Education, Science, Technology, Innovation and Life
Open Access
Sign In

An Exploration of Ball Game Momentum Fluctuations Based on Multiple Regression Analysis and Convolutional Neural Networks

Download as PDF

DOI: 10.23977/jeis.2025.100102 | Downloads: 22 | Views: 695

Author(s)

Yuqing Xia 1, Zhihan Gong 1, Fangyu Wei 1

Affiliation(s)

1 School of Mathematics and Statistics, Northwestern Polytechnical University, Xi'an, China

Corresponding Author

Yuqing Xia

ABSTRACT

The aim of this study is to explore the patterns of player momentum fluctuations in tennis matches through a model combining multiple regression analysis and convolutional neural network (CNN). The study first analyzes real-time match data using analysis of variance (ANOVA) to identify the key factors that affect players' scores. Based on these factors, a multivariate regression analysis model is constructed for evaluating players' winning ability and their performance at specific moments. Then, the game data are deeply analyzed by convolutional neural networks to capture the fluctuating trends of player momentum. In addition, this paper verifies the non-randomness of momentum fluctuation by hypothesis testing method, which proves that the fluctuation of momentum in a match has a certain regularity and is closely related to the performance of players. The innovation of this study is that an analytical framework combining multiple regression and convolutional neural network is proposed, which not only improves the accuracy of momentum prediction, but also provides a new idea for dynamic analysis and optimal training of tennis.

KEYWORDS

ANOVA, Multiple Linear Regression Models, Hypothesis Testing, Convolutional Neural Networks

CITE THIS PAPER

Yuqing Xia, Zhihan Gong, Fangyu Wei, An Exploration of Ball Game Momentum Fluctuations Based on Multiple Regression Analysis and Convolutional Neural Networks. Journal of Electronics and Information Science (2025) Vol. 10: 15-20. DOI: http://dx.doi.org/10.23977/10.23977/jeis.2025.100102.

REFERENCES

[1] Liu Changyu. Optimal experimental design for the comparison of regression model curves [D]. Shanghai Normal University, 2024.DOI: 10.27312/d.cnki.gshsu.2024.000172.
[2] Fan Jiangyuan. Analysis of variance and covariance matrix function of multivariate functional type data testing problems and applications [D]. Huaqiao University, 2023. DOI: 10. 27155/ d.cnki.ghqiu.2023.000636.
[3] Xu Jianjun. Research on hypothesis testing and sufficient downscaling in functional regression models[D]. University of Science and Technology of China, 2024. DOI: 10. 27517/ d.cnki.gzkju.2024.000004.
[4] Qi Zhankui, Zhang Xinpeng, Liu Xuliang, et al. A one-dimensional convolutional neural network-based intelligent identification method for well test model [J]. Oil and Gas Well Testing, 2024, 33(02): 72-78.DOI: 10.19680/j.cnki.1004-4388.2024.02.012.
[5] Zhang Peixiao. Construction of tennis match result prediction model[J]. Science and Technology Innovation, 2024, (19):33-36.
[6] Balasubramanian A G, Vinuesa R, Tammisola O. Prediction of flow and elastic stresses in a viscoelastic turbulent channel flow using convolutional neural networks[J]. Geophysical Journal, 2024, V41(4).

Downloads: 12710
Visits: 493275

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.