Improving Upper Limb Movement Classification from EEG Signals Using Enhanced Regularized Correlation-Based Common Spatio-Spectral Patterns

Detection of movement from electroencephalogram (EEG) signals is crucial for advancing brain-computer interface (BCI) systems, particularly in rehabilitating individuals with disabilities. This study focuses on decoding two types of ipsilateral movements (right arm and thumb) and the resting state from EEG signals—a challenging task due to the reduced signal discrimination between ipsilateral movements. To address this challenge, we propose a novel framework that combines precise segmentation of EEG signals during movement with an improved feature extraction method. First, we detect accurate segmentation of EEG signals by using the teager-kaiser energy operator for electromyographic (EMG) signals, which allows for precise detection of the onset and end of movements. Next, for feature extraction, we developed the regularized correlation-based common spatio-spectral patterns (RCCSSP) algorithm, which improves the traditional common spatial patterns (CSP) by incorporating regularization based on correlation. RCCSSP employs spatio-spectral canonical correlation analysis (SS-CCA) with an advanced regularization approach. Specifically, this method calculates the correlation between two classes for each channel, assigning higher weights to channels with lower correlation to increase their impact while minimizing the effect of noisy channels with higher correlation. Classification is then performed using distance-weighted k-nearest neighbor and support vector machine algorithms. Experimental results from 15 healthy subjects demonstrate that the proposed approach achieves an average classification accuracy of 88.94%, representing a significant 11.66% improvement over the best-reported method. This work highlights the potential of precise movement segmentation and robust feature extraction in decoding ipsilateral movements for BCI applications.