EEG-based BCI System for Classifying Motor Imagery Tasks of the Same Hand Using Empirical Mode Decomposition

In this paper, we present an EEG-based brain-computer interface (BCI) system for classifying motor imagery (MI) tasks of the same hand using empirical mode decomposition (EMD) method. The EMD method is employed to decompose the EEG signals into a set of intrinsic mode functions (IMFs). Then, a set of features is extracted from the obtained IMFs. These features are used to construct a three-layer hierarchical classification model to discriminate between four MI tasks of the same hand, namely rest, wrist-related tasks, finger-related task, and grasp-related task. In order to evaluate the performance of the proposed approach, we have collected EEG signals for 18 able-bodied subjects while imaging to perform the four MI tasks. Experimental results demonstrate the efficacy of the proposed approach in decoding MI tasks of the same hand based on analyzing EEG signals using the EMD method.