Prediction device, prediction method, and prediction program

Abstract

To provide a prediction device, prediction method, and prediction program capable of predicting the running time of an athlete who competes by running a wheelchair, on the basis of expected values of items characterizing the physical ability of the athlete.SOLUTION: A prediction device 21 that predicts a running time of a subject who competes by running a wheelchair 1, comprises: a storage device 24 that stores, in association, measurement values of a plurality of items related to the physical ability of an athlete who competes and the running time of the athlete, acquired in the past; and a processor 22 that acquires expected values corresponding to the respective items, calculates and outputs a predicted value of the corresponding running time.SELECTED DRAWING: Figure 9

Description

[Technical Field]

[0001] The present invention relates to a prediction device, a prediction method, and a prediction program for predicting the running time of an athlete competing in a race by moving a wheelchair. [Background technology]

[0002] In racing wheelchairs used in track races, marathons, etc., there is a need to accurately determine the position on the hand rim where the driving force from the occupant is applied, for the purpose of training the occupant. Accordingly, Patent Document 1 discloses an application position estimation system that can accurately estimate the position where the driving force of the wheelchair occupant is applied. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7157723 Summary of the Invention [Problem to be solved by the invention]

[0004] In track races, marathons, and other events using wheelchairs, running times are competed against each other. The position at which the driving force is applied, obtained by the driving force application position estimation system of Patent Document 1, can be a factor that determines running time. However, it is thought that running time also depends on factors that characterize physical ability other than the driving force application position.

[0005] The inventors of the present application thought that if they could predict how running time would change by inputting expected values ​​after training for items that characterize an athlete's physical abilities, they could provide training suggestions to athletes and coaches.

[0006] In view of the above background, an object of the present invention is to provide a prediction device, a prediction method, and a prediction program that can appropriately predict the running time of an athlete competing in a race by moving a wheelchair, based on expected values ​​of items that characterize the athlete's physical abilities. [Means for solving the problem]

[0007] In order to solve the above problem, one aspect of the present invention is a prediction device (21) that predicts the running time of a subject competing in a competition by moving a wheelchair (1), and includes a storage device (24) that stores a measurement value corresponding to at least one item related to the physical ability of the athlete competing in the competition, which has been obtained in the past, in association with the athlete's running time, and a processor (22) that obtains an expected value corresponding to the item, calculates and outputs a predicted value of the corresponding running time.

[0008] According to this aspect, it is possible to refer to the measurement values ​​of each of multiple items related to the physical ability of the athlete participating in the competition that have been obtained in the past, and the athlete's running time, so that the running time can be appropriately predicted based on the expected values ​​of the items that characterize the athlete's physical ability.

[0009] In the above aspect, the items preferably include at least one of six abilities: speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and power ability.

[0010] According to this aspect, it is possible to set items that characterize the physical abilities of the athlete.

[0011] In the above aspect, preferably, the movable angular capacity is obtained as the angle difference from a contact start position where the athlete starts contacting the hand rim to a contact end position where the athlete ends contacting the hand rim.

[0012] According to this aspect, the movable angle capability can be appropriately evaluated.

[0013] In the above aspect, preferably, the endurance ability is acquired by having the athlete run around a track multiple times and calculating the degree of reduction in the time required to run around one track.

[0014] According to this aspect, endurance ability can be appropriately evaluated.

[0015] In the above aspect, preferably, the rhythmic ability is obtained by calculating a correlation coefficient of a waveform showing the change over time in the driving force applied by the athlete when the rear wheels of the wheelchair rotate once or the tangential component of the driving force applied to the hand rim.

[0016] According to this embodiment, rhythmic ability can be appropriately evaluated.

[0017] In the above aspect, the discrimination ability is preferably obtained by the ratio of the tangential force, which is the tangential component of the driving force exerted by the athlete in the direction tangential to the hand rim, to the pressing force, which is the resultant force of the components of the driving force excluding the tangential component.

[0018] According to this aspect, the discrimination ability can be appropriately evaluated.

