JP6703456B2 - Method of operating determination device, determination device, and wearable sensor system - Google Patents

Description

The present invention relates to a wearable sensor system that detects biological information, and more particularly to a method of operating a determination device that determines the risk of heat damage to a living body , a determination device, and a wearable sensor system.

In recent years, combined with the effects of global warming and the heat island phenomenon, the risk of contracting a heat disorder represented by heat stroke in Japan is increasing. Heat disorders, such as heat stroke, cause dehydration when people are subjected to heat stress, such as in a high-temperature environment, and the balance of water and salt in the body is disrupted. It is a disorder that may reach (see Non-Patent Document 1).

Data released by government agencies show that the number of people who die from heat stroke increases as summer days and tropical nights continue. Specifically, if the "heat index WBGT (Wet Bulb Globe Temperature)", which is an index focusing on the heat balance between the human body and the outside air, exceeds 28 degrees, the number of deaths due to heat stroke It is known that the mortality rate increases with the increase of WBGT. In addition, people who exercise or work such as sports tend to develop heat stroke outdoors, and people who live their daily lives, especially elderly people, tend to develop heat stroke indoors. Is also known. On the other hand, it is said that heat disorders represented by heat stroke can be prevented.

In order to protect the central nervous system, which is vulnerable to heat, in response to an increase in body temperature, humans first move blood to the skin surface to promote heat diffusion by conduction and radiation, and promote evaporation by a large amount of sweating Relieves stress. As described in Non-Patent Document 1, the external environment, the cardiac function, and the intravascular volume are known as factors for suppressing the increase in body temperature.
For example, the risk of developing heat stroke can be reduced by taking appropriate actions such as drinking water, replenishing salt, refrigerating to a cold place, and cooling the body based on the regional heat index WBGT announced by the administrative agency. It is believed that.

Moreover, when a heat disorder represented by heat stroke develops, the core temperature (body temperature) of the body rises. Therefore, by taking appropriate action while constantly monitoring the body temperature, the risk of developing heat stroke. Is believed to be suppressed.

"Heat Stroke-Fear of Heat Waves Attacking Japan", edited by Japan Society of Emergency Medicine, Herusu Publishing, May 2011, p. 9-15

However, in today's society, which often moves, it is not easy for the user to act while always being aware of the heat index WBGT at the current location.
In addition, the heat index WBGT is information of outdoor measurement points in a specific area, and is a reference value that does not directly reflect the current situation of the user. Therefore, as many heat strokes have been reported indoors, merely relying on the heat index WBGT to act does not always prevent heat disorders leading to heat stroke.

The present invention has been made in view of the above problems, and an object thereof is to determine the degree of risk of heat injury of a living body without relying on reference values such as the heat index WBGT.

The present invention relates to a method of operating a determination device including a computer including a CPU and a storage device, which is a data acquisition for receiving heartbeat data, body temperature data, and skin blood flow data from a wearable sensor terminal. A step of determining a risk degree of heat injury of a living body based on the heart rate data, the body temperature data, and the skin blood flow data in the CPU according to a program stored in the storage device. Among the sensors of the wearable sensor terminal that obtains the heart rate data, the body temperature data, and the skin blood flow data, the body temperature data is the deep part measured by the sensor attached to the ear of the living body. It is data of body temperature, and the determination step creates teacher data in which the wearable sensor terminal classifies multiple sets of data of heart rate, deep body temperature, and skin blood flow preliminarily measured for a living body of a test subject according to risk levels. Based on the proximity of the teacher data to the data of heart rate, core body temperature, and skin blood flow measured by the wearable sensor terminal for the living body to be determined, the heat of the living body to be determined. look including the risk assessment step of determining the risk of failure, the teacher data creating step performs a principal component analysis on previously measured data about the living body of the test subject, data after principal component analysis Based on the closeness of the safety zone data, the danger zone data and other data to the safety zone data and the danger zone data based on the preset conditions. In addition, the method includes the step of creating the teacher data by classifying the data into either the caution area or the caution area, wherein the risk determination step includes the heart rate and the deep body temperature measured for the determination target living body. And the data of skin blood flow are added to the data measured in advance for the living body of the test target, the principal component analysis is performed on the data after the addition, and the principal component space obtained by this principal component analysis is calculated. The method further comprises the step of determining the degree of risk of heat injury of the determination target biological body based on the proximity of the determination target biological data and the teacher data .

Further , the present invention is a method of operating a determination device including a computer having a CPU and a storage device, wherein heartbeat data of a living body, body temperature data, and skin blood flow data are received from a wearable sensor terminal. Data acquisition step, based on the data of the heart rate, the data of the body temperature and the data of the skin blood flow, the determination step of determining the risk of thermal injury of the living body, according to the program stored in the storage device. A teacher that causes the CPU to execute the determination step, and creates teacher data in which the wearable sensor terminal classifies a plurality of sets of data of the heart rate, the body temperature, and the skin blood flow, which are preliminarily measured for the living body to be tested, according to risk levels. Data creation step, based on the proximity of the heart rate, body temperature, and skin blood flow data measured by the wearable sensor terminal for the living body to be judged, to the teacher data, the risk of thermal injury to the living body to be judged And a risk determining step for determining the degree, the teacher data creating step performs a principal component analysis on the data measured in advance for the living body of the test subject, and sets the data after the principal component analysis in advance. Based on the specified conditions, the data are classified into three, safe area data, dangerous area data, and other data. Based on the proximity of the other data to the safe area and dangerous area data, the caution area By including the step of creating the teacher data by classifying into one of the data of the caution area and the caution area, the risk determination step includes the heart rate, the body temperature, and the skin blood flow measured for the living body of the determination target. Data is added to the data measured in advance for the living body of the test target, the principal component analysis is performed on the data after the addition, on the principal component space obtained by this principal component analysis, of the determination target It is characterized by including a step of determining a risk degree of heat injury of the living body to be determined based on the proximity of the living body data and the teacher data.
Further, in one configuration example of the operating method of the determination device of the present invention, the teacher data creating step may use k-means clustering or a method of classifying the other data into any of a caution area and a caution area. It is characterized by using an EM algorithm.

Further, in one configuration example of the operation method of the determination device of the present invention, the risk determination step is performed on the main component space obtained by the main component analysis performed on the data after the addition, to determine the determination target. A predetermined number of data closest to the biological data is extracted, the risk of the extracted data is determined based on the teacher data, and the majority of the risks of the extracted data is determined by the thermal failure of the determination target biological body. It is characterized by including a step of determining the degree of danger of.
In addition, one configuration example of the operating method of the determination device of the present invention is to replace the measurement data of the skin blood flow used in the teacher data creation step with the skin blood flow rate of the living body of the test subject when no exercise load is applied. When the initial value, using the rate of change of the measurement data of the skin blood flow of the test subject to the initial value, instead of the measurement data of the skin blood flow used in the risk determination step, the exercise load is When the skin blood flow rate of the determination target living body when not applied is set as an initial value, it is characterized by using the rate of change of the measurement data of the skin blood flow rate of the determination target living body with respect to this initial value. is there.

