Signal analysis and classification of a novel active brain-computer interface based on four-category sequential coding. (September 2022)

• Record Type: Journal Article
• Authors: Wang, Li; Huang, Xuewen; Ren, Lingling; Zhan, Qianqian
• Is Part Of: Biomedical signal processing and control. Volume 78(2022)
• Publication Date: 2022-09
• Subjects: Brain-computer interface (BCI) -- Sequential coding -- Motor imagery -- Speech imagery -- Electroencephalogram (EEG); 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.2022.103857
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A novel experimental paradigm based on sequential coding is proposed. Four imagination tasks are obtained with the sequence combination of motor imagery and speech imagery. The features of EEG signals are analyzed from the temporal, frequency and spatial domains. The EEG signals are classified by a multi-classification model based on time sequence. Abstract: In order to increase the number of instruction sets for the active brain-computer interface (BCI), a novel experimental paradigm based on the sequential coding of motor imagery and speech imagery is proposed in this paper. By dividing one motor imagery and one speech imagery into time series, four imagination tasks are obtained: 1) motor imagery; 2) speech imagery; 3) motor imagery first and then speech imagery; 4) speech imagery first and then motor imagery. After analyzing the temporal, frequency and spatial features of electroencephalography (EEG) signals, four types of signals are classified by a multi-classification model based on time sequence. In this model, feature extraction and classification are accomplished by common spatial pattern (CSP) and support vector machine (SVM), respectively. 12 subjects participate in this experimental paradigm, and their average classification accuracy is 68.94%. The classification results are much higher than random probability, so the proposed experimental paradigm is feasible and valuable. The experimental paradigm based on sequential coding can effectively increase the number of instruction sets of active BCIs, so the practicability of BCIs is also improved.