Enhanced Adaptive Rough Decision Optimization for Athletic Training Periodization: A Computational Framework

Choosing the most effective periodization strategy in athletic training is essential for enhancing performance and reducing the likelihood of overtraining. This paper proposes a novel method, the Enhanced Adaptive Rough Decision Optimization (EARDO) Algorithm, for evaluating and ranking periodization strategies. The EARDO algorithm is designed to accommodate the dynamic, multifactorial nature of athletic training, where training load impact depends on factors such as daily variability, recovery, individual responses, and intensity. The algorithm integrates adaptive rough set theory to handle uncertainty and captures the trade-offs in performance gains and injury risks. The effectiveness of the EARDO approach was evaluated through computational experiments on three periodization strategies—linear, undulating, and block. The results showed that EARDO could accurately determine the optimal training load for each athlete (98.75%), assess overtraining risk (98.5%), and identify overtraining periods (98.35%). Comparisons with existing fuzzy logic and rough set methods revealed a substantial improvement in accuracy (6-8% higher) for selecting optimal periodization strategies and predicting overtraining and injury risks. These findings suggest that the EARDO algorithm offers a more precise, flexible, and adaptable framework for optimizing athletic training.