In addition, the determination device of the present invention is a communication unit that receives heartbeat data of a living body, body temperature data, and skin blood flow data from a wearable sensor terminal, the heart rate data, body temperature data, and skin blood flow. And a determination unit that determines the risk of thermal injury of the living body based on the data of the body temperature data, the body temperature data is the wearable that acquires the heart rate data, the body temperature data, and the skin blood flow data. Of the sensors of the sensor terminal, is the data of the deep body temperature measured by the sensor attached to the ear of the living body, the determination means, the wearable sensor terminal the heart rate and the deep body temperature previously measured for the living body of the test subject, A plurality of sets of data of skin blood flow, a teacher data creation unit that creates teacher data by classifying the data according to risk levels, and heart rate, deep body temperature, and skin blood flow data measured by the wearable sensor terminal for a living body to be determined. of, based on the proximity of said teacher data, the saw including a danger evaluator to determine the risk of thermal failure determination target living, before Symbol teacher data creating unit for biometric of the test object Principal component analysis is performed on the pre-measured data, and the data after this principal component analysis is divided into three data, that is, the safety region data, the dangerous region data, and other data based on the preset conditions. , The teacher data is created by classifying the other data into data of either the caution area or the caution area based on the proximity to the data of the safety area and the danger area, and the risk data is created. The determination unit adds the data of the heart rate, the core body temperature, and the skin blood flow measured for the biological body of the determination target to the data measured in advance for the biological body of the test target, and the main component with respect to the data after the addition. Performing an analysis, on the principal component space obtained by this principal component analysis, based on the proximity of the data of the living body of the determination target and the teacher data, the risk of heat injury of the living body of the determination target It is characterized by making a determination.
In addition, the determination device of the present invention is a communication unit that receives heartbeat data of a living body, body temperature data, and skin blood flow data from a wearable sensor terminal, the heart rate data, body temperature data, and skin blood flow. Based on the data, and a determination means for determining the risk of heat injury of the living body, the determination means, the wearable sensor terminal of the heart rate and body temperature and skin blood flow pre-measured for the living body of the test subject. A plurality of sets of data, a teacher data creation unit that creates teacher data that is classified according to risk levels, and the teacher data of heart rate, body temperature, and skin blood flow data measured by the wearable sensor terminal for a living body to be determined. Based on the closeness of, and including a risk determination unit to determine the risk of thermal injury of the living body of the determination target, the teacher data creation unit, for the data measured in advance for the living body of the test target The principal component analysis is performed by using the data, and the data after the principal component analysis is divided into three data, that is, the data in the safety region, the data in the dangerous region, and the other data based on the preset conditions. Based on the proximity to the data of the safe area and the dangerous area, the teacher data is created by classifying the data into either the caution area or the caution area, The heart rate, body temperature, and skin blood flow data measured for the living body are added to the data previously measured for the living body to be tested, and the principal component analysis is performed on the data after the addition, and this principal component analysis is performed. Characterized in that the degree of risk of heat injury of the determination target biological body is determined based on the proximity of the determination target biological data and the teacher data on the principal component space obtained in Is.
Further, the wearable sensor system of the present invention is characterized by including a wearable sensor terminal for acquiring heartbeat data, body temperature data, and skin blood flow data of a living body, and the determination device.

The present invention is a mechanism for increasing the heart rate and peripheral blood flow for the purpose of suppressing the increase in body temperature while the living body changes from a normal state to a state in which high temperature injury is caused, and further increase in body temperature continues. In this case, in order to capture the changes in the mechanism that makes it impossible for the living body to increase blood flow, it is characterized by measuring skin blood flow data in addition to data related to the heart function and body temperature of the living body. .. ADVANTAGE OF THE INVENTION According to this invention, since the risk degree of heat injury of a living body can be appropriately determined, it is possible to provide appropriate state information regarding the heat injury of a living body without relying on reference values such as the heat index WBGT. It will be possible.

It is a figure which shows the structure of the wearable sensor system which concerns on embodiment of this invention. It is a block diagram which shows the structure of the determination device of the wearable sensor system which concerns on embodiment of this invention. 5 is a flowchart illustrating a method of creating teacher data according to the embodiment of the present invention. It is a figure which shows the example of preparation of the teacher data in embodiment of this invention. 6 is a flowchart illustrating a method for determining a risk degree of heat injury according to the embodiment of the present invention. It is a figure which shows the example of the risk determination result of the heat failure in embodiment of this invention.

Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing a configuration of a wearable sensor system according to an embodiment of the present invention, and is a schematic diagram showing a state in which the wearable sensor system is mounted on a human body. The wearable sensor system includes a wearable sensor terminal 1 that acquires data related to a cardiac function of a user 100 who wears the wearable sensor system, a wearable sensor terminal 2 that acquires body temperature data of the user 100, and a skin of the user 100. Wearable sensor terminal 3 for acquiring blood flow data, heart function data acquired by wearable sensor terminal 1, body temperature data acquired by wearable sensor terminal 2, and skin blood flow acquired by wearable sensor terminal 3. The determination device 4 is provided to determine the risk of heat injury of the user 100 based on the data.

