Comparative analysis of features extracted from EEG spatial, spectral and temporal domains for binary and multiclass motor imagery classification

• Published in: Information sciences Vol. 502; pp. 190 - 200
• Main Authors: Lee, Seung-Bo, Kim, Hyun-Ji, Kim, Hakseung, Jeong, Ji-Hoon, Lee, Seong-Whan, Kim, Dong-Joo
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01-10-2019
• Subjects: Brain-computer interface; Electroencephalogram; Feature extraction; Motor imagery; Multiclass discrimination; Brain-computer interface; Feature extraction; Motor imagery; Electroencephalogram; Multiclass discrimination
• ISSN: 0020-0255; 1872-6291
• DOI: 10.1016/j.ins.2019.06.008

•The efficacies of three EEG feature domains for motor imagery BCI were investigated.•Contrary to common beliefs, the temporal features were best suited for MI-BCI.•The number of target classes little affected the temporal feature extraction speed.
The electroencephalogram (EEG) remains the predominant source of neurophysiological signals for motor imagery-based brain-computer interfaces (MI-BCIs). Various features can be derived from three distinctive domains (i.e., spatial, temporal and spectral); however, the efficacies of the existing feature extraction methods when discriminating complex multiclass MI tasks have yet to be reported. This study investigates the performances of EEG feature extraction techniques from varying domains against different levels of complex, multiclass MI tasks. Ten healthy volunteers underwent multiple complex MI tasks via a robotic arm (i.e., hand grasping and wrist twisting; grasp, spread, pronation and supination). The discrimination performances of various feature extraction (i.e., common spatial patterns (CSP), time domain parameters (TDP), and power spectral density (PSD)) and classification methods for EEG were tested to perform binary (hand grasping/wrist twisting), ternary ((A) grasp/spread/wrist twisting and (B) hand grasping/pronation/supination) and quaternary (grasp/spread/pronation/supination) discrimination. Based on the available data, the combination of shrinkage-regularized linear discriminant analysis (SRLDA) and TDP achieved the highest accuracy. The findings suggest that multiclass complex MI-BCI task discrimination could gain more benefit from analyzing simple and symbolic features such as TDP rather than more complex features such as CSP and PSD.