Sports Training System Based on Convolutional Neural Networks and Data Mining.

Area of Science:

• Sports Science
• Artificial Intelligence
• Data Mining

Background:

• The Chinese sports industry faces challenges in scientifically guaranteeing athlete training efficiency.
• Accurate guidance of sports training using algorithms and data mining is a growing research area.

Purpose of the Study:

• To develop a gait recognition model for sports training using convolutional neural network (CNN) algorithms.
• To optimize and improve existing gait recognition methods in athletic training.

Main Methods:

• Analysis of the current state of gait recognition in sports training.
• Optimization and application of CNN algorithms and data mining techniques for gait recognition.
• Model reconstruction and strategy optimization based on identified gait differences.

Main Results:

• The CNN-based gait recognition model successfully identifies and reconstructs athletes' gaits during training.
• The model facilitates optimal training strategies tailored to individual athlete gait variations.
• Recognition accuracy for athlete gaits exceeded 97% in experimental trials.

Conclusions:

• Convolutional neural network algorithms are effective for athlete gait recognition in sports training.
• This approach provides a scientific basis for optimizing training efficiency and personalized strategies.
• The developed model demonstrates high accuracy and potential for practical application in elite sports.