Improved motor imagery brain-computer interface performance via adaptive modulation filtering and two-stage classification

Electroencephalogram (EEG) based brain-computer interfaces (BCI) monitor neural activity and translate these signals into actions and/or decisions, with the final goal of enabling users to interact with a computer using only their thoughts. To this end, users must produce specific neural activity patterns that are used by the system as control signals. A common task used to elicit such signals is motor imagery (MI), where specific patterns are elicited in the sensorimotor cortex during imagination of movements (e.g., of the hands, arms, feet or tongue). The processing pipeline typically used in EEG-BCIs consists of three stages: pre-processing, feature extraction, and classification. Here, we propose innovations in pre-processing and classification and quantify the gains achieved on 4-class MI-based BCI performance. More specifically, for the pre-processing stage, we propose the concept of spectro-temporal filtering as we show that MI-elicited neural patterns have varying amplitude modulation variations relative to artifacts. For the classification stage, in turn, a two-step classification method is proposed. First, LDA classifiers are used to discriminate between different pair-wise MI tasks. Next, a naive Bayes classifier is used to predict the final task performed by the user based on the weighted outputs of the LDA classifiers. Experimental results showed that the proposed system outperformed the first-place winner of the BCI competition IV by 3.5 %. (C) 2019 Elsevier Ltd. All rights reserved.