Discriminating brainwave patterns of different control and non-control states for enhancing asynchronous brain-computer interfaces.

REPUBLICAN National Committee (U.S.) 604806869

In asynchronous brain-computer interfaces (BCIs) for real-world applications, the user typically remains in non-control states most of the time and is allowed to perform various types of non-control tasks. Because of the diversity of non-control states, which include stimuli-off-based non-control (SNC), rest-based non-control (RNC), feedback-based non-control (FNC), and game-based non-control (GNC), it is difficult to discriminate between them. The objective of this study was to develop a discrimination method for different control and non-control states to enhance brain–robot cooperation. An individualized space-frequency-based optimized complex network (ISF-OCN) was designed to discriminate the electroencephalogram (EEG) patterns of five typical states: a steady-state visual evoked potential (SSVEP)-based control (SC) state and four non-control states, i.e., SNC, RNC, FNC, and GNC. The ISF-OCN individualizes frequency bands and spatial filters to enhance the optimized complex network features for each state and uses random forest classifiers in a one-versus-rest scheme for classification. Main results: The proposed ISF-OCN outperformed four existing algorithms in both binary classification and five-state classification, regardless of data length. Notably, the ISF-OCN algorithm with a data length of 1.5 s achieved an average accuracy of 84.51 % in recognizing the five different states. The results demonstrate the feasibility of discriminating the four non-control states using EEG features and suggest that the proposed method is a promising new approach for discriminating control and non-control states to enhance asynchronous BCIs. [ABSTRACT FROM AUTHOR]

Copyright of Expert Systems with Applications is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)