[0019] In the above aspect, the items preferably include at least four of six items: speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and power ability.

[0020] According to this embodiment, the items that characterize the physical abilities of the athlete can be set more appropriately.

[0021] In the above aspect, preferably, the wheelchair (1A) includes a body frame (3), a rear wheel (13), a hand rim (15) attached to the rear wheel, and sensors (43, 44) for detecting the force applied to the hand rim and the rotational position of the hand rim, and the measurements are obtained by having the athlete travel using the wheelchair.

[0022] According to this aspect, the measurement value can be appropriately acquired.

[0023] In the above aspect, preferably, the storage device stores a running log for each of the multiple athletes in which the measurement values ​​for each of the items and the corresponding running times are associated and recorded, and the processor uses the running log to derive a prediction model showing the relationship between the measurement values ​​and the running times, and predicts the running times using the prediction model and the expected values.

[0024] According to this aspect, the running time can be predicted by a simple method.

[0025] In the above aspect, preferably, the processor obtains the prediction model by performing multiple regression analysis using the measured values ​​of each of the items for each athlete and the corresponding running time.

[0026] According to this aspect, a prediction model for predicting a running time can be obtained.

[0027] In order to solve the above problems, one aspect of the present invention is a prediction method for predicting the running time of a subject competing in a competition by moving a wheelchair (1), which is executed by a prediction device comprising: a memory device (24) that stores past measured values ​​of each of a plurality of items related to the physical ability of the athlete competing in the competition in association with the athlete's running time; and a processor (22), wherein the processor obtains expected values ​​corresponding to each of the items, calculates and outputs a predicted value of the corresponding running time.

[0028] According to this aspect, it is possible to refer to the measurement values ​​of each of multiple items related to the physical ability of the athlete participating in the competition that have been obtained in the past, and the athlete's running time, so that the running time can be appropriately predicted based on the expected values ​​of the items that characterize the athlete's physical ability.

[0029] In order to solve the above-mentioned problems, one aspect of the present invention is a prediction program for predicting the running time of a subject competing in a competition by moving a wheelchair (1), the prediction program being executed by a prediction device comprising: a storage device (24) that stores past measured values ​​of a plurality of items related to the physical ability of the athlete competing in the competition in association with the athlete's running time; and a processor (22), wherein the processor obtains expected values ​​corresponding to each of the items, calculates and outputs a predicted value of the corresponding running time.

[0030] According to this aspect, it is possible to refer to the measurement values ​​of each of multiple items related to the physical ability of the athlete participating in the competition that have been obtained in the past, and the athlete's running time, so that the running time can be appropriately predicted based on the expected values ​​of the items that characterize the athlete's physical ability. [Effects of the Invention]

[0031] According to the above configuration, it is possible to provide a prediction device, a prediction method, and a prediction program that can appropriately predict the running time of an athlete competing by moving a wheelchair based on the expected values ​​of items that characterize the athlete's physical abilities. [Brief explanation of the drawings]

[0032] [Figure 1] Side view of wheelchair and measuring device [Figure 2] Top view of wheelchair and measuring device [Figure 3] System configuration diagram of the prediction device [Figure 4] Functional block diagram of the prediction device [Figure 5] Example of a driving log [Figure 6] An explanatory diagram to explain the arm movements of an athlete when driving a wheelchair and the COP angle range. [Figure 7] Graph to explain how to acquire endurance ability [Figure 8]A table showing the combinations of explanatory variables and the accuracy rate obtained for each. [Figure 9] Example of a display screen including a column for accepting changes DETAILED DESCRIPTION OF THE INVENTION

[0033] Hereinafter, a prediction device, a prediction method, and a prediction program according to the present invention will be described with reference to the drawings.

[0034] The prediction device, prediction method, and prediction program according to the present invention are used in training an athlete who competes by moving a wheelchair 1, and are used to predict the athlete's post-training record before training. The competitions for which records are predicted using the prediction device, prediction method, and prediction program are competitions in which the running time required to run a predetermined distance is competed for, and may include track races, marathons, etc.

[0035] FIG. 1 shows a side view of a wheelchair 1 used in competition, and FIG. 2 shows a top view of the wheelchair 1 shown in competition.

[0036] 1 and 2, the wheelchair 1 includes a body frame 3, a cockpit 5 where a rider sits, and a steering handle 7. A front wheel 9 (steering wheel) and a front fork 11 are provided at the front of the body frame 3. A pair of left and right rear wheels 13 (drive wheels) and hand rims 15 are provided at the rear of the body frame 3.

[0037] The rear wheels 13 are rotatably supported on the body frame 3 on the left and right sides of the cockpit 5. Hand rims 15 are provided on each rear wheel 13 on the side opposite the cockpit 5. When the athlete sits in the cockpit 5 and pushes in on the hand rims 15, a driving force is applied to rotate the rear wheels 13, and the wheelchair 1 moves.

[0038] The prediction device 21 executes a prediction program to implement a prediction method for predicting post-training records. Specifically, the prediction device 21 obtains expected post-training values ​​for each of multiple items that indicate the physical ability of the target athlete, and obtains and outputs a predicted running time after training based on the expected values. This allows the athlete and a trainer who provides training guidance to the athlete to understand how the predicted running time will change by changing the expected values, and therefore understand the content of the training that should be performed. Hereinafter, the athlete whose running time is to be predicted will be referred to as the prediction target.

[0039] As shown in Figure 3, the prediction device 21 is composed of a computer including a processor 22 such as a CPU or MPU, a memory 23 such as a RAM or ROM, a storage device 24 (also called storage) such as an SSD or HDD, a display device 25 such as a display, and an input device 26 such as a keyboard or mouse.

[0040] The prediction device 21 includes functional units for acquiring and outputting predicted values, such as a memory unit 31, a prediction formula generation unit 32, an input reception unit 33, a prediction execution unit 34, and an output unit 35, as shown in FIG. 4.

[0041] The memory unit 31 may be configured by the storage device 24. The memory unit 31 stores a running log 31A. The running log 31A records the measured values ​​of each of a plurality of items indicating the physical abilities of each athlete, which were measured in the past for a plurality of athletes, in association with the running times of the athletes.

[0042] An example of a running log 31A is shown in Figure 5. The items indicating the athlete's physical ability include at least five of the following six categories: speed ability, angular mobility ability, endurance ability, rhythm ability, discrimination ability, and power ability.

[0043] The prediction device 21 may include a measurement wheelchair 1A for acquiring the measurement values ​​included in the running log 31A. In this case, the measurement values ​​corresponding to at least one item included in the running log 31A are acquired by the evaluator having the athlete run using the measurement wheelchair 1A.

[0044] As shown in Figures 1 and 2, the measurement wheelchair 1A has a configuration similar to that of the wheelchair 1 used in competitions, and may further include various sensors, such as a driving force detection sensor 43 that detects the driving force applied to the hand rims 15 and a rotation angle sensor 44 that detects the rotation angle of the hand rims 15 (i.e., the rotation angle of the rear wheels 13, also referred to as the rotation position). The driving force detection sensor 43 may include a strain gauge sensor provided on the outer surface of the hand rim 15. The measurement wheelchair 1A may be provided with a transmitting device (not shown) that outputs the detection results of the driving force detection sensor 43 and the rotation angle sensor 44 as wireless signals. The measurement wheelchair 1A may also be provided with storage (not shown) that holds and stores the detection results of the driving force detection sensor 43 and the rotation angle sensor 44.

[0045] Speed ​​ability is an index showing the quickness of an athlete, and is expressed by the maximum rotational speed of the rear wheel 13 that the athlete can achieve.

[0046] 1 and 2 show a wheelchair 1 (specifically, a measurement wheelchair 1A) as well as an example of a measurement device 40 used to measure the speed ability of an athlete.

[0047] The measuring device 40 has an ergometer arranged so as to come into contact with each rear wheel 13. The ergometer includes rollers 42 that come into contact with the rear wheels 13 of the wheelchair 1, a motor (not shown) that rotates the rollers 42, and a torque meter (not shown). The torque meter detects the rotational state (i.e., torque, rotational speed, etc.) of the rollers 42.

[0048] In this embodiment, when the athlete runs at full speed with no load being generated by the motor, the rotational speed of the roller 42 measured by the torque meter or the maximum value (maximum speed) obtained by the rotational angle sensor 44 included in the rear wheel 13 is acquired as a characteristic quantity of speed ability.

[0049] The movable angle ability is an index that represents the range of hand movement in a total physical movement, and specifically corresponds to the area where the athlete presses (contacts) the hand rim 15 when rotating the rear wheel 13 once.

[0050] In this embodiment, the movable angular capacity is expressed by the COP angle range. The COP (center of pressure) here refers to the point (application position) at which the driving force (pressure) is centered when the athlete applies the driving force to the hand rim 15.

[0051] When driving the wheelchair 1, the athlete makes contact with the hand rim 15 (FIG. 6(A)), pushes the hand rim 15 to rotate it (FIG. 6(B)), then releases the hand rim 15 (FIG. 6(C)), and then pushes the hand rim 15 again (FIG. 6(D)). The COP angle range θ is defined as the angle difference between the position P1 (contact start position) where contact with the hand rim 15 begins and the position P2 (contact end position) where contact with the hand rim 15 ends when the athlete rotates the rear wheel 13 once and drives the wheelchair 1 at full speed, as shown in FIG. 5(B). In other words, the COP angle range θ is expressed by the angle between the line connecting the axle center O of the rear wheel 13 to P1 and the line connecting the axle center O to P2. Using the COP angle range in this way allows for an appropriate evaluation of the vehicle's angular mobility.

[0052] The COP angle range can be measured using an application position estimation system that detects the COP. The application position estimation system can be configured, for example, by a driving force detection sensor 43 and a rotation angle sensor 44. Alternatively, the application position estimation system can be configured, for example, by the method described in Japanese Patent No. 7157723. The COP angle range can be obtained, for example, by using the application position estimation system described in Japanese Patent No. 7157723 to connect the COP positions when the athlete rotates the rear wheel 13 once. Alternatively, the application position estimation system can be configured using a computer (evaluation device) that estimates the rotation angle of the hand rim 15 based on the measurement results of the measurement device 40 and determines the range in which driving force is applied based on the detection results of the driving force detection sensor 43, thereby calculating the COP angle range.

[0053] Endurance ability is an index that indicates the limit power that can be sustained for a long period of time without fatigue, and corresponds to a feature amount that indicates the degree of attenuation of maximum speed according to the distance traveled.

[0054] Endurance ability is measured by having the athlete run around the track multiple times using the measurement wheelchair 1A and calculating the degree of reduction in the time required to run one track. In this embodiment, the evaluator assessing endurance ability has the athlete run three laps of a 400m track at full speed, obtaining the maximum speed in six straight sections. The maximum speed may be calculated by obtaining the rotational speed of the wheel and using the wheel outer diameter. Then, as shown in Figure 7, the evaluator plots the running order of the straight section on the horizontal axis and the maximum speed on the vertical axis, and obtains the slope of the linear approximation as a measurement value of endurance ability. Using this slope, which indicates the degree of reduction, allows for an appropriate and simple evaluation of endurance ability.

[0055] Rhythmic ability (also called coordination ability) is an index that indicates the characteristics of the rhythm of the movement when the athlete operates the rear wheel 13, and increases as the change in the rhythm of the movement decreases.

