Information processing device, information processing method, and program

Abstract

This information processing device classifies a pattern of the biological activity of an animal. The information processing device comprises a calculation circuit which receives a biological signal that is a detection result of the biological activity of an animal detected by a sensor unit including a sensor having a plurality of detection channels or a plurality of sensors. The calculation circuit detects a quasi-periodic signal from the detection result, expands and contracts the quasi-periodic signal in a time direction, generates an elastic signal of which the period is a prescribed value, decomposes the elastic signal into a plurality of frequency components, acquires time-series phase information about the plurality of frequency components, and classifies the pattern of the biological activity on the basis of the time-series phase information.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] There are known techniques for analyzing periodic waveforms or quasi-periodic signals having quasi-periodic characteristics. Here, quasi-periodic means, for example, that the period of the signal waveform is not precisely constant but varies. For example, Patent Document 1 discloses a method for decomposing the waveform of a quasi-periodic signal obtained from an electrocardiogram into multiple frequency components by wavelet transform and storing the phase information of each frequency component in a storage device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] U.S. Patent No. 7,702,502 Summary of the Invention [Problem to be solved by the invention]

[0004] However, since the frequency of the quasi-periodic signal representing biological activity is not constant over time, the process of decomposing the quasi-periodic signal into multiple frequency components becomes complicated, and the amount of calculation required by an information processing device performing such processing may also increase.

[0005] An object of the present disclosure is to provide an information processing device, an information processing method, and a program that can further reduce the processing load of decomposing a quasi-periodic signal into a plurality of frequency components. [Means for solving the problem]

[0006] An information processing device according to one aspect of the present disclosure includes: An information processing device that classifies patterns of biological activity of an animal, a calculation circuit that receives a biological signal that is a detection result of biological activity of the animal detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors; The arithmetic circuit comprises: detecting a quasi-periodic signal from the detection result; stretching or contracting the quasi-periodic signal in a time direction to generate a stretched or contracted signal having a predetermined period; decomposing the stretched signal into a plurality of frequency components; acquiring time-series phase information of the plurality of frequency components; The pattern of the biological activity is classified based on the time-series phase information.

[0007] An information processing method according to one aspect of the present disclosure is an information processing method for classifying a pattern of a biological activity of an animal, the information processing method comprising: a step in which an arithmetic circuit receives a biological signal, which is a detection result of biological activity of the animal, detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors, and detects a quasi-periodic signal from the detection result of biological activity; the arithmetic circuit stretches or contracts the quasi-periodic signal so that the period of the quasi-periodic signal after the stretching or contraction becomes a predetermined value, thereby generating a stretched or contracted signal; The calculation circuit decomposes the expansion / contraction signal into a plurality of frequency components; the calculation circuit acquiring time-series phase information of the plurality of frequency components; The calculation circuit classifies the pattern of the biological activity based on the time-series phase information.

[0008] A program according to one aspect of the present disclosure causes an arithmetic circuit to execute the information processing method. [Effects of the Invention]

[0009] According to the information processing device, information processing method, and program of the present disclosure, it is possible to further reduce the processing load of decomposing a quasi-periodic signal into a plurality of frequency components. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram illustrating an example configuration of a gait classification device according to an embodiment of the present disclosure. [Figure 2] 2 is a schematic diagram illustrating the position and direction in which the acceleration sensor unit of FIG. 1 is attached. FIG. [Figure 3] 2 is a flowchart showing an example of a gait classification method executed by the gait classification device of FIG. 1. [Figure 4] FIG. 10 is an exemplary schematic diagram for explaining an overview of a scaling process. [Figure 5] FIG. 10 is an exemplary schematic diagram for explaining an overview of a scaling process. [Figure 6A] 10 is a graph illustrating an example of a process for detecting the period of a quasi-periodic signal. [Figure 6B] 10 is a graph illustrating an example of a process for detecting the period of a quasi-periodic signal. [Figure 7A] 10A and 10B are diagrams for explaining the effect of expanding and contracting a quasi-periodic signal so that the period of the expanded or contracted signal becomes a predetermined value. [Figure 7B] 10A and 10B are diagrams for explaining the effect of expanding and contracting a quasi-periodic signal so that the period of the expanded or contracted signal becomes a predetermined value. [Figure 7C] 10A and 10B are diagrams for explaining the effect of expanding and contracting a quasi-periodic signal so that the period of the expanded or contracted signal becomes a predetermined value. [Figure 7D] 10A and 10B are diagrams for explaining the effect of expanding and contracting a quasi-periodic signal so that the period of the expanded or contracted signal becomes a predetermined value. [Figure 8] 6 is a graph illustrating a plurality of frequency components obtained by performing a wavelet transform on the warped signal Sz of FIG. 5. [Figure 9] FIG. 10 is a schematic diagram illustrating an example of a phase analysis process. [Figure 10] FIG. 1 illustrates a topological object. [Figure 11] 1A and 1B are schematic diagrams illustrating original signal waveforms corresponding to walk, trot, and run gaits, and phase objects obtained by analyzing each original signal waveform according to the present embodiment. [Figure 12A] FIG. 1 is a schematic diagram showing a topological object corresponding to a walk and a color map visualizing the features of the topological object. [Figure 12B] FIG. 10 is a schematic diagram showing a phase object corresponding to a trot and a color map visualizing the characteristics of the phase object. [Figure 12C] FIG. 10 is a schematic diagram showing a phase object corresponding to a run and a color map visualizing the characteristics of the phase object. [Figure 13] 10 is a confusion matrix showing the relationship between correct categories of a plurality of acceleration data and prediction results of gait classification by the gait classification device 100 according to this embodiment. [Figure 14] FIG. 10 is a schematic diagram illustrating the original signal waveforms of pulse wave data measured under three different conditions, and phase objects obtained by analyzing each original signal waveform. DETAILED DESCRIPTION OF THE INVENTION

[0011] (Background to this disclosure) There is a demand for technology to detect biological activities of humans and animals such as pets using sensors, etc., and grasp the biological activities of animals. By grasping the biological activities of animals, for example, information such as the animal's health condition and amount of exercise can be obtained, and this information can be used for healthcare.

[0012] The prior art (see Patent Document 1) discloses a method for decomposing the waveform of a quasi-periodic signal obtained from an electrocardiogram into multiple frequency components by wavelet transform. The wavelet transform is realized, for example, by inputting the results of biological activity detection by a sensor into a filter bank. The characteristics of the filters in each frequency band that make up the filter bank are, for example, Nd, k p , Ni, w p It depends on multiple parameters such as the above (see FIGS. 1 to 5 and their descriptions in Patent Document 1).

[0013] The characteristics of conventional filter banks must be predetermined according to the fundamental frequency of the quasi-periodic signal input to the filter bank. However, the frequency of signals representing biological activities of animals, such as walking, heartbeat, and breathing, is not constant. In order to be able to perform wavelet transform even when the signal frequency changes, the parameters that determine the filter bank characteristics must be able to be changed as needed in response to changes in the signal frequency. This makes wavelet transform complicated, and the amount of calculation required by an information processing device performing such processing can also increase. For example, to determine the characteristics of a filter bank, the number of parameters required is calculated by multiplying the number of parameters in one frequency band by the number of frequency bands.

[0014] Furthermore, in gait analysis, which is an example of a technology for understanding the biological activity of animals, the walking state of an animal is detected using sensors such as an acceleration sensor, but in order to understand the characteristics of the animal's walking, it is often necessary to detect forward / backward, left / right, and up / down movements. Therefore, there is room for more accurate estimation of the walking state of an animal by detecting acceleration in multiple directions rather than detecting acceleration in only one axial direction.

[0015] Therefore, it is conceivable to detect acceleration in multiple directions using an acceleration sensor unit composed of multiple acceleration sensors or an acceleration sensor with multiple channels. Even in this case, there is room for more accurate estimation of the animal's walking state by analyzing the acceleration signals in multiple directions comprehensively or in a comprehensive manner, rather than just analyzing them individually. While conventional technology analyzes each signal individually, the inventor, after extensive research, has come up with a technology that takes into account the mutual temporal relationships between the acceleration signals in multiple directions and analyzes the acceleration signals in multiple directions comprehensively rather than individually.

[0016] Furthermore, Patent Document 1 discloses a technology that makes it possible to detect abnormalities in the measurement results of a certain one channel of an electrocardiogram, but does not disclose a technology that classifies patterns of biological activity such as gait (or gait pattern), heart rate, breathing, etc. As a result of diligent research, the inventors found that a technology that classifies patterns of biological activity such as gait, heart rate, breathing, etc. using the detection results of biological activity obtained by multiple sensors or sensors with multiple channels is useful for understanding information such as an animal's health condition and amount of exercise, and came up with such a classification technology.

[0017] (Embodiment) Hereinafter, an embodiment of an information processing device according to the present disclosure will be described with reference to the accompanying drawings. Note that in the following embodiments, identical or similar components are designated by the same reference numerals. In the accompanying drawings, the shape, size, positional relationship, etc. of each component may be exaggerated to facilitate understanding of the description.

[0018] FIG. 1 is a block diagram showing an example configuration of a gait classification device 100 according to an embodiment of the present disclosure. The gait classification device 100 is an example of an information processing device according to the present disclosure. The gait classification device 100 classifies the gait of an animal that walks on all fours, such as a dog. For example, the gait classification device 100 classifies the dog's gait into a walk, a trot, or a gallop or run.

[0019] The gait classification device 100 includes an input / output unit 11, an arithmetic circuit 12, a storage device 13, and a communication unit 14.

[0020] The input / output unit 11 is an interface circuit that connects the gait classification device 100 to an external device, such as the acceleration sensor unit 2, in order to receive information from the external device or to output information to the external device. The input / output unit 11 may be a communication circuit that performs data communication in accordance with an existing wired communication standard or wireless communication standard.

[0021] The arithmetic circuit 12 performs information processing to realize the functions of the gait classification device 100. Such information processing is realized, for example, by the arithmetic circuit 12 executing a program stored in the storage device 13. The arithmetic circuit 12 is configured, for example, with circuits such as a CPU, an MPU, and an FPGA. The arithmetic circuit 12 may be realized by such a single circuit or by multiple circuits. Furthermore, functions of the components of the arithmetic circuit 12 may be omitted, replaced, or added as appropriate depending on the embodiment.

[0022] The storage device 13 stores various data including programs and trained models required to realize the functions of the gait classification device 100. The storage device 13 is realized, for example, by a semiconductor storage device such as a flash memory or a solid-state drive (SSD), a magnetic storage device such as a hard disk drive (HDD), or other recording media, either alone or in combination. The storage device 13 may also include a temporary storage device such as an SRAM or a DRAM.

[0023] The acceleration sensor unit 2 is a sensor capable of detecting a first plurality of acceleration components. The first plurality of acceleration components are, for example, n acceleration components, where n is an integer equal to or greater than 2. For example, the acceleration sensor unit 2 is a sensor capable of detecting acceleration in three mutually orthogonal axial directions (x, y, and z directions) (n=3). The acceleration sensor unit 2 is an acceleration sensor having three channels corresponding to the three axial directions. Alternatively, the acceleration sensor unit 2 may be a unit having a first acceleration sensor that detects acceleration in the x direction, a second acceleration sensor that detects acceleration in the y direction, and a third acceleration sensor that detects acceleration in the z direction.

[0024] Fig. 2 is a schematic diagram illustrating the mounting position and direction of the acceleration sensor unit 2 in Fig. 1. The acceleration sensor unit 2 is attached to a harness, such as a collar or harness, worn by a dog. The direction in which the dog moves forward is defined as the forward direction, and the acceleration sensor unit 2 is attached to the harness so as to detect acceleration in, for example, the mutually orthogonal left-right direction (x direction), front-back direction (y direction), and vertical direction (z direction). The positive direction of each axis is illustrated in Fig. 2.

[0025] 3 is a flowchart showing an example of a gait classification method executed by the gait classification device 100. First, the arithmetic circuit 12 acquires acceleration data in the x, y, and z directions from the acceleration sensor unit 2 (S1). The arithmetic circuit 12 may acquire the acceleration data in real time from the acceleration sensor unit 2. Alternatively, the storage device 13 may store the acceleration data measured by the acceleration sensor unit 2, and the arithmetic circuit 12 may read out the acceleration data stored in the storage device 13.

[0026] Next, the arithmetic circuit 12 analyzes the acceleration data acquired in step S1 to detect a quasi-periodic signal (S2). The waveform representing a biological signal generated by biological activity, such as acceleration acquired in step S1, is usually not a waveform in which a completely identical waveform is repeated at regular time intervals. Therefore, in this specification, such a biological signal is referred to as a quasi-periodic signal. If a quasi-periodic signal is not detected in step S2, the arithmetic circuit 12 ends the process of FIG. 3 or returns to step S1.

[0027] Between steps S1 and S2, or in step S2, filtering may be performed to remove noise contained in the acceleration data. Such noise may be caused by, for example, external disturbances, animal movements, etc. The filtering may be performed by, for example, an infinite impulse response (IIR) band-pass filter. The filtering may also be performed by other band-pass filters, such as a finite impulse response (FIR) filter.

[0028] Next, the arithmetic circuit 12 obtains a stretched or compressed signal by stretching or compressing the quasi-periodic signal detected in step S2 in the time direction (S3). In step S3, the arithmetic circuit 12 stretches or compresses the quasi-periodic signal so that the period of the stretched or compressed signal becomes a predetermined value.

[0029] 4 and 5 are exemplary schematic diagrams for explaining the outline of the expansion / contraction process in step S3. FIG. 4 shows the acceleration data (a x ,a y ,a z ) is a graph showing the quasi-periodic signal, acceleration a x , a y , a z Each period T0 x , T0 y , T0 z The periods of these quasi-periodic signals are detected by the arithmetic circuit 12 in step S2 or S3, for example.

[0030] FIG. 5 shows the acceleration data (a x ,a y ,a z ) are respectively stretched and compressed to obtain the stretched signal (S x ,S y ,S z ) is a graph showing the expansion / contraction signal S x , S y , S z The periods are T1 x , T1 y , T1 z T1 x is a preset value T x is equal to T1 y is a preset value T y is equal to T1 z is a preset value T z Equal to T x , T y , T z may be different values ​​or may be equal to each other.

[0031] In this way, in step S3, the calculation circuit 12 calculates the period T1 of the expansion / contraction signal. x , T1 y , T1 z is the predetermined value T x , T y , T z For example, the quasi-periodic signal a z The period is T0 z Therefore, the calculation circuit 12 converts the original signal into a signal with a sampling rate of T z / T0 z By resampling by a factor of T, the period is z The stretched signal S z can be obtained.

[0032] 6A and 6B are graphs for explaining an example of a process for detecting the period of a quasi-periodic signal. FIG. 6A shows the waveform of acceleration data obtained by the acceleration sensor unit 2 attached to a dog that is walking. FIG. 6B shows the waveform of acceleration data obtained by the acceleration sensor unit 2 attached to a dog that is trotting. In the graphs of FIG. 6A and 6B, the acceleration a in the x direction x is shown by a solid line, and the acceleration in the y direction is a y is shown by a dashed line, and the acceleration in the z direction is a z is shown by the dotted line.

[0033] The circles (◯) shown in Figures 6A and 6B represent the acceleration a in the z direction. z represents the point at which the dynamic threshold is crossed in the negative direction. This dynamic threshold is, for example, z For example, the calculation circuit 12 may calculate the time between adjacent dynamic thresholds as a function of the acceleration a in the z direction. z The same applies to the x and y directions.

[0034] 7A to 7D are diagrams for explaining the effect of expanding or contracting a quasi-periodic signal (original signal) in the time direction so that the period of the expansion or contraction signal becomes a predetermined value. FIG. 7A is a graph showing acceleration data in the x, y, and z directions acquired from the acceleration sensor unit 2 in step S1 under measurement condition 1. FIG. 7B is a graph showing an expansion or contraction signal obtained by expanding or contracting the original signal of FIG. 7A in step S3. FIG. 7C is a graph showing acceleration data in the x, y, and z directions acquired from the acceleration sensor unit 2 in step S1 under measurement condition 2. x ,a y ,a z 7D is a graph showing the scaled signal obtained by scaling the original signal of FIG. 7C in step S3.

[0035] Although the original signal under measurement condition 1 in Fig. 7A and the original signal under measurement condition 2 in Fig. 7C have different periods, the periods of the stretched and contracted signals in Fig. 7B and Fig. 7D are the same. Therefore, by performing the stretching process in step S3 on the quasi-periodic signal, the gait classification device 100 can perform the wavelet transform or phase analysis in step S4 using the same parameters, even if the quasi-periodic signal was obtained under different conditions. This further reduces the processing load of decomposing the quasi-periodic signal into multiple frequency components.

[0036] Returning to FIG. 3, after step S3, the arithmetic circuit 12 performs a wavelet transform on the warped signal obtained in step S3 (S4). As a result, the arithmetic circuit 12 decomposes the warped signal into multiple (m (m≧2)) frequency components. The wavelet transform is realized, for example, by inputting the warped signal to a filter bank. The filter bank has a configuration similar to that of the filter bank described in Patent Document 1, for example.

[0037] Figure 8 shows the expansion / contraction signal S z 8 is a graph illustrating a plurality of frequency components obtained by performing a wavelet transform on the warped signal S. In FIG. 8, m=5, but the value of m is not limited to this. x and S ySimilarly, wavelet transform can be performed on the

[0038] Returning to FIG. 3, after step S4, the arithmetic circuit 12 performs phase analysis on the multiple frequency components of the expansion / contraction signal obtained in step S4 (S5).

[0039] FIG. 9 is a schematic diagram showing an example of the phase analysis processing of step S5. For example, as shown in FIG. 9, the arithmetic circuit 12 classifies the waveform representing the frequency components of the expansion / compression signal into four phase segments A, B, C, and D. Phase segment A is the phase segment from the point where the waveform crosses the zero crossing point in the positive amplitude direction to the positive peak point (local maximum or maximal point) of the waveform. Phase segment B is the phase segment from the end point of phase segment A to the point where the waveform crosses the zero crossing point in the negative amplitude direction. Phase segment C is the phase segment from the end point of phase segment B to the negative peak point (local minimum or minimal point) of the waveform. Phase segment D is the phase segment from the end point of phase segment C to the point where the waveform crosses the zero crossing point in the positive amplitude direction. If the waveform is an approximately sinusoidal curve as shown in FIG. 9, the end point of phase segment D coincides with the start point of phase segment A in the expansion / compression signal of the next period.

[0040] Information including the positions of these phase segments A to D, for example, the start time and end time of each phase segment, and the labels (A to D) attached to each phase segment, is an example of phase information of the present disclosure.

[0041] Returning to FIG. 3, after step S5, the arithmetic circuit 12 creates a phase object using the phase analysis result (S6). The phase object is, for example, information obtained by arranging the phase information of the frequency components of a plurality of expansion / contraction signals in a time series. Using FIG. 10, the two frequency components QP of the expansion / contraction signal in the x direction are x,1 and QP x,2 and the two frequency components QP of the expansion / contraction signal in the y direction. y,1 and QP y,2 Next, an example of a process in which the arithmetic circuit 12 creates a phase object will be described.

[0042] In step S6, the arithmetic circuit 12 selects at least two frequency components from a total of 3m frequency components obtained by decomposing each of the three expansion / contraction signals corresponding to the three directions x, y, and z into m frequency components. This selection process is performed so that the selected frequency components include frequency components corresponding to at least two of the three directions x, y, and z. In this selection process, the arithmetic circuit 12 selects the at least two frequency components by, for example, extracting components that best represent the characteristics from the 3m frequency components.

[0043] In step S6, after the above selection process, the calculation circuit 12 obtains phase information in time series for at least two selected frequency components to create a phase object. x,1 and QP x,2 and the frequency component QP in the y direction y,1 and QP y,2 , and the resulting topological object is shown.

[0044] In Figure 10, the frequency component QP x,1 , Q.P. x,2 , Q.P. y,1 , and QP y,2 The phase division of these frequency components between the times when at least one of the frequency components QP changes is determined as a phase object. x,1 , Q.P. x,2 , Q.P. y,1 , and QP y,2 Each time at least one of these changes, the phase divisions of these frequency components are stored in the storage device 13. The time-series phase information of the frequency components generated in this way becomes a phase object.

[0045] FIG. 11 is a schematic diagram illustrating original signal waveforms corresponding to walk, trot, and run gaits, and phase objects obtained by analyzing each original signal waveform according to this embodiment. The original signal waveforms in FIG. 11 are waveforms showing acceleration data obtained in step S1 of FIG. 3. In FIG. 11, in the phase objects, phase section A is shown in the darkest gray (75% gray), phase section B is shown in a medium-density gray (50% gray), phase section C is shown in a medium-density gray (25% gray), and phase section D is shown in white. Unlike FIG. 10, in which the phase objects are arranged horizontally in chronological order, the phase objects in FIG. 11 are arranged vertically in chronological order. In other words, the time axis of the phase objects in FIG. 11 extends vertically into the paper.

[0046] 11, when the period of the frequency component corresponding to the acceleration in the x direction is T, a feature appears in the phase object corresponding to the waveform of the frequency component around T / 4 or 3T / 4. Therefore, the arithmetic circuit 12 can classify the pattern of biological activity based on the feature of the phase information corresponding to the frequency component at T / 4, 3T / 4, or parts around these.

[0047] Here, a waveform of a frequency component around T / 4 includes a waveform included within the frequency component T / 4±T / 4, for example, within T / 4±T / 8, T / 4±T / 10, or T / 4±T / 16. Similarly, a waveform of a frequency component around 3T / 4 includes a waveform included within the frequency component 3T / 4±T / 4, for example, within 3T / 4±T / 8, 3T / 4±T / 10, or 3T / 4±T / 16.

[0048] Returning to FIG. 3, after step S6, the arithmetic circuit 12 classifies the gait based on the phase object created in step S6 (S7). Classifying a biological activity pattern (e.g., gait) means determining which of the predetermined patterns the biological activity pattern corresponds to. In this embodiment, the arithmetic circuit 12 classifies the dog's gait as either a walk, trot, gallop, or run.

[0049] In step S7, the arithmetic circuit 12 inputs the topological object into a trained model stored in the storage device 13, for example, and causes the trained model to detect the gait classification result. The trained model is generated, for example, by a supervised learning method in which the arithmetic circuit 12 or another information processing device trains the model on the relationship between the topological object and the correct answer information. An example of such a model is a training model having a neural network structure, such as a convolutional neural network (CNN). The model may also be a training model such as a decision tree model that performs machine learning using a decision tree technique including a classification tree, or a support vector machine.

[0050] 12A, 12B, and 12C are schematic diagrams showing phase objects corresponding to walk, trot, and run (gallop), respectively, and color maps visualizing the characteristics of the phase objects. In each of FIGS. 12A, 12B, and 12C, the left side shows the phase objects, and the right side shows the color maps.

[0051] These color maps are obtained, for example, by applying Gradient-weighted Class Activation Mapping (Grad-CAM) to the topological object. Grad-CAM is a technology that is inserted into the convolutional layer of a CNN to generate a color map by emphasizing characteristic regions in the input image. In the color maps of Figures 12A, 12B, and 12C, characteristic parts of the topological object input to Grad-CAM are shown in bright (white) colors. In the color maps, weakly characteristic parts are shown in black, and as the characteristics become stronger, they become whiter.

[0052] In step S7, the calculation circuitry 12 can classify gaits using characteristic parts of the phase objects as shown in Figures 12A, 12B and 12C.

[0053] Fig. 13 shows a confusion matrix indicating the relationship between ground truth categories of multiple acceleration data and prediction results (Prediction) of gait classification by the gait classification device 100 according to this embodiment. The top row of the confusion matrix in Fig. 13 shows that when gait classification is performed by the gait classification device 100 on the waveform of acceleration data obtained by the acceleration sensor unit 2 attached to a dog that is walking, for example, the number of predictions as "walk" is 31, the number of predictions as "trot" is 2, and the number of predictions as "run" is 0.

[0054] As shown in FIG. 13, the majority of the classification results by the gait classification device 100 are arranged on the diagonal of the confusion matrix, which indicates that the accuracy of classification by the gait classification device 100 is high.

[0055] As described above, the gait classification device 100 according to this embodiment classifies patterns of biological activity of an animal. The gait classification device 100 includes a calculation circuit 12 that receives biological signals, which are the detection results of biological activity of an animal, detected by a sensor having multiple detection channels or a sensor unit including multiple sensors. The calculation circuit 12 detects a quasi-periodic signal from the detection results (S2), stretches or compresses the quasi-periodic signal in the time direction to generate a stretched or compressed signal having a predetermined period (S3), performs a wavelet transform on the stretched or compressed signal to decompose the stretched or compressed signal into multiple frequency components (S4), obtains time-series phase information of the multiple frequency components (S5), and classifies the pattern of biological activity based on the time-series phase information (S6). This configuration enables classification of biological activity patterns. Furthermore, the gait classification device 100 can further reduce the processing load on the calculation circuit 12.

[0056] As exemplified in this embodiment, the biological activity may be the movement of an animal. The detection result of the biological activity may be acceleration measured by the acceleration sensor unit 2 attached to the animal. The pattern of the biological activity may be the gait of the animal. With this configuration, the gait of the animal to which the acceleration sensor unit 2 is attached can be classified.

[0057] As exemplified in this embodiment, the animal may be a quadrupedal animal. The arithmetic circuit 12 may classify the pattern of biological activity by determining, based on the time-series phase information, which of predetermined gait patterns of quadrupedal animals the pattern of biological activity corresponds to. This configuration makes it possible to classify the gait of quadrupedal animals. The quadrupedal animal may be, for example, a dog.

[0058] As illustrated in this embodiment, the acceleration sensor unit 2 may be capable of measuring a first plurality (n) of acceleration components of acceleration corresponding to a plurality of mutually different directions. In the process of detecting a quasi-periodic signal, the arithmetic circuit 12 detects a first plurality of quasi-periodic signals from each of the first plurality of acceleration components measured by the acceleration sensor unit 2. In the process of generating an expansion / contraction signal, the arithmetic circuit 12 expands or contracts each of the first plurality of quasi-periodic signals in the time direction to generate an expansion / contraction signal having a predetermined period, thereby generating the first plurality of expansion / contraction signals. In the process of decomposing the expansion / contraction signal into a plurality of frequency components, the arithmetic circuit 12 decomposes each of the first plurality of expansion / contraction signals into a second plurality (m) of frequency components. In the process of acquiring time-series phase information of the plurality of frequency components, the arithmetic circuit 12 acquires time-series phase information for at least one of the second plurality of frequency components corresponding to each of the first plurality of expansion / contraction signals. In the process of classifying a biological activity pattern, the arithmetic circuit 12 classifies the biological activity pattern using a phase object in which phase information is arranged based on a time series.

[0059] By performing classification using the analysis results of multiple acceleration components, it is possible to more accurately classify patterns of biological activity. For example, by performing classification using the detection results of the forward / backward, left / right, and up / down movements of an animal, it is possible to accurately estimate the animal's gait.

[0060] In the process of classifying patterns of biological activity, the arithmetic circuit 12 may classify patterns of biological activity based on the characteristics of phase information of the time series corresponding to a portion of the frequency component at T / 4 or 3T / 4, where T is the period of one of the plurality of frequency components. This configuration limits the analysis portion to the portion, thereby enabling accurate classification while reducing calculation costs, resources, or the processing load of the arithmetic circuit 12.

[0061] (Variation) Although the embodiments of the present disclosure have been described in detail above, the above description is merely an example of the present disclosure in every respect. Various improvements and modifications can be made without departing from the scope of the present disclosure. For example, the following modifications are possible. Note that, in the following, the same reference numerals are used for components similar to those in the above embodiment, and descriptions of the same points as those in the above embodiment will be omitted as appropriate. The following modifications can be combined as appropriate.

[0062] In the above embodiment, an example of an "animal" in the present disclosure is described as a quadrupedal animal, but the present disclosure is not limited thereto. For example, the "animal" in the present disclosure includes a bipedal animal. For example, the "animal" in the present disclosure includes a human. Therefore, the information processing device according to the present disclosure can also classify a human gait as a classification of an animal's gait.

[0063] In the above embodiment, an example has been described in which an animal's gait is classified based on the results obtained by expanding and decomposing acceleration data detected by the acceleration sensor unit 2 attached to the animal. However, the information processing device according to the present disclosure is not limited to this. For example, the information processing device may classify or estimate heart rate-related conditions based on the results obtained by expanding and decomposing pulse wave data of the animal.

[0064] FIG. 14 is a schematic diagram illustrating the raw signal waveforms of pulse wave data measured under three different conditions and phase objects obtained by analyzing each raw signal waveform. The pulse wave data is measured, for example, by a photoplethysmograph. The photoplethysmograph is a device that detects pulse wave information associated with heartbeats by measuring changes in blood volume in blood vessels corresponding to changes in heart rate. The photoplethysmograph includes, for example, a light source and a photodetector. The light source emits light of multiple channels with different wavelengths. The light source emits at least infrared light. The infrared light emitted by the light source is transmitted through the animal's tissue, absorbed by hemoglobin in the blood, and reflected by the tissue before reaching the photodetector. Because the amount of light reaching the photodetector is proportional to the tissue blood volume, the photoplethysmograph can detect pulse wave information. The photoplethysmograph including the above-described light source and photodetector is an example of a "sensor unit" of the present disclosure.

[0065] The graph on the right side of Figure 14 shows the original signal waveform of pulse wave data measured using three LEDs that emit infrared light under different conditions. The original signal waveform, which is a quasi-periodic signal, is expanded / contracted (S3 in Figure 3), wavelet transformed (S4), and phase analyzed (S5) by the arithmetic circuit 12, and a phase object is created (S6). In Figure 11, in the phase object, phase segment A is shown in the darkest gray (75% gray), phase segment B is shown in medium gray (50% gray), phase segment C is shown in medium gray (25% gray), and phase segment D is shown in white.

[0066] In this modification, when the period of the frequency component is T, a feature appears in the phase object corresponding to the waveform of the frequency component around T / 2. The arithmetic circuitry 12 can classify or estimate the condition related to the heartbeat based on the phase object. As another modification, the arithmetic circuitry 12 may classify or estimate the state of blood flow obtained by various measurement methods.

[0067] Aspects of the present disclosure The following additionally describes aspects of the present disclosure.

[0068] <Aspect 1> An information processing device that classifies patterns of biological activity of an animal, a calculation circuit that receives a biological signal that is a detection result of biological activity of the animal detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors; The arithmetic circuit comprises: detecting a quasi-periodic signal from the detection result; stretching or contracting the quasi-periodic signal in a time direction to generate a stretched or contracted signal having a predetermined period; decomposing the stretched signal into a plurality of frequency components; acquiring time-series phase information of the plurality of frequency components; classifying the pattern of the biological activity based on the time-series phase information; Information processing device.

[0069] <Aspect 2> 2. The information processing device according to aspect 1, wherein the arithmetic circuit decomposes the expanded / contracted signal into a plurality of frequency components by performing a wavelet transform on the expanded / contracted signal.

[0070] <Aspect 3> The biological activity is movement of an animal, the sensor unit is an acceleration sensor unit attached to the animal; the detection result of the biological activity is acceleration measured by the acceleration sensor unit; The biological activity pattern is the gait of the animal. 3. The information processing device according to aspect 1 or 2.

[0071] <Aspect 4> the animal is a quadrupedal animal; the arithmetic circuit classifies the pattern of biological activity by determining, based on the time-series phase information, which of predetermined gait patterns of a quadrupedal animal the pattern of biological activity corresponds to; The information processing device according to aspect 3.

[0072] <Aspect 5> 5. The information processing device according to claim 4, wherein the animal is a dog.

[0073] <Aspect 6> the sensor unit is an acceleration sensor unit attached to the animal; the detection result of the biological activity is acceleration measured by the acceleration sensor unit; the acceleration sensor unit is capable of measuring a first plurality of acceleration components of the acceleration corresponding to a plurality of directions different from each other; The arithmetic circuit comprises: In the process of detecting the quasi-periodic signals, a first plurality of quasi-periodic signals are detected from the first plurality of acceleration components measured by the acceleration sensor unit, respectively; In the process of generating the expanded / contracted signals, the first plurality of quasi-periodic signals are expanded or contracted in a time direction to generate expanded / contracted signals each having a predetermined period, and In the process of decomposing the expansion / contraction signal into a plurality of frequency components, each of the first plurality of expansion / contraction signals is decomposed into a second plurality of frequency components; In the process of acquiring time-series phase information of the plurality of frequency components, time-series phase information of at least one of the second plurality of frequency components corresponding to each of the first plurality of expansion / contraction signals is acquired; In the process of classifying the pattern of the biological activity, the pattern of the biological activity is classified using a phase object in which the phase information is arranged based on a time series. 6. The information processing device according to any one of aspects 1 to 5.

[0074] <Aspect 7> In the process of classifying the pattern of the life activity, when a period of one frequency component of the plurality of frequency components is T, the arithmetic circuit classifies the pattern of the life activity based on a feature of phase information of the time series corresponding to a portion of the frequency component at T / 4 or 3T / 4. 7. The information processing device according to any one of aspects 1 to 6.

[0075] <Aspect 8> An information processing method for classifying patterns of biological activity of an animal, comprising: a step in which an arithmetic circuit receives a biological signal, which is a detection result of biological activity of the animal, detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors, and detects a quasi-periodic signal from the detection result of biological activity; the arithmetic circuit stretches or contracts the quasi-periodic signal so that the period of the quasi-periodic signal after the stretching or contraction becomes a predetermined value, thereby generating a stretched or contracted signal; The calculation circuit decomposes the expansion / contraction signal into a plurality of frequency components; the calculation circuit acquiring time-series phase information of the plurality of frequency components; a step in which the arithmetic circuit classifies the pattern of the biological activity based on the time-series phase information; An information processing method, including:

[0076] <Aspect 9> A program for causing an arithmetic circuit to execute the information processing method according to aspect 8. [Explanation of symbols]

[0077] 2 Acceleration sensor unit 11 Input / output section 12 Arithmetic circuit 13 Storage device 14 Communications Department 100 Gait Classification Device

Claims

1. An information processing device that classifies patterns of biological activity of an animal, a calculation circuit that receives a biological signal that is a detection result of biological activity of the animal detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors; The arithmetic circuit comprises: detecting a quasi-periodic signal from the detection result; stretching or contracting the quasi-periodic signal in a time direction to generate a stretched or contracted signal having a predetermined period; decomposing the stretched signal into a plurality of frequency components; acquiring time-series phase information of the plurality of frequency components; classifying the pattern of the biological activity based on the time-series phase information; Information processing device.

2. The information processing apparatus according to claim 1 , wherein the arithmetic circuit decomposes the expanded / contracted signal into a plurality of frequency components by performing a wavelet transform on the expanded / contracted signal.

3. The biological activity is movement of an animal, the sensor unit is an acceleration sensor unit attached to the animal; the detection result of the biological activity is acceleration measured by the acceleration sensor unit; The biological activity pattern is the gait of the animal.

3. The information processing device according to claim 1 or 2.

4. the animal is a quadrupedal animal; the arithmetic circuit classifies the pattern of biological activity by determining, based on the time-series phase information, which of predetermined gait patterns of a quadrupedal animal the pattern of biological activity corresponds to; The information processing device according to claim 3 .

5. The information processing device according to claim 4 , wherein the animal is a dog.

6. the sensor unit is an acceleration sensor unit attached to the animal; the detection result of the biological activity is acceleration measured by the acceleration sensor unit; the acceleration sensor unit is capable of measuring a first plurality of acceleration components of the acceleration corresponding to a plurality of directions different from each other, The arithmetic circuit comprises: In the process of detecting the quasi-periodic signal, a first plurality of quasi-periodic signals are detected from the first plurality of acceleration components measured by the acceleration sensor unit, respectively; In the process of generating the expanded / contracted signals, the first plurality of quasi-periodic signals are expanded or contracted in a time direction to generate expanded / contracted signals each having a predetermined period, and In the process of decomposing the expansion / contraction signal into a plurality of frequency components, each of the first plurality of expansion / contraction signals is decomposed into a second plurality of frequency components; In the process of acquiring time-series phase information of the plurality of frequency components, time-series phase information of at least one of the second plurality of frequency components corresponding to each of the first plurality of expansion / contraction signals is acquired; In the process of classifying the pattern of the biological activity, the pattern of the biological activity is classified using a phase object in which the phase information is arranged based on a time series.

3. The information processing device according to claim 1 or 2.

7. In the process of classifying the pattern of the life activity, when a period of one frequency component of the plurality of frequency components is T, the arithmetic circuit classifies the pattern of the life activity based on a feature of phase information of the time series corresponding to a portion of the frequency component at T / 4 or 3T / 4.

3. The information processing device according to claim 1 or 2.

8. An information processing method for classifying patterns of biological activity of an animal, comprising: a step in which an arithmetic circuit receives a biological signal, which is a detection result of biological activity of the animal, detected by a sensor having a plurality of detection channels or a sensor unit including a plurality of sensors, and detects a quasi-periodic signal from the detection result of biological activity; the arithmetic circuit stretches or contracts the quasi-periodic signal so that the period of the quasi-periodic signal after the stretching or contraction becomes a predetermined value, thereby generating a stretched or contracted signal; The calculation circuit decomposes the expansion / contraction signal into a plurality of frequency components; the calculation circuit acquiring time-series phase information of the plurality of frequency components; a step in which the arithmetic circuit classifies the pattern of the biological activity based on the time-series phase information; An information processing method, including:

9. A program for causing an arithmetic circuit to execute the information processing method according to claim 8.

Images