Privacy-aware and Efficient Student Clustering for Sport Training with Hash in Cloud Environment

Area of Science:

• Sports Science
• Data Science
• Computer Science

Background:

• Analyzing personalized student sports preferences is crucial but challenged by large datasets and privacy concerns.
• Existing methods struggle with the volume and sensitivity of student sports training records stored centrally.
• Efficient and private analysis of student sports data is an emergent research area.

Purpose of the Study:

• To propose a novel privacy-aware and efficient student clustering (PESC) approach.
• To address the challenges of large data volumes and sensitive information in student sports records.
• To enable effective analysis of personalized sports preferences.

Main Methods:

• Developed a privacy-aware and efficient student clustering (PESC) approach.
• Utilized a hash technique for uniform mapping and indexing of student sports records.
• Deployed on a central cloud platform connecting multiple local servers for efficient processing.

Main Results:

• PESC effectively clusters students based on their sports training records using hash indexes.
• The approach demonstrates feasibility through a case study and experiments on a time-aware dataset.
• Personalized sport preferences are inferred based on cluster membership.

Conclusions:

• PESC offers a viable solution for analyzing personalized sports preferences efficiently and privately.
• The hash-based clustering method effectively handles large and sensitive student sports data.
• This approach has significant implications for personalized sports training and health education.