Using Multiresolution Space-Time-Frequency Features for the Classification Motor Imagery Eeg Recordings in a Brain Computer Interface Task

We introduce an adaptive space time frequency analysis to extract and classify subject specific brain oscillations induced by motor imagery in a brain computer interface task. The proposed method requires no prior knowledge of the reactive frequency bands, their temporal behavior or cortical locations. By using a modified local discriminant base algorithm (flexible LDB), our procedure calculates an arbitrary time-frequency segmentation of the given multichannel brain activity recordings to extract subject specific ERD and ERS patterns. The extracted time-frequency features are processed by principal component analysis to reduce the feature set which is highly correlated due to volume conduction and the neighbor cortical regions. The reduced feature set is then fed into a linear discriminant analysis for classification. We describe experimental results for 9 subjects that show the superior performance of the proposed method. The classification accuracy for the subjects varied between 76.4% and 96.8% and the average classification accuracy was 84.9%.