A dynamic and self-adaptive classification algorithm for motor imagery EEG signals.

Background: Brain-computer interface (BCI) is a communication pathway applied for pathological analysis or functional substitution. BCI based on functional substitution enables the recognition of a subject's intention to control devices such as prosthesis and wheelchairs. Discrimination of electroencephalography (EEG) trials related to left- and right-hand movements requires complex EEG signal processing to achieve good system performance.

New Method: In this study, a novel dynamic and self-adaptive algorithm (DSAA) based on the least-squares method is proposed to select the most appropriate feature extraction and classification algorithms couple for each subject. Specifically, the best couple identified during the training of the system is updated during online testing in order to check the stability of the selected couple and maintain high system accuracy.

Results: Extensive and systematic experiments were conducted on public datasets of 17 subjects in the BCI-competition and the results show an improved performance for DSAA over other selected state-of-the-art methods.

Comparison With Existing Methods: The results show that the proposed system enhanced the classification accuracy for the three chosen public datasets by 8% compared to other approaches. Moreover, the proposed system was successful in selecting the best path despite the unavailability of reference labels.

Conclusions: Performing dynamic and self-adaptive selection for the best feature extraction and classification algorithm couple increases the recognition rate of trials despite the unavailability of reference trial labels. This approach allows the development of a complete BCI system with excellent accuracy.