BCI competition 2003-data set IV:An algorithm based on CSSD and FDA for classifying single-trial EEG

• Published in: IEEE transactions on biomedical engineering Vol. 51; no. 6; pp. 1081 - 1086
• Main Authors: Wang, Y., Zhang, Z., Li, Y., Gao, X., Gao, S., Yang, F.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2004; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial Intelligence; Biological neural networks; Biomedical engineering; Brain computer interfaces; Cerebral Cortex - physiology; Cognition - physiology; Computer Peripherals; Data mining; Databases, Factual; Delay; Discriminant Analysis; Electroencephalography; Electroencephalography - classification; Electroencephalography - methods; Evoked Potentials, Motor - physