Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
412105 | Robotics and Autonomous Systems | 2015 | 12 Pages |
•Multi-class classification of motor imagery EEG signal.•Adaptive neural fuzzy inference system (ANFIS) using one-vs-one and one-vs-all methods.•Proposed an interval type-2 fuzzy fusion with ANFIS to improve uncertainty handling.•Experimented on an online control task of moving a robot towards a target.•The success rate of the robot reaching the target is above 60% for most subjects.
Brain–computer interfacing is an emerging field of research where signals extracted from the human brain are used for decision making and generation of control signals. Selection of the right classifier to detect the mental states from electroencephalography (EEG) signal is an open area of research because of the signal’s non-stationary and Ergodic nature. Though neural network based classifiers, like Adaptive Neural Fuzzy Inference System (ANFIS), act efficiently, to deal with the uncertainties involved in EEG signals, we have introduced interval type-2 fuzzy system in the fray to improve its uncertainty handling. Also, real-time scenarios require a classifier to detect more than two mental states. Thus, a multi-class discriminating algorithm based on the fusion of interval type-2 fuzzy logic and ANFIS, is introduced in this paper. Two variants of this algorithm have been developed on the basis of One-Vs-All and One-Vs-One methods. Both the variants have been tested on an experiment involving the real-time control of robot arm, where both the variants of the proposed classifier, produces an average success rate of reaching a target to 65% and 70% respectively. The result shows the competitiveness of our algorithm over other standard ones in the domain of non-stationary and uncertain signal data classification.