Have a personal or library account? Click to login

Design and implementation of a countermovement jump performance estimation system using a wearable device with IMUs based on machine learning algorithms

Open Access
|Oct 2025

Figures & Tables

Figure 1:

The process and corresponding force-time data of a CMJ. (A) The entire CMJ process. (B) Force-time data corresponding to the CMJ shown in (A). CMJ, countermovement jump.
The process and corresponding force-time data of a CMJ. (A) The entire CMJ process. (B) Force-time data corresponding to the CMJ shown in (A). CMJ, countermovement jump.

Figure 2:

Seven performance variables used to assess CMJ, derived from the force-time curve and the power-time curve. CMJ, countermovement jump.
Seven performance variables used to assess CMJ, derived from the force-time curve and the power-time curve. CMJ, countermovement jump.

Figure 3:

Proposed architecture and application workflow for a machine learning model that can predict CMJ performance variables from IMU sensor data. CMJ, countermovement jump; IMU, inertial measurement unit.
Proposed architecture and application workflow for a machine learning model that can predict CMJ performance variables from IMU sensor data. CMJ, countermovement jump; IMU, inertial measurement unit.

Figure 4:

Data preprocessing of CMJ acceleration data. (A) Raw IMU acceleration data (B) Raw IMU data post-Butterworth filter. (C) Post-Butterworth filter data, after elimination of the gravity component. (D) Acceleration data after jump segmentation. CMJ, countermovement jump; IMU, inertial measurement unit.
Data preprocessing of CMJ acceleration data. (A) Raw IMU acceleration data (B) Raw IMU data post-Butterworth filter. (C) Post-Butterworth filter data, after elimination of the gravity component. (D) Acceleration data after jump segmentation. CMJ, countermovement jump; IMU, inertial measurement unit.

Figure 5:

Critical point extraction from post-processed IMU acceleration-time data. IMU, inertial measurement unit.
Critical point extraction from post-processed IMU acceleration-time data. IMU, inertial measurement unit.

Figure 6:

Data preprocessing of CMJ force data. (A) Raw force data. (B) Force data, divided by the subject weight. CMJ, countermovement jump.
Data preprocessing of CMJ force data. (A) Raw force data. (B) Force data, divided by the subject weight. CMJ, countermovement jump.

Figure 7:

Data preprocessing of CMJ power data. (A) Raw power data. (B) Power data, divided by the subject weight. CMJ, countermovement jump.
Data preprocessing of CMJ power data. (A) Raw power data. (B) Power data, divided by the subject weight. CMJ, countermovement jump.

Figure 8:

A NAXSEN IMU tied on a jumper and a Kistler 9260AA6 force plate. (A) Appearance of the SIPPLink Technology. (B) Placement of the IMU on the test subject. (C) Kistler 9260AA6 force plate used during this study. IMU, inertial measurement unit.
A NAXSEN IMU tied on a jumper and a Kistler 9260AA6 force plate. (A) Appearance of the SIPPLink Technology. (B) Placement of the IMU on the test subject. (C) Kistler 9260AA6 force plate used during this study. IMU, inertial measurement unit.

Figure 9:

Prediction results from varying the number (k) of selected features for each performance variable, under each of the five regression models. (A) Peak force. (B) Second peak force. (C) Flight time. (D) Average loading rate. (E) Net impulse. (F). Peak power. (G) RFD. DTR, decision tree regression; LGBMR, light gradient boosting machine regression; LR, linear regression; LSVR, linear support vector regression; MAPE, mean absolute percentage error; RFD, rate of force development; XGBR, eXtreme gradient boosting regression.
Prediction results from varying the number (k) of selected features for each performance variable, under each of the five regression models. (A) Peak force. (B) Second peak force. (C) Flight time. (D) Average loading rate. (E) Net impulse. (F). Peak power. (G) RFD. DTR, decision tree regression; LGBMR, light gradient boosting machine regression; LR, linear regression; LSVR, linear support vector regression; MAPE, mean absolute percentage error; RFD, rate of force development; XGBR, eXtreme gradient boosting regression.

Figure 10:

Rabboni IMU tied on a jumper. (A) Commercially available Rabboni IMU device. (B) Placement of the device on a test subject. IMU, inertial measurement unit.
Rabboni IMU tied on a jumper. (A) Commercially available Rabboni IMU device. (B) Placement of the device on a test subject. IMU, inertial measurement unit.

Figure 11:

System architecture and application workflow. CMJ, countermovement jump.
System architecture and application workflow. CMJ, countermovement jump.

Figure 12.

Prototype system predicting CMJ variable performance in a live test. CMJ, countermovement jump.
Prototype system predicting CMJ variable performance in a live test. CMJ, countermovement jump.

Machine learning parameter settings for the models used in this study

ModelParameterSetting value
LSVR [11]Epsilon0.0
Tol0.0001
C1.0
Lossepsilon_insensitive

DTR [11]intercept_scaling1.0
max_iter100,000
max_depthNone
min_samples_split2
min_samples_leaf1
min_weight_fraction_leaf0.0

XGBRmax_leaf_nodesNone
min_impurity_decrease0.0
learnig_rate0.3
Subsample1
n_estimators100
Gamma0.0
max_depth6
min_child_weight1
max_delta_step0
num_leaves31
max_depth−1 (no limit)
Subsample1

LGBMRlearning_rate0.1
n_estimators100
min_split_gain0.0
min_child_weight0.001
min_child_samples20

Relative predictive performance of the CMJ flight time variable, measured using MAPE

Integration-based methodLGBMR
CMJ11.752.04

Data features used to predict values for the seven CMJ performance variables

FeaturePeak forceSecond peak forceFlight timeAverage loading rateNet impulsePeak powerRFD
MeanVVVVVV
SDVVVV VV
IQRVVVVVVV
SkewnessVVVVVVV
Kurtosis VVV V
FrequencyVVVV V
EntropyVVVVV V
value_AVVVVVVV
value_CV VVVVV
value_EVVVVVVV
value_FVVVVV V
duration_AC VVVVVV
duration_BDVVVVVVV
duration_CEVVVVVVV
duration_EF VVVVVV
slope_ALVVVVVVV
slope_ARVVVVVVV
slope_CLVVVVVVV
slope_CRV VV V
slope_EL VVVVV
slope_ERVVVVVVV
slope_FLVVVVVVV
slope_FRVV V V
slope_ACVVVVV V
slope_CEVVVVV V
slope_DE VVVV V
slope_EFVVVVV V
IntegrationVVVVVVV
average_AVVVVVVV
average_CVVVVVVV
average_EVVVVVVV

Comparison of MAPE for original data and up-sampling data_

(a) MAPE of different models utilizing the original data (1,000 Hz native).
VariableModelLR [11]LSVR [11]DTR [11]XGBRLGBMR
Peak force7.9710.847.545.505.00
Second peak force24.8828.3123.8419.1618.07
Flight time2.594.632.852.092.04
Average loading rate34.3233.5430.6823.5023.59
Net impulse2.994.633.282.612.42
Peak power5.736.867.215.605.43
RFD21.1223.1621.7317.5016.56

31 features extracted from the acceleration data

FeatureDescription
MeanThe mean of the acceleration data
SDThe standard deviation of the acceleration data
IQRThe interquartile range of the acceleration data
SkewnessThe skewness of the acceleration data
KurtosisThe kurtosis of the acceleration data
FrequencyThe dominant frequency of the acceleration data
EntropyThe sample entropy of the acceleration data
value_AThe value of point A
value_CThe value of point C
value_EThe value of point E
value_FThe value of point F
duration_ACThe time interval from point A to point C
duration_BDThe time interval from point B to point D
duration_CEThe time interval from point C to point E
duration_EFThe time interval from point E to point F
slope_ALThe slope from (point A − 20 ms) to point A
slope_ARThe slope from point A to (point A + 20 ms)
slope_CLThe slope from (point C − 20 ms) to point C
slope_CRThe slope from point C to (point C + 20 ms)
slope_ELThe slope from (point E − 10 ms) to point E.
slope_ERThe slope from point E to (point E + 10 ms).
slope_FLThe slope from (point F − 10 ms) to point F
slope_FRThe slope from point F to (point F + 10 ms)
slope_ACThe slope from point A to point C
slope_CEThe slope from point C to point E
slope_DEThe slope from point D to point E
slope_EFThe slope from point E to point F.
IntegrationThe integration value before point C
average_AThe average value between (point A − 80 ms) and (point A + 20 ms)
average_CThe average value between (point C − 20 ms) and (point C + 180 ms).
average_EThe average value between (point E − 20 ms) and (point E + 180 ms)
Language: English
Submitted on: Apr 4, 2025
Published on: Oct 13, 2025
Published by: Professor Subhas Chandra Mukhopadhyay
In partnership with: Paradigm Publishing Services
Publication frequency: 1 issue per year

© 2025 Jhe-Sheng Yang, Jun-Zhe Wang, published by Professor Subhas Chandra Mukhopadhyay
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.