Feature Extraction Method of Motor Imagery EEG Based on DTCWT Sample Entropy

Aiming at the applications of Brain Computer Interface (BCI) based on motor imagery EEG, this paper presents a feature extraction method combining Dual-Tree Complex Wavelet Transform (DTCWT) and sample entropy. Firstly, the motor imagery EEG signals are decomposed by DTCWT. Then, the rhythm waves corresponding to the event-related desynchronization (ERD)/event-related synchronization (ERS) phenomenon are extracted and reconstructed. Finally, the features are extracted from the rhythm signal using sample entropy. The Datasets1 of BCI Competition IV, including motor imagery EEG data of left hand, right hand and foot, is used to verify the proposed method. A Support Vector Machine (SVM) classifier is introduced in the classification experiments. The average classification accuracy rate of four subjects is 87.25% in the experiments with the Datasets1 of BCI Competition IV. The results show that the feature extraction method has more obvious separability and practicability.