In the example of FIG. 1, the wearable sensor terminal 1 is attached to a shirt-type wearable device 10 worn by a user 100. The wearable device 10 is provided with an electrode 11 so as to come into contact with the skin surface around the heart 101 of the user 100. The wearable sensor terminal 1 is connected to the electrode 11 via the wiring 12 provided in the wearable device 10. The wearable sensor terminal 1 measures the electrocardiographic waveform of the user 100 via the electrode 11 and analyzes the electrocardiographic waveform to acquire the heart rate as data regarding the cardiac function of the user 100. Since the method of measuring the electrocardiographic waveform and the method of acquiring the heart rate are known techniques, detailed description thereof will be omitted.

Then, the wearable sensor terminal 1 wirelessly or wiredly transmits the acquired heart rate data to the determination device 4.
The wearable sensor terminal 1 may be fixed to clothing (a shirt in the example of the present embodiment) that is a base material of the wearable device 10, or may be configured to be removable from the base material. ..

The wearable sensor terminal 2 acquires data on the body temperature of the user 100. As such a wearable sensor terminal 2, for example, a device is known in which a sensor is attached to the ear portion of the user 100 to measure the core body temperature from the eardrum temperature. Other methods of measuring the core body temperature include a method of estimating from the skin temperature. The wearable sensor terminal 2 wirelessly or wiredly transmits the acquired body temperature data to the determination device 4.

The wearable sensor terminal 3 is attached to, for example, the arm of the user 100, and acquires data on the skin blood flow of the user 100. Examples of such wearable sensor terminal 3 include, for example, documents “K.Kuwabara, Y.Higuchi, T.Ogasawara, H.Koizumi, T.Haga, “Wearable Blood Flowmeter Appcessory with Low-Power Laser Doppler Signal Processing for Daily-Life”. Healthcare Monitoring”, Proceeding of 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014, p. 6274-6277”. The wearable sensor terminal 3 wirelessly or wiredly transmits the acquired data of the skin blood flow to the determination device 4.

FIG. 2 is a block diagram showing the configuration of the determination device 4 of this embodiment. The determination device 4 includes a communication unit 40 that receives measurement data from the wearable sensor terminals 1 to 3, a storage unit 41 for storing data, and a teacher data creation unit 42 that creates teacher data in advance based on subject data. And a risk degree determination unit 43 for determining the risk degree of heat failure of the user 100, a determination result output unit 44 for outputting the determination result of the risk degree determination unit 43, and an input unit for giving a command to the determination device 4. And 45.

An example of the determination device 4 is a smartphone carried by the user 100. However, the determination device 4 may be provided inside any of the wearable sensor terminals 1 to 3.

Next, a method of creating in advance the teacher data which is the basis for the risk determination of the high temperature failure will be described with reference to FIG. In the present embodiment, in order to create the teacher data, the heart rate, the body temperature, and the skin blood flow when the subject (living body to be tested) is given an arbitrary exercise load (workload) are measured. The more subjects and measurement points, the more desirable. Here, the number of measurement data consisting of a set of heart rate, body temperature, and skin blood flow is n (n is an integer of 2 or more).

First, the heart rate, body temperature, and skin blood flow of a subject when given an arbitrary workload in the range of 0 to 80% are measured for a plurality of subjects using the wearable sensor terminals 1 to 3 shown in FIG. To do. The term 0 to 80% as used herein means the exercise intensity defined by the maximum oxygen uptake amount (VO ₂ max).

The communication unit 40 of the determination device 4 receives the data of the heart rate, the body temperature, and the skin blood flow from the wearable sensor terminals 1 to 3 worn by the subject (step S100 in FIG. 3). The received data is stored in the storage unit 41. In order to be able to recognize the subject and the amount of the workload given to the subject, the data can be stored in the storage unit 41 by adding the ID (identification information) unique to the subject and the information on the workload. It is desirable to keep it. These ID and workload information are input from the input unit 45 operated by a worker who creates teacher data, for example.

The teacher data creation unit 42 of the determination device 4 applies to D-dimensional data (D=3D of heart rate, body temperature, and skin blood flow in the example of the present embodiment)×n pieces of data stored in the storage unit 41. Principal component analysis is performed (step S101 in FIG. 3). However, instead of using the measurement data as it is for the skin blood flow rate, the skin blood flow rate of the subject when the workload is not applied is set as an initial value, and the rate of change in the measurement data of the skin blood flow rate with respect to this initial value, Used as the skin blood flow change rate (percentage).

