A bayesian inference and neural network model for predicting physical fitness consumption in table tennis athletes
- 1School of Physical Education & Sport Science, South China Normal University, Guangzhou, 510006 China
Abstract
Correctly predicting athletes’ physical energy consumption is helpful for scientifically managing the training load to improve sports performance, especially for sports with high density and frequent movement changes, such as table tennis. This study proposes a Bayesian inference-based Autoformer temporal neural network model, termed Bayesian Autoformer (B-Autoformer), for multivariate physiological signal-based physical exertion prediction. The B-Autoformer model integrates Bayesian inference with the Autoformer temporal architecture, introducing probabilistic parameter modeling within the encoder and decoder components, and combining multi-head autocorrelation mechanisms with joint quantile loss functions to achieve both point prediction and interval prediction of VO2-related physical exertion. The experimental data comprise two components. The Physical Activity Monitoring 2 Dataset (PAMAP2) is a publicly available multimodal physiological dataset derived from daily activity and exercise scenarios, encompassing triaxial acceleration, heart rate, and energy expenditure-related indicators, and is employed for model pre-training and generic feature learning. In this study, a special table tennis dataset was collected, including the continuous physiological signals of 18 male athletes during fixed-point technique, left and right push attack, non-fixed-point spin of the whole table and simulated competition training, and used for model fine-tuning and special verification. After filtering, time alignment and sliding window segmentation, the data are evaluated by five-fold cross-validation, combined with paired t-test and 95% confidence interval analysis. The evaluation indexes include Mean Square Error (MSE), Mean Absolute Error (MAE), coefficient of determination (R2) and interval coverage. The experimental results show that, compared with other comparison models, the MSE, MAE and R2 of B-Autoformer on PAMAP2 dataset are 0.260, 0.363 and 0.906, which are significantly better than the baseline model (p < 0.05). In table tennis, MSE is 0.355, MAE is 0.435, R2 is 0.875, and the highest interval coverage rate is 88%. The performance of the model remains relatively stable under different action types. The error increases slightly in complex simulated game scenes, but the trend consistency is still obvious. The results show that the model has certain advantages in representing the dynamic change and uncertainty of body movement. It can be used for training load monitoring and action intensity evaluation, thus providing reference for personalized regulation in special table tennis training.
Related
- Effects of low dose caffeinated coffee consumption on energy system contributions and repeated sprint indices in combat sports athletes
- An Analytical Study of the 2026 U.S. Dietary Guidelines in Light of Athletes’ Nutritional Needs Across Different Types of Physical Activity
- Effects of core training on physical fitness in trained adolescent athletes: a systematic review and meta-analysis
- Oral Frailty Is Associated With the Physical Component of Health‐Related Quality of Life in Middle‐Aged and Older Japanese Master Athletes
- Spatial structure in urban water consumption: A Bayesian space-time analysis of Bogotá (2019–2024)
BibTeX
@article{wang2026bayesian,
title = {{A bayesian inference and neural network model for predicting physical fitness consumption in table tennis athletes}},
author = {Ran Wang},
journal = {BMC Sports Science, Medicine and Rehabilitation},
year = {2026},
month = jul,
doi = {10.1186/s13102-026-01923-2},
url = {https://doi.org/10.1186/s13102-026-01923-2},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - A bayesian inference and neural network model for predicting physical fitness consumption in table tennis athletes
AU - Ran Wang
PY - 2026
DA - 2026/07/30
JO - BMC Sports Science, Medicine and Rehabilitation
DO - 10.1186/s13102-026-01923-2
UR - https://doi.org/10.1186/s13102-026-01923-2
AB - Correctly predicting athletes’ physical energy consumption is helpful for scientifically managing the training load to improve sports performance, especially for sports with high density and frequent movement changes, such as table tennis. This study proposes a Bayesian inference-based Autoformer temporal neural network model, termed Bayesian Autoformer (B-Autoformer), for multivariate physiological signal-based physical exertion prediction. The B-Autoformer model integrates Bayesian inference with the Autoformer temporal architecture, introducing probabilistic parameter modeling within the encoder and decoder components, and combining multi-head autocorrelation mechanisms with joint quantile loss functions to achieve both point prediction and interval prediction of VO2-related physical exertion. The experimental data comprise two components. The Physical Activity Monitoring 2 Dataset (PAMAP2) is a publicly available multimodal physiological dataset derived from daily activity and exercise scenarios, encompassing triaxial acceleration, heart rate, and energy expenditure-related indicators, and is employed for model pre-training and generic feature learning. In this study, a special table tennis dataset was collected, including the continuous physiological signals of 18 male athletes during fixed-point technique, left and right push attack, non-fixed-point spin of the whole table and simulated competition training, and used for model fine-tuning and special verification. After filtering, time alignment and sliding window segmentation, the data are evaluated by five-fold cross-validation, combined with paired t-test and 95% confidence interval analysis. The evaluation indexes include Mean Square Error (MSE), Mean Absolute Error (MAE), coefficient of determination (R2) and interval coverage. The experimental results show that, compared with other comparison models, the MSE, MAE and R2 of B-Autoformer on PAMAP2 dataset are 0.260, 0.363 and 0.906, which are significantly better than the baseline model (p < 0.05). In table tennis, MSE is 0.355, MAE is 0.435, R2 is 0.875, and the highest interval coverage rate is 88%. The performance of the model remains relatively stable under different action types. The error increases slightly in complex simulated game scenes, but the trend consistency is still obvious. The results show that the model has certain advantages in representing the dynamic change and uncertainty of body movement. It can be used for training load monitoring and action intensity evaluation, thus providing reference for personalized regulation in special table tennis training.
SN - 2052-1847
ER -