Background: The number of commands in a brain-computer interface (BCI) system is important. This study proposes a new BCI technique to increase the number of commands in a single BCI system without loss of accuracy.
New method: We expected that a flickering action video with left and right elbow movements could simultaneously activate the different pattern of event-related desynchronization (ERD) according to the video contents (e.g., left or right) and steady-state visually evoked potential (SSVEP). The classification accuracy to discriminate left, right, and rest states was compared under the three following feature combinations: SSVEP power (19-21 Hz), Mu power (8-13 Hz), and simultaneous SSVEP and Mu power.
Results: The SSVEP feature could discriminate the stimulus condition, regardless of left or right, from the rest condition, while the Mu feature discriminated left or right, but was relatively poor in discriminating stimulus from rest. However, combining the SSVEP and Mu features, which were evoked by the stimulus with a single frequency, showed superior performance for discriminating all the stimuli among rest, left, or right.
Comparison with the existing method: The video contents could activate the ERD differently, and the flickering component increased its accuracy, such that it revealed a better performance to discriminate when considering together.
Conclusions: This paradigm showed possibility of increasing performance in terms of accuracy and number of commands with a single frequency by applying flickering action video paradigm and applicability to rehabilitation systems used by patients to facilitate their mirror neuron systems while training.
Keywords: Action observation; BCI; Flickering video; Mirror neuron system; SSVEP.
Copyright © 2019 Elsevier B.V. All rights reserved.