[0056] Rhythmic ability is expressed, for example, by the driving force applied when the athlete rotates the rear wheel 13 of the wheelchair 1 once, or by the correlation coefficient of a waveform showing the time change in the tangential component of the driving force at the hand rim 15. In this embodiment, the evaluator evaluating rhythmic ability has the athlete run 300 meters on a 400-meter track using a wheelchair 1 (measurement wheelchair 1A) equipped with a driving force detection sensor 43. Using the detection results of the driving force detection sensor 43, the evaluator obtains waveforms λ1 to λ4 showing the time change in the tangential force (the tangential component of the driving force at the hand rim 15) for four rotations (four strokes) of the rear wheel 13 before reaching maximum speed in a straight section just before the 300-meter run (note that the subscripts 1 to 4 indicate the running order).

[0057] Next, the evaluator calculates the correlation coefficients for the combinations of adjacent waveforms in the running order, i.e., the correlation coefficients between λ1 and λ2, the correlation coefficients between λ2 and λ3, and the correlation coefficients between λ3 and λ4, and obtains the average of these correlation coefficients as a measurement value indicating rhythmic ability. The more similar the waveforms are (i.e., the more consistent the rhythm), the higher the measurement value indicating rhythmic ability. Note that the tangential force may be obtained using a six-axis force sensor (not shown) installed between the hand rim 15 and the drive wheel (rear wheel 13), as described in Japanese Patent No. 7157723. In this way, using the correlation coefficients for waveforms λ1 to λ4 allows for an appropriate and simple evaluation of rhythmic ability.

[0058] Discrimination ability is an indicator of an athlete's ability to grasp their own physical condition and surrounding circumstances and to operate the wheelchair precisely. For example, discrimination ability relates to the degree to which the driving force exerted by the athlete contributes to the movement of wheelchair 1.

[0059] In this embodiment, the athlete runs at full speed for 1200 m (three laps around a 400 m track) using the measurement wheelchair 1A, and the evaluator uses the detection results of the driving force detection sensor 43 to obtain the tangential component of the driving force, i.e., the tangential force, and the resultant force of the components of the driving force excluding the tangential component (hereinafter referred to as the hand rim pressing force, or simply the pressing force). The evaluator calculates the discrimination ability as the ratio between the tangential force and the hand rim pressing force, i.e., discrimination ability = tangential force / hand rim pressing force. This allows for an appropriate and simple evaluation of discrimination ability.

[0060] The power capacity is an index showing the instantaneous power, and corresponds to the maximum tangential force (the maximum value of the tangential component of the driving force of the hand rim 15) that the athlete can exert.

[0061] The athlete uses a wheelchair 1 (measurement wheelchair 1A) equipped with a driving force detection sensor 43 to run 1200m at full speed, a 100m sprint, and a 300m sprint, and the evaluator uses the detection results of the driving force detection sensor 43 to obtain the tangential force for each stroke, and obtains the maximum value as a characteristic of force ability.

[0062] The running times of the athletes included in the running log 31A are running times for a race in which the prediction target person competes, and may be three-minute running distances or 1200m running times. In this embodiment, the race in which the prediction target person competes is a 1200m race, and the running log 31A records the running times for the 1200m race for each athlete.

[0063] The running log 31A includes the measured values ​​of the endurance ability, speed ability, movable angle ability, strength ability, and discrimination ability of the person whose running time is being predicted, as well as the running time at the time the measurements were taken.

[0064] The prediction formula generation unit 32 may be configured with a memory 23, a storage device 24, and a processor 22. Using the driving log 31A, the prediction formula generation unit 32 performs multiple regression analysis with the driving time y as the objective variable and five or more of the measured values ​​xi (i = 1 to 6) of each item as explanatory variables, to calculate a regression formula. The regression formula is given by the following formula (1).

[0065]

number

[0066] In equation (1), w i (i=1 to 6) are predetermined coefficients, x1, x2, x3, x4, x5, and x6 represent the measured value of endurance ability, the measured value of speed ability, the measured value of angular mobility ability, the measured value of strength ability, the measured value of rhythm ability, and the measured value of discrimination ability, respectively, and Z represents the intercept term.

[0067] In order to select an appropriate regression equation, the prediction equation generating unit 32 performs an evaluation process for each of all combinations that include five or more explanatory variables, and selects the optimal regression equation.

