Feature extraction device, state estimation device, feature extraction method, state estimation method, and program

Abstract

A feature amount of a biological signal suitable for estimating the state of a subject is extracted, and the state of the subject is estimated with high accuracy based on the feature amount extracted in this way. [Solution] The feature extraction device includes a biosignal acquisition unit (110) that acquires a target biosignal, a time window setting unit (120) that sets multiple time windows of different time lengths as multiple extraction time windows within a certain period of time while the biosignal is being acquired, and a feature extraction unit (130) that extracts features of the biosignal in each of the multiple extraction time windows.

Description

[Technical field]

[0001] The present invention relates to a feature extraction device, a state estimation device, a feature extraction method, a state estimation method, and a program. [Background technology]

[0002] Conventionally, a device disclosed in Patent Document 1 is known as a device for estimating a state of a target. This conventional device is configured to estimate a person's sleep state, and includes a sensor made of a piezoelectric element attached to the person's chest. In addition, in the conventional device, a predetermined determination unit time (hereinafter referred to as "epoch") is set in the person's respiratory waveform data detected by the sensor, and multiple feature amounts such as the peak-to-peak difference of the respiratory waveform data are extracted for each epoch, and the extracted feature amounts are used to estimate which of the three stages of the person's sleep state is, "wakefulness," "light sleep," or "deep sleep." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-217130 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the above-mentioned conventional device, multiple features are extracted for each specified epoch, so it is not possible to extract features suitable for estimating the state of a subject, such as the subject's (person's) sleeping state, and as a result, there is a risk that it is not possible to accurately estimate a person's sleeping state.

[0005] The present invention has been made in consideration of the above, and has a first object to provide a feature extraction device, a feature extraction method, and a program capable of extracting features of a biological signal suitable for estimating the state of a target, and a second object to provide a state estimation device, a state estimation method, and a program capable of accurately estimating the state of a target based on the features thus extracted. [Means for solving the problem]

[0006] In order to achieve the first object, a feature extraction device according to the present invention comprises: An acquisition means for acquiring a biological signal of a subject; A setting means for setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; For the same biological signal being acquired, In each of the plurality of extraction time windows Special An extraction means for extracting a trace amount; Equipped with The setting means sets at least both a first layer in which a plurality of extraction time windows having a first time length for extracting macroscopic features are provided so as to partially overlap each other on a time axis, and a second layer in which a plurality of extraction time windows having a second time length shorter than the first time length for extracting microscopic features are provided so as not to overlap each other on a time axis. death , The extraction means extracts the same feature amount in at least both an extraction time window corresponding to the first layer and an extraction time window corresponding to the second layer. Characterized by 。

[0007] In order to achieve the second object, a state estimation device according to the present invention comprises: The feature extraction device, an estimation means for estimating a state of the object based on the feature extracted by the feature extraction device; Equipped with. Effect of the Invention

[0008] According to the present invention, it is possible to extract features of a biological signal suitable for estimating the condition of a subject, and to accurately estimate the condition of the subject based on the features thus extracted. [Brief description of the drawings]

[0009] [Figure 1] 1 is a diagram showing a mechanical configuration of a state estimating device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram illustrating a functional configuration of a state estimating device according to an embodiment of the present invention. [Diagram 3] 5A and 5B are diagrams showing detected waveforms of a pulse wave sensor according to an embodiment of the present invention. [Figure 4] 4 is a flowchart showing a sleep state estimation process according to an embodiment of the present invention. [Diagram 5] 4 is a flowchart showing a biological signal acquisition process according to an embodiment of the present invention. [Figure 6] FIG. 4 is a diagram showing an example of an estimated heartbeat interval according to an embodiment of the present invention. [Figure 7] 4 is a flowchart showing a feature extraction process according to the embodiment of the present invention. [Figure 8] FIG. 13 is a diagram showing an example of resampling of heartbeat intervals according to an embodiment of the present invention. [Figure 9] 4 is a flowchart showing a frequency system feature extraction process according to the embodiment of the present invention. [Figure 10] 1 is a diagram illustrating an extraction time window used to extract a data string according to an embodiment of the present invention. FIG. [Figure 11] 1 is a flowchart showing a respiratory system feature extraction process according to an embodiment of the present invention. [Figure 12] 4 is a flowchart showing a time system feature extraction process according to an embodiment of the present invention. [Figure 13] FIG. 4 illustrates an estimation unit according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A feature extraction device, a state estimation device, a feature extraction method, a state estimation method, and a program according to embodiments of the present invention will be described below with reference to the drawings.

[0011] (First embodiment) In this embodiment, an example will be described in which the sleep state of a human subject is estimated as the target state.

[0012] As shown in FIG. 1, the state estimation device 10 according to this embodiment physically comprises a control unit 11, a memory unit 12, a user interface 13, a communication unit 14, a pulse wave sensor 15, and a body movement sensor 16.

[0013] The control unit 11 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). The CPU is, for example, a microprocessor, and is a central processing unit that executes various processes and calculations. In the control unit 11, the CPU is connected to each part of the state estimation device 10 via a system bus, and functions as a control means that reads out a control program stored in the ROM and controls the operation of the entire state estimation device 10 while using the RAM as a work memory.

[0014] The storage unit 12 is a non-volatile memory such as a flash memory or a hard disk. The storage unit 12 stores programs and data used by the control unit 11 to perform various processes. For example, the storage unit 12 stores biological data to be used as teacher data, and a table that defines various settings for biological state estimation. The storage unit 12 also stores data generated or acquired by the control unit 11 performing various processes.

[0015] The user interface 13 includes an input receiving unit such as an input key, a button, a switch, a touch pad, a touch panel, etc., a display unit such as a liquid crystal panel, an LED (Light Emitting Diode), etc., a sound output unit such as a speaker, a buzzer, etc., a vibration unit such as a vibrator, etc. The user interface 13 receives various operation instructions from a user via the input unit, and transmits the received operation instructions to the control unit 11. The user interface 13 also obtains various information from the control unit 11, and displays an image indicating the obtained information on the display unit.

[0016] The communication unit 14 includes an interface for the state estimation device 10 to communicate with an external device. The external device is, for example, a terminal device such as a personal computer, a tablet terminal, or a smartphone. The communication unit 14 communicates with the external device via, for example, a universal serial bus (USB), a wireless local area network (LAN) such as wireless fidelity (Wi-Fi), Bluetooth (registered trademark), or the like. Under the control of the control unit 11, the communication unit 14 acquires various data including teacher data from the external device via such wired or wireless communication. The data may be stored in the storage unit 12 in advance.

[0017] Pulse wave sensor 15 detects a pulse wave, which is one of the biological signals of the subject. Pulse wave sensor 15 is attached, for example, to the tragus, arm, finger, etc. of the subject. Pulse wave sensor 15 detects changes in the amount of light absorbed by oxyhemoglobin in the blood by irradiating light onto the surface of the subject's skin and observing the reflected light and transmitted light. This change in the amount of light absorbed corresponds to a change in the volume of blood vessels, so pulse wave sensor 15 can obtain a pulse wave 201 that captures the change in the volume of blood vessels as a waveform, as shown in Figure 3.

[0018] Since the change in the volume of blood vessels is considered to be synchronized with the pulsation of the heart, the timing (time point) when the amplitude of the pulse wave peaks can be estimated as the timing when the heart pulsates (hereinafter referred to as the "pulse timing"). Also, the time interval between two peaks of the pulse wave adjacent to each other on the time axis can be estimated as the heartbeat interval (RR Interval, hereinafter referred to as the "RRI"). Therefore, the control unit 11 can estimate the heartbeat interval based on the pulse wave detected by the pulse wave sensor 15. The pulsation timing can be estimated, for example, using a timer (or clock) of the CPU or a sampling frequency of the pulse wave, but it may be estimated by other appropriate methods. In FIG. 3, the timing when the pulse wave 201 peaks corresponds to the pulsation timings 201t, 202t, and 203t, and the interval between the peaks of the pulse wave 201 corresponds to the heartbeat intervals 202i and 203i. In this embodiment, an example in which the pulse wave (heartbeat) is detected by LED light will be described. Of course, the electrical signal of the heart may be detected directly.

[0019] The body motion sensor 16 is an acceleration sensor that detects acceleration in three mutually orthogonal axial directions of the X, Y and Z axes as the body motion of the subject. The body motion sensor 16 is attached to the tragus of the subject, for example. Alternatively, a gyro sensor, a piezoelectric sensor, or the like may be used as the body motion sensor 16.

[0020] Next, the functional configuration of the control unit 11 in the state estimation device 10 will be described with reference to FIG. 2. As shown in FIG. 2, the state estimation device 10 functionally includes a biosignal acquisition unit 110 which is an acquisition means for acquiring a biosignal of a subject, a time window setting unit 120 which is a setting means for setting an extraction time window for extracting a feature from the biosignal acquired by the biosignal acquisition unit 110, a feature extraction unit 130 which is an extraction means for extracting a feature from the biosignal within the range of the extraction time window set by the time window setting unit 120, and an estimation unit 140 which is an estimation means for estimating a sleep state based on the extracted feature. In the control unit 11, the CPU reads a program stored in the ROM into the RAM and executes it, thereby functioning as each of these units. Note that the portion of the state estimation device 10 excluding the estimation unit forms a feature extraction device according to the first embodiment.

[0021] Next, each function of the state estimation device 10 will be described together with the process flow of the sleep state estimation process with reference to Fig. 4. When the state estimation device 10 is booted, this sleep state estimation process starts. Alternatively, the state estimation device 10 may start the sleep state estimation process upon receiving an instruction from a user via an input unit. First, the biosignal acquisition unit 110 of the state estimation device 10 executes the biosignal acquisition process (step S101).

[0022] 5 shows a flowchart of this biological signal acquisition process. First, biological signal acquisition unit 110 acquires a pulse wave signal from pulse wave sensor 15 and a body movement signal from body movement sensor 16 (step S201). The pulse wave signal acquired from pulse wave sensor 15 is sampled at a certain frequency (e.g., 250 Hz), and the sampled pulse wave signal is filtered by a pre-filter consisting of a band-pass filter to remove low-frequency components and high-frequency noise (step S202). Next, the RRI is calculated (estimated) from the filtered pulse wave signal (step S203).

[0023] As methods for calculating the RRI, there are various methods such as a method using a correlation function, a method using a fast Fourier transform (FFT), and a method for calculating based on detection of the maximum value of the amplitude. For example, when calculating the RRI based on detection of the maximum value of the amplitude, the maximum value of the amplitude is detected from the pulse wave signal, and it is compared with a plurality of other detected maximum values of the amplitude within a predetermined time before and after the timing at which the maximum value of the amplitude is detected. As a result of the comparison, the timing at which the maximum value of the largest amplitude is detected is estimated as the pulsation timing. Such comparison is performed for each maximum value of the amplitude of the pulse wave signal, and the time interval between two pulsation timings adjacent to each other on the time axis is calculated as the RRI. When the calculated RRIs are arranged with time on the horizontal axis and RRI on the vertical axis, a graph as shown in FIG. 6 is obtained. In FIG. 6, the interval between two adjacent pulsation timings (such as 202t) corresponds to the RRI, and an example is shown in which the pulsation originally existing between the pulsation timing 204t and the pulsation timing 205t could not be calculated.

[0024] When the RRI is calculated, an outlier process for removing outliers (abnormal values) of the RRI is performed (step S204). The outlier process is performed, for example, as follows. The entire section of the calculated RRI is divided at regular intervals (for example, 2 sec), and the standard deviation of each divided section is calculated. If the calculated standard deviation is less than a predetermined threshold value, the RRI of that section is regarded as an outlier and removed. Also, it is determined whether the RRI is within a predetermined range where it is normally expected (for example, 0.4 sec < RRI < 2.0 sec). If the RRI is not within this predetermined range, it is considered that the inter-beat interval at rest is not satisfied, and the RRI of that section is regarded as an outlier and removed. Further, it is determined whether the difference between adjacent RRIs exceeds a predetermined value (for example, 0.3 sec). If the difference between adjacent RRIs exceeds this value, since a rapid change in the inter-beat interval is unlikely, both of the adjacent RRIs are regarded as outliers and removed. The heart rate interval 205i in the figure is removed as an outlier (abnormal value).

[0025] Next, the biological signal acquiring unit 110 samples the body motion signal acquired in step S201, i.e., the acceleration in the three axial directions of the X, Y and Z axes, at a certain sampling rate (e.g., 30 Hz), and then resamples it at a lower sampling rate (e.g., 2 Hz) to acquire acceleration time series data, and calculates the magnitude (norm) of the resultant vector of the acceleration in the X, Y and Z axial directions from the acquired acceleration data (step S205). Although not shown, the calculated norm of the resultant vector is filtered by a band-pass filter to remove noise. In this case, the pass band of the band-pass filter is set to, for example, 0.05 Hz to 0.25 Hz.

[0026] 4, when the biosignal acquiring unit 110 finishes the biosignal acquiring process, the feature extracting unit 130 performs a feature extracting process for extracting feature values ​​from the RRI and acceleration norm calculated by the biosignal acquiring unit 110 (step S102). The feature values ​​are extracted according to the extraction time window set by the time window setting unit 120.

[0027] The feature extraction unit 130 extracts, as features, a frequency-based feature that is a feature based on the frequency of the RRI, a respiratory-based feature that is a feature based on the respiratory signal extracted from the RRI, and a time-based feature that is a feature based on the time of the RRI and the acceleration norm. These features can be regarded as feature of the pulse wave signal because the RRI is based on the subject's pulse wave signal, and the time-based feature can be regarded as feature of the body movement signal because the acceleration norm is based on the subject's body movement signal. The feature extraction process performed in step S102 will be described in order according to the flowchart in FIG.

[0028] When the RRI is calculated, the feature extraction unit 130 performs a process of generating equally-spaced RRI by adjusting the irregularity of the sampling intervals due to the fluctuation of the RRI as a pre-processing of the feature extraction (step S301). By making the sampling intervals equal, FFT processing performed for feature extraction becomes possible. For example, as shown in FIG. 8, the RRI after removing outliers is linearly interpolated (spline interpolation etc. is also possible) to obtain a dotted line 200, and the values ​​on the interpolated dotted line 200 are resampled at a resampling frequency (2 Hz) set to the same value as the sampling frequency of the body movement signal of the body movement sensor 16, that is, every 0.5 seconds, as in points 211, 212, ..., 223, to make the sampling intervals equal. As a result, a data string of equally-spaced RRI is generated.

[0029] After completing the pre-processing in step S301, the feature extracting section 130 performs various feature extraction processes for extracting the frequency system feature amounts, the respiratory system feature amounts, and the time system feature amounts described above (step S302).

[0030] 9 shows a frequency system feature extraction process for extracting frequency system features among various feature extraction processes executed in step S302. First, an overview of this frequency system feature extraction process will be described. In the frequency system feature extraction process, the data string rdata[i] of the equally-spaced RRI extracted by each extraction time window described later is subjected to FFT processing for frequency analysis, and the distribution of the power spectrum in frequency is calculated. From the distribution of the power spectrum, the power spectrum of the low frequency band and the power spectrum of the high frequency band are obtained, and multiple parameters based on these power spectra are extracted as features.

[0031] The power spectrum of the low frequency band lf (e.g., 0.01 Hz to 0.15 Hz) mainly represents the activation state of the sympathetic nerves, and the larger the power spectrum of the low frequency band lf, the more active the subject's sympathetic nerves are. Also, the power spectrum of the high frequency band hf (e.g., 0.15 Hz to 0.5 Hz) mainly represents the activation state of the parasympathetic nerves, and the larger the power spectrum of the high frequency band hf, the more active the subject's parasympathetic nerves are.

[0032] The sympathetic and parasympathetic nerves have a certain correlation with the state of sleep. A person's sleep state can be classified into stages such as wakefulness, REM sleep, and non-REM sleep. Non-REM sleep can be further classified into stages such as light sleep and deep sleep. During non-REM sleep, the sympathetic nerves are at rest and pulse slows down. In contrast, during REM sleep, the sympathetic nerves are active to the same extent as when awake, and pulse speeds faster than during non-REM sleep. Therefore, the sleep state can be estimated using the power spectrum of the low frequency band lf and the power spectrum of the high frequency band hf of the equidistant RRI.

[0033] As shown in FIG. 9, in the frequency system feature extraction process, first, an extraction time window for performing the above-mentioned FFT process is set (step S401). The time window setting unit 120 sets an extraction time window, which is a section for extracting features from the RRI and acceleration norm acquired by the biological signal acquisition unit 110. In polysomnography (PSG), sleep states are estimated in epoch units, which are a fixed time. An epoch of 30 seconds is often selected. In accordance with this, the extraction time window is set while shifting it by 30 seconds on the time axis, and the feature of the RRI within the set extraction time window is extracted. The extraction time window is set in multiple stages, such as a long-time window for extracting global features, a short-time window for extracting instantaneous features, and intermediate windows between these. By configuring in this way, various features can be acquired.

[0034] FIG. 10 shows an extraction time window set at a reference time t of an epoch. The horizontal axis represents the time axis, and extraction time windows having different periods from each other are set from layer 0 to layer 3 within a period of 256 sec (≈4 min) including a sample frequency of 2 Hz and 512 sample points, centered on the reference time t. Window 1, which is a period having a time length of 256 sec (≈4 min), is set in layer 0. Window 1 includes 2×256=512 sample points. Three extraction time windows, Window 2 to Window 4, which are periods having a time length of 128 sec (≈2 min), are set in layer 1. Window 2 to Window 4 are set at different positions on the time axis so that adjacent windows overlap by 64 sec (≈1 min). Therefore, window 3 is set at the center of the reference time t. Each extraction time window includes 256 sample points. Seven extraction time windows, Window 5 to Window 11, each having a time length of 64 sec (≈1 min), are set in Layer 2. Windows 5 to 11 are set at different positions on the time axis so that adjacent windows overlap by 32 sec. Therefore, Window 8 is set at the center of the reference time t. Each extraction time window includes 128 sample points. Eight extraction time windows, Window 12 to Window 19, each having a time length of 32 sec, are set in Layer 3. Windows 12 to 19 are set at different positions on the time axis so that they do not overlap with each other and are continuous with no gaps. Each extraction time window includes 64 sample points. Hereinafter, the data string extracted by each extraction time window from the data string of the uniformly spaced RRI is represented as rdata[p][i]. Note that p is the time window number and i is the sample number. In other words, p is a value from 1 to 19, and if the number of samples in each extraction time window used to extract the data string rdata[p][i] is n, then i is a value from 1 to n.

[0035] According to the extraction time window set in step S401, data for feature extraction is extracted (step S402). The extraction time window used varies depending on the feature to be extracted. FFT processing is performed on the data extracted according to the extraction time window (step S403). In the frequency system feature extraction processing, FFT processing is performed using all the extraction time windows (window 1 to window 19) from layer 0 to layer 3. FFT frequency analysis processing is performed on the data string rdata[p][i] of the equally-spaced RRI extracted in each extraction time window, and when the frequency power spectrum density is calculated, the feature of the RRI is extracted for each extraction time window (step S404). In this case, in order to determine the sleep state, the following nine feature amounts including the power spectrum of the low frequency band lf and the power spectrum of the high frequency band hf described above are extracted as the feature of the RRI. lf,hf,vlf,tf,hf_lfhf,lf_hf,vlf / tf,lf / tf,hf / tf Where: lf: Power spectrum greater than 0.01Hz and less than 0.15Hz hf: Power spectrum greater than 0.15Hz and less than 0.5Hz vlf: power spectrum below 0.01Hz tf:vlf+lf+hf hf_lfhf:hf / (hf+lf) lf_hf:lf / hf It is.

[0036] As described above, a total of 19 extraction time windows are set: 1 window for layer 0, 3 windows for layer 1, 7 windows for layer 2, and 8 windows for layer 3. Each extraction time window extracts 9 RRI features, so a total of 171 (= 9 × 19) dimensional RRI features are extracted.

[0037] Next, the respiratory system feature extraction process will be described among the various feature extraction processes executed in step S302 in Fig. 7. The respiratory system feature is a feature related to respiration as a biological signal. The RRI includes a respiratory fluctuation component, and fluctuations of about 0.25 Hz occur due to respiratory sinus arrhythmia (hereinafter referred to as "RSA"), which occurs when the heart rate decreases with exhalation and increases with inhalation. This RSA is used as the feature related to respiration.

[0038] FIG. 11 shows a respiratory system feature extraction process for extracting respiratory system features, which is executed in step S302 of FIG. 7. First, in step S501, an extraction time window is set. Next, data for feature extraction is extracted according to the extraction time window set in step S501 (step S502). FFT processing is performed on the data extracted according to the extraction time window (step S503). In this respiratory system feature extraction process, in step S501, three extraction time windows, window 2 to window 4, of layer 1 are set. Then, in steps S502 and S503, FFT frequency analysis processing is performed on the data strings (rdata[2][i], rdata[3][i], and rdata[4][i]) of the equally spaced RRI extracted in each extraction time window, and the frequency with the maximum power spectrum density in the range of 0.1 Hz to 0.4 Hz is obtained as RSA. After the RSA is obtained, extraction of features related to breathing is performed for each extraction time window (step S504). Since breathing is stable during non-REM sleep, the standard deviation is small. Conversely, during wakefulness and REM sleep, breathing is not stable, and the standard deviation is large. Therefore, from the breathing data contained in the equally-spaced RRI data string, the following six feature values ​​that are thought to be correlated with sleep are extracted.

[0039] For the RSA[j] obtained above (j corresponds to the extraction time window used for extraction (window 2: j=0, window 3: j=1, window 4: j=2)), mRSA:Average value of RSA[j] = (RSA[0] + RSA[1] + RSA[2]) / 3 sdRSA: Standard deviation of RSA[j] = Standard deviation obtained from RSA[0], RSA[1], and RSA[2] minRSA: The minimum value of RSA[j] = min(RSA[0],RSA[1],RSA[2]) maxRSA: maximum value of RSA[j] = max(RSA[0],RSA[1],RSA[2]) cvRSA: sdRSA / mRSA (However, if mRSA≒0, cvRSA=0) Coefficient of respiratory variation RSA[1]: RSA with window 3, the central extraction window In this respiratory system feature extraction process, six-dimensional features are extracted from three extraction time windows, Window 2 to Window 4.

[0040] Next, the time-based feature extraction process among the various feature extraction processes executed in step S302 in Fig. 7 will be described. The time-based feature extraction process includes an RRI-based feature extraction process that extracts features obtained from the equally-spaced RRI data sequence rdata[p][i] (time-series data) itself, and a body movement-based feature extraction process that extracts features obtained from the acceleration data sequence mdata[p][i] itself. This acceleration data sequence mdata[p][i] is the acceleration norm data sequence calculated in step S205 in Fig. 5, where p and i are the time window number and the sample number.

[0041] In the time-based feature extraction process, as shown in Fig. 12, after an extraction time window is set in step S601, data for feature extraction is extracted according to the set extraction time window (step S602). In the time-based feature extraction process, all extraction time windows (windows 1 to 19) from layer 0 to layer 3 are set. RRI-based features are extracted for the RRI data string rdata[p][i] extracted according to each extraction time window, and body motion-based features are extracted for the acceleration data string mdata[p][i] (step S603). The RRI-based features and body motion-based features are as follows:

[0042] (RRI-based features) As RRI-related features, the following six values ​​are calculated (derived): mRRI, mHR, sdRRI, cvRRI, RMSSD, and pNN50 for each extraction time window. Note that the unit of the value of rdata[p][i] is milliseconds, and each value is as follows: mRRI = average value of rdata[p][i] mHR=60000 / mRRI (Note: To calculate the number of beats per minute (mHR) from the mRRI in milliseconds, divide 60 seconds x 1000 = 60,000 by the mRRI.) sdRRI = standard deviation of rdata[p][i] cvRRI=sdRRI / mRRI RMSSD = Root mean square of the squared differences between adjacent rdata[p][i] pNN50 = The percentage of times that the difference between adjacent rdata[p][i] exceeds a given time (e.g. 50 msec). (Note: The rate at which the difference between successive adjacent heartbeat intervals exceeds 50 msec is considered to be an indicator of vagus nerve tone strength, so in this embodiment, 50 msec is used as the above-mentioned predetermined time.) The above six values ​​are obtained for each extraction time window, and since there are 19 extraction time windows, a total of 6 × 19 = 114 feature quantities are derived.

[0043] (Body movement feature) The magnitude and frequency of body movements measured by the acceleration sensor differ between awake and asleep states. The following five values, mACT, sdACT, minACT, maxACT, and cvACT, are derived as body movement feature quantities for each extraction time window. Each value is as follows: mACT: average value of mdata[p][i] sdACT: Standard deviation of mdata[p][i] minACT: The minimum value of mdata[p][i] maxACT: Maximum value of mdata[p][i] cvACT:sdACT / mACT The above five values ​​are obtained for each extraction time window, and since there are 19 extraction time windows, a total of 5 × 19 = 95 feature quantities are derived.

[0044] In addition to the above-mentioned feature quantities, the elapsed time from the occurrence of a large body movement may be extracted as a feature quantity. The body movement is expressed by the above-mentioned acceleration norm, and the average value mACT of the body movement is calculated for each reference time t. It is determined that a large body movement has occurred when mACT exceeds a predetermined threshold. Four different values ​​are set as the threshold value. The elapsed time is measured by counting one each time the next epoch reference time t is reached after the detection of a large body movement. The count values ​​are the count value after mACT last exceeded 1.05, the count value after mACT last exceeded 1.10, the count value after mACT last exceeded 1.15, and the count value after mACT last exceeded 1.20, and a four-dimensional feature quantity is extracted. Here, mACT=1.0 indicates that the subject is stationary, and the larger the value, the larger the subject's body movement.

[0045] Returning to FIG. 7, when each feature is calculated, a feature selection (dimensionality reduction) process is performed to reduce unnecessary features from these features (step S303). When using a machine learning model that uses features as input to estimate the sleep state of a subject, it is important to determine an effective combination of features. Some features may not only not contribute to the performance of the model, but may even have a negative effect. By selecting features, it is possible to reduce variables and improve interpretability, reduce computational costs and shorten learning time, and avoid overfitting to improve versatility. As a method of feature selection, for example, feature reduction is performed by analysis of variance (ANOVA) and recursive feature elimination (RFE). In RFE, a machine learning model is actually used to learn and evaluate a feature set to confirm which features are important, and features are eliminated until the specified number of features is reached.

[0046] When the features are reduced by the dimensionality reduction, a feature amount expansion process is performed in which the remaining features are moved forward (to the future) or backward (to the past) on the time axis and added as features (step S304). Note that the above-mentioned dimensionality reduction process (step S303) and feature amount expansion process (step S304) are not necessarily required to implement the present invention and may be omitted.

[0047] The feature quantity that has been subjected to the feature quantity expansion process is smoothed in the time direction by a pre-filter (step S305). The pre-filter is, for example, a Gaussian filter, and prevents unnatural data that changes suddenly from being input to the estimation unit 140, thereby preventing erroneous estimation of the sleep state. The extracted feature quantity is normalized between 0 and 1 and input to the estimation unit 140.

[0048] 4, when the feature amount extraction unit 130 extracts a plurality of feature amounts (frequency system feature amount, respiratory system feature amount, and time system feature amount), the estimation unit 140 estimates the sleep state based on the feature amounts extracted by the feature amount extraction unit 130 (step S103). This estimation of the sleep state is performed in 30-second intervals.

[0049] The estimation unit 140 is configured with a multi-class classifier that combines two-class classifiers. The classifier employs, for example, multi-class logistic regression. For example, it is possible to know which combination of explanatory variables (independent variables) that are feature quantities such as tf, vlf, lf, hf, hf_lfhf, lf_hf, vlf / tf, lf / tf, and hf / tf significantly affects a dependent variable (objective variable) that is divided into two classes, an [awake] class in which the subject's sleep state is an awake state, and an [other] class in which the subject's sleep state is a state other than an awake state. For the input feature quantity, the output is one of four outputs that indicate that the sleep state is an awake state (awake), a REM sleep state (rem), a light sleep state (light), and a deep sleep state (deep). For this reason, the estimation unit 140 is configured with a combination of four two-class classifiers, as shown in FIG. 13. That is, the estimation unit 140 includes a first classifier 301 that classifies whether the sleep state is an awake state [awake] or a state other than an awake state [other than awake], a second classifier 302 that classifies whether the sleep state is an REM sleep state [rem] or a state other than an REM sleep state [other than rem], a third classifier 303 that classifies whether the sleep state is a light sleep state [light] or a state other than a light sleep state [other than light], and a fourth classifier 304 that classifies whether the sleep state is a deep sleep state [deep] or a state other than a deep sleep state [other than deep], and also includes a score classifier 305 that scores the outputs of the first to fourth classifiers 301 to 304. In the logistic regression, the objective variable and the explanatory variable are expressed by the following relational expression (sigmoid function).

[0050] (Number 1) f(x)=1 / {1+exp[-(a1·x1+a2·x2+ ...+an·xn+a0)]}

[0051] f(x) is the probability of an event occurring, which is the objective variable, xn is the various features, which are the explanatory variables, an is the learning coefficient (a parameter for the judgment conditions), and n is the number of dimensions, which is the number of types of data. By comparing the magnitude of f(x) and 1-f(x), it is determined which of the two classes it belongs to. Using the above formula, the predicted value is calculated, and the contribution of the explanatory variables used in the formula to the objective variable is clarified.

[0052] When features are input to each of the one-versus-other two-class classifiers, that is, the first classifier 301, the second classifier 302, the third classifier 303, and the fourth classifier 304, each classifier performs a classification process.

[0053] The first classifier 301 outputs a probability P1 (=f(x)) that the subject's sleep state is an awake state, and when compared with the probability 1-P1 (=1-f(x)) of not being in an awake state, if the probability P1 is greater than 1-P1, the output probability P1 indicates that the sleep state is an awake state, and when 1-P1 is greater than P1, it indicates that the sleep state is other than an awake state. The second classifier 302 outputs a probability P2 that the subject's sleep state is an REM sleep state, and when compared with the probability 1-P2 of not being in an REM sleep state, if the probability P2 is greater than 1-P2, the output probability P2 indicates that the sleep state is a REM sleep state, and when 1-P2 is greater, it indicates that the sleep state is other than an REM sleep state. The third classifier 303 outputs a probability P3 of the subject being in a light sleep state, and when the probability P3 is greater than 1-P3 as a result of comparing the probability P3 with the probability 1-P3 of not being in a light sleep state, the output probability P3 indicates that the sleep state is a light sleep state, and when 1-P3 is large, the output probability P3 indicates that the sleep state is other than a light sleep state. The fourth classifier 304 outputs a probability P4 of the subject being in a deep sleep state, and when the probability P4 is greater than 1-P4 as a result of comparing the probability P4 with the probability 1-P4 of not being in a deep sleep state, the output probability P4 indicates that the sleep state is deep sleep, and when 1-P4 is large, the output probability P4 indicates that the sleep state is other than a deep sleep state. A time-direction Gaussian filter is provided for each class output result. The output data is smoothed by the filter to remove unnatural and sudden changes in the output data, thereby preventing erroneous estimation of the sleep state.

[0054] The outputs (probabilities P1 to P4) of the first to fourth classifiers 301 to 304 smoothed by the Gaussian filter are input to the score determiner 305. The score determiner 305 compares the outputs (probabilities P1 to P4) of the first to fourth classifiers 301 to 304, estimates that the subject's sleep state is the sleep state corresponding to the maximum value of the probabilities P1 to P4, and outputs data indicating this to the user interface 13. In this way, the estimated sleep state is presented to the user.

[0055] The parameter an of the judgment condition is determined by machine learning using sample data. Since the estimation unit 140 estimates the sleep state in 30-second intervals, a label recording the sleep state estimated by an expert based on an electroencephalogram, an electrocardiogram, or the like is added to the sample data of the feature amount every 30 seconds. Sample data is prepared for each of the awake state, REM sleep state, light sleep state, and deep sleep state. A feature amount extraction process is performed on the prepared sample data. The extracted feature amount data and the label are associated with each other and stored as teacher data. Note that machine learning may be performed within this identification device, or may be performed in a separate device and the judgment model may be stored in this identification device.

[0056] In the above embodiment, the estimation unit 140 is configured by providing multiple one-to-other two-class classifiers using a sigmoid function as an activation function, but the present invention is not limited to this, and the estimation unit 140 may be configured as a multi-class classifier using a softmax function as an activation function. The estimation unit 140 may also be configured by providing multiple one-to-one two-class classifiers. In addition, although logistic regression is used as a machine learning algorithm, the present invention is not limited to this, and other algorithms such as a support vector machine, a neural network, a decision tree, and a random forest may also be used. A combination of multiple algorithms may also be used. For example, there are SVC (Support Vector Classification), SVR (Support Vector Regression), Linear SVC (Support Vector Classification), and xgboost (eXtreme Gradient Boosting).

[0057] Returning to FIG. 4, the estimation unit 140 estimates the sleep state in real time in 30-second intervals. The control unit 11 determines whether or not a termination condition is met (step S104). The termination condition is, for example, when the elapsed time from the start of processing reaches a set time, when an instruction to terminate is given via the input unit, etc. If the termination condition is not met (step S104: NO), the process returns to step S101 and continues the sleep state estimation process. If the termination condition is met (step S104: YES), the sleep state estimation process is terminated.

[0058] As described above, according to the present embodiment, by setting a plurality of extraction time windows with different time lengths within a certain period during which a biosignal is acquired, and extracting the feature of the biosignal in each of the plurality of extraction time windows, it is possible to extract macroscopic features of the biosignal that change over a long period of time and microscopic features that change over a short period of time as feature amounts. For example, even if the feature of the biosignal that changes over time is a major factor in estimating the sleep state, if the extraction time window for feature amount extraction is short, it is not possible to extract the feature that changes over time. In this case, by performing estimation based on the feature amount extracted using a window 1 that is widely spread toward the past and future within a certain period of time, it is possible to correctly estimate the sleep state based on the feature amount estimated in this way.

[0059] Conversely, even if a local short-time change in a biosignal is a major factor in determining a sleep state as a feature, if the time window for feature extraction is long, the local change cannot be grasped as a feature. In this case, by shortening the time window for feature extraction, the local change can be extracted as a feature, and a correct sleep state can be estimated based on the feature estimated in this way. In addition, in determining a sleep state based on a feature of a biosignal within a certain period of time, for example, a local change in a biosignal at a time point some time back in the past may be a major factor in determining the sleep state. Furthermore, such local changes in a biosignal may occur at multiple different times. In this case, by shortening the time window for feature extraction and setting the extraction time window at multiple positions going back in the past within a predetermined period on the time axis, it is possible to improve the accuracy of estimating the sleep state. In addition, by partially overlapping adjacent extraction time windows on the time axis on the time axis, the feature can be extracted in detail (without omission). In addition, by setting the extraction time windows to be continuous within a certain period, it is possible to extract features from all the biosignals acquired within a certain period. The positions and ranges of the occurrence of features that are major factors in determining the sleep state are considered to be diverse. Therefore, by setting extraction time windows of different lengths at different positions on the time axis and using the features obtained from these extraction time windows in combination, it is possible to capture macroscopic and microscopic changes in the features without missing them, and to improve the accuracy of estimating the sleep state.

[0060] Furthermore, the feature to be extracted may be changed depending on the purpose of estimating the sleep state. For example, if it is desired to know the tendency of the sleep state throughout the entire sleep period, a feature obtained from a long extraction time window may be selected, whereas if it is desired to know the details of the sleep state at a certain point during sleep, a feature obtained from a short extraction time window may be selected.

[0061] By the above-described sleep state estimation process, the state estimation device 10 can estimate the sleep state of the subject in real time even while the subject is asleep.

[0062] When the sleep states of 45 subjects were estimated by this embodiment, the total_accuracy and total_kappa, which indicate the estimation accuracy, were 0.7229 and 0.5960, respectively. In contrast, when the feature amount of the biosignal was extracted using a single extraction time window (30 seconds) as in the conventional method described above, and the sleep states of the same 45 subjects were estimated based on the extracted feature amount of the biosignal, the total_accuracy was 0.6942 and the total_kappa was 0.5576. Thus, it was found that the sleep states of the subjects could be estimated more accurately than when a single extraction time window was used.

[0063] In the above embodiment, at least one of the number and time length of the multiple extraction time windows may be set variably according to various conditions and parameters. For example, the number and time length of the multiple extraction time windows are changed based on the change in the sleep state of the subject. In this case, in a situation where the sleep state changes, the extraction time windows are set so that more feature amounts are extracted in order to increase the estimation accuracy of the sleep state. Conversely, in a situation where the sleep state does not change, the number of extraction time windows is reduced and the time length of the extraction time windows is set long, thereby reducing the calculation load. The situation where the sleep state changes can be determined based on, for example, the degree of change in the outside air temperature around the subject, the degree of change in the illuminance around the subject, the degree of change in the deep body temperature of the subject, etc. (at least one of these). This determination is performed by the CPU functioning as a determination means. The deep body temperature of the subject can be detected using a sensor or the like from the ear or head of the subject. In addition, the situation where the sleep state changes can be determined based on the heart rate, body movement, etc., or the feature amount itself. Alternatively, at least one of the number and time length of extraction time windows may be set to be different depending on whether the subject (human) is at rest or exercising. The CPU functions as a determining means to determine whether the subject is at rest or exercising, and is based on the detection results of the body movement sensor 16, etc.

[0064] Furthermore, at least one of the number and time length of extraction time windows may be set according to individual information of the subject including at least one of the gender and age of the subject. In this case, the individual information of the subject (human) is input by a user via the user interface 13, and the input individual information is acquired by the CPU functioning as individual information acquisition means.

[0065] In the above embodiment, the extraction time windows (windows 12 to 19) each having a relatively short time length are set so as not to overlap with each other and to be continuous with each other without any gaps on the time axis, but they may be set so as to be spaced apart from each other on the time axis. In that case, it is possible to reduce the amount of data of the feature amount while suppressing the deterioration of the accuracy of the feature amount of the biological signal.

[0066] In the above-described embodiment, the pulse wave sensor 15 for detecting the pulse wave of the subject (target) and the body movement sensor 16 for detecting the body movement are provided, but the type of sensor is not limited to these. Any sensor that acquires a target's biosignal may be provided. In addition, for example, if a biosignal or a feature of a biosignal can be received from an external device or the like via the communication unit 14, the state estimation device 10 does not need to be provided with a sensor.

[0067] In the above embodiment, the state estimation device 10 uses the pulse wave from a pulse wave sensor attached to the tragus and the acceleration from an acceleration sensor attached to the tragus as the biosignal, but the biosignal is not limited to these. Biosignals that the state estimation device 10 can use include body movement (detected by an acceleration sensor attached to the head, arms, chest, legs, torso, etc.), electromyogram (detected by an electromyogram sensor attached to the head (temples and around the nose), arms, chest, legs, torso, etc.), sweat (detected by a skin potential meter or humidity sensor), heart rate (detected by an electrocardiogram, a pressure sensor attached under the bed (detection of ballistocardiogram waveform), a pulse wave sensor attached to the head, arms, chest, legs, torso, etc.), etc.

[0068] In the above embodiment, the state estimation device 10 uses frequency system features based on RRI, time system features based on RRI and body movement, and respiratory system features as features for estimating the sleep state, but the features are not limited to the above features, and any type of feature can be used as long as it is a feature for estimating the sleep state, and the number of features is not limited. For example, if myoelectricity, sweat, etc. are also used as biosignals, the detected values ​​for these may be sampled at, for example, 2 Hz like other features, and data may be extracted in multiple extraction time windows based on a reference time point t, to calculate the features.

[0069] In the above embodiment, the state estimation device 10 estimates the sleep state of a human subject. However, the subject for which the sleep state is estimated is not limited to a human, and can be a general subject such as a dog, a cat, a horse, a cow, a pig, or a chicken. This is because it is possible to obtain the feature amount required for sleep state estimation by attaching a pulse wave sensor or an acceleration sensor to these subjects. In addition, in the embodiment, the sleep state is estimated as the subject's state, but instead, emotions (joy, sadness, anger, resignation, surprise, disgust, fear, relaxation, etc.) may be estimated. For example, the sympathetic nerve works actively when in a state of tension such as stress. In contrast, the parasympathetic nerve works actively when in a relaxed state. The sympathetic nerve works to speed up the heartbeat, and the parasympathetic nerve works to slow down the heartbeat. Therefore, it is possible to estimate whether the subject is in a relaxed state based on the feature amount based on the power spectrum of the low frequency band lf and the high frequency band hf of the RRI. Of course, it is also possible to extract feature amounts of other appropriate biological signals suitable for estimating the subject's state.

[0070] In the above embodiment, the control unit 11 functions as the biosignal acquisition unit 110, the time window setting unit 120, the feature extraction unit 130, and the estimation unit 140 by the CPU executing the program stored in the ROM. However, the control unit 11 may include dedicated hardware such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), and various control circuits, and the dedicated hardware may function as the biosignal acquisition unit 110, the time window setting unit 120, the feature extraction unit 130, and the estimation unit 140. In this case, the functions of each unit may be realized by individual hardware, or the functions of each unit may be realized by a single hardware. In addition, some of the functions of each unit may be realized by dedicated hardware, and the other parts may be realized by software or firmware.

[0071] In addition, it is possible to provide a wireless communication device having a configuration for implementing the functions according to the present invention. Furthermore, by applying the program, an existing information processing device or the like can function as the wireless communication device according to the present invention. The method of applying such a program is arbitrary. The program can be applied by storing it in a computer-readable storage medium such as a flexible disk, a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc)-ROM, or a memory card. Furthermore, the program can be superimposed on a carrier wave and applied via a communication medium such as the Internet. For example, the program may be posted and distributed on a bulletin board (BBS: Bulletin Board System) on a communication network. Then, the program may be started and executed under the control of an OS (Operating System) in the same way as other application programs, so that the above processing can be executed.

[0072] Although the embodiment of the present invention has been described, the scope of the present invention is not limited to the above embodiment, but includes the scope of the invention described in the claims and its equivalents. The invention described in the claims first attached to this application is appended below. The appended number is the same as the claims first attached to this application.

[0073] (Appendix 1) An acquisition means for acquiring a biological signal of a subject; A setting means for setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction means for extracting a feature amount of the biological signal in each of the plurality of extraction time windows; A feature extraction device comprising:

[0074] (Appendix 2) the setting means further sets, as the plurality of extraction time windows, a plurality of time windows having the same time length at different positions on a time axis; 2. A feature extraction device as described in claim 1.

[0075] (Appendix 3) At least two of the plurality of extraction time windows are set to be spaced apart from each other on a time axis. 3. The feature extraction device according to claim 1 or 2.

[0076] (Appendix 4) At least two of the plurality of extraction time windows are set to partially overlap each other on a time axis. 4. A feature extraction device according to claim 1.

[0077] (Appendix 5) At least two of the plurality of extraction time windows are set so as not to overlap with each other on a time axis and so as to be consecutive with each other without any interval. 5. A feature extraction device according to claim 1 .

[0078] (Appendix 6) The subject's biological signals are pulse waves and body movements. 6. A feature extraction device according to any one of claims 1 to 5.

[0079] (Appendix 7) The feature amount is at least one of a frequency system feature amount based on a frequency of a heartbeat interval obtained from the pulse wave of the human subject, a time system feature amount obtained from time series data of the heartbeat interval, a time system feature amount obtained from time series data of the body movement of the human subject, and a respiratory system feature amount that is a feature amount based on a respiratory fluctuation component included in the heartbeat interval. 7. A feature extraction device as described in appendix 6.

[0080] (Appendix 8) A feature extraction device according to any one of appendix 1 to 7, an estimation means for estimating a state of the object based on the feature extracted by the feature extraction device; A state estimation device comprising:

[0081] (Appendix 9) An acquisition step of acquiring a biological signal of a subject; a setting step of setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction step of extracting a feature amount of the biological signal in each of the plurality of extraction time windows; The feature extraction method includes:

[0082] (Appendix 10) an estimation step of estimating a state of the object based on the feature extracted by the feature extraction method described in Supplementary Note 9; A state estimation method comprising:

[0083] (Appendix 11) On the computer, acquiring a biological signal of the subject; a setting step of setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction step of extracting a feature amount of the biological signal in each of the plurality of extraction time windows; A program for executing.

[0084] (Appendix 12) On the computer, an estimation step of estimating a state of the object based on the feature amount extracted by executing the program described in Supplementary Note 11; A program for executing.

[0085] (Appendix 13) A determination means for determining a state of the subject is further provided, the setting means sets at least one of the number and the time length of the extraction time windows based on a state of the target. 8. A feature extraction device according to any one of claims 1 to 7.

[0086] (Appendix 14) The determination means determines whether or not a state of the object is changing; the setting means sets, when it is determined that the state of the object is changing, at least one of the number and the time length of the extraction time windows to be different from those when it is determined that the state of the object is not changing. 14. The feature extraction device according to claim 13.

[0087] (Appendix 15) The method further includes: acquiring individual information including at least one of the sex and age of the subject; the setting means sets at least one of the number and the time length of the extraction time windows in accordance with the individual information. 15. The feature extraction device according to claim 13 or 14. [Explanation of symbols]

[0088] 10...state estimation device, 11...control unit, 12...storage unit, 13...user interface, 14...communication unit, 15...pulse wave sensor, 16...body movement sensor, 110...biological signal acquisition unit, 120...time window setting unit, 130...feature extraction unit, 140...estimation unit, 200...dotted line, 201...pulse wave, 202i, 203i, 204i, 205i, 206i, 207i...heartbeat interval Intervals, 201t, 202t, 203t, 204t, 205t, 206t, 207t...beat timing, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223...points, 301...first classifier, 302...second classifier, 303...third classifier, 304...fourth classifier, 305...score determiner

Claims

1. An acquisition means for acquiring a biological signal of a subject; A setting means for setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction means for extracting feature amounts in each of the plurality of extraction time windows for the same acquired biological signal; Equipped with the setting means sets at least both a first layer in which a plurality of extraction time windows having a first time length for extracting macroscopic features are provided so as to partially overlap each other on a time axis, and a second layer in which a plurality of extraction time windows having a second time length shorter than the first time length for extracting microscopic features are provided so as not to overlap each other on the time axis, The extraction means extracts the same feature amount in at least both an extraction time window corresponding to the first layer and an extraction time window corresponding to the second layer. The feature extraction device according to the present invention is characterized in that

2. the setting means further sets, as the plurality of extraction time windows, a plurality of time windows having the same time length at different positions on a time axis; The feature extraction device according to claim 1 .

3. At least two of the plurality of extraction time windows are set to be spaced apart from each other on a time axis. The feature extraction device according to claim 1 .

4. At least two of the plurality of extraction time windows are set to partially overlap each other on a time axis. The feature extraction device according to claim 1 .

5. At least two of the plurality of extraction time windows are set so as not to overlap with each other on a time axis and so as to be consecutive with each other without any interval. The feature extraction device according to claim 1 .

6. The subject's biological signals are a pulse wave and a body movement, The extraction means extracts each of the plurality of feature amounts in at least both an extraction time window corresponding to the first layer and an extraction time window corresponding to the second layer. The feature extraction device according to claim 1 .

7. The subject's biological signals are pulse waves and body movements, the feature amount is at least one of a frequency system feature amount based on a frequency of a heartbeat interval obtained from the pulse wave of the human subject, a time system feature amount obtained from time series data of the heartbeat interval, a time system feature amount obtained from time series data of the body movement of the human subject, and a respiratory system feature amount that is a feature amount based on a respiratory fluctuation component included in the heartbeat interval. The feature extraction device according to claim 1 .

8. The feature extraction device according to claim 1 , an estimation means for estimating a state of the object based on the feature extracted by the feature extraction device; A state estimation device comprising:

9. An acquisition step of acquiring a biological signal of a subject; a setting step of setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction step of extracting feature amounts in each of the plurality of extraction time windows for the same acquired biological signal; Equipped with In the setting step, at least both of a first layer in which a plurality of extraction time windows having a first time length for extracting macroscopic features are provided so as to partially overlap each other on a time axis, and a second layer in which a plurality of extraction time windows having a second time length shorter than the first time length for extracting microscopic features are provided so as not to overlap each other on the time axis are set; In the extraction step, the same feature amount is extracted in at least both an extraction time window corresponding to the first layer and an extraction time window corresponding to the second layer. A feature extraction method comprising:

10. an estimation step of estimating a state of the object based on the feature extracted by the feature extraction method according to claim 9; A state estimation method comprising:

11. On the computer, acquiring a biological signal of the subject; a setting step of setting a plurality of time windows having different time lengths as a plurality of extraction time windows within a certain period during which the biological signal is acquired; an extraction step of extracting feature amounts in each of the plurality of extraction time windows for the same acquired biological signal; Run the command, In the setting step, at least both of a first layer in which a plurality of extraction time windows having a first time length for extracting macroscopic features are provided so as to partially overlap each other on a time axis, and a second layer in which a plurality of extraction time windows having a second time length shorter than the first time length for extracting microscopic features are provided so as not to overlap each other on the time axis are set; In the extraction step, the same feature amount is extracted in at least both an extraction time window corresponding to the first layer and an extraction time window corresponding to the second layer. A program characterized by:

12. On the computer, an estimation step of estimating a state of the object based on the feature amount extracted by executing the program according to claim 11; A program for executing the above.

Images