Detecting and classifying three different hand movement types through electroencephalography recordings for neurorehabilitation

Brain-computer interfaces can be used for motor substitution and recovery; therefore, detection and classification of movement intention are crucial for optimal control. In this study, palmar, lateral and pinch grasps were differentiated from the idle state and classified from single-trial EEG using only information prior to the movement onset. Fourteen healthy subjects performed the three grasps 100 times, while EEG was recorded from 25 electrodes. Temporal and spectral features were extracted from each electrode, and feature reduction was performed using sequential forward selection (SFS) and principal component analysis (PCA). The detection problem was investigated as the ability to discriminate between movement preparation and the idle state. Furthermore, all task pairs and the three movements together were classified. The best detection performance across movements (79 ± 8 %) was obtained by combining temporal and spectral features. The best movement-movement discrimination was obtained using spectral features: 76 ± 9 % (2-class) and 63 ± 10 % (3-class). For movement detection and discrimination, the performance was similar across grasp types and task pairs; SFS outperformed PCA. The results show it is feasible to detect different grasps and classify the distinct movements using only information prior to the movement onset, which may enable brain-computer interface-based neurorehabilitation of upper limb function through Hebbian learning mechanisms.