Neural Signal Processing in EEG-Based BCI Systems for Wheelchair Control

This narrative review explores recent advancements in neural signal processing techniques applied to EEG-based brain-computer interface (BCI) systems for wheelchair control, aimed at improving mobility for individuals with severe motor impairments. It discusses core concepts such as motor imagery paradigms and the modulation of sensorimotor rhythms as fundamental methods for translating neural activity into wheelchair commands. The review traces the progression from early EEG-controlled systems to current sophisticated approaches utilizing advanced machine learning models, spatial filtering, and adaptive classifiers to enhance decoding accuracy and responsiveness. Current trends highlight hybrid BCIs that merge EEG with additional biosignals , alongside wireless, multimodal sensor integration and mental state-aware adaptive control strategies designed to address challenges like signal variability, noise interference, and cognitive demand on users. Despite significant technological advancements, the review identifies ongoing challenges including the need for long-term usability studies, continuous monitoring of mental states, and development of calibration-free, personalized BCI interfaces for practical daily use. The review concludes by emphasizing the necessity of balancing system complexity with user accessibility and calls for future research focused on creating robust, user-centric BCI solutions that facilitate real-world integration, thereby restoring autonomy and enhancing quality of life.

Keywords:

Brain-computer interface , EEG signal processing , Wheelchair control , Hybrid BCI systems , Motor imagery , Neural decoding.