Real-time multiclass motor imagery brain-computer interface by modified common spatial patterns and adaptive neuro-fuzzy classifier. (March 2020)

• Record Type: Journal Article
• Authors: Jafarifarmand, Aysa; Badamchizadeh, Mohammad Ali
• Is Part Of: Biomedical signal processing and control. Volume 57(2020)
• Publication Date: 2020-03
• Subjects: Adaptive neuro-fuzzy classification -- Self-regulated learning -- Common spatial patterns -- Multiclass brain-computer interface -- Electroencephalogram; 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.2019.101749
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Artifacts highly degrade the command translation in a real-time multiclass BCI. Feature extraction using JAD based CSP by FFDIAG has decent speed and performance. Artifact robustified MCSP well deals with the artifacts without time increment. SRSG-FasArt performs effectively in coping with uncertainties in multiclassification. Metacognition and Incremental learning ability provide decent classifying accuracy. Abstract: Motor imagery (MI) brain-computer interface (BCI) performance is highly influenced by non-stationarity and artifact contamination of electroencephalogram (EEG) signals. This paper presents a framework for overcoming EEG uncertainties in real-time multiclass MI BCI. An artifact rejected multiclass extension of common spatial pattern (CSP) by using joint approximate diagonalization (JAD) is proposed for feature extraction. Artifactual trials are excluded in spatial filters calculation that results in more informative features. In order to cope with non-stationarities, an adaptive resonance theory (ART) based neuro-fuzzy classifier, named self-regulated supervised Gaussian fuzzy adaptive system Art (SRSG-FasArt) is implemented for multiclass applications. The proposed framework is evaluated based on a standard dataset of BCI competition IV. Applying the system in real-time performance shows significant improvement in multiclass classification accuracy compared to state of the art methods.