so as to obtain a Gaussian distribution probability density function of the physiological data of the healthy user.
3. The wearable device power saving method of claim 1, wherein before entering the first physiological data into a preset classification algorithm to obtain the activity state of the user at the current moment, further comprising:
acquiring physiological data of a plurality of age-group healthy users containing acceleration data and heart rate data in different activity states, and marking the activity state category of each data sample to obtain second sample data;
training by using the second sample data to obtain a decision tree as the preset classification algorithm; the decision tree is one of ID3, C4.5 or CART.
4. The energy-saving method for the wearable device according to claim 1, wherein the preset classification algorithm is based on a support vector machine, a generative confrontation network or a convolutional neural network training.
5. The energy saving method for the wearable device according to claim 1, wherein before obtaining the probability density function of gaussian distribution of physiological data of the healthy user and the set probability threshold for determining normality and abnormality of the physiological data, the method further comprises:
acquiring a cross validation set, wherein the cross validation set comprises normal physiological data obtained based on healthy users and abnormal physiological data obtained based on unhealthy users;
and calculating the probability of the normal physiological data and the abnormal physiological data by using the Gaussian distribution probability density function, and determining a set probability threshold value for judging the normality and the abnormality of the physiological data.
6. The method for saving energy of the wearable device according to claim 1, further comprising:
during the period that the heart rate sensor works and samples at a first frequency, if the first physiological data is judged to be abnormal at the current moment, the heart rate sensor is immediately instructed to be converted from the first frequency to a second frequency to work and sample, and the work and the sampling lasts for at least the first set time.
7. The wearable device power saving method of claim 1, wherein the activity state comprises at least: lying still, sitting still, standing still, sitting for working, walking, going upstairs and downstairs, jumping and running.
8. The energy-saving method for the wearable device according to claim 1, wherein the static state at least comprises: the normal state at least comprises the following steps: sit to work, walk, go upstairs and downstairs, the motion state includes at least: jumping and running.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 8 are implemented when the processor executes the program.
10. A wearable device, characterized in that it comprises at least:
the acceleration sensor is used for acquiring acceleration data of a user;
the heart rate sensor is used for collecting heart rate data of a user;
the GPS positioning module is used for recording the displacement change data of the user;
a processor configured to perform the method of any one of claims 1 to 8.
CN202210362067.4A 2022-04-07 2022-04-07 Energy saving method and equipment for wearable equipment Active CN114756114B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210362067.4A CN114756114B (en) 2022-04-07 2022-04-07 Energy saving method and equipment for wearable equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210362067.4A CN114756114B (en) 2022-04-07 2022-04-07 Energy saving method and equipment for wearable equipment

Publications (2)

Publication Number Publication Date
CN114756114A true CN114756114A (en) 2022-07-15
CN114756114B CN114756114B (en) 2023-05-30

Family

ID=82328362

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210362067.4A Active CN114756114B (en) 2022-04-07 2022-04-07 Energy saving method and equipment for wearable equipment

Country Status (1)

Country Link
CN (1) CN114756114B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115590505A (en) * 2022-12-15 2023-01-13 楠楠聚智信息科技有限责任公司（Cn） Data anomaly analysis method for intelligent motion monitoring device
CN115798167A (en) * 2023-01-05 2023-03-14 石家庄市惠源淀粉有限公司 Equipment abnormity alarm method and device for starch glucose production process
CN117357104A (en) * 2023-12-07 2024-01-09 深圳市好兄弟电子有限公司 Audio analysis method based on user characteristics

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160302671A1 (en) * 2015-04-16 2016-10-20 Microsoft Technology Licensing, Llc Prediction of Health Status from Physiological Data
CN106971059A (en) * 2017-03-01 2017-07-21 福州云开智能科技有限公司 A kind of wearable device based on the adaptive health monitoring of neutral net
CN107550475A (en) * 2017-07-31 2018-01-09 深圳真时科技有限公司 A kind of method, apparatus and wearable device for monitoring human heart rate
CN110806733A (en) * 2019-10-30 2020-02-18 中国神华能源股份有限公司国华电力分公司 Thermal power plant equipment monitoring method and device and electronic equipment

