ECoG recognition of motor imagery based on SVM Ensemble

In this paper, a method of ECoG identification based on SVM ensemble was proposed to solve the problems of low classification accuracy and weak robustness for ECoG collection during different period of time. Common spatial pattern (CSP) algorithm is used for feature extraction, and support vector machine (SVM) ensemble is applied for classification of ECoG. Besides, bagging algorithm and cross-validation technique are adopted in individual generation of the SVM Ensemble. The experiment results verified that the accuracy of SVM ensemble is better than that of single SVM for ECoG collection in different period of time, and the cross-validated technique has good performance than that of bagging. Therefore, SVM ensemble has stronger robustness and generalization ability compared with individual SVMs, and will improve classification of ECoG signals.