Tensor decomposition-based channel selection for motor imagery-based brain-computer interfaces

• Published in: Cognitive neurodynamics 2024-06, Vol.18 (3), p.877-892
• Main Authors: Huang, Ziwei, Wei, Qingguo
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial Intelligence; Biochemistry; Biochips; Biomedical and Life Sciences; Biomedicine; Brain; Channels; Classification; Cognitive Psychology; Computer applications; Computer Science; Datasets; Decomposition; EEG; Electroencephalography; Feature extraction; Fourier transforms; Human-computer interface; Imagery; Implants; Matrix methods; Mental task performance; Methods; Neurosciences; Research Article; Support vector machines; Tensors; Wavelet transforms
• ISSN: 1871-4080; 1871-4099
• DOI: 10.1007/s11571-023-09940-4

The number of electrode channels in a brain-computer interface (BCI) affects not only its classification performance, but also its convenience in practical applications. Despite many studies on channel selection in motor imagery (MI)-based BCI systems, they consist in matrix analysis of EEG signals, which inevitably loses the interactive information among multiple domains such as space, time and frequency. In this paper, a tensor decomposition-based channel selection (TCS) method is employed for MI BCIs. A three-way tensor is yielded by wavelet transform of a single-trial EEG signal and decomposed into three factor matrices by a regularized canonical polyadic decomposition (CPD). The channel factor matrix is used for channel selection and the important channels are selected by calculating the correlation between channels. Regularized common spatial pattern (RCSP) is employed for feature extraction and support vector machine (SVM) for classification. The proposed TCS-RCSP algorithm was evaluated on three BCI data sets and compared with the RCSP with all channels (AC-RCSP) and the RCSP with selected channels by correlation-based channel selection method (CCS-RCSP). The results indicate that TCS-RCSP achieved significantly better overall accuracy than AC-RCSP (94.4% vs. 86.3%) with ρ < 0.01 and CCS-RCSP (94.4% vs. 90.2%) with ρ < 0.05, proving the efficacy of the proposed algorithm for classifying MI tasks.