Exercise ability estimation method, exercise ability estimation device, and program

Abstract

Provided is a method for accurately estimating the exercise ability of a part of a body using a numerical value calculated in consideration of age. The method uses data on a periodic exercise of the part of the body as exercise data, and includes: a variation calculation step in which an exercise ability estimation device calculates normalized exercise data by normalizing exercise data of a subject, and calculates the variation D of the exercise data of the subject from the normalized exercise data; and a skill index calculation step in which the exercise ability estimation device obtains the average ^D(α) of the variation of exercise data of a person of the same age as the subject and the standard deviation σ^D(α) of the variation of the exercise data of the person of the same age as the subject from the age α of the subject, the average of the variation of age-specific exercise data stored in a storage unit included in the exercise ability estimation device, and the standard deviation of the variation of the age-specific exercise data, and calculates a skill index SQ as the exercise ability of the subject from the variation D, the average ^D(α) of the variation, and the standard deviation σ^D(α) of the variation using a predetermined formula.

Description

Athletic ability estimation method, athletic ability estimation device, and program

[0001] The present invention relates to a technique for estimating motor skills of hands and feet.

[0002] Conventionally, the difference in motor ability of the hands and feet, that is, the dominant hand or foot, has been estimated by a survey using a questionnaire (see Non-Patent Documents 1 and 2). Furthermore, Patent Document 1 proposes a technology for estimating the dominant hand based on the variability of data related to periodic hand movements.

[0003] International Publication No. 2022 / 230097

[0004] RC Oldfield, “The assessment and analysis of handedness: the Edinburgh inventory,” Neuropsychologia, 9(1), pp.97-113, 1971. S. Coren, “The lateral preference inventory for measurement of handedness, footedness, eyedness, and earedness: Norms for young adults,” Bulletin of the Psychonomic Society, 31(1), pp.1-3, 1993.

[0005] However, in surveys using questionnaires, the response data to the questions tends to be biased toward the left or right, so for example, even if it is known that a person is right-handed, it is not possible to determine the degree of right-handedness, that is, the degree of hand or foot dominance. Furthermore, the technology of Patent Document 1 can estimate the degree of handedness in the sense that it is possible to estimate whether handedness has been corrected based on the difference between the variance in data related to the periodic movement of the right hand and the variance in data related to the periodic movement of the left hand, but it does not determine the degree of hand motor ability taking age into account. In order to know the degree of hand or foot motor ability taking age into account, it is necessary to quantify hand or foot motor ability taking age into account, but until now, there has been no method for accurately estimating hand or foot motor ability using a value calculated taking age into account.

[0006] Therefore, an object of the present invention is to provide a technology for accurately estimating the motor ability of a part of the body using a value calculated taking age into consideration.

[0007] In one aspect of the present invention, the motion data is data relating to periodic motion of a part of the body, and an athletic ability estimation device calculates normalized motion data by normalizing the motion data of the subject and calculates a variance D of the motion data of the subject from the normalized motion data; and the athletic ability estimation device calculates an average value ^D(α) of the variance of the motion data of people of the same age as the subject and a standard deviation σ of the variance of the motion data of people of the same age as the subject, based on the age α of the subject and the average value and standard deviation of the variance of the motion data for each age recorded in a recording unit included in the athletic ability estimation device. ^D(α) The variance D, the mean value of the variance ^D(α), and the standard deviation of the variance σ ^D(α) A skill index calculation step of calculating a skill index SQ as the motor ability of the subject using the following formula: (where M represents the normalized mean value and V represents the normalized standard deviation).

[0008] According to the present invention, it is possible to accurately estimate the motor ability of a part of the body using a value calculated taking age into consideration.

[0009] FIG. 1 is a diagram showing an example of the variance in movement data of the left and right hands. FIG. 2 is a diagram showing an example of the variance in movement data of the dominant hand and dominant foot by age. FIG. 3 is a diagram showing how the average value and standard deviation of the variance in movement data of the dominant hand and dominant foot by age are calculated by linear regression. FIG. 4 is a diagram showing an example of the skill index SQ. FIG. 5 is a diagram showing an example of the skill index SQ. FIG. 6 is a block diagram showing an example of the configuration of the athletic ability estimation device 100. FIG. 7 is a flowchart showing an example of the operation of the athletic ability estimation device 100. FIG. 8 is a diagram showing an example of the functional configuration of a computer that realizes each device in an embodiment of the present invention.

[0010] Hereinafter, embodiments of the present invention will be described in detail. Components having the same functions are given the same numbers, and duplicated explanations will be omitted.

[0011] <Technical Background> In an embodiment of the present invention, the variance in data related to periodic hand and foot movements (hereinafter referred to as movement data) is used to estimate hand and foot motor abilities. This makes it possible to quantify hand and foot motor abilities and to numerically indicate the degree of difference between left and right hand and foot motor abilities. Here, the periodic hand movement can be, for example, a movement in which a hand holding a measuring device equipped with a triaxial acceleration sensor rotates 40 or more times in a circle of approximately 5 cm diameter in 15 seconds. In this case, the movement data is time-series data of hand acceleration. Figure 1 is a diagram showing an example of the variance in left and right hand movement data. Figure 1 shows the results of a survey of the variance in left and right hand movement data for 262 subjects, including 203 right-handed subjects, 18 left-handed subjects, and 41 subjects who had corrected their right-handedness. The vertical axis of Figure 1 represents the variance in the movement data, and the horizontal axis represents left and right. As can be seen from Figure 1, the variance in the movement data is smaller for dominant hands. Furthermore, it can be seen that the difference between the variability of left-hand movement data and the variability of right-hand movement data is smaller for people who have been corrected to right-handedness than for right-handed or left-handed people. From the above, it can be said that the method of quantitatively estimating motor ability using the variability of movement data is reliable.

[0012] Figure 2 shows an example of the variability of motor data for dominant hand and dominant foot by age. Figure 2(A) shows the results of a survey of variability in motor data for dominant hand by age for 433 subjects. Figure 2(B) shows the results of a survey of variability in motor data for dominant foot by age for 138 subjects. The vertical axis of Figures 2(A) and 2(B) represents the variability of motor data, and the horizontal axis represents age. As can be seen from Figure 2, the variability decreases with growth until about age 20, then changes little and remains stable until about age 60, and then increases with aging after age 60. From the above, by estimating motor ability using the variability of motor data, it is possible to understand changes in motor ability with age.

[0013] Figure 3 shows how the mean and standard deviation of the variance in motor data for dominant hand and foot by age are calculated using linear regression. Figure 3(A) shows how the mean is calculated using linear regression. Figure 3(B) shows how the standard deviation is calculated using linear regression. The vertical axis of Figure 3(A) represents the variance in the motor data, and the horizontal axis represents age. The vertical axis of Figure 3(B) represents the standard deviation of the variance in the motor data, and the horizontal axis represents age. Figures 3(A) and 3(B) were obtained by linear regression of intervals with large changes in motor ability (e.g., the intervals from 4 to 17 years old and the intervals from 61 to 100 years old) and other intervals (e.g., the intervals from 18 to 60 years old). Figures 3(A) and 3(B) provide the mean and standard deviation of motor ability by age, respectively. This makes it possible to compare age-dependent motor ability with that of people of the same age.

[0014] Based on the above results, we define a Skill Quotient, which is an index of motor ability that can be intuitively understood. Specifically, the Skill Quotient SQ is defined by the following formula: Here, D is the variance of the exercise data of the person for whom the skill index SQ is calculated, α is the age of the person for whom the skill index SQ is calculated, ^D(α) is the average value of the variance of the exercise data of a person of age α, and σ ^D(α)is the standard deviation of the variation in the exercise data of a person of age α, M is the normalized mean value, and V is the normalized standard deviation. The values ​​of the normalized mean value M and the normalized standard deviation V are arbitrary, and can be, for example, M=100 and V=15.

[0015] The average value of motor ability of the same age^D(α) and the standard deviation of motor ability of the same age σ ^D(α) Since the skill index SQ is calculated using the above formula, it is possible to compare athletic ability with that of people of the same age.

[0016] In addition, if the skill index SQ value is M, it indicates that the person has average athletic ability among people of the same age, and if it is M+V, it indicates that the person has athletic ability that is in the top 33%.

[0017] The skill index SQ will be explained below with reference to Figures 4 and 5. Here, the skill index SQ is calculated assuming M=100 and V=15.

[0018] FIG. 4 shows an example of the skill index SQ. FIG. 4(A) shows the skill index SQ of the hands and feet of a certain subject P1. FIG. 4(B) shows the skill index SQ of the hands and feet of another subject P2. From FIG. 4(A), it can be seen that for subject P1, the left hand skill index SQ is smaller than the average of 100 due to the large variance in the left hand movement data. Furthermore, it can be seen that the left foot skill index SQ and the right foot skill index SQ are both smaller than 100 due to the large variance in the left and right foot movement data. Furthermore, from FIG. 4(B), it can be seen that for subject P2, the left hand skill index SQ and the right hand skill index SQ are both larger than 100 due to the small variance in the left and right hand movement data. Furthermore, it can be seen that the difference between the left hand skill index SQ and the right hand skill index SQ is also small for subject P2. In this way, by using the skill index SQ, it becomes possible to intuitively understand the difference in athletic ability between people of the same age.

[0019] 5A and 5B are diagrams showing examples of skill quotients SQ. Fig. 5A shows the skill quotient SQ of the hand of 7-year-old subject P3 when the skill quotient SQ is calculated without taking age into consideration. Fig. 5B shows the skill quotient SQ of the hand of 7-year-old subject P3 when the skill quotient SQ is calculated using equation (1) taking age into consideration. The equation for calculating the skill quotient SQ without taking age into consideration is as follows, and the skill quotient SQ in Fig. 5A was calculated with M=100 and V=15. Here, D is the variance of the exercise data of the person for whom the skill index SQ is calculated, ^D is the average value of the variance of the exercise data, and σ ^D represents the standard deviation of the variation in the movement data, M represents the normalized mean value, and V represents the normalized standard deviation.

[0020] Figure 5(A) shows that if the skill index SQ of 7-year-old subject P3, who is still developing, is calculated using equation (2), which does not take age into account, the skill index SQ will be a small value. Also, Figure 5(B) shows that if the skill index SQ of 7-year-old subject P3 is calculated using equation (1), which takes age into account, subject P3 has average motor ability for a 7-year-old child. This shows that estimating motor ability without taking age into account can lead to an incorrect assessment.

[0021] Finally, the distance used to calculate the variation in movement data will be described. In the technology of Patent Document 1, the variation is calculated using the Fréchet distance or the Euclidean distance, but the calculated distance value varies greatly depending on how one period is separated from the data related to periodic movement. Therefore, in an embodiment of the present invention, the variation is calculated using the Hausdorff distance. This makes it possible to calculate the distance robustly, without being affected by how one period is separated from the data related to periodic movement. Note that the variation may be calculated using the logarithm of the Hausdorff distance instead of the Hausdorff distance.

[0022] First Embodiment The athletic ability estimation device 100 will be described below with reference to FIGS. 6 and 7. FIG. 6 is a block diagram showing the configuration of the athletic ability estimation device 100. FIG. 7 is a flowchart showing the operation of the athletic ability estimation device 100. As shown in FIG. 6, the athletic ability estimation device 100 is connected to a measurement device 900. The measurement device 900 measures the periodic movement of a body part and outputs data related to the periodic movement of the body part (hereinafter referred to as movement data). Here, the body part refers to, for example, the right hand, left hand, right foot, and left foot. The measurement device 900 also includes a triaxial acceleration sensor, as described in the Technical Background section. In this case, the movement data is time-series data of the acceleration of the body part. The athletic ability estimation device 100 includes a variance calculation unit 110, a skill index calculation unit 120, and a recording unit 190. The recording unit 190 is a component that appropriately records information necessary for processing by the athletic ability estimation device 100. The recording unit 190 pre-records the average value of the variation of the exercise data for each age and the standard deviation of the variation of the exercise data for each age. The recording unit 190 also pre-records the normalized average value and the normalized standard deviation value. Here, the average value of the variation of the exercise data for each age can be obtained by calculating the variation of the exercise data obtained from a predetermined number of subjects and performing linear regression on the pair of age and variation for several age intervals. The standard deviation of the variation of the exercise data for each age can also be obtained by calculating the standard deviation using the variation calculated from the exercise data obtained from a predetermined number of subjects and the average value of the variation of the exercise data for each age, and performing linear regression on the pair of age and standard deviation for several age intervals. The method for calculating the variation is the same as in S110 described below. The age intervals may be, for example, intervals where athletic ability changes significantly (e.g., the interval from 4 to 17 years old or the interval from 61 to 100 years old) and other intervals (e.g., the interval from 18 to 60 years old).

[0023] The operation of the athletic ability estimation device 100 will be described with reference to FIG.

[0024] In S110, the variance calculation unit 110 receives the motion data of subject P output by the measurement device 900, normalizes the motion data to calculate normalized motion data, and calculates and outputs the variance D of the motion data of subject P from the normalized motion data. The variance calculation unit 110 normalizes the motion data, which is time-series data, using, for example, the mean, median, or maximum value of the motion data. Furthermore, the variance calculation unit 110 calculates the variance D by, for example, calculating the distance between motion data obtained by dividing the normalized motion data into data for one cycle using the Hausdorff distance. Note that the logarithm of the Hausdorff distance, the Fréchet distance, or the Euclidean distance may be used instead of the Hausdorff distance.

[0025] In S120, the skill index calculation unit 120 receives the age α of the subject P and the variance D calculated in S110 as input, and calculates the average value ^D(α) of the variance in the exercise data of people of the same age as the subject P and the standard deviation σ of the variance in the exercise data of people of the same age as the subject P from the age α of the subject P and the average value of the variance in the exercise data of each age recorded in the recording unit 190 and the standard deviation of the variance in the exercise data of each age. ^D(α) The variance D, the mean value of the variance ^D(α), and the standard deviation of the variance σ ^D(α) From this, the skill index SQ is calculated as the motor ability of subject P using the following formula and output. (where M represents the normalized mean value and V represents the normalized standard deviation.) According to the embodiment of the present invention, it is possible to accurately estimate the athletic ability of a part of the body using a value calculated taking age into consideration. Furthermore, it is possible to compare athletic ability by age using a value calculated taking age into consideration.

[0026] <Additional Notes> 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), CPUs (Central Processing Units), 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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 in its storage device 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 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 the 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).

[0033] 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.

[0034] The present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention. Furthermore, the processes described in the above embodiments may not only be executed in chronological order according to the order described, but may also be executed in parallel or individually depending on the processing capacity of the device that executes the processes or as needed.

Claims

1. The motion data is regarded as data related to the periodic motion of a part of the body. The motion ability estimation device calculates the normalized motion data by normalizing the motion data of the subject, and a variation calculation step of calculating the variation D of the motion data of the subject from the normalized motion data. The motion ability estimation device calculates the average value ^D(α) of the variation of the motion data of people of the same age as the subject and the standard deviation σ of the variation of the motion data of people of the same age as the subject from the age α of the subject and the average value of the variation of the motion data recorded for each age in the recording unit included in the motion ability estimation device and the standard deviation of the variation of the motion data recorded for each age. ^D(α) to obtain the variation D, the average value ^D(α) of the variation, and the standard deviation σ of the variation ^D(α) and a skill index calculation step of calculating a skill index SQ as the motion ability of the subject by the following formula: (where M represents the normalized average value and V represents the normalized standard deviation). A motion ability estimation method including this.

2. The method for estimating motor ability according to claim 1, wherein the part of the body is any one of the right hand, left hand, right foot, and left foot.

3. The method for estimating motor ability according to claim 1, wherein the variation calculation step calculates the variation D by calculating the distance between the motion data obtained by dividing the normalized motion data into data for one cycle by the Hausdorff distance.

4. The motion data is data related to the periodic motion of a part of the body. A recording unit records the average value of the variation in the motion data for each age and the standard deviation of the variation in the motion data for each age. A variation calculation unit calculates the normalized motion data by normalizing the motion data of the subject, and calculates the variation D of the motion data of the subject from the normalized motion data. From the age α of the subject, the average value ^D(α) of the variation in the motion data of people of the same age as the subject, and the standard deviation σ of the variation in the motion data for each age recorded in the recording unit ^D(α) are obtained, and from the variation D, the average value ^D(α) of the variation, and the standard deviation σ of the variation ^D(α) a skill index calculation unit calculates a skill index SQ as the motion ability of the subject according to the following formula: (where M represents the normalized average value and V represents the normalized standard deviation), a motion ability estimation device.

5. A program for causing a computer to execute the method for estimating motor ability according to any one of claims 1 to 3.

Images