Application of Distributed Probability Model in Sports Based on Deep Learning: Deep Belief Network (DL-DBN) Algorithm...

Area of Science:

• Computer Science
• Sports Science
• Data Science

Background:

• Information technology advancements impact all sectors, with age, education, and gender not hindering IT knowledge acquisition.
• Mobile devices and gadgets are integral to daily life, facilitating ease and efficiency.
• Machine Learning (ML) techniques are crucial for data analysis, enabling classification and prediction based on specific problem statements.

Purpose of the Study:

• To analyze human behavior in sports using advanced computational methods.
• To implement a Deep Learning-Deep Belief Network (DL-DBN) algorithm for sports behavior analysis.
• To develop a distributed probability model for classifying sports-related human behaviors.

Main Methods:

• The study implemented the Deep Learning-Deep Belief Network (DL-DBN) algorithm.
• A distributed probability model was utilized for behavior classification.
• The DL-DBN algorithm was applied to analyze human behavior data within a sports context.

Main Results:

• The classification accuracy for strength training varied significantly, with a maximum of 99% and a minimum of 71%.
• The DL-DBN algorithm demonstrated effectiveness in analyzing and classifying human behavior in sports.
• The distributed probability model provided a framework for nuanced behavior classification.

Conclusions:

• Deep Learning-Deep Belief Network (DL-DBN) is a viable tool for analyzing human behavior in sports.
• The accuracy of classification can vary widely depending on the specific activity, as seen in strength training.
• Further research can refine the distributed probability model for more precise sports behavior analysis.