2012 | OriginalPaper | Chapter
Multi-class Feature Extraction Based on Common Spatial Patterns of Multi-band Cross Filter in BCIs
Authors : Banghua Yang, Meiyan He, Yanyan Liu, Zhijun Han
Published in: System Simulation and Scientific Computing
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
The CSP (Common Spatial Patterns) has been proved to be an effective feature extraction method in Brain Computer Interfaces. It is widely used for two-class problem. In this paper, the CSP algorithm is expanded to realize the EEG feature extraction for three-class problem. Firstly, the 8 ~ 30 Hz frequency band is divided into eight cross frequency bands and original EEG signals are filtered according to the eight bands. Each filtered signal can be regarded as a new channel. Then the “one to one” strategy is applied to the CSP for three-class problem. Finally, the proposed method is used to analyze the data from BCI Competition IV and the experimental data from our laboratory. The obtained features are input to SVM (Support Vector Machine) for classification. Comparing the proposed method with simple CSP, the accuracy of the former is higher than the latter by 10%.