That is, the teacher data creation unit 42 calculates the skin blood flow change ratio by dividing the measurement data of the skin blood flow of the subject by the initial value of the skin blood flow of the subject. Although the initial value of the skin blood flow varies depending on the subject, the initial value measured for each subject may be stored in the storage unit 41. Thus, the teacher data creation unit 42 performs the principal component analysis on the D=three-dimensional data of the heart rate, the body temperature, and the skin blood flow change rate.
In this embodiment, an example will be described in which the same D=three-dimensional synthetic variable (principal component) is obtained for D=three-dimensional data.

Subsequently, the teacher data creation unit 42 classifies the data after the principal component analysis into three risk levels of level 1 (safety zone), level 4 (risk zone), and levels other than levels 1 and 4. (FIG. 3 step S102). Here, after the principal component analysis corresponding to the data (heart rate, body temperature, skin blood flow change rate) before the principal component analysis in which the workload was 0% to 30% and the body temperature was less than 37.5°C. The data is level 1 (safety zone) data. Further, the data after the principal component analysis corresponding to the data before the principal component analysis in which the body temperature is higher than 38.5° C. is set as the data of level 4 (danger area). Such classification conditions of level 1 and level 4 are preset in the teacher data creation unit 42. In FIG. 3, the number of level 1 (safety zone) data is n4, and the number of level 4 (dangerous zone) data is n1.

Next, the teacher data creation unit 42 performs k-means clustering on {n-(n1+n4)} pieces of data after principal component analysis excluding level 1 (safety area) and level 4 (dangerous area). The data after the principal component analysis is divided into two groups (step S103 in FIG. 3). Specifically, the teacher data creation unit 42 sets the coordinates of the center of the cluster (group) to which the level 1 data belongs and the coordinates of the center of the cluster to which the level 4 data belongs in the three-dimensional space after the principal component analysis. Each of them is calculated, and the spatial distance between these centers and the data to be separated after the principal component analysis is calculated, and the data close to the center of the level 1 cluster is the level 2 (attention area) data and the level 4 cluster. The data near the center of is the data of level 3 (area of caution). In FIG. 3, the number of level 2 data is n2, and the number of level 3 data is n3 (n1+n2+n3+n4=n).

Thus, n1 data of level 1 (safety zone), n2 data of level 2 (warning zone), n3 data of level 3 (warning zone) and n4 data of level 4 (danger zone) Teacher data consisting of and can be created. This teacher data is stored in the storage unit 41. This completes the creation of teacher data.
An EM (exception-maximization) algorithm can be used as the classification algorithm in step S103.

FIG. 4A to FIG. 4C show examples of creating teacher data. Here, 612 pieces of teacher data created from n=612 data obtained from 9 subjects are represented by points on the principal component space with the first principal component, the second principal component, and the third principal component as axes. expressing. 4A to 4C, C1 is a cluster to which level 1 (safety zone) data belongs, C2 is a cluster to which level 2 (warning zone) data belongs, and C3 is a level 3 (warning zone). The cluster to which the data belongs, C4 is the cluster to which the data of level 4 (dangerous area) belongs.

As is clear from FIG. 4(A), n1=35 pieces of data of level 1 (safety area) and n4=91 pieces of level 4 (dangerous area) of the classification processing of step S102 for creating teacher data Separated from data. FIG. 4B shows the result of performing the classification process of step S103 on {n-(n1+n4)}=486 data other than level 1 and level 4 in points on the principal component space. It is FIG. 4(C).

Next, a method for determining the risk degree of thermal injury of the user 100 (living body to be determined) who wears the wearable sensor system shown in FIG. 1 and acts will be described with reference to FIG.
The communication unit 40 of the determination device 4 receives the data of the heart rate, the body temperature, and the skin blood flow of the user 100 from the wearable sensor terminals 1 to 3 worn by the user 100 (step S200 in FIG. 5). The received data is stored in the storage unit 41.

