Research the role of artificial intelligence in developing personalized training plans to maximize the potential of basketball players

Journal of Computational Methods in Sciences and Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: May 8, 2025

Basketball players can maximize their potential and enhance skills, strength, overall performance with the help of customized training routines. Players in games must quickly adapt to changing court circumstances, often adjusting tactics, but identifying best course action real-time is challenging due complexity handling data signals. This research explores use artificial intelligence (AI) creating personalized plans improve basketball players’ abilities. Specifically, a novel Intelligent Cheetah Optimizer Flexible Recurrent Neural Networks (ICO-FRNN) was proposed generate by individual player strengths areas for improvement. To get information from sensors during practice competition, monitor physical indicators such as heart rate, speed, jump height, endurance, biomechanical movements. The collected undergoes preprocessing address missing values, normalize formats, remove outliers using Z-score normalization linear discriminant analysis (LDA) used feature extraction. findings show that ICO-RNN approach enables more intelligent, player-specific plans, facilitating improved decision-making, skill improvement, injury avoidance. Findings indicate AI-driven result notable gains when compared conventional regimens. metrics are accuracy (0.9680), recall F1 score (0.9681), precision (0.9700). demonstrates AI revolutionize coaching techniques data-driven, dynamic programs optimize potential.

Language: Английский

Application of action recognition and tactical optimization methods for rope skipping competitions based on artificial intelligence

Molecular & cellular biomechanics, Journal Year: 2024, Volume and Issue: 21(4), P. 936 - 936

Published: Dec. 30, 2024

To solve the problems that action recognition methods in rope skipping competitions rely on manual annotation and are prone to misjudgment complex movements, this study implemented an AI-based tactical optimization method, using artificial intelligence technology achieve efficient accurate adjustment. The feature extraction of video frames is performed through Convolutional Neural Network (CNN), processed sequence sent Long Short-Term Memory (LSTM) network for processing, so as actions. optimize competition strategy, Deep Q (DQN) used execution. Experimental results show proposed model can recognize common movements such single jump, double-leg jump cross with average accuracy 98.4%; strategy optimized by reinforcement learning significantly improves performance athletes, jumping frequency increases 4.59% error rate decreases 0.986%. This not only provides intelligent evaluation solution competitions, but also has certain reference significance decision-making other sports.

Language: Английский