Momentum Prediction Model Combining Markov Chain And MLP
DOI:
https://doi.org/10.54097/wbvghq46Keywords:
Entropy weight method, Markov Chain, Multi-Layer Perceptron, SHAP Method.Abstract
In sports competitions, it is common for a certain player to dominate and score consecutively, which can be described as the effect of "momentum". To portray the abstract momentum to describe the change of athletes' state during the competition, and thus provide technical support for the subsequent training of athletes, a volume prediction model combining Markov chain and MLP is proposed. Firstly, the resultant variables are calculated by the entropy value method for momentum scoring, after that, technical indicators are considered, Markov features are calculated by the Markov chain model and added into the MLP model for momentum prediction, and finally, the important factors determining the momentum are analyzed by SHAP method. The experimental results show that the accuracy of predicting athletes' state reaches 98%, which can provide credible race reviews and guidance suggestions.
Downloads
References
MAD, LI Shaocong, ZHANG Junfeng. Design of athlete-specialized performance prediction system based on hybrid genetic neural network[J]. Modern Electronic Technology,2018,41(08):183-186.
Jevdokim Parfianovic,Elena Bobkova, Aaron An. Neural network prediction of physical fitness in 15-17 years old 400 m athletes[J]. Journal of Beijing Sport University,2024,47(02):154-156.
Chen Bo. Prediction and analysis of world 100m running performance in 2022 using gray Markov chain model[J]. Sports Goods and Technology,2021(15):203-205.
LONG Jiayong, WEI Zhuohong. Research on the prediction of Olympic men's 100m gold medal performance based on GM (1,1) gray model[J]. Journal of Southwest Normal University (Natural Science Edition),2023,48(07):123-128.
LI Ge, SHEN Jinbo. Heart rate load prediction method for aerobic endurance training in basketball players[J]. Contemporary Sports Science and Technology,2023,13(29):20-23.
Arshad M B, Aneed A A M A, Shibili N, et al. Analysis of the kinematic variables that predict jump serve efficacy among volleyball players. [J]. Medicine,2023,102(31): e34471-e34471.
Zhu Chun. Joint injury prediction method of athlete intensity training based on improved Logistic regression algorithm [J]. Journal of Hebei North University (Natural Science Edition),2022,38(07):13-18.
WANG Yongmin, LI Jing. Research on the influence of tennis players' psychological factors on tournament performance[J]. Sports World,2024(04):121-123.
ZHEN ZHANG, ENB GUO, ENZHONG GUO, et al. Fault diagnosis scheme for charging piles with GBDT and sensing machine fusion[J]. Automation and Instrumentation,2024,39(04):153-157.
LUNDBERG S M, LEE S I.A unified approach to interpreting model predictions[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.ACM,2017:4765-4774.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
