Improving the separability of motor imagery EEG signals using a cross correlation-based least square support vector machine for brain–computer interface

Abstract

Although brain–computer interface (BCI) techniques have been developing quickly in recent decades, there still exist a number of unsolved problems, such as improvement of motor imagery (MI) signal classi􀂿cation. In this paper, we propose a hybrid algorithm to improve the classi􀂿cation success rate of MI-based electroencephalogram (EEG) signals in BCIs. The proposed scheme develops a novel cross-correlation based feature extractor, which is aided with a least square support vector machine (LS-SVM) for two-class MI signals recognition. To verify the effectiveness of the proposed classi􀂿er, we replace the LS-SVM classi􀂿er by a logistic regression classi􀂿er and a kernel logistic regression classi􀂿er, separately, with the same features extracted from the cross-correlation technique for the classi􀂿cation. The proposed approach is tested on datasets, IVa and IVb of BCI Competition III. The performances of those methods are evaluated with classi􀂿cation accuracy through a 10-fold cross-validation procedure. We also assess the performance of the proposed method by comparing it with eight recently reported algorithms. Experimental results on the two datasets show that the proposed LS-SVM classi􀂿er provides an improvement compared to the logistic regression and kernel logistic regression classi􀂿ers. The results also indicate that the proposed approach outperforms the most recently reported eight methods and achieves a 7.40% improvement over the best results of the other eight studies.