Adaptive binary multi-objective harmony search algorithm for channel selection and cross-subject generalization in motor imagery-based BCI. (1st August 2022)

• Record Type: Journal Article
• Authors: Shi, Bin; Yue, Zan; Yin, Shuai; Wang, Weizhen; Yu, Haoyong; Huang, Zhen; Wang, Jing
• Is Part Of: Journal of neural engineering. Volume 19:Number 4(2022)
• Publication Date: 2022-08-01
• Subjects: brain-computer interface -- motor imagery (MI) -- electroencephalogram (EEG) -- multi-objective algorithm -- channel selection; Neurosciences -- Periodicals; Biomedical engineering -- Periodicals; 612.8
• DOI: 10.1088/1741-2552/ac7d73
• Languages: English
• ISSNs: 1741-2560

Abstract

Abstract: Objective. Multi-channel electroencephalogram data containing redundant information and noise may result in low classification accuracy and high computational complexity, which limits the practicality of motor imagery (MI)-based brain-computer interface (BCI) systems. Therefore, channel selection can improve BCI performance and contribute to user convenience. Additionally, cross-subject generalization is a key topic in the channel selection of MI-based BCI. Approach. In this study, an adaptive binary multi-objective harmony search (ABMOHS) algorithm is proposed to select the optimal set of channels. Furthermore, a new adaptive cross-subject generalization model (ACGM) is proposed. Three public MI datasets were used to validate the effectiveness of the proposed method. Main results. The Wilcoxon signed-rank test was performed on the test accuracies, and the results indicated that the ABMOHS method significantly outperformed all channels ( p < 0.001), the C3–Cz–C4 channels ( p < 0.001), and 20 channels ( p < 0.001) in the sensorimotor cortex. The ABMOHS algorithm based on Fisher's linear discriminant analysis (FLDA) and support vector machine (SVM) classifiers greatly reduces the number of selected channels, especially for larger channel sizes (Dataset 2), and obtains a comparative classification performance. Although there was no significant difference in test classification performance between ABMOHS and non-dominated sorting genetic algorithm II (NSGA-II) when FLDA and SVM were used, ABMOHS required less computational time than NSGA-II. Furthermore, the number of channels obtained by ABMOHS algorithm were significantly smaller than those obtained by common spatial pattern-Rank and correlation-based channel selection algorithm. Additionally, the generalization of ACGM to untrained subjects shows that the mean test classification accuracy of ACGM created by a small sample of trained subjects is significantly better than that of Special-16 and Special-32. Significance. The proposed method can reduce the calibration time in the training phase and improve the practicability of MI-BCI.