[0068] In the evaluation process, the prediction formula generation unit 32 first calculates the coefficients w other than the items selected as explanatory variables. i is set to zero, and multiple regression analysis is performed to obtain a regression equation (prediction model). When obtaining the regression equation, the prediction equation generation unit 32 separates the driving log 31A into learning data and test data, and obtains the regression equation using only the learning data. The prediction equation generation unit 32 uses the regression equation to verify consistency with the test data (cross-validation).

[0069] In this embodiment, the running log 31A includes data for N people (N is an integer equal to or greater than 4), and the prediction formula generation unit 32 selects data for two people as test data and sets data for N-2 people as learning data. Next, the prediction formula generation unit 32 generates a regression formula from the learning data, and uses the generated regression formula to obtain predicted values ​​of the running times of the two people in the test data, and determines whether the magnitude relationship of the predicted values ​​matches the magnitude relationship of the measured running times of the two people in the test data.

[0070] The prediction formula generation unit 32 selects test data for all combinations and verifies consistency for each combination (i.e., determines whether the magnitude relationship between the predicted values ​​and the measured values ​​matches). The prediction formula generation unit 32 obtains the consistency rate (correct answer rate) as an evaluation value for the regression formula (learning model).

[0071] The prediction formula generating unit 32 obtains the accuracy rate for all cases including five or more explanatory variables, and selects the regression formula with the highest accuracy rate to obtain it as the prediction formula.

[0072] Fig. 8 shows combinations of explanatory variables and the accuracy rate obtained for each. In the example of Fig. 8, the accuracy rate is highest when five items excluding rhythmic ability are used as explanatory variables (see the colored part in Fig. 8). Therefore, the prediction formula generation unit 32 obtains, as the prediction formula, the regression formula obtained when five items excluding rhythmic ability are used as explanatory variables.

[0073] The prediction formula generation unit 32 obtained a prediction formula for obtaining a predicted value by performing multiple regression analysis, but the prediction formula is an example of a prediction model for obtaining a predicted value generated from the driving log 31A, and the prediction formula generation unit 32 may also obtain a predicted value by using various other prediction models.

[0074] The input receiving unit 33 includes the memory 23, the processor 22, the display device 25, and the input device 26, and can be configured by the processor 22 executing a predetermined program. The input receiving unit 33 causes the display device 25 (display) to display a display screen 52 including a field 50 for receiving the amount of change (also referred to as the expected amount of improvement) of the item acquired as the explanatory variable.

[0075] FIG. 9 shows an example of a display screen 52 including a change amount acceptance field 50. The example shown in FIG. 9 corresponds to a case where five explanatory variables, namely, endurance ability, speed ability, strength ability, rhythm ability, and discrimination ability, are selected. The display screen 52 has change amount acceptance fields 50 corresponding to the five items corresponding to the selected explanatory variables. Each acceptance field 50 is made up of a slider 50A for accepting input of an increase rate (%) and an input field 50B for accepting numerical input. When the display screen 52 is displayed, the value of each slider 50A is set to 0 (the increase rate is 0).

[0076] When the change amount is input, the input receiving unit 33 acquires the measurement values ​​of the prediction target person for the items corresponding to the explanatory variables from the driving log 31A, and calculates an expected value that reflects the change amount input in the reception field 50. In this embodiment, the input receiving unit 33 accepts input of the increase rate in the reception field 50, so it acquires the measurement values ​​of the prediction target person for the items corresponding to the explanatory variables, and multiplies the measurement values ​​by the increase rate to obtain an expected value. Once acquisition of the expected value is complete, the input receiving unit 33 outputs the measurement values ​​of the items corresponding to the explanatory variables and the corresponding expected value to the prediction execution unit 34.

[0077] The prediction execution unit 34 can be configured by executing a predetermined program by the processor 22. When the prediction execution unit 34 acquires an expected value for each item corresponding to the explanatory variable from the input reception unit 33, the prediction execution unit 34 substitutes the expected value into the regression equation expressed by equation (1) to acquire a predicted value of the running time.

[0078] The prediction execution unit 34 outputs the acquired predicted value of the running time to the output unit 35. In this embodiment, the prediction execution unit 34 outputs to the output unit 35 the measured value for each item corresponding to the explanatory variable and the corresponding expected value, along with the predicted value of the running time.

[0079] The output unit 35 may be configured by the display device 25. When the output unit 35 acquires the predicted value of the running time from the prediction execution unit 34, it displays the predicted value of the running time in a display field 54 provided on the display screen 52.

[0080] In this embodiment, the display screen 52 is provided with a display field 56 showing the predicted value of the running time calculated using the regression equation when the items corresponding to the explanatory variables are measured values, and a display field 58 showing the measured value of the running time at that time.

[0081] In this embodiment, the output unit 35 further displays the measurement values ​​for each item acquired from the prediction execution unit 34 and their respective expected values ​​on the display screen 52. In the example shown in Fig. 9, five items, endurance ability, speed ability, strength ability, rhythm ability, and discrimination ability, have been selected as explanatory variables, and therefore the respective measurement values ​​(dashed lines) and expected values ​​(bold lines) are shown by a radar chart 60. The radar chart 60 also shows ideal values ​​(solid lines) for the five explanatory variables.

[0082] Next, the operation and effects of the prediction device 21, the prediction method, and the prediction program configured as described above will be described.

[0083] The storage device 24 of the prediction device 21 stores, as a running log 31A, measurement values ​​of each of a plurality of items related to the physical ability of an athlete participating in a competition that have been acquired in the past, in association with the athlete's running time.

[0084] When the display screen 52 is displayed, the processor 22 executes a prediction program that implements the prediction method. The processor 22 (prediction execution unit 34) first obtains the amount of change from the input value (in this case, the increase rate is 0) in the reception field 50, and calculates an expected value for each item corresponding to the explanatory variable. The processor 22 (prediction execution unit 34) then calculates a predicted value for the running time of the person being predicted, and displays the predicted value in the display field 54 of the display (output unit 35).

[0085] The items corresponding to the explanatory variables include at least five of the six items: speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and force ability. As shown in Figure 8, it can be seen that when five or more of these items are included, the accuracy rate exceeds 70%. From this, it can be seen that running time can be predicted by using the five items corresponding to the explanatory variables: speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and force ability.

[0086] When the athlete or coach operates slider 50A provided on display screen 52 (or inputs into input field 50B), processor 22 (input receiving unit 33, prediction execution unit 34) acquires the amount of change, calculates an expected value, and causes the display (output unit 35) to display the measured value and the expected value as a radar chart 60. Furthermore, processor 22 (prediction execution unit 34) substitutes the expected value into the regression equation expressed by equation (1), calculates a predicted value of the running time, and displays it on display screen 52 of the display (output unit 35).

[0087] When an athlete or trainer selects an item and operates the slider 50A (or inputs data into the input field 50B), the running time changes. Therefore, the athlete or trainer can understand how the running time depends on the selected item. This allows the athlete and / or trainer to understand the content of the training that the athlete should perform.

[0088] Although the description of the specific embodiment has been completed above, the present invention is not limited to the above embodiment and can be widely modified and implemented.

[0089] The present invention is not limited by the number of data included in the driving log 31A (i.e., the number N) or the number of test data and learning data. The consistency verification method in the above embodiment is merely an example, and various known methods can be adopted.

[0090] In the above embodiment, the measured value of rhythmic ability was calculated as the average value of the correlation coefficients between λ1 and λ2, the correlation coefficients between λ2 and λ3, and the correlation coefficients between λ3 and λ4. However, the measured value of rhythmic ability may also be calculated by calculating the correlation coefficients for all combinations of waveforms λ1 to λ4 and averaging them.

[0091] In the above embodiment, the measurement value of the discrimination ability was calculated as the ratio between the tangential force component of the driving force and the hand rim pressing force component, but the measurement value of the discrimination ability may also be calculated as the ratio between the tangential force component of the driving force and the magnitude of the driving force.

[0092] In the above embodiment, the case where at least five of the six items, speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and strength ability, are included as items corresponding to the explanatory variables has been described, but this is not limited to this. For example, it is sufficient that the items corresponding to the explanatory variables include one of the six items, speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and strength ability, and it is preferable that at least four of them are included.

[0093] Furthermore, in the above embodiment, the prediction device 21 is configured to output a predicted value of the running time for a 1200m sprint, but this is not limited to the prediction target of the prediction device 21. The prediction device 21 may also be configured to predict the running distance of a 300m sprint, a 500m sprint, a 3-minute sprint, etc. [Explanation of symbols]

[0094] 1: Wheelchair 1A: Measurement wheelchair 21: Prediction device 22: Processor 24:Storage device 43: Driving force detection sensor 44: Rotation angle sensor

Claims

1. A prediction device for predicting a running time of a subject competing in a race by running a wheelchair, a storage device that stores a previously acquired measurement value corresponding to at least one item related to the physical ability of the athlete participating in the competition in association with the running time of the athlete; A prediction device comprising: a processor that acquires expected values ​​corresponding to the items, calculates and outputs predicted values ​​of the corresponding running times.

2. The prediction device according to claim 1 , wherein the items include at least one of six items: speed ability, movable angle ability, endurance ability, rhythm ability, discrimination ability, and power ability.

3. 3. The prediction device according to claim 2, wherein the movable angular capacity is obtained from an angle difference between a contact start position where the athlete starts contacting the hand rim and a contact end position where the athlete stops contacting the hand rim.

4. 3. The prediction device according to claim 2, wherein the endurance ability is obtained by having the athlete run around a track a plurality of times and calculating the degree of reduction in the time required to run around one track.

5. The prediction device of claim 2, wherein the rhythmic ability is obtained by calculating a correlation coefficient of a waveform that indicates the time change in the driving force applied by the athlete when the rear wheels of the wheelchair rotate once or the tangential component of the hand rim of the driving force.

6. 3. The prediction device according to claim 2, wherein the discrimination ability is obtained by the ratio of a tangential force, which is a component of the driving force exerted by the athlete in the tangential direction of the hand rim, to a pushing force, which is a resultant force of the components of the driving force excluding the tangential component.

7. The prediction device according to claim 2 , wherein the items include at least four of six items: the speed ability, the movable angle ability, the endurance ability, the rhythm ability, the discrimination ability, and the strength ability.

8. the wheelchair includes a body frame, rear wheels, hand rims provided on the rear wheels, and sensors for detecting a force applied to the hand rims and a rotational position of the hand rims, The prediction device according to claim 1 , wherein the measured values ​​are obtained by having the athlete run using the wheelchair.

9. the storage device stores a running log in which the measured values ​​of each of the items and the corresponding running times are associated with each other for each of the plurality of athletes; The processor uses the driving log to derive a prediction model showing the relationship between the measurement value and the driving time, and predicts the driving time using the prediction model and the expected value. A prediction device described in any one of claims 1 to 8.

10. The prediction device according to claim 9 , wherein the processor obtains the prediction model by performing multiple regression analysis using the measured values ​​of each of the items for each athlete and the corresponding running times.

11. A method for predicting a running time of a subject competing in a race by running a wheelchair, comprising: The prediction method is executed by a prediction device including: a storage device that stores past measured values ​​of each of a plurality of items related to the physical ability of an athlete participating in the competition in association with the running time of the athlete; and a processor; The processor obtains an expected value corresponding to each of the items, and calculates and outputs a predicted value of the corresponding running time.

12. A prediction program for predicting a running time of a subject competing by running a wheelchair, The prediction method is executed by a prediction device including: a storage device that stores past measured values ​​of each of a plurality of items related to the physical ability of an athlete participating in the competition in association with the running time of the athlete; and a processor; The processor is a prediction program that acquires expected values ​​corresponding to each of the items, calculates and outputs a predicted value of the corresponding running time.

Images