A TB-CSP Motor Imagery EEG Recognition Method for Neural-controlled Manipulator System

To develop a manipulator system based on spontaneous EEG signal control, this paper proposes a common spatial pattern method combined with the Bhattacharyya distance of time-frequency signal (TB-CSP) for EEG signal feature extraction. Firstly, for different subjects, the original EEG signal is divided by a specific time window and different frequency band; Secondly, the average Bhattacharyya distance of different frequency bands in a specific time window is calculated to select the optimal time-frequency signal and input it to CSP for feature extraction; Finally, the extracted features are input into SVM and LDA to classify and complete the control of the manipulator. The proposed method achieves 82.6% accuracy on the public dataset BCI IVa and 79.48% accuracy on the self-collected dataset.