Optimized Feature Selection and Neural Network-Based Classification of Motor Imagery Using EEG Signals

Machine learning- and deep learning-based models have recently been employed in motor imagery intention classification from electroencephalogram (EEG) signals. Nevertheless, there is a limited understanding of feature selection to assist in identifying the most significant features in different spatial locations. This study proposes a feature selection technique using sequential forward feature selection with support vector machines and feeding the selected features to deep neural networks to classify motor imagery intention using multi-channel EEG. The proposed model was evaluated with a publicly available dataset and achieved an average accuracy of 79.70 ± 7.98% for classifying two motor imagery scenarios. These results demonstrate that our method effectively identifies the most informative and discriminative characteristics of neural activity at different spatial locations, offering potential for future prosthetics and brain–computer interface (BCI) applications. This approach enhances model performance while identifying key spatial EEG features, advancing BCIs and prosthetic systems.