The risk determination unit 43 of the determination device 4 adds the data of the user 100 (hereinafter, unknown data) stored in the storage unit 41 to the n pieces of data from which the teacher data was created (step in FIG. 5). S201). However, as described above, the measurement data is not used for the skin blood flow rate as it is, but the skin blood flow rate of the user 100 when the workload is not applied is set as an initial value, and the skin blood flow rate relative to this initial value is The rate of change in measurement data is defined as the rate of change in skin blood flow. The initial value of the skin blood flow of the user 100 is stored in the storage unit 41 in advance. In this way, one unknown data (heart rate, body temperature and skin blood flow change rate) of D dimension is similarly added to D dimension (D=3 dimension of heart rate, body temperature and skin blood flow change rate)×n data. to add.

Subsequently, the risk degree determination unit 43 performs the principal component analysis on the D-dimensional×(n+1) pieces of data after the unknown data is added (step S202 in FIG. 5).
Then, the risk degree determination unit 43 calculates the spatial distance between the unknown data and the other data on the principal component space obtained by the process of step S202, and the predetermined number k (k) closest to the unknown data ( Data of k is an odd number is extracted (step S203 in FIG. 5).

Next, the risk determining unit 43 determines which of the k levels of the extracted data are level 1 (safety zone), level 2 (caution zone), level 3 (warning zone), and level 4 (danger zone). For each data is determined (step S204 in FIG. 5). As described above, since the teacher data classified into four risk levels is prepared in the storage unit 41, it goes without saying that the risk levels of k pieces of data can be easily determined.

Finally, the risk level determination unit 43 determines the risk level of the unknown data by majority decision of the risk level of the extracted k data (step S205 in FIG. 5). For example, when a large number of k data are level 1 (safety zone), the risk level of unknown data is level 1.

Note that when a plurality of data groups are included in the k number of data, the highest risk level among the levels of these groups is set as the risk level of unknown data. For example, when the same number of data of level 3 (required area) and data of level 4 (danger area) exist, the risk level of unknown data is set to level 4.

The determination result output unit 44 of the determination device 4 outputs the determination result of the risk determination unit 43 (step S206 in FIG. 5). Examples of the output method include, for example, displaying the determination result, outputting the determination result by voice, and transmitting the determination result data.
When continuously acquiring the data of the heart rate, the body temperature, and the skin blood flow of the user 100, the processes of steps S200 to S206 as described above may be periodically performed.

6(A) to 6(D) show examples of the risk determination result of heat failure. Here, 204 pieces of data were prepared as unknown data, and the risk level of these unknown data was determined. It should be noted that, although the information of the workload is originally unnecessary for the unknown data, the unknown data with the clear workload was applied to the determination in order to show the validity of the determination of the present embodiment.

6(A) shows unknown data determined to be level 1 (safety zone), FIG. 6(B) shows unknown data determined to be level 2 (caution zone), and FIG. 6(C) is level 3 The unknown data determined to be the "attention area" is shown, and FIG. 6D shows the unknown data determined to be the level 4 (dangerous area).

According to FIG. 6(A) to FIG. 6(D), for example, data having a high body temperature of 38.5° C. or higher was determined to be level 4 (dangerous area). Data with a workload of 50% and a body temperature of 37°C were determined to be level 2 (attention zone). Data with a workload of 30% and a body temperature of around 38°C were judged to be level 3 (zone of caution).

As described above, in the present embodiment, it is possible to appropriately determine the risk of heat injury (the risk level of unknown data) of the user who wears the wearable sensor system, and thus the heat index WBGT or the like can be determined. It is possible to provide the state information regarding the heat injury of the user without depending on the reference value.

Body temperature is an important parameter that reflects the individual's condition, but when considering the condition that causes high temperature disorders such as heat stroke, the increase in body temperature alone is at the level of caution or caution. I can't judge. In addition to increasing the exercise load, the heart rate also increases due to the mechanism of lowering body temperature to increase blood flow. Therefore, in the present embodiment, it is possible to make a more detailed determination by using a parameter based on the skin blood flow volume that increases in order to suppress an increase in body temperature.

When the process of step S202 is performed on the axes (the first principal component, the second principal component, and the third principal component) obtained in the process of step S101 when creating the teacher data, the axis shift due to the addition of unknown data is performed. However, if there is a large amount of teaching data, it is possible to suppress the above-mentioned axis deviation to the extent that it does not affect the determination.

The determination device 4 described in the present embodiment can be realized by a computer having a CPU (Central Processing Unit), a storage device, and an interface, and a program that controls these hardware resources. The CPU executes the processing described in the present embodiment according to the program stored in the storage device.

INDUSTRIAL APPLICABILITY The present invention can be applied to a technique for determining the risk of heat injury of a living body.

1 to 3... Wearable sensor terminal, 4... Judgment device, 10... Wearable device, 11... Electrode, 12... Wiring, 40... Communication unit, 41... Storage unit, 42... Teacher data creating unit, 43... Danger degree judging unit, 44... Judgment result output unit, 45... Input unit.

Claims (8)

A method for operating a determination device, which comprises a computer having a CPU and a storage device,
A data acquisition step of receiving heartbeat data, body temperature data, and skin blood flow data of the living body from the wearable sensor terminal,
Based on the data of the heart rate, the data of the body temperature, and the data of the skin blood flow, a determination step of determining the risk of heat injury of the living body, causing the CPU to execute in accordance with a program stored in the storage device,
The data of the body temperature is, of the sensors of the wearable sensor terminal for acquiring the data of the heart rate, the data of the body temperature, and the data of the skin blood flow, the data of the deep body temperature measured by the sensor attached to the ear of the living body. And
The determination step is
Teacher data creating step of creating teacher data in which the wearable sensor terminal preliminarily measures a plurality of sets of heart rate, core body temperature, and skin blood flow for a living body to be tested, and classifies the teacher data according to risk levels.
Based on the proximity of the heart rate, the core body temperature, and the skin blood flow data measured by the wearable sensor terminal for the living body to be judged, to the teacher data, the risk of heat injury of the living body to be judged is judged. viewing including the risk determining step,
In the teacher data creating step, a principal component analysis is performed on the data measured in advance for the living body to be tested, and the data after the principal component analysis is combined with the data in the safe area and the risk based on preset conditions. The data of the area is classified into three, that is, the other data, and the other data is classified into one of the caution area and the caution area based on the proximity to the data of the safety area and the danger area. Thereby including the step of creating the teacher data,
The risk determination step, the heart rate and the core body temperature and skin blood flow data measured for the biological body of the determination target is added to the data previously measured for the biological body of the test target, for the data after the addition The principal component analysis is performed by using the principal component analysis, and based on the proximity of the data of the living body to be determined and the teacher data on the principal component space obtained by the principal component analysis, A method for operating a determination device, comprising the step of determining a risk . A method for operating a determination device, which comprises a computer having a CPU and a storage device,
A data acquisition step of receiving heartbeat data, body temperature data, and skin blood flow data of the living body from the wearable sensor terminal,
Based on the data of the heart rate, the data of the body temperature, and the data of the skin blood flow, a determination step of determining the risk of heat injury of the living body, causing the CPU to execute in accordance with a program stored in the storage device,
The determination step is
Teacher data creation step of creating teacher data in which the wearable sensor terminal preliminarily measures the heart rate, the body temperature, and the skin blood flow for the living body to be tested, and separates the teacher data by risk level,
The risk of determining the risk of heat injury of the living body of the determination target based on the proximity of the teacher data to the heart rate, body temperature, and skin blood flow data measured by the wearable sensor terminal for the living body of the determination target. And a degree determination step,
In the teacher data creating step, a principal component analysis is performed on the data measured in advance for the living body to be tested, and the data after the principal component analysis is combined with the data in the safe area and the risk based on preset conditions. The data of the area is classified into three, that is, the other data, and the other data is classified into one of the caution area and the caution area based on the proximity to the data of the safety area and the danger area. Thereby including the step of creating the teacher data,
The risk determination step, the heart rate and body temperature and skin blood flow data measured for the biological body of the determination target is added to the data previously measured for the biological body of the test target, for the data after addition A principal component analysis is performed, and on the basis of the proximity of the data of the living body to be judged and the teacher data on the principal component space obtained by this principal component analysis, the risk of heat injury of the living body to be judged. A method for operating a determination device, comprising the step of determining a degree. The method for operating the determination device according to claim 1 or 2 ,
In the teacher data creating step, a k-means clustering method or an EM algorithm is used as a method of classifying the other data into data of either a caution area or a caution area. The operating method of the determination device according to any one of claims 1 to 3 ,
The risk determination step extracts a predetermined number of data closest to the data of the living body to be determined on the principal component space obtained by the principal component analysis performed on the data after the addition, and extracts the extracted data. Determining device based on the teacher data, and determining the risk of heat injury of the living body of the determination target by majority decision of the risk of the extracted data. How to operate. The operating method of the determination device according to any one of claims 1 to 4 ,
Instead of the measurement data of the skin blood flow used in the teacher data creation step, when the skin blood flow volume of the test subject when an exercise load is not applied is set as an initial value, the living body of the test subject with respect to this initial value Using the rate of change of measurement data of skin blood flow of
Instead of the measurement data of the skin blood flow used in the risk determination step, when the skin blood flow volume of the determination target living body when no exercise load is applied is an initial value, the determination target living body with respect to this initial value A method for operating a determination device, characterized by using a rate of change in measurement data of the skin blood flow rate. A communication unit that receives the heart rate data of the living body, the body temperature data, and the skin blood flow data from the wearable sensor terminal,
Based on the data of the heart rate, the data of the body temperature and the data of the skin blood flow, a determining means for determining the risk of heat injury of the living body,
The data of the body temperature is, of the sensors of the wearable sensor terminal for acquiring the data of the heart rate, the data of the body temperature, and the data of the skin blood flow, the data of the deep body temperature measured by the sensor attached to the ear of the living body. And
The determination means is
A plurality of sets of data of the heart rate, the core body temperature, and the skin blood flow that the wearable sensor terminal previously measured for the living body to be tested, and a teacher data creation unit that creates teacher data classified by risk level,
Based on the proximity of the heart rate, the core body temperature, and the skin blood flow data measured by the wearable sensor terminal for the living body to be judged, to the teacher data, the risk of heat injury of the living body to be judged is judged. viewing including the risk determining unit,
The teacher data creation unit performs a principal component analysis on the data measured in advance for the living body to be tested, and the data after the principal component analysis is combined with the data in the safe area and the risk based on the preset conditions. The data of the area is classified into three, that is, the other data, and the other data is classified into one of the caution area and the caution area based on the proximity to the data of the safety area and the danger area. By creating the teacher data,
The risk determination unit adds the data of the heart rate, the core body temperature, and the skin blood flow measured for the living body of the determination target to the data measured in advance for the living body of the test target, with respect to the data after the addition. The principal component analysis is performed by using the principal component analysis, and based on the proximity of the data of the living body to be determined and the teacher data on the principal component space obtained by the principal component analysis, A determination device characterized by determining the degree of risk . A communication unit that receives the heart rate data of the living body, the body temperature data, and the skin blood flow data from the wearable sensor terminal,
Based on the data of the heart rate, the data of the body temperature and the data of the skin blood flow, a determining means for determining the risk of heat injury of the living body,
The determination means is
A plurality of sets of data of the heart rate, body temperature, and skin blood flow that the wearable sensor terminal previously measured for a living body to be tested, a teacher data creation unit that creates teacher data classified by risk level,
The risk of determining the risk of heat injury of the living body of the determination target based on the proximity of the teacher data to the heart rate, body temperature, and skin blood flow data measured by the wearable sensor terminal for the living body of the determination target. Including a degree determination unit,
The teacher data creation unit performs a principal component analysis on the data measured in advance for the living body to be tested, and the data after the principal component analysis is combined with the data in the safe area and the risk based on the preset conditions. The data of the area is classified into three, that is, the other data, and the other data is classified into one of the caution area and the caution area based on the proximity to the data of the safety area and the danger area. By creating the teacher data,
The risk determination unit adds the data of the heart rate, the body temperature, and the skin blood flow measured for the living body of the determination target to the data measured in advance for the living body of the test target, with respect to the data after the addition. A principal component analysis is performed, and on the basis of the proximity of the data of the living body to be judged and the teacher data on the principal component space obtained by this principal component analysis, the risk of heat injury of the living body to be judged. A judging device characterized by judging the degree. A wearable sensor terminal that acquires heart rate data, body temperature data, and skin blood flow data of a living body,
A wearable sensor system comprising: the determination device according to claim 6 or 7 .

Images