System Construction of Athlete Health Information Protection Based on Machine Learning Algorithm

Area of Science:

• Sports Science
• Information Technology
• Data Security

Background:

• Athlete health data protection is increasingly critical due to rising sports participation.
• Existing data protection models face challenges with athlete health information complexity and security.
• Technological advancements in machine learning and blockchain offer new solutions for the sports industry.

Purpose of the Study:

• To propose and evaluate a Machine Learning and Blockchain-based Athlete Health Information Protection System (MLB-AHIPS).
• To enhance the security, decentralization, traceability, and credibility of athlete health data.
• To systematically assess sportspersons' physical fitness and manage health information.

Main Methods:

• Utilizing machine learning (ML) for data cleaning, processing, and secure management of athlete fitness information.
• Implementing attribute-based access control for dynamic and fine-grained data access.
• Storing athlete health data on a blockchain with smart contracts for security and tamper-proofing.

Main Results:

• The MLB-AHIPS achieved a high accuracy ratio of 97.8%.
• The system demonstrated strong security (98.3%), efficiency (97.1%), and scalability (98.9%).
• A high data access rate of 97.2% was recorded.

Conclusions:

• The proposed MLB-AHIPS effectively protects athlete health information using ML and blockchain.
• The system offers a secure, efficient, and scalable solution for managing sensitive sports data.
• MLB-AHIPS significantly outperforms existing approaches in key performance metrics.