Transformed common spatial pattern for motor imagery-based brain-computer interfaces

Abstract

ObjectiveThe motor imagery (MI)-based brain–computer interface (BCI) is one of the most popular BCI paradigms. Common spatial pattern (CSP) is an effective algorithm for decoding MI-related electroencephalogram (EEG) patterns. However, it highly depends on the selection of EEG frequency bands. To address this problem, previous researchers often used a filter bank to decompose EEG signals into multiple frequency bands before applying the traditional CSP.ApproachThis study proposed a novel method, i.e., transformed common spatial pattern (tCSP), to extract the discriminant EEG features from multiple frequency bands after but not before CSP. To verify its effectiveness, we tested tCSP on a dataset collected by our team and a public dataset from BCI competition III. We also performed an online evaluation of the proposed method.Main resultsAs a result, for the dataset collected by our team, the classification accuracy of tCSP was significantly higher than CSP by about 8% and filter bank CSP (FBCSP) by about 4.5%. The combination of tCSP and CSP further improved the system performance with an average accuracy of 84.77% and a peak accuracy of 100%. For dataset IVa in BCI competition III, the combination method got an average accuracy of 94.55%, which performed best among all the presented CSP-based methods. In the online evaluation, tCSP and the combination method achieved an average accuracy of 80.00 and 84.00%, respectively.SignificanceThe results demonstrate that the frequency band selection after CSP is better than before for MI-based BCIs. This study provides a promising approach for decoding MI EEG patterns, which is significant for the development of BCIs.

Predicting Motor Imagery BCI Performance Based on EEG Microstate Analysis

“…During slow-wave sleep, the executive control network overlapped the fMRI deactivation of microstate C [ 24 ]. In this paper, the increase in MS3 (microstate C) mean duration in the resting-state EEG before the MI task was another characteristic of the subjects’ better MI-BCI performance, which can be understood as the emergence of executive control networks, and the enhancement of the brain’s autonomic neural processing ability is related to the subjects’ MI-BCI performance [ 34 , 35 ].…”

EEG control intention decoding based on improved discriminant analysis

“…CSP determines the ideal spatial projection to maximize the power of both types of signals and does not demand pre-selection of idiosyncratic bands. Therefore, it can extract the task-relevant signal components through the assessment of two spatial filters, leading to the simultaneous removal of task irrelevant components and noise [14].…”