Classification of opening/closing hand motor imagery induced by left and right robotic gloves through EEG signals

This study presents a novel strategy for classifying Motor Imagery (MI) related to hand opening/closing actions using electroencephalography signals. This approach combines the passive motion induced by a robotic glove and action observation. Two groups of subjects executed a protocol based on left and right hand movement MI to address this. Subsequently, spectral features were used on $mu$ and $beta$ bands, and machine-learning algorithms were used for classification. The results showed better performance for right-hand motion recognition using k-Nearest Neighbors (kNN), which achieved the highest performance metrics of 0.71, 0.76, and 0.28 for Accuracy (ACC), true positive rate, and false positive rate, respectively. These findings demonstrate the feasibility of the proposed methodology for improving the recognition of MI tasks of the same limb, which can contribute to the design of more robust brain-computer interfaces for the enhancement of rehabilitation therapy for post-stroke patients.