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160302671A1 (en) * 2015-04-16 2016-10-20 Microsoft Technology Licensing, Llc Prediction of Health Status from Physiological Data
CN106971059A (en) * 2017-03-01 2017-07-21 福州云开智能科技有限公司 A kind of wearable device based on the adaptive health monitoring of neutral net
CN107550475A (en) * 2017-07-31 2018-01-09 深圳真时科技有限公司 A kind of method, apparatus and wearable device for monitoring human heart rate
CN110806733A (en) * 2019-10-30 2020-02-18 中国神华能源股份有限公司国华电力分公司 Thermal power plant equipment monitoring method and device and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
于冰洁;夏战国;王久龙;: "基于高斯过程模型的异常检测算法", 计算机工程与设计 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115590505A (en) * 2022-12-15 2023-01-13 楠楠聚智信息科技有限责任公司（Cn） Data anomaly analysis method for intelligent motion monitoring device
CN115590505B (en) * 2022-12-15 2023-03-14 楠楠聚智信息科技有限责任公司 Data anomaly analysis method for intelligent motion monitoring device
CN115798167A (en) * 2023-01-05 2023-03-14 石家庄市惠源淀粉有限公司 Equipment abnormity alarm method and device for starch glucose production process
CN117357104A (en) * 2023-12-07 2024-01-09 深圳市好兄弟电子有限公司 Audio analysis method based on user characteristics
CN117357104B (en) * 2023-12-07 2024-04-26 深圳市好兄弟电子有限公司 Audio analysis method based on user characteristics

Also Published As

Publication number Publication date
CN114756114B (en) 2023-05-30

Similar Documents

Publication Publication Date Title
CN114756114B (en) Energy saving method and equipment for wearable equipment
US20200237262A1 (en) Activity recognition
Karantonis et al. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring
Dalton et al. Development of a body sensor network to detect motor patterns of epileptic seizures
US20160228053A1 (en) Wireless monitoring system with activity manager for monitoring user activity
Cancela et al. A comprehensive motor symptom monitoring and management system: the bradykinesia case
US9848776B2 (en) Methods using activity manager for monitoring user activity
Magno et al. DeepEmote: Towards multi-layer neural networks in a low power wearable multi-sensors bracelet
Sun et al. PEAR: Power efficiency through activity recognition (for ECG-based sensing)
US9345403B2 (en) Wireless monitoring system with activity manager for monitoring user activity
US9149189B2 (en) User or patient monitoring methods using one or more analysis tools
CN102917661A (en) Multivariate residual-based health index for human health monitoring
Wang et al. A system of human vital signs monitoring and activity recognition based on body sensor network
CN103268419A (en) Health management system with waistband-type monitoring device and cloud through internet of things and operation method
CN112353368B (en) Multi-input signal epileptic seizure detection system based on feedback adjustment
CN104539726A (en) System and method used for concerning behavior rules of the old by children
US9357922B2 (en) User or patient monitoring systems with one or more analysis tools
Jeong et al. Classification of posture and movement using a 3-axis accelerometer
Dong et al. A two-layer ensemble method for detecting epileptic seizures using a self-annotation bracelet with motor sensors
Altini et al. Personalization of energy expenditure estimation in free living using topic models
Wang et al. A low-power fall detection algorithm based on triaxial acceleration and barometric pressure
CN108542368A (en) A kind of wearable device promotes the method and system of sleep quality
Feng et al. Modeling behavioral consistency in large-scale wearable recordings of human bio-behavioral signals
Nguyen et al. A Bayesian nonparametric framework for activity recognition using accelerometer data
Mani et al. Smart suspenders with sensors and machine learning for human activity monitoring

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant