Exercise ability estimation device and exercise ability estimation method

Abstract

The present invention estimates a variation in exercise ability without depending on coordinate axes of a device. This exercise ability estimation device 1 comprises an exercise data acquisition unit 10 and an exercise ability estimation unit 20. The exercise data acquisition unit 10 acquires exercise data composed of data of each of three axes obtained by measuring periodic exercise of a prescribed part of an experiment participant. The exercise ability estimation unit 20 normalizes the variation in each piece of the exercise data, quantifies the normalized variations by using principal component analysis to project the quantified result onto a prescribed plane, and calculates a variation degree of the projected quantified result.

Description

Athletic ability estimation device and athletic ability estimation method

[0001] The present disclosure relates to a technique for estimating athletic ability.

[0002] Techniques for estimating athletic ability have been known for some time. For example, Patent Document 1 discloses a technique for evaluating variability in periodic exercise.

[0003] International Publication No. 2022 / 230097

[0004] However, the technology of Patent Document 1 only supports predetermined periodic motion. That is, evaluation is performed based on the variation of the predetermined periodic motion according to the coordinate system of the device. Therefore, the evaluation method is restricted to the coordinate system of the device, and the robustness of the evaluation method is not particularly high.

[0005] Therefore, an object of the present disclosure is to provide a technology for estimating variations in athletic ability without relying on the coordinate axes of a device.

[0006] The athletic ability estimation device disclosed herein includes an athletic data acquisition unit that acquires athletic data consisting of data for each of three axes obtained by measuring the periodic movements of specific parts of an experimental participant, and an athletic ability estimation unit that normalizes the variability of each piece of athletic data, quantifies the normalized variability using principal component analysis, projects it onto a specific plane, and calculates the degree of variability of the projected, quantified athletic data.

[0007] According to the athletic ability estimation device according to the embodiment of the present disclosure, the variation in athletic ability can be estimated without relying on the coordinate axes of the device.

[0008] FIG. 1 is a diagram showing an example of the functional configuration of an athletic ability estimation device according to this embodiment. FIG. 2 is a diagram showing an example of the processing flow of the athletic ability estimation device according to this embodiment. FIG. 3 is a diagram showing an example of exercise data acquisition by a smartphone. FIG. 4 is a diagram showing an example of a trajectory of periodic movement extracted using a conventional method. FIG. 5 is a diagram showing an example of a trajectory of periodic movement extracted by the athletic ability estimation device according to this embodiment. FIG. 6 is a diagram showing an example of a trajectory divided into periods in periodic movement extracted by a conventional method. FIG. 7 is a diagram showing an example of a trajectory divided into periods in periodic movement extracted by the athletic ability estimation device according to this embodiment. FIG. 8 is a diagram showing an example of the functional configuration of a computer.

[0009] <Character notation> In this disclosure, for example, the "~" at the top left of a character, such as "~x(t)", is normally positioned above the character, but in the text of the specification, the symbol that should be placed above the character is shifted to the left and written. On the other hand, in the mathematical formulas in the specification, it can be written, so it is written above the character. This point is － x" in the upper left corner of the character. － The same applies to ".

[0010] Embodiments Hereinafter, embodiments of the present disclosure will be described in detail. Note that components having the same functions are assigned the same numbers, and duplicated descriptions will be omitted.

[0011] FIG. 1 is a diagram showing an example of the functional configuration of an athletic ability estimation device according to this embodiment. As shown in FIG. 1, the athletic ability estimation device 1 of this embodiment includes an athletic data acquisition unit 10 and an athletic ability estimation unit 20. The athletic ability estimation unit 20 includes a normalization unit 21, a principal component analysis unit 22, and an evaluation unit 23. The athletic ability estimation device 1 performs the athletic ability estimation method of this embodiment by implementing the processing flow shown in FIG. 2. Below, with reference to FIG. 2, an example of the processing flow of the athletic ability estimation method in the athletic ability estimation device 1 will be described in procedural order.

[0012] The motion data acquisition unit 10 acquires motion data consisting of data for each of three axes, measuring the periodic motion of a predetermined part of the experimental participant (step S10). Here, the predetermined part is, for example, a part of a human body that exists on both the left and right sides, such as a hand or a foot. However, the estimation target of the athletic ability estimation device 1 of the present disclosure is not limited to this, and other parts of a human body may be used as long as they are parts on both the left and right sides and can measure periodic motion. Alternatively, other animals may be used, not just humans, as long as periodic motion can be measured. For convenience of explanation, the following description will be given using a human hand as an example.

[0013] The measuring device used for measurement may be, for example, a device that is equipped with an acceleration sensor, has the function of recording data, and can be held in the hand. Other examples of sensors that can be installed in the measuring device include a speed sensor, an angular velocity sensor, a magnetic sensor, and a GPS. When an acceleration sensor is used, a multi-axis acceleration sensor is preferable, and for example, a triaxial acceleration sensor can be used. An example of the measuring device is a smartphone. For example, the participant holds the measuring device in their right and left hands and repeatedly performs the same movement, such as a rotational movement. Note that if the measurement target is a part of the body that cannot be held by holding the measuring device, such as the foot, the measuring device can be placed in close contact with the part of the body to be measured, such as the foot, and then secured with a band or the like.

[0014] In the example shown in Figure 3, the participant rotates a device equipped with a three-axis acceleration sensor for 15 seconds, rotating it at least 30 times (N times). The diameter of the rotation circle is approximately 10 cm (see Figure 3). For example, measurements are taken once for each of the right and left hands.

[0015] The exercise data acquisition unit 10 records (buffers) the acquired exercise data for a certain period of time. The buffered exercise data is transmitted to the normalization unit 21. At this time, for example, the time immediately after the start of exercise may be removed from the data transmitted to the normalization unit 21. For example, data obtained by removing the first 1.5 seconds of the above-mentioned 15-second exercise may be transmitted to the normalization unit 21. Note that the function for removing the time immediately after the start may be provided in the athletic ability estimation unit 20, rather than in the exercise data acquisition unit 10.

[0016] In this example, if the movement is properly measured, the movement data will include at least the following data. For example, if the rotational movement of the right hand shown in Figure 3 is measured, the movement data will include time-series data showing the relationship between time and acceleration in each of the three axes (x-axis, y-axis, and z-axis) of the right hand movement. Therefore, one set of movement data will include at least three types of data.

[0017] The normalization unit 21 normalizes the variation of the motion data (step S21). The normalization performed by the normalization unit 21 is performed, for example, by the following method.

[0018] First, if there are N data points in the x-axis, y-axis, and z-axis directions in the motion data, the average value, － x, － y, － Calculate z.

[0019] Next, the average norm D is calculated by the following formula.

[0020] Next, the normalized values ​​~x(t), ~y(t), and ~z(t) are calculated using the following equations.

[0021] Although the above example uses the mean norm, other norms such as the maximum norm may be used for calculation. The calculated normalized values ​​~x(t), ~y(t), and ~z(t) are sent to the principal component analysis unit 22.

[0022] The principal component analysis unit 22 quantifies the normalized variations by principal component analysis and projects the quantified variations onto a predetermined plane (step S22). The principal component analysis by the principal component analysis unit 22 is performed, for example, as follows.

[0023] First, the covariance C of [~x(t), ~y(t), ~z(t)] is subjected to singular value decomposition, and the eigenvectors V are rearranged according to the magnitude of the eigenvalues ​​D to obtain the rotation matrix R.

[0024] Next, the rotation matrix R is used to rotate [~x(t), ~y(t), ~z(t)], and the rotated data [X(t), Y(t), Z(t)] is calculated. As a result, three-dimensional data is generated in which the top two axes with the largest variances among X, Y, and Z are regarded as the principal components. For example, if the above-mentioned principal components are X and Y, the three-dimensional data is generated as projected onto the XY plane. In other words, the above-mentioned predetermined plane is a plane formed by the top two axes with the largest variances among the quantified variations.

[0025] The calculated [X(t), Y(t), Z(t)] is sent to the evaluation unit 23.

[0026] The evaluation unit 23 calculates the degree of dispersion of the projected quantified motion data (hereinafter also referred to as "degree of dispersion σ") (step S23). The degree of dispersion σ is calculated by the following method.

[0027] First, the position where atan2 = 0 is considered to be the point where a new cycle will begin (hereinafter also referred to as the "extraction point"), and the cycle is extracted starting from this extraction point. For example, if the principal components mentioned above are X and Y, the extraction point is calculated using the following formula: The extracted period in the above example is generated as three-dimensional data projected onto the XY plane. This extraction is performed for the entire period M. The extraction point may be at another angle.

[0028] Next, as shown in the following equation, the distance d between the locus extracted from the nth period (the collective locus of the variation in the nth period) and the locus extracted from the n+1th period (the collective locus of the variation in the n+1th period) is ｎ is calculated over the entire period M to obtain the degree of variation σ. Here, the distance d ｎ may be calculated, for example, by the Hausdorff distance described in Reference 1 below.

[0029] (Reference Non-Patent Document 1: Huttenlocher, Daniel P., Gregory A. Klanderman, and William J. Rucklidge. "Comparing images using the Hausdorff distance." IEEE Transactions on Pattern Analysis and Machine Intelligence 15.9 (1993): 850-863. <URL: https: / / ieeexplore.ieee.org / abstract / document / 232073>)

[0030] The calculated degree of variation σ may be output as a numerical value as a result of the athletic ability estimation device 1, or the generated three-dimensional data may be displayed as a trajectory. That is, the trajectory of the quantified athletic data projected onto a predetermined plane may be displayed. Alternatively, both the numerical value of the degree of variation σ and the trajectory of the generated three-dimensional data may be displayed. Furthermore, by specifying the numerical value of an arbitrary period number n, it may be configured to display, for example, a trajectory extracted from the nth period and a trajectory extracted from the (n+1)th period superimposed on each other.

[0031] Fig. 4 is a diagram showing an example of a trajectory of periodic movement extracted by a conventional method. Here, the technology of Patent Document 1 is used as the conventional method. Fig. 5 is a diagram showing an example of a trajectory of periodic movement extracted by the athletic ability estimation device according to this embodiment. Fig. 5 uses the same movement data as Fig. 4. In each of Figs. 4 and 5, (a) shows the trajectory of periodic movement of the left hand, and (b) shows the trajectory of periodic movement of the right hand.

[0032] The conventional method described in Patent Document 1 could only evaluate predetermined periodic movements, and so when attempting to extract each periodic movement using a device task system, it was sometimes possible to extract only a trajectory that appeared to be a reciprocating movement on a single axis, as shown in particular in (a) of Figure 4. When the athletic ability estimation device 1 disclosed herein is used, principal component analysis is performed, and the movement is rotated in a direction that makes it easier to confirm that it is a periodic movement, as shown in Figure 5, making it easier to confirm the variation in the movement trajectory. In other words, performing principal component analysis of movement expands the periodic movements that can be evaluated, improving feedback to the experiment participants.

[0033] Fig. 6 is a diagram showing an example of a trajectory divided into periods in periodic movement extracted by a conventional method. Here, the technology of Patent Document 1 is used as the conventional method. Fig. 7 is a diagram showing an example of a trajectory divided into periods in periodic movement extracted by the athletic ability estimation device according to this embodiment. Fig. 7 uses the same movement data as Fig. 6. In Figs. 6 and 7, (a) is a diagram of the trajectory of periodic movement of the left hand, and (b) shows the trajectory obtained by cutting out the nth period and the trajectory obtained by cutting out the (n+1)th period in (a).

[0034] Conventional methods have been unable to accurately extract periods, resulting in the data for one revolution being mistakenly divided into two pieces, as shown in (b) of Figure 6, resulting in failure to quantify the variability of periodic movement. The method using the athletic ability estimation device 1 of the present disclosure performs principal component analysis to rotate the data in a direction that makes it easy to confirm that it is periodic movement, thereby correctly separating the data for each period, as shown in (b) of Figure 7, improving the accuracy of the variability assessment. That is, as shown in Figures 6 and 7, the athletic ability estimation method using the athletic ability estimation device 1 of the present disclosure is more robust to dividing the data into periods and can improve the stability of the variability assessment.

[0035] As described above, the athletic ability estimation device according to the present disclosure performs principal component analysis of movements to expand the range of periodic movements that can be evaluated, thereby improving feedback to participants. Furthermore, the device is more robust when dividing data into periods, improving the stability of variability assessment. Therefore, the athletic ability estimation device according to the present disclosure can estimate variability in athletic ability without relying on the coordinate axes of the device.

[0036] The various processes described in the embodiments of the present disclosure may not only be performed in chronological order according to the order described, but may also be performed in parallel or individually depending on the processing capacity of the device performing the processes or as needed.

[0037] Furthermore, a device (terminal) for using the device of the present disclosure or the method of the present disclosure via a network (telecommunications line) may also be provided. The "device (terminal) for using" may be provided with functions (e.g., control function, decoding function, restoration function, input / output function, etc.) necessary to obtain the effects of implementing the device of the present disclosure or the method of the present disclosure.

[0038] [Processor, Program, Recording Medium] The functions performed by the components described herein may be implemented in circuitry or processing circuitry, including general-purpose processors, application-specific processors, integrated circuits, ASICs (Application Specific Integrated Circuits), a CPU (a Central Processing Unit), conventional circuits, and / or combinations thereof, programmed to perform the described functions. A processor includes transistors and other circuits and is considered to be circuitry or processing circuitry. A processor may also be a programmed processor that executes a program stored in a memory.

[0039] In this specification, a circuitry, unit, or means is hardware that is programmed to realize or performs the described functions, which may be any hardware disclosed herein or any hardware known to be programmed to realize or perform the described functions.

[0040] If the hardware is a processor considered to be a type of circuitry, the circuitry, means, or unit is a combination of the hardware and software used to configure the hardware and / or processor.

[0041] The various processes described above can be implemented by loading a program that executes each step of the above method into the recording unit 2020 of the computer 2000 shown in Figure 8, and operating the control unit 2010, input unit 2030, output unit 2040, display unit 2050, etc.

[0042] The program describing the processing contents can be recorded on a computer-readable recording medium, which may be, for example, a magnetic recording device, an optical disk, a magneto-optical recording medium, a semiconductor memory, or any other suitable recording medium.

[0043] The program may be distributed by, for example, selling, transferring, lending, etc. portable recording media such as DVDs and CD-ROMs on which the program is recorded. Furthermore, the program may be stored in a storage device of a server computer, and then transferred from the server computer to other computers via a network, thereby distributing the program.

[0044] A computer that executes such a program may first temporarily store the program recorded on a portable recording medium or transferred from a server computer in its own storage device. Then, when executing a process, the computer reads the program stored on its own recording medium and executes the process in accordance with the read program. Alternatively, the computer may read the program directly from a portable recording medium and execute the process in accordance with the program. Furthermore, the computer may execute the process in accordance with the received program each time a program is transferred from a server computer to the computer. Alternatively, the server computer may not transfer the program to the computer, but may instead execute the process through a so-called ASP (Application Service Provider) service, which realizes the processing function by issuing an execution instruction and obtaining the results. Furthermore, the server computer may execute the process at the terminal using a so-called SaaS (Software as a Service) service, which allows users to use part of a server computer along with the program. In this embodiment, the program includes information used for processing by an electronic computer that is equivalent to a program (such as data that is not a direct instruction to a computer but has properties that dictate computer processing).

[0045] Furthermore, in this embodiment, the device is configured by executing a predetermined program on a computer, but at least a part of the processing contents may be realized by hardware.

Claims

1. An athletic ability estimation device comprising: an athletic data acquisition unit that acquires athletic data consisting of data for each of three axes obtained by measuring the periodic movements of a specified part of an experimental participant; and an athletic ability estimation unit that normalizes the variability of each of the athletic data, quantifies the normalized variability using principal component analysis, projects it onto a specified plane, and calculates the degree of variability of the projected, quantified athletic data.

2. The athletic ability estimation device according to claim 1, wherein the predetermined plane is a plane formed by the top two axes with the largest variances of the quantified variation.

3. The athletic ability estimation device according to claim 2, wherein the athletic ability estimation unit displays a trajectory of the quantified athletic data projected onto the predetermined plane.

4. A method for estimating athletic ability, in which an athletic data acquisition unit of an athletic ability estimation device acquires athletic data consisting of data for each of three axes that measure the periodic movements of a specified part of an experimental participant, and an athletic ability estimation unit of the athletic ability estimation device normalizes the variability of each of the athletic data, quantifies the normalized variability using principal component analysis, projects it onto a specified plane, and calculates the degree of variability of the projected, quantified athletic data.

Images