A novel method for classification of multi-class motor imagery tasks based on feature fusion. (March 2022)

• Record Type: Journal Article
• Authors: Hou, Yimin; Chen, Tao; Lun, Xiangmin; Wang, Fang
• Is Part Of: Neuroscience research. Volume 176(2022)
• Page Start: 40
• Page End: 48
• Publication Date: 2022-03
• Subjects: Motor imagery based brain–computer interface (MI-BCI) -- Electroencephalography (EEG) -- Feature extraction -- Feature selection -- SVM; Neurosciences -- Research -- Periodicals; Neurosciences -- Research -- Japan -- Periodicals; Neurology -- Periodicals; Neurosciences -- Periodicals; Neurosciences -- Recherche -- Périodiques; Neurosciences -- Recherche -- Japon -- Périodiques; Neurosciences -- Research; Japan; Periodicals; 612.8
• DOI: 10.1016/j.neures.2021.09.002
• Languages: English
• ISSNs: 0168-0102

Abstract

Highlights: A novel framework based on bispectrum, Shannon entropy and common spatial patterns. Higher-order statistics reduce the influence of non-linear and non-Gaussian noise. Tree-based feature selection method is used to select features. Abstract: Motor imagery based brain computer interface (MI-BCI) has the advantage of strong independence that can rely on the spontaneous brain activity of the user to operate external devices. However, MI-BCI still has the problem of poor control effect, which requires more effective feature extraction algorithms and classification methods to extract distinctly separable features from electroencephalogram (EEG) signals. This paper proposes a novel framework based on Bispectrum, Entropy and common spatial pattern (BECSP). Here we use three methods of bispectrum in higher order spectra, entropy and CSP to extract MI-EEG signal features, and then select the most contributing features through tree-based feature selection algorithm. By comparing the classification results of SVM, Random Forest, Naive Bayes, LDA, KNN, Xgboost and Adaboost, we finally decide to use the SVM algorithm based on RBF kernel function which obtained the best result among them for classification. The proposed method is applied to the BCI competition IV data set 2a and BCI competition III data set IVa. On data set 2a, the highest accuracy on the evaluation data set reaches 85%. The experiment on data set IVa can also achieve good results. Compared with other algorithms that use the same data set, the performance of our algorithm has also been improved.