ChatPPG.
Join free
First page or project page of “Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes” (opens in a new tab)

Paperdoi:10.3389/fphys.2026.1889980

Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes

Venue listedDated Nov 11, 2026Added Nov 12, 2026

  • CG
  • MC
  • YT
  • YS
  • ZZ
  • JA
  • ZG
  • LZ
  • +1

Authors: Chunhui Gong, Meng Liu (corresponding), Yike Tang, Yujie Shan, Zhile Zhu, Jun Ai, Zhenxiang Guo, Limingfei Zhou, Liang Zhang (ethics approval: Beijing Sport University)

Frontiers in Physiology 17:1889980, 2026

Publisher (opens in a new tab) Cite
CC BY 4.0
First page or project page of “Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes” (opens in a new tab)

Chunhui Gong et al., "Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes", doi:10.3389/fphys.2026.1889980, CC BY 4.0

TL;DR

Accelerometer-only fatigue classification during badminton smashes (25 athletes, 70 recordings) with athlete-grouped nested CV: fold-mean AUC 0.655–0.846 (7 sensors) and 0.715–0.846 (right forearm alone), specificity only 0.48–0.70. Authors explicitly disclaim real-time or physiological validity.

  • Form factor: body-worn IMUs (right forearm subset is wrist-adjacent)

Abstract

Objective

To evaluate offline binary classification of recorded fatigue conditions using inertial measurement unit (IMU) acceleration features and five machine-learning algorithms.

Methods

The author-confirmed performance dataset contained 32 observations per condition. The revised primary IMU dataset comprised 70 recordings from 25 roster-linked athletes, with 22 non-fatigue and 48 fatigue labels after correction of four misclassified recordings. Seven-sensor and right-forearm configurations provided 231 and 33 candidate features. A newly reconstructed analysis retained five documented outer athlete-grouped folds and used three grouped inner folds for training-only preprocessing, sparse logistic feature selection and hyperparameter tuning.

Results

CMJ was 40.01 ± 8.51 and 30.27 ± 7.29 in the non-fatigue and fatigue conditions, respectively. Across classifiers, fold-mean AUC ranged from 0.655 to 0.846 for seven sensors and from 0.715 to 0.846 for the right forearm. Macro F1 ranged from 0.600 to 0.775 and from 0.655 to 0.775, respectively. Specificity ranged from 0.483 to 0.700 and from 0.550 to 0.650. Code, inclusion decisions, actual inner and outer assignments and held-out predictions are supplied for this new run.

Conclusion

The results support further investigation of IMU-based condition classification, but do not establish algorithm superiority, sensor equivalence, physiological validity of every recording label, or real-time monitoring performance.

Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0/

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Stress

Signals

IMU

Keywords

Exercise FatiguePhysical FatigueAccelerometer OnlyBadmintonForearmAthlete Grouped CVNested CVSmall N

How it works

How Method works: Setup → Method → TargetSetup: Signals (acc); Form factor (body-worn IMUs (right forearm subset is wrist-adjacent)). Method: Method. Target: Stress.SetupSignals: accxyzSignalsaccForm factor: body-worn IMUs (right forearm subset is wrist-adjacent)Form factorbody-worn IMUs (right forearm subset is…MethodMethodTargetStressStress

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Gong, C., Liu, M., Tang, Y., Shan, Y., Zhu, Z., Ai, J., Guo, Z., Zhou, L., & Zhang, L. (2026). Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes. Frontiers in Physiology , 2026, 17, 1889980. https://doi.org/10.3389/fphys.2026.1889980
Gong, Chunhui, Meng Liu, Yike Tang, Yujie Shan, Zhile Zhu, Jun Ai, Zhenxiang Guo, Limingfei Zhou, and Liang Zhang. 2026. "Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes." Frontiers in Physiology , 2026 17: 1889980. https://doi.org/10.3389/fphys.2026.1889980.
Gong, C., Liu, M., Tang, Y., Shan, Y., Zhu, Z., Ai, J., Guo, Z., Zhou, L. and Zhang, L. (2026) 'Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes', Frontiers in Physiology , 2026, 17, p. 1889980. doi: 10.3389/fphys.2026.1889980.
Gong, Chunhui, et al. "Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes." Frontiers in Physiology , 2026, vol. 17, 2026, p. 1889980. https://doi.org/10.3389/fphys.2026.1889980.
C. Gong et al., "Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes," Frontiers in Physiology , 2026, vol. 17, p. 1889980, 2026, doi: 10.3389/fphys.2026.1889980.
@article{gong2026application,
  title         = {{Application of inertial measurement units and machine learning for fatigue assessment in badminton athletes}},
  author        = {Gong, Chunhui and Liu, Meng and Tang, Yike and Shan, Yujie and Zhu, Zhile and Ai, Jun and Guo, Zhenxiang and Zhou, Limingfei and Zhang, Liang},
  year          = {2026},
  journal       = {Frontiers in Physiology , 2026},
  volume        = {17},
  pages         = {1889980},
  doi           = {10.3389/fphys.2026.1889980}
}

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models

Datasets