Feature subset and time segment selection for the classification of EEG data based motor imagery. (August 2020)

• Record Type: Journal Article
• Authors: Wang, Jie; Feng, Zuren; Ren, Xiaodong; Lu, Na; Luo, Jing; Sun, Lei
• Is Part Of: Biomedical signal processing and control. Volume 61(2020)
• Publication Date: 2020-08
• Subjects: Brain-computer interface (BCI) -- Feature selection -- Time segment selection -- Kullback-Leibler divergence (KLD) -- Mutual information (MI) -- Motor imagery classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.102026
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: CSP and AR are employed after a filter bank to extract band power and time point features. Two Parzen window based methods are proposed to select feature subset and time segment. We extend the proposed methods to multi-class motor imagery classification and achieve superior performance. Our proposed methods would contribute to online BCI system. Abstract: The selection of feature subset and time segment is of great significance to the benefit of motor imagery classification. Hence, applying it in classification as well as itself alone has become an increasingly important research field in the brain-computer interface (BCI) systems. Most of the existing literatures only focus on binary-class classification situations in a fixed time segment. However, the modern BCI systems usually have to deal with more motor imagery classes. In this paper, we propose two Parzen window based methods to select the discriminative feature subset and subject-specific time segment. Further, we extend the proposed methods to multi-class issues. Finally, a soft Naive Bayesian classifier is designed to solve not only binary-class but also multi-class motor imagery problems. The proposed methods are validated on two well-known datasets, BCI competition IV dataset 2a and 2b. Experimental results reveal that the proposed methods achieve an improvement of 4.38 % for 2a and 2.54 % for 2b in comparison with the state-of-the-art methods, respectively. Meanwhile, both proposed methods achieve an improvement of 0.04 for 2a and 0.05 for 2b in kappa coefficient, respectively. Besides, the proposed multi-class methods would potentially contribute to the online BCI systems in practice.