Exploring the Effects of Offline Paradigms and Feature Extraction Techniques on Performance of Motor Imagery Brain-Computer Interface: Longitudinal Pilot Study.

Motor Imagery (MI) Brain-Computer Interface (BCI) is a popular way of allowing disabled and healthy individuals to use brain signals to communicate with their environment, despite the technical and human factor challenges that affect MI BCI classification performance. This study explored the influence of paradigm choice and phase synchronization-based features on classification performance by comparing primary datasets to older supplemental datasets. Area Under the Curve (AUC) Receiver Operating Characteristics (ROC) curve was the metric for classification performance. Results showed that using both advanced paradigms and features significantly improved both classification and usability; TD-CSP-wPLI (16-30Hz) and S-CSP-wPLI (12-15Hz) frequency bands produced the most noticeable change in performance.