Research on the application of big data in personalized sports health management
Data and Metadata · 11.05.2026 · 5 · 789
DOI: 10.56294/dm2026789 ↗Kurz gefasst
Fachartikel in der Zeitschrift Data and Metadata, online erschienen am 11.05.2026. Verfasst von Huiming Su und 2 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The rapid advancement of digital technologies and big data analytics has transformed sports health management, enabling personalized, data-driven interventions it enhance fitness and well-being. However, existing approaches often struggle to effectively integrate heterogeneous physiological and activity-based data while capturing temporal dependencies in user behavior.
Objective
This research aims to develop an intelligent and adaptive framework for personalized sports health management that improves exercise recommendation, injury risk prediction, and health monitoring accuracy using big data analytics and deep learning techniques.
Method
The proposed framework, termed Dynamic Coyote Optimized Enriched Convolutional Gated Recurrent Unit (DCO–EnCon–GRU), integrates deep learning and optimization techniques for personalized sports prediction and recommendation. Initially, comprehensive physiological, demographic, and activity-related data are collected and preprocessed using Min–Max normalization for uniform feature scaling. Linear Discriminant Analysis (LDA) is applied for feature extraction and dimensionality reduction. The Enriched Convolutional Network (EnCon) captures complex behavioral patterns, while the Gated Recurrent Unit (GRU) models temporal dependencies in sequential health data. Dynamic Coyote Optimization (DCO) is incorporated for optimal hyperparameter tuning. The framework is implemented using Python and TensorFlow for efficient training and adaptive prediction.
Results
The proposed DCO–EnCon–GRU framework achieved improved predictive performance compared with existing methods, obtaining accuracy (0,95), specificity (0,96), precision (0,97), and F1-score (0,94). The results demonstrate enhanced prediction reliability and effectiveness in personalized sports health management.
Conclusion
The research demonstrates that big data-driven deep learning approaches can effectively support personalized, adaptive, and efficient sports health management. The proposed framework improves predictive capability and exercise recommendation while addressing challenges associated with data integration, scalability, and adaptive health monitoring.
Zitieren
APA
Su, H., Wu, F., & Zhou, Z. (2026). Research on the application of big data in personalized sports health management. Data and Metadata, 5, 789. https://doi.org/10.56294/dm2026789
Vancouver
Su H, Wu F, Zhou Z. Research on the application of big data in personalized sports health management. Data and Metadata. 2026;5:789. doi:10.56294/dm2026789
BibTeX
@article{Su2026,
author = {Su, Huiming and Wu, Fuwei and Zhou, Zhishuai},
title = {Research on the application of big data in personalized sports health management},
journal = {Data and Metadata},
year = {2026},
volume = {5},
pages = {789},
doi = {10.56294/dm2026789}
}
EUVIMED