JP6845520B1 - Biological information calculation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a biological information calculation system for improving evaluation accuracy. A biological information calculation system that outputs information on the characteristics of carbon dioxide in the blood of a user, and includes acquisition means, a database, and generation means. The acquisition means acquires evaluation data based on the pulse wave of the user. The database uses a pair of input data based on the learning pulse wave acquired in advance and reference data including the characteristics of blood carbon dioxide associated with the input data as training data, and uses a plurality of the training data. The generated classification information is stored. The generation means refers to the database and generates an evaluation result including the characteristics of the blood carbon dioxide with respect to the evaluation data. [Selection diagram] Fig. 1

Description

The present invention relates to a biometric information calculation system that outputs information regarding the characteristics of carbon dioxide in the blood of a user.

Conventionally, as a method of estimating information about a living body such as a partial pressure of carbon dioxide in the blood (PaCO _{2) of a user, a method such as Patent Document 1 has been proposed.}

In Patent Document 1, after constructing an average frame for each of at least two volume pulse waves having different light wavelengths, it is used to estimate the gain between the two average frames for those two volume pulse waves. Is possible and its gain value is used to estimate information for obtaining blood oxygen saturation, or other components present in the blood, such as hemoglobin, carbon dioxide or the like. It is disclosed that it may be used.

Special Table 2020-513876

Here, when measuring the value of the partial pressure of carbon dioxide in the blood of the user, the health condition of the user can be grasped in detail by monitoring the measured value at a specific cycle. However, when monitoring the measured values, the variation in the measured values due to the measurement conditions and the like becomes large, and the deterioration of the evaluation accuracy is raised as an issue. In this regard, Patent Document 1 estimates the characteristics of blood carbon dioxide based on volume pulse waves using two types of light wavelengths. For this reason, there is a concern that the measured values may vary greatly due to the emission of light or a slight difference in the angle incident on the sensor.

Therefore, the present invention has been devised in view of the above-mentioned problems, and an object of the present invention is to provide a biometric information calculation system for improving evaluation accuracy.

The biometric information calculation system according to the first invention is a biometric information calculation system that outputs information on the characteristics of carbon dioxide in the blood of the user, and is an acquisition means for acquiring evaluation data based on the pulse wave of the user and acquisition in advance. Classification information generated using a plurality of the learning data, using a pair of input data based on the learned pulse wave and reference data including the characteristics of blood carbon dioxide associated with the input data as the learning data. Is provided, and a generation means for generating an evaluation result including the characteristics of the blood carbon dioxide with respect to the evaluation data by referring to the database.

In the biological information calculation system according to the second invention, in the first invention, the reference data includes state information indicating the health state of the subject who measured the learning pulse wave, and the classification information includes a plurality of the above-mentioned classification information. The generation means includes a trained model generated by machine learning using training data, refers to the trained model, and obtains a health condition result indicating the health condition of the user associated with the evaluation data. It is characterized in that it is included in the evaluation result and generated.

In the biometric information calculation system according to the third invention, in the second invention, the plurality of the learning data include only the input data and the reference data at the time of the health of the subject, and the health state result is the above-mentioned health state result. The user's health condition associated with the evaluation data indicates health or non-health.

The biometric information calculation system according to the fourth invention is a calibration model obtained by using PLS regression analysis using the input data as an explanatory variable and the reference data as an objective variable in the first invention. It is characterized by that.

In the first invention, the biometric information calculation system according to the fifth invention includes that the acquisition means acquires preliminary evaluation data different from the evaluation data based on the pulse wave, and the generation means is the database. It is characterized by including generating a preliminary evaluation result including the biometric information of the user with respect to the preliminary evaluation data.

In the fifth invention, the biometric information calculation system according to the sixth invention includes preliminary input data based on the learning pulse wave and the biometric information associated with the preliminary input data in the database. A pair of data is used as preliminary learning data, and preliminary classification information generated by using the plurality of preliminary learning data is stored, and the generation means refers to the preliminary classification information and refers to the preliminary evaluation data. It is characterized by including generating an evaluation result.

In the first invention, the biometric information calculation system according to the seventh invention includes that the acquisition means acquires preliminary evaluation data different from the evaluation data based on the pulse wave, and the classification information is different from each other. A selection means that includes a plurality of attribute-based classification information calculated using the learning data, the generation means refers to the preliminary evaluation data, and selects the first classification information from the plurality of attribute-based classification information. And the attribute-specific generation means for generating the evaluation result with respect to the evaluation data with reference to the first classification information.

In the seventh invention, the biometric information calculation system according to the eighth invention acquires data corresponding to the velocity pulse wave based on the pulse wave as the evaluation data, and the acceleration pulse wave based on the pulse wave. It is characterized in that the data corresponding to is acquired as the preliminary evaluation data.

According to the first to eighth inventions, the producing means refers to a database and generates an evaluation result including the characteristics of blood carbon dioxide with respect to the evaluation data. In addition, the database stores classification information calculated using a plurality of learning data. Therefore, when generating the evaluation result, it is possible to include quantitative characteristics of blood carbon dioxide based on past proven data (input data and characteristics of blood carbon dioxide). This makes it possible to improve the evaluation accuracy.

In particular, according to the second invention, the generation means can refer to the trained model and include the health condition result associated with the evaluation data in the evaluation result and generate it. Therefore, the health condition based on the characteristics of blood carbon dioxide can be notified to the user, and the health condition can be easily grasped as compared with the case where only the characteristics of blood carbon dioxide are notified. it can. This makes it possible to improve convenience for the user.

In particular, according to the third invention, the plurality of learning data includes only the input data and the reference data at the time of the subject's health, and the health condition result indicates whether the user's health condition associated with the evaluation data is healthy. Indicates whether or not. Therefore, even when the input data based on the learning pulse wave at the time of unhealthy state and the characteristics of carbon dioxide in the blood cannot be prepared, it is possible to generate a result showing the health condition of the user. As a result, it is possible to further improve the convenience for the user without increasing the difficulty level when generating the classification information.

In particular, according to the fourth invention, the classification information is a calibration model obtained by using PLS regression analysis with the input data as the explanatory variable and the reference data as the objective variable. Therefore, the number of learning data can be significantly reduced and the calibration model can be easily updated as compared with the case where the classification information is calculated by using machine learning or the like. This makes it possible to facilitate the construction and update of the biometric information calculation system.

In particular, according to the fifth invention, the generation means refers to the database and generates a preliminary evaluation result including the user's biological information with respect to the preliminary evaluation data. Therefore, the preliminary evaluation result generated from a viewpoint different from the evaluation result can be used, and a multifaceted evaluation can be performed. This makes it possible to realize an appropriate evaluation according to the user's request.

In particular, according to the sixth invention, the generation means includes referring to the preliminary classification information and generating the preliminary evaluation result for the preliminary evaluation data. Therefore, it is possible to use the preliminary evaluation result generated by referring to the information different from the evaluation result, and it is possible to carry out a more multifaceted evaluation. This makes it possible to easily realize an appropriate evaluation according to the user's request.

In particular, according to the seventh invention, the generation means refers to the preliminary evaluation data and selects the first classification information, and refers to the first classification information to generate the evaluation result for the evaluation data by attribute. Including means. Therefore, it is possible to generate the evaluation result for the evaluation data after selecting the optimum attribute classification information for the characteristics of the pulse wave. This makes it possible to further improve the evaluation accuracy.

In particular, according to the eighth invention, the acquisition means acquires data corresponding to a velocity pulse wave based on the pulse wave as evaluation data. Further, the preliminary acquisition means acquires data corresponding to the acceleration pulse wave based on the pulse wave as preliminary evaluation data. Therefore, the attribute classification information can be selected by using the acceleration pulse wave, which makes it easier to classify the characteristics of the pulse wave than the velocity pulse wave. In addition, the evaluation result can be generated by using the velocity pulse wave, which is easier to calculate the characteristics of blood carbon dioxide than the acceleration pulse wave. This makes it possible to further improve the evaluation accuracy.

FIG. 1 is a schematic diagram showing an example of a biological information calculation system according to the first embodiment. 2 (a) and 2 (b) are schematic views showing an example of the operation of the biometric information calculation system according to the first embodiment. FIG. 3A is a schematic diagram showing an example of classification information, and FIGS. 3B and 3C are schematic diagrams showing an example of processing for sensor data. FIG. 4A is a schematic diagram showing an example of the configuration of the biological information arithmetic unit, and FIG. 4B is a schematic diagram showing an example of the function of the biological information arithmetic unit. 5 (a) and 5 (b) are schematic views showing an example of the sensor. FIG. 6 is a flowchart showing an example of the operation of the biometric information calculation system according to the first embodiment. FIG. 7 is a schematic diagram showing an example of the operation of the biometric information calculation system according to the second embodiment. 8 (a) and 8 (b) are schematic views showing an example of processing for calculating biological information for sensor data. FIG. 9 is a schematic diagram showing a modified example of the operation of the biological information calculation system according to the second embodiment. FIG. 10 is a schematic diagram showing an example of the operation of the biometric information calculation system according to the third embodiment. FIG. 11 is a schematic diagram showing a classification example of data corresponding to an acceleration pulse wave. FIG. 12 is a schematic diagram showing a classification example of data corresponding to a velocity pulse wave.

Hereinafter, an example of the biological information calculation system according to the embodiment of the present invention will be described with reference to the drawings.

(First Embodiment: Biological Information Calculation System 100)
FIG. 1 is a schematic diagram showing an example of the biometric information calculation system 100 according to the first embodiment.

The biological information calculation system 100 is used to output information regarding the characteristics of carbon dioxide in the blood of the user. The biological information calculation system 100 can generate an evaluation result including the characteristics of blood carbon dioxide from the evaluation data based on the user's pulse wave. The "characteristics of carbon dioxide in blood" indicates the degree of carbon dioxide contained in the user's blood. As a feature of the blood carbon dioxide, for example, in addition to the value of the blood carbon dioxide partial pressure (PaCO ₂₎ is used, and the dissolved concentration in blood carbon dioxide, bicarbonate, bicarbonate contained in the blood _- the (HCO ³⁾ The concentration may be used, and a value considering the pH of blood may be used depending on the situation. Hereinafter, the case where the value of the partial pressure of carbon dioxide in blood is used as a characteristic of carbon dioxide in blood will be mainly described.

As shown in FIG. 1, the biometric information calculation system 100 may include a biometric information calculation device 1, for example, at least one of a sensor 5 and a server 4. The biological information arithmetic unit 1 is connected to the sensor 5 and the server 4 via, for example, the communication network 3.

In the biometric information calculation system 100, for example, as shown in FIG. 2A, the biometric information calculation device 1 acquires the sensor data generated by the sensor 5 or the like. After that, the biometric information calculation device 1 performs preprocessing such as filter processing on the acquired data to acquire evaluation data.

The biological information arithmetic unit 1 refers to a database and calculates the characteristics of blood carbon dioxide (for example, the value of blood carbon dioxide partial pressure) with respect to the evaluation data. In the database, for example, classification information for calculating the value of the partial pressure of carbon dioxide in blood from the evaluation data is stored.

As the classification information, for example, as shown in FIG. 3A, a pair of input data based on the learning pulse wave acquired in the past and a pair of reference information including the value of the blood carbon dioxide partial pressure associated with the input data are used. It is generated using a plurality of training data as training data. For this reason, as learning data, it is possible to use data for subjects whose health condition is clear, and therefore, it is possible to generate reliable classification information as compared with the case where simply accumulated data is used. Is possible. In addition, by referring to the classification information, it is possible to calculate the quantitative value of the partial pressure of carbon dioxide in blood without changing the calculation standard with time.

The biological information arithmetic unit 1 generates an evaluation result including the calculated value of the partial pressure of carbon dioxide in blood, and outputs it to, for example, a display. In addition to the blood carbon dioxide partial pressure value, the evaluation result may include information indicating the evaluation of the blood carbon dioxide partial pressure value, such as "normal" and "abnormal".

As described above, the biometric information calculation system 100 in the present embodiment can refer to the database and generate an evaluation result including the characteristics of blood carbon dioxide with respect to the evaluation data. Therefore, when generating the evaluation result, it is possible to include the quantitative characteristics of carbon dioxide in the blood based on the data that have been proven in the past. This makes it possible to improve the evaluation accuracy.

In the biometric information calculation system 100, evaluation data may be acquired from the sensor 5 or the like, for example, as shown in FIG. 2B. In this case, the preprocessing for acquiring the evaluation data from the sensor data is performed by the sensor 5 or the like.

<Sensor data>
The sensor data includes data indicating the characteristics of the user's pulse wave, and may include, for example, data (noise) indicating characteristics other than the pulse wave. The sensor data is data showing the amplitude with respect to the measurement time, and by performing filter processing according to the application and the generation conditions of the sensor data, data corresponding to the acceleration pulse wave, the velocity pulse wave, etc. is acquired from the sensor data. be able to.

The sensor data can be generated by a known sensor such as a strain sensor, a gyro sensor, a photoelectric volume pulse wave (PPG) sensor pressure sensor, or the like. The sensor data may be, for example, an analog signal as well as a digital signal. The measurement time when generating the sensor data is, for example, the measurement time for 1 to 20 cycles of the pulse wave, and can be arbitrarily set according to the conditions such as the sensor data processing method and the data communication method. Can be done.

<Evaluation data>
The evaluation data shows data for calculating the characteristics of blood carbon dioxide. The evaluation data shows, for example, data corresponding to an acceleration pulse wave based on a user's pulse wave, and shows an amplitude with respect to a specific period (for example, one period).

The evaluation data is acquired by processing (preprocessing) the sensor data by the biological information arithmetic unit 1 or the like. For example, as shown in FIGS. 3 (b) and 3 (c), evaluation data can be obtained by performing a plurality of processes on the sensor data. Details of each process will be described later.

<Database>
The database is mainly used to calculate the characteristics of blood carbon dioxide with respect to the evaluation data. In addition to storing one or more classification information, the database may store, for example, a plurality of learning data used for generating the classification information.

The classification information is, for example, a function showing the interphase relationship between the past evaluation data (input data) acquired in advance and the reference information including the characteristics of blood carbon dioxide. The classification information shows, for example, a calibration model generated based on the analysis result obtained by analyzing the input data as an explanatory variable and the reference information as an objective variable by regression analysis or the like. For example, the calibration model can be updated periodically, and the classification information may be generated according to attribute information such as the user's gender, age, and health condition.

As a method of regression analysis used when generating classification information, for example, PLS (Partial Least Squares) regression analysis and SIMCA (Soft Independent Modeling of Class Analogy) method for obtaining a principal component model by performing principal component analysis for each class are used. Regression analysis and the like can be used.

The classification information may include, for example, a trained model generated by machine learning using a plurality of training data. The trained model shows, for example, a neural network model such as CNN (Convolutional Neural Network) and SVM (Support vector machine). Further, as machine learning, for example, deep learning can be used.

As the input data, the same type of data as the evaluation data is used, and for example, past evaluation data in which the characteristics of the corresponding blood carbon dioxide are clarified is shown. The input data indicates data acquired based on the pulse wave (learning pulse wave) of the subject whose health condition and the like are clear.

For example, the subject is made to wear a sensor 5 or the like to generate sensor data (learning sensor data) showing the characteristics of the learning pulse wave. Then, the input data can be acquired by performing the processing on the learning sensor data. The input data may be acquired from the user of the biometric information calculation system 100, or may be acquired from a user other than the user, for example. That is, the above-mentioned subject may be a user of the biometric information calculation system 100, may be a target other than the user, and may be a specific or unspecified majority.

It is preferable that the input data is acquired according to the same contents as, for example, the type of the sensor 5 used when acquiring the evaluation data, the generation condition of the sensor data, and the processing condition for the sensor data. For example, by unifying the above three contents, it is possible to dramatically improve the accuracy when calculating the characteristics of blood carbon dioxide.

The reference information includes the characteristics of the subject's blood carbon dioxide measured using a measuring device. For example, when a subject is equipped with a sensor 5 or the like to generate learning sensor data, reference information associated with the input data can be acquired by measuring the characteristics of carbon dioxide in the blood of the subject. .. In this case, the timing of measuring the characteristics of blood carbon dioxide is preferably the same as the timing of generating the learning sensor data, but it may be, for example, about 1 to 10 minutes.

As a measuring device, for example, a known device such as a percutaneous blood gas monitor TCM5 (manufactured by Radiometer Basel) is used, or even if a known device for measuring or estimating the _{partial pressure of blood carbon dioxide (PaCO 2) is used.} Good. Incidentally, for example, as a measuring device, bicarbonate, bicarbonate contained in the blood (HCO 3 ^_-) and concentration of, pH may be a known measuring device is used which can measure or estimate the blood. In addition, the reference information includes the characteristics of blood carbon dioxide such as the value of blood carbon dioxide partial pressure, and the characteristics of blood carbon dioxide such as the value of oxygen saturation and the value of atmospheric pressure. Measurements that may be relevant may be included.

<Biological information arithmetic unit 1>
The biological information arithmetic unit 1 indicates an electronic device such as a personal computer (PC), a mobile phone, a smartphone, a tablet terminal, or a wearable terminal, and is an electronic device capable of communicating via a communication network 3 based on, for example, a user's operation. Indicates the device. The biological information arithmetic unit 1 may include a sensor 5. Hereinafter, an example in which a PC is used as the biometric information calculation device 1 will be described.

FIG. 4A is a schematic diagram showing an example of the configuration of the biological information arithmetic unit 1, and FIG. 4B is a schematic diagram showing an example of the function of the biological information arithmetic unit 1.

As shown in FIG. 4A, for example, the biological information arithmetic unit 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, and the like. A storage unit 104 and an I / F 105-107 are provided. Each configuration 101-107 is connected by an internal bus 110.

The CPU 101 controls the entire biometric information arithmetic unit 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a work area used during the operation of the CPU 101. The storage unit 104 stores various information such as a database and evaluation data. As the storage unit 104, for example, in addition to an HDD (Hard Disk Drive), a data storage device such as an SSD (Solid State Drive) is used. For example, the biological information calculation device 1 may have a GPU (Graphics Processing Unit) (not shown).

The I / F 105 is an interface for transmitting and receiving various information to and from the server 4, the sensor 5, and the like as needed via the communication network 3. The I / F 106 is an interface for transmitting and receiving information to and from the input unit 108. For example, a keyboard is used as the input unit 108, and a user or the like of the biometric information calculation device 1 inputs various information, a control command of the biometric information calculation device 1, or the like via the input unit 108. The I / F 107 is an interface for transmitting and receiving various information to and from the display unit 109. The display unit 109 displays various information stored in the storage unit 104, evaluation results, and the like. A display is used as the display unit 109, and for example, in the case of a touch panel type, it is provided integrally with the input unit 108.

FIG. 4B is a schematic diagram showing an example of the function of the biological information arithmetic unit 1. The biological information calculation device 1 includes an acquisition unit 11, a generation unit 12, an output unit 13, and a storage unit 14, and may include, for example, a learning unit 15. Each function shown in FIG. 4B is realized by the CPU 101 executing a program stored in the storage unit 104 or the like using the RAM 103 as a work area.

<Acquisition unit 11>
The acquisition unit 11 acquires evaluation data based on the user's pulse wave. The acquisition unit 11 acquires the evaluation data by, for example, acquiring the sensor data from the sensor 5 or the like and then performing processing on the sensor data.

As shown in FIG. 3B, for example, the acquisition unit 11 performs a filtering process (filter process) on the acquired sensor data. In the filtering process, for example, a bandpass filter of 0.5 to 5.0 Hz is used. As a result, the acquisition unit 11 extracts data (pulse wave data) corresponding to the user's pulse wave. The pulse wave data indicates, for example, data corresponding to a velocity pulse wave. The pulse wave data may indicate data corresponding to, for example, an acceleration pulse wave or a volumetric pulse wave, and can be arbitrarily set according to the type and application of the sensor. Further, the filter range of the bandpass filter can be arbitrarily set according to the intended use.

The acquisition unit 11 performs differential processing on, for example, pulse wave data. For example, when the differential processing is performed on the pulse wave data corresponding to the velocity pulse wave, the acquisition unit 11 acquires the data (differential data) corresponding to the acceleration pulse wave. In the differentiation process, the differentiation may be performed twice in addition to the one-time differentiation.

The acquisition unit 11 performs division processing on, for example, the differential data. In the division process, for example, the differential data corresponding to the acceleration pulse wave of a plurality of cycles is divided into the data (divided data) corresponding to the acceleration pulse wave of each cycle. Therefore, the acquisition unit 11 can acquire a plurality of divided data by, for example, performing differential processing on one differential data. In the division process, the differential data can be divided into arbitrary cycles (for example, positive multiples of the cycles) depending on the application.

For example, in the division process, the amount of data in each of the divided data may be different. In this case, the acquisition unit 11 may specify the divided data having the smallest amount of data and reduce (trim) the amount of data with respect to the other divided data. As a result, the amount of data in each divided data can be unified, and the data in each divided data can be easily compared.

In addition to the above, for example, standardization processing may be performed on values corresponding to the time axis of the divided data. In the standardization process, for example, standardization is carried out in which the minimum value corresponding to the time axis is set to 0 and the maximum value is set to 1. This facilitates the comparison of the data in each divided data.

The acquisition unit 11 may calculate, for example, the average of a plurality of divided data for which the amount of data has been reduced or standardized, and use the divided data as the divided data.

The acquisition unit 11 performs standardization processing on the divided data. In the standardization process, standardized data (normalized data) is generated for the values corresponding to the amplitude. In the normalization process, for example, standardization is performed in which the minimum value of the amplitude is set to 0 and the maximum value of the amplitude is set to 1. The acquisition unit 11 acquires, for example, standardized data as evaluation data. In this case, as evaluation data, data corresponding to the acceleration pulse wave of the user is obtained.

In addition to sequentially performing each of the above-mentioned processes, the acquisition unit 11 does not have to perform the differential process, for example, as shown in FIG. 3 (c). In this case, as evaluation data, data corresponding to the velocity pulse wave of the user is obtained.

Further, the acquisition unit 11 may perform only a part of each of the above-described processes, for example. In this case, the acquisition unit 11 may acquire any of pulse wave data, differential data, divided data, trimmed divided data, and divided data in which values corresponding to the time axis are standardized as evaluation data. , Can be set arbitrarily according to the application.

<Generator 12>
The generation unit 12 refers to the database and generates an evaluation result including the characteristics of blood carbon dioxide (for example, the value of the partial pressure of carbon dioxide in blood) with respect to the evaluation data. The generation unit 12 refers to, for example, the classification information stored in the database, and calculates the characteristics of blood carbon dioxide with respect to the evaluation data. The generation unit 12 generates an evaluation result in which the characteristics of blood carbon dioxide are converted into a format that can be understood by the user by using, for example, a display format stored in advance in a storage unit 104 or the like.

For example, when the classification information includes a trained model, the generation unit 12 may refer to the trained model and generate a health condition result indicating the user's health condition associated with the evaluation data by including it in the evaluation result. Good. In this case, the reference data used in generating the trained model includes state information indicating the health state of the subject who measured the learning pulse wave. The status information includes detailed information on the subject's current and past health status, such as "health", "possible XX", "past experience of □□ disease", and the like.

The plurality of learning data used when generating the trained model may include, for example, only the input data and the reference data at the time of the subject's health. In this case, the evaluation result (health condition result) may indicate only the health condition of the user associated with the evaluation data is healthy or non-healthy. That is, when the evaluation data is similar to the learning data, "health" is shown as the health condition result, and when the evaluation data deviates from the learning data, "non-health" is shown as the health condition result. 12 may generate an evaluation result. The threshold value for classifying "health" and "non-health" can be arbitrarily set.

<Output unit 13>
The output unit 13 outputs the evaluation result. In addition to outputting the evaluation result to the display unit 109, the output unit 13 may output the evaluation result to, for example, a sensor 5.

<Memory unit 14>
The storage unit 14 retrieves various data such as a database stored in the storage unit 104 as needed. The storage unit 14 stores various data acquired or generated by the configurations 11 to 13 and 15 in the storage unit 104 as needed.

<Learning Department 15>
The learning unit 15 generates classification information using, for example, a plurality of learning data. The learning unit 15 may acquire new learning data, for example, and update the existing classification information.

<Communication network 3>
The communication network 3 is a known Internet network or the like in which the biometric information arithmetic unit 1, the server 4, and the sensor 5 are connected via a communication line. When the biometric information calculation system 100 is operated in a certain narrow area, the communication network 3 may be configured by a LAN (Local Area Network) or the like. Further, the communication network 3 may be composed of a so-called optical fiber communication network. Further, the communication network 3 is not limited to the wired communication network, but may be realized by a wireless communication network, and can be arbitrarily set according to the application.

The server 4 stores information sent via the communication network 3. The server 4 transmits the information accumulated via the communication network 3 to the biometric information arithmetic unit 1 based on the request from the biometric information arithmetic unit 1.

<Sensor 5>
The sensor 5 generates sensor data. The sensor 5 includes a detection unit 6, for example, as shown in FIG. 5A. The sensor 5 is mounted at a position where the pulse wave of the user can be detected via the detection unit 6, and is fixed to, for example, a wristband 55.

As the detection unit 6, a known detection device capable of detecting the pulse wave of the user is used. The detector 6 includes, for example, a strain sensor such as a fiber bragg grating (FBG) sensor, a gyro sensor, one or more electrodes for pulse wave signal measurement, a photoelectric volume pulse wave (PPG) sensor, a pressure sensor, and an optical detection module. At least one of the above is used. A plurality of detection units 6 may be arranged, for example.

The sensor 5 may be embedded in clothing. Further, the user who wears the sensor 5 may target not only humans but also pets such as dogs and cats, and may target livestock such as cows and pigs, and aquaculture of fish and the like.

As shown in FIG. 5B, for example, the sensor 5 includes an acquisition unit 50, a communication I / F 51, a memory 52, and a command unit 53, and each configuration is connected by an internal bus 54.

The acquisition unit 50 measures the pulse wave of the user via the detection unit 6 and generates sensor data. The acquisition unit 50 transmits, for example, the generated sensor data to the communication I / F 51 or the memory 52.

The communication I / F 51 transmits various data such as sensor data to the biometric information calculation device 1 and the server 4 via the communication network 3. Further, the communication I / F 51 is equipped with a line control circuit for connecting to the communication network 3, a signal conversion circuit for performing data communication with the biometric information arithmetic unit 1 and the server 4, and the like. The communication I / F 51 performs conversion processing on various instructions from the internal bus 54 and sends them to the communication network 3 side, and when data from the communication network 3 is received, the communication I / F 51 performs a predetermined conversion processing on the conversion processing. Is applied and transmitted to the internal bus 54.

The memory 52 stores various data such as sensor data transmitted from the acquisition unit 50. The memory 52 transmits various data such as stored sensor data to the communication I / F 51 by receiving a command from another terminal device connected via the communication network 3, for example.

The command unit 53 includes an operation button, a keyboard, and the like for acquiring sensor data, and includes, for example, a processor such as a CPU. When the command unit 53 receives the command for acquiring the sensor data, the command unit 53 notifies the acquisition unit 50 of this. Upon receiving this notification, the acquisition unit 50 acquires the sensor data. The command unit 53 may perform a process for acquiring evaluation data from the sensor data, for example, as shown in FIGS. 3 (b) and 3 (c).

Here, a case where an FBG sensor is used will be described as an example of acquiring sensor data.

The FBG sensor has a diffraction grating structure formed in one optical fiber at predetermined intervals. The FBG sensor is characterized in that, for example, the length of the sensor portion is 10 mm, the wavelength resolution is ± 0.1 pm, the wavelength range is 1550 ± 0.5 nm, the fiber diameter is 145 μm, and the core diameter is 10.5 μm. Using the FBG sensor as the detection unit 6 described above, measurement can be performed in a state where the FBG sensor is in contact with the user's skin.

For example, as a light source used for an optical fiber, an ASE (Amplified Spontaneous Emission) light source having a wavelength range of 1525-1570 nm is used. The light emitted from the light source is incident on the FBG sensor via the circulator. The reflected light from the FBG sensor is guided to the Mach-Zehnder interferometer via the circulator, and the output light from the Mach-Zehnder interferometer is detected by the photodetector. The Mach-Zehnder interferometer is for splitting into two optical paths having different optical paths by a beam splitter and then superimposing them on one another by a beam splitter to generate interferometric light. In order to make an optical path difference, for example, the length of one optical fiber may be increased. Since coherent light produces interference fringes according to the optical path difference, it is possible to detect a change in distortion generated in the FBG sensor, that is, a pulse wave by measuring the pattern of the interference fringes. The acquisition unit 50 generates sensor data based on the detected pulse wave. As a result, sensor data is acquired.

The optical fiber sensor system that detects the amount of distortion of the FBG sensor and detects the waveform of the pulse wave is a means for using a wide band ASE light source, a circulator, and a Mach Zender interferometer, in addition to the light source incident on the FBG sensor. , An optical system such as a beam splitter, a light receiving sensor included in a light detector, and an analysis means for analyzing a wavelength shift amount. The optical fiber sensor system can be used by selecting a light source or band light according to the characteristics of the FBG sensor to be used, and various methods can be adopted as analysis means such as a detection method.

(Embodiment 1: Operation of biometric information calculation system 100)
Next, an example of the operation of the biometric information calculation system 100 in this embodiment will be described. FIG. 6 is a flowchart showing an example of the operation of the biometric information calculation system 100 in the present embodiment.

The biometric information calculation system 100 is executed, for example, via a biometric information calculation program installed in the biometric information calculation device 1. That is, the user operates the biometric information calculation device 1 or the sensor 5, and through the biometric information calculation program installed in the biometric information calculation device 1, the characteristics of blood carbon dioxide (for example, blood carbon dioxide content) from the sensor data. The evaluation result including the pressure value) can be obtained.

The operation of the biological information calculation system 100 includes acquisition means S110 and generation means S120, and may include output means S130, for example.

<Acquisition means S110>
The acquisition means S110 acquires evaluation data based on the user's pulse wave. For example, the acquisition unit 50 of the sensor 5 measures the pulse wave of the user via the detection unit 6 and generates sensor data. The acquisition unit 50 transmits the sensor data to the biometric information calculation device 1 via the communication I / F 51 and the communication network 3. The acquisition unit 11 of the biological information calculation device 1 receives the sensor data from the sensor 5.

The acquisition unit 11 executes the process shown in FIG. 3B, for example, on the sensor data and acquires the evaluation data. The acquisition unit 11 stores the acquired evaluation data in the storage unit 104, for example, via the storage unit 14. Conditions such as the frequency with which the acquisition unit 11 acquires sensor data from the sensor 5 can be arbitrarily set according to the application.

<Generation means S120>
Next, the generation means S120 refers to the database and generates an evaluation result including the characteristics of blood carbon dioxide (for example, the value of the partial pressure of carbon dioxide in blood) with respect to the evaluation data. For example, the generation unit 12 refers to the classification information and calculates the value of the partial pressure of carbon dioxide in the blood with respect to the evaluation data. The generation unit 12 generates an evaluation result including the calculated value. The generation unit 12 stores the generated evaluation result in the storage unit 104, for example, via the storage unit 14. In addition to showing a specific value as the value of the partial pressure of carbon dioxide in blood, for example, an error range (for example, "○○ ± 2 mmHg") may be calculated.

For example, the generation unit 12 may calculate the value of the partial pressure of carbon dioxide in blood for a plurality of evaluation data having different measurement times, and include each value in the evaluation result. In this case, the user or the like can easily grasp the change over time, the average value, etc. of the partial pressure of carbon dioxide in the blood.

<Output means S130>
Next, for example, the output means S130 may output the evaluation result. For example, the output unit 13 outputs the evaluation result to the display unit 109.

As a result, the operation of the biometric information calculation system 100 is completed. The frequency and order of performing each step can be arbitrarily set according to the application.

According to the present embodiment, the generation means S120 refers to the database and generates an evaluation result including the characteristics of blood carbon dioxide with respect to the evaluation data. In addition, the database stores classification information calculated using a plurality of learning data. Therefore, when generating the evaluation result, it is possible to include quantitative characteristics of blood carbon dioxide based on past proven data (input data and characteristics of blood carbon dioxide). This makes it possible to improve the evaluation accuracy.

Further, according to the present embodiment, the generation means S120 can refer to the trained model and include the health condition result associated with the evaluation data in the evaluation result and generate it. Therefore, the health condition based on the characteristics of blood carbon dioxide can be notified to the user, and the health condition can be easily grasped as compared with the case where only the characteristics of blood carbon dioxide are notified. it can. This makes it possible to improve convenience for the user.

Further, according to the present embodiment, the plurality of learning data includes only the input data and the reference data at the time of the subject's health, and the health condition result indicates whether the user's health condition associated with the evaluation data is healthy. Indicates whether or not. Therefore, even when the input data based on the learning pulse wave at the time of unhealthy state and the characteristics of carbon dioxide in the blood cannot be prepared, it is possible to generate a result showing the health condition of the user. As a result, it is possible to further improve the convenience for the user without increasing the difficulty level when generating the classification information.

Further, according to the present embodiment, the classification information is a calibration model obtained by using PLS regression analysis with the input data as the explanatory variable and the reference data as the objective variable. Therefore, the number of learning data can be significantly reduced and the calibration model can be easily updated as compared with the case where the classification information is calculated by using machine learning or the like. This makes it possible to facilitate the construction and update of the biometric information calculation system 100.

(Second Embodiment: Biological Information Calculation System 100)
Next, an example of the biometric information calculation system 100 according to the second embodiment will be described. The difference between the above-described embodiment and the second embodiment is that preliminary evaluation data based on pulse waves is acquired. The description of the same contents as those of the above-described embodiment will be omitted.

As shown in FIG. 7, for example, the biological information arithmetic unit 1 in the present embodiment performs two types of processing on one sensor data generated based on the pulse wave. As a result, the biometric information calculation device 1 acquires the evaluation data and preliminary evaluation data different from the evaluation data. A plurality of preliminary evaluation data may be acquired.

The biological information calculation device 1 calculates biological information for preliminary evaluation data, and generates, for example, a preliminary evaluation result including biological information. For example, the biological information arithmetic unit 1 can output a preliminary evaluation result in addition to the evaluation result. For example, in the biometric information calculation device 1, the evaluation result may include biometric information.

As biological information, for example, at least one of pulse rate and respiratory rate can be calculated. In this case, for example, as shown in FIGS. 8A and 8B, the content of the preprocessing performed by the acquisition means S110 and the content of the database referenced by the generation means S120 may differ. Hereinafter, an example of calculating the pulse rate and the respiratory rate as biological information will be described.

<Calculation of pulse rate>
For example, when calculating the pulse rate, as shown in FIG. 8A, the acquisition unit 11 performs the above-mentioned filter processing on the sensor data and extracts the pulse wave data.

Then, the acquisition unit 11 performs a peak position calculation process on the pulse wave data. In the peak position calculation process, a plurality of peaks (maximum amplitude values) included in the pulse wave data are detected, and the sampling order (corresponding to the time from the start of measurement) is specified. As a result, the acquisition unit 11 acquires the peak position data included in the pulse wave data.

After that, the acquisition unit 11 performs a peak interval average calculation process on the peak position data. In the peak interval average calculation process, the interval between peaks included in the peak position data (difference in the order in which adjacent peaks are sampled) is calculated, and for example, the average value of the peak intervals is calculated. After that, the acquisition unit 11 divides the peak interval or the average value of the peak intervals by the sampling rate of the sensor data, and acquires data indicating the peak interval corresponding to the number of seconds as preliminary evaluation data.

After that, the generation unit 12 refers to the database and calculates the pulse rate with respect to the preliminary evaluation data. At this time, the generation unit 12 refers to the pulse rate classification information stored in the database. The pulse rate classification information shows, for example, a function of dividing 60 [seconds] by the peak interval. Therefore, the generation unit 12 can calculate, for example, the pulse rate (= 71 [bpm]) for the preliminary evaluation data (peak interval = 0.85 [seconds]). As a result, the generation unit 12 can generate an evaluation result or a preliminary evaluation result including the pulse rate.

<Calculation of respiratory rate>
For example, when calculating the respiratory rate, as shown in FIG. 8B, the acquisition unit 11 performs the above-mentioned filter processing on the sensor data and extracts the pulse wave data.

After that, the acquisition unit 11 performs a Fourier transform process on the pulse wave data. In the Fourier transform process, for example, pulse wave data indicating sampling time vs. amplitude is converted into frequency data indicating frequency vs. intensity. As a result, the acquisition unit 11 acquires frequency data with respect to the pulse wave data.

After that, the acquisition unit 11 performs the maximum frequency detection process on the frequency data. In the maximum frequency detection process, the frequency having the maximum intensity between 0.15 and 0.35 Hz is specified in the frequency data. As a result, the acquisition unit 11 acquires the value of the specified frequency as preliminary evaluation data.

After that, the generation unit 12 refers to the database and calculates the respiratory rate for the preliminary evaluation data. At this time, the generation unit 12 refers to the respiratory rate classification information stored in the database. The respiratory rate classification information indicates, for example, a function of multiplying the specified frequency by 60 [seconds]. Therefore, the generation unit 12 can calculate, for example, the respiratory rate (= 13.5 [bpm]) for the preliminary evaluation data (specified frequency = 0.225 Hz). As a result, the generation unit 12 can generate an evaluation result or a preliminary evaluation result including, for example, the respiratory rate.

As described above, in the biometric information calculation device 1, the preprocessing for the sensor data can be set according to the content of the biometric information included in the preliminary evaluation result, and the content of the database to be referred to can be arbitrarily set.

In addition to the above-mentioned pulse rate and respiratory rate, information that can be calculated based on pulse waves, such as stress, blood glucose level, blood pressure, oxygen saturation, blood vessel age, and degree of diabetes, should be used as biological information. Can be done.

Further, the preliminary classification information used for the calculation may be stored in the database in advance according to the content of the biological information to be calculated. In this case, a plurality of pairs of preliminary input data indicating the above-mentioned learning pulse wave and preliminary reference data including biometric information associated with the preliminary input data are prepared as preliminary learning data. Then, for example, the learning unit 15 generates preliminary classification information using a plurality of preliminary learning data and stores it in the database.

The biometric information included in the preliminary reference data can be acquired by measuring the subject using a measuring device for measuring the necessary biometric information, as in the case of the reference information described above. .. Further, as the method for learning the preliminary classification information, the same method as the above-mentioned classification information can be used.

In addition to the above, the biometric information calculation device 1 can generate and output a comprehensive evaluation result based on the evaluation result and the preliminary evaluation result, as shown in FIG. 9, for example. Therefore, in the biometric information calculation system 100, the preliminary evaluation result generated from a viewpoint different from the evaluation result can be used, and a multifaceted evaluation can be performed.

The biometric information calculation device 1 may acquire evaluation data and preliminary evaluation data from the sensor data by, for example, performing the two types of processing shown in FIGS. 3 (b) and 3 (c). That is, when the data corresponding to the acceleration pulse wave of the user is obtained as the evaluation data, the data corresponding to the velocity pulse wave of the user is obtained as the preliminary evaluation data. In this case, more accurate evaluation can be realized by using the evaluation result generated for the evaluation data and the preliminary evaluation result generated for the preliminary evaluation result.

According to the present embodiment, in addition to the effects of the above-described embodiment, the generation means S120 refers to the database and generates a preliminary evaluation result including the biometric information of the user with respect to the preliminary evaluation data. Therefore, the preliminary evaluation result generated from a viewpoint different from the evaluation result can be used, and a multifaceted evaluation can be performed. This makes it possible to realize an appropriate evaluation according to the user's request.

Further, according to the present embodiment, the generation means S120 includes referring to the preliminary classification information and generating a preliminary evaluation result for the preliminary evaluation data. Therefore, it is possible to use the preliminary evaluation result generated by referring to the information different from the evaluation result, and it is possible to carry out a more multifaceted evaluation. This makes it possible to easily realize an appropriate evaluation according to the user's request.

(Third Embodiment: Biological information calculation system 100)
Next, an example of the biometric information calculation system 100 according to the third embodiment will be described. The difference between the above-described embodiment and the third embodiment is that the classification information suitable for the evaluation data is selected from the plurality of classification information. The description of the same contents as those of the above-described embodiment will be omitted.

As shown in FIG. 10, for example, the biological information calculation device 1 in the present embodiment refers to preliminary evaluation data and selects (selects) specific classification information (for example, first classification information) from a plurality of attribute-specific classification information. means). In addition, the biological information calculation device 1 refers to the selected first classification information, calculates the characteristics of blood carbon dioxide with respect to the evaluation data (for example, the value of the partial pressure of carbon dioxide in blood), and generates an evaluation result (attribute). Another generation means).

The plurality of attribute-based classification information is calculated using different learning data. For example, when data corresponding to the acceleration pulse wave of the subject is used as the input data of the learning data, input data is prepared for each of the seven types (A to G) as shown in FIG. 11, and seven types of attributes are prepared. Generate classification information.

When such a plurality of attribute-based classification information is stored in the database, for example, the acquisition unit 11 acquires the evaluation data corresponding to the acceleration pulse wave of the user and the preliminary evaluation data. Then, the generation unit 12 refers to the preliminary evaluation data and selects the first classification information. After that, the generation unit 12 refers to the first classification information and calculates the characteristics of blood carbon dioxide (for example, the value of blood carbon dioxide partial pressure) with respect to the evaluation data. Therefore, it is possible to select the most suitable classification information for the user from each attribute classification information.

For example, when data corresponding to the velocity pulse wave of the subject is used as the input data of the learning data, the input data is prepared for each of the two types (group 1 and group 2) as shown in FIG. 12, for example. Two types of attribute classification information may be generated.

Here, while the data corresponding to the acceleration pulse wave shown in FIG. 11 can be easily classified in detail based on the characteristics, there is a concern that the accuracy may decrease due to erroneous detection of peaks when calculating the characteristics of blood carbon dioxide. Is listed as. Further, the data corresponding to the velocity pulse wave shown in FIG. 12 is more difficult to classify in detail based on the characteristics than the data corresponding to the acceleration pulse wave, but since there are few false detections of peaks and the like, carbon dioxide in blood Features can be calculated with high accuracy.

Based on the above, the plurality of attribute classification information includes data corresponding to the acceleration pulse wave as shown in FIG. 11, as selection data used for selecting specific classification information, and when generating the attribute classification information. Data corresponding to the velocity pulse wave may be used as the training data of.

In this case, as the acquisition means S110, for example, the acquisition unit 11 acquires data corresponding to the velocity pulse wave as evaluation data from the sensor data based on the user's pulse wave. Further, the acquisition unit 11 acquires data corresponding to the acceleration pulse wave as preliminary evaluation data from the sensor data.

Next, as a selection means, for example, the generation unit 12 refers to the preliminary evaluation data, and among the plurality of selection data including the data corresponding to the acceleration pulse wave, the selection data most similar to the preliminary evaluation data (first). The selection data) is specified, and the first classification information associated with the first selection data is selected. Then, as the attribute-based generation means, the generation unit 12 refers to the first classification information and generates the evaluation result for the evaluation data. This makes it possible to further improve the evaluation accuracy.

Here, an example of data used for the above-mentioned selection data and the like will be described.

For example, as shown in FIG. 11, the acceleration pulse wave has inflection points a to e. For example, the maximum peak in the acceleration pulse wave is set to point a, each inflection point is set to point b, c, d, and e in order from point a, point a is set to 1, and the minimum value is point b or d. When standardization is performed with the points set to 0, the acceleration pulse wave can be classified into 7 patterns by using a method of classifying by the value of each inflection point and the magnitude relation of the difference. First, when the value of the inflection point is b <d, it is classified into pattern A or B. If b <d and c ≧ 0.5, it is classified as A, otherwise it is classified as B. Next, when the value of the inflection point is b≈d, it is classified into pattern C or D. If b≈d and c≈0, it is classified into pattern D, and if not, it is classified into pattern C. Finally, when b> d, it can be classified into any of patterns E, F, and G. If b> d and b <c, it is classified into pattern E, if b≈c, it is classified into pattern F, and if b> c, it is classified into pattern G.

For example, the generation unit 12 determines which pattern in FIG. 11 the preliminary evaluation data applies to, and specifies the first selection data. For example, if the inflection point b of the input preliminary evaluation data is smaller than the inflection point d and the inflection point c ≧ 0.5, the pattern A is set as the first selection data. This makes it possible to accurately calculate the characteristics of blood carbon dioxide by referring to the classification information suitable for the characteristics of the evaluation data.

According to the present embodiment, in addition to the effects of the above-described embodiment, the generation means S120 refers to the preliminary evaluation data and refers to the selection means for selecting the first classification information and the first classification information with respect to the evaluation data. Includes attribute-based generation means for generating evaluation results. Therefore, it is possible to generate the evaluation result for the evaluation data after selecting the optimum attribute classification information for the characteristics of the pulse wave. This makes it possible to further improve the evaluation accuracy.

Further, according to the present embodiment, the acquisition means S110 acquires data corresponding to a velocity pulse wave based on the pulse wave as evaluation data. Further, the preliminary acquisition means acquires data corresponding to the acceleration pulse wave based on the pulse wave as preliminary evaluation data. Therefore, the attribute classification information can be selected by using the acceleration pulse wave, which makes it easier to classify the characteristics of the pulse wave than the velocity pulse wave. In addition, the evaluation result can be generated by using the velocity pulse wave, which is easier to calculate the characteristics of blood carbon dioxide than the acceleration pulse wave. This makes it possible to further improve the evaluation accuracy.

In each of the above-described embodiments, the case where the value of the partial pressure of carbon dioxide in blood is mainly used as the characteristic of carbon dioxide in blood has been described, but the dissolved concentration of carbon dioxide in blood and the bicarbonate contained in blood have been described. -Since the same applies to the case where at least one of the concentration of bicarbonate and the pH of blood is used, the description thereof will be omitted. In particular, when the value of the partial pressure of carbon dioxide in blood is used as a characteristic of carbon dioxide in blood, it tends to be easier to collect reference information than other values. Therefore, it is possible to realize a significant reduction in the time and cost required for generating the classification information.

Although embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. Such a novel embodiment can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. This embodiment and its modifications are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

1: Biological information arithmetic unit 3: Communication network 4: Server 5: Sensor 6: Detection unit 10: Housing 11: Acquisition unit 12: Generation unit 13: Output unit 14: Storage unit 15: Learning unit 50: Acquisition unit 51: Communication I / F
52: Memory 53: Instruction unit 54: Internal bus 55: Wristband 100: Biometric information calculation system 101: CPU
102: ROM
103: RAM
104: Preservation unit 105: I / F
106: I / F
107: I / F
108: Input unit 109: Display unit 110: Internal bus S110: Acquisition means S120: Generation means S130: Output means

Claims (8)

A biometric information calculation system that outputs information about the characteristics of carbon dioxide in the user's blood.
An acquisition means for acquiring evaluation data based on the user's pulse wave, and
A pair of input data based on a learning pulse wave acquired in advance and reference data including characteristics of blood carbon dioxide associated with the input data are used as learning data, and are generated by using a plurality of the learning data. A database that stores classification information and
With reference to the database, a generation means for generating an evaluation result including the characteristics of the blood carbon dioxide with respect to the evaluation data, and
A biometric information calculation system characterized by being equipped with. The reference data includes state information indicating the health state of the subject who measured the learning pulse wave.
The classification information includes a trained model generated by machine learning using the plurality of the training data.
The generation means is characterized in that it refers to the trained model and includes and generates a health condition result indicating the health condition of the user associated with the evaluation data in the evaluation result. 1 The biometric information calculation system according to 1. The plurality of learning data include only the input data and the reference data at the time of the subject's health.
The biometric information calculation system according to claim 2, wherein the health state result indicates that the health state of the user associated with the evaluation data is healthy or non-healthy. The biometric information calculation system according to claim 1, wherein the classification information is a calibration model obtained by using PLS regression analysis using the input data as an explanatory variable and the reference data as an objective variable. The acquisition means includes acquiring preliminary evaluation data different from the evaluation data based on the pulse wave.
The biometric information calculation system according to claim 1, wherein the generation means includes referring to the database and calculating biometric information of the user with respect to the preliminary evaluation data. In the database, a pair of preliminary input data based on the learning pulse wave and a pair of preliminary reference data including the biological information associated with the preliminary input data are used as preliminary learning data, and a plurality of the preliminary learning data are used. Preliminary classification information generated in
The biometric information calculation system according to claim 5, wherein the generation means includes referring to the preliminary classification information and calculating the biometric information with respect to the preliminary evaluation data. The acquisition means includes acquiring preliminary evaluation data different from the evaluation data based on the pulse wave.
The classification information includes a plurality of attribute-specific classification information calculated using the different learning data.
The generation means
With reference to the preliminary evaluation data, a selection means for selecting the first classification information from the plurality of attribute-specific classification information, and
The biometric information calculation system according to claim 1, further comprising an attribute-based generation means for generating the evaluation result for the evaluation data with reference to the first classification information. The acquisition means
Data corresponding to the velocity pulse wave based on the pulse wave is acquired as the evaluation data, and the data is obtained.
The biometric information calculation system according to claim 7, wherein data corresponding to an acceleration pulse wave based on the pulse wave is acquired as the preliminary evaluation data.

Images