Optimization research on biomechanical characteristics and motion detection technology of lower limbs in basketball sports

In basketball, the biomechanics of the lower limbs play a significant role in executing specific movements like sprints, jumps, and directional changes. Optimizing the performance of these movements is necessary for enhancing overall athletic performance and reducing injury risks. The objective of the research is to generate and execute a motion detection algorithm focusing on lower limbs in basketball utilizing a deep learning (DL) based approach. The study proposes the Refined Harries Hawks optimized Intelligent Long-Short Term Memory (RHH-ILSTM) method to improve the accuracy of detecting and analyzing biomechanical characteristics of lower limb movements. Data collection involved basketball players equipped with wearable sensors on their lower limbs to gather on-time data throughout dynamic movements to train the method. The data is pre-processed to remove noise, normalize values, and segment movements into discrete time intervals. Principal Component Analysis (PCA) is utilized to extract characteristics by reducing the dimensionality of the data while maintaining significant biomechanical aspects. The RHH-ILSTM system combines the exploration capabilities of the RHH optimization algorithm with ILSTM’s capacity to handle time-series data, leading to improved detection accuracy of lower limb biomechanics. The model efficiently captures crucial lower limb biomechanics, achieving a higher accuracy (94.58%) and recall (95.62%) in detecting movement phases and joint stresses. The proposed RHH-ILSTM method provides a robust solution for monitoring and analyzing lower limb movements in basketball.