Title :
BCI competition 2003-data set IV:An algorithm based on CSSD and FDA for classifying single-trial EEG
Author :
Wang, Yijun ; Zhang, Zhiguang ; Li, Yong ; Gao, Xiaorong ; Gao, Shangkai ; Yang, Fusheng
Author_Institution :
Dept. of Biomed. Eng., Tsinghua Univ., Beijing, China
fDate :
6/1/2004 12:00:00 AM
Abstract :
This paper presents an algorithm for classifying single-trial electroencephalogram (EEG) during the preparation of self-paced tapping. It combines common spatial subspace decomposition with Fisher discriminant analysis to extract features from multichannel EEG. Three features are obtained based on Bereitschaftspotential and event-related desynchronization. Finally, a perceptron neural network is trained as the classifier. This algorithm was applied to the data set of "BCI Competition 2003" with a classification accuracy of 84% on the test set.
Keywords :
bioelectric potentials; electroencephalography; feature extraction; handicapped aids; medical signal processing; perceptrons; signal classification; BCI Competition 2003; Bereitschaftspotential; CSSD; FDA; Fisher discriminant analysis; common spatial subspace decomposition; electroencephalogram; event-related desynchronization; feature extraction; perceptron neural network; self-paced tapping; single-trial EEG classification; Biological neural networks; Biomedical engineering; Brain computer interfaces; Data mining; Delay; Electroencephalography; Feature extraction; Fingers; Rhythm; Testing; Algorithms; Artificial Intelligence; Cerebral Cortex; Cognition; Computer Peripherals; Databases, Factual; Discriminant Analysis; Electroencephalography; Evoked Potentials, Motor; Fingers; Humans; Imagination; Models, Neurological; Motor Cortex; Movement; Pattern Recognition, Automated; Principal Component Analysis; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Somatosensory Cortex; User-Computer Interface;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2004.826697
