1. TACTICAL OPTIMISATION AND OPPONENT ANALYSIS FOR FOOTBALL TEAMS WITH BIG DATA MINING AND MACHINE LEARNING.
- Author
-
Xiaoliang Ju, Xiyao Chen, Yu Zhang, Qishen Zhou, and Jie Zhao
- Subjects
FOOTBALL teams ,DATA mining ,FOOTBALL training - Abstract
Football tactical training is of great significance to the improvement of football level and the development of football, while the tactical training system is rich in content and diversified in structure, how to coordinate the content of tactical training system has become a key topic to improve the effectiveness of tactical training. In this paper, we design the method of tactical training for college football teams, aiming at building a tactical optimisation and opponent analysis model based on big data mining and machine learning from the reality of tactical training for college high-level football teams. Specifically, the convolutional neural network with two levels of cascade detection and regression in the model adopts the classic ideas of face key point detection and human body key point detection: the idea of cascade regression is used for the detection of the key point location from coarse to fine; the heat map of the key point obtained from the first level network is used as the supplemental information, and the original map is used for the feature fusion; the Heatmap, which has better effect, is used as the Ground Truth of the network; the Heatmap is used as the ground truth of the network; the Heatmap, which has better effect, is used as the ground truth of the network. The second stage regression network uses Heatmap as the Ground Truth of the network, which provides pixel-by-pixel supervision for the regression of the key points' positions and the prediction of whether the key points are visible or not. In addition, this paper combines the idea of adversarial learning to design the loss function to solve the fuzzy problem of regression-to-the-mean when regressing Heatmap. The second-stage network is used as the generator, and the discriminator is designed to define the loss function to judge the reliability of the generated Heatmap. Through the training method of adversarial learning, the second-stage network converges and predicts the reliable Heatmap, and then obtains the key point coordinates to identify the opponents to optimise the tactics of football teams. The final simulation experimental results demonstrate the effectiveness and superiority of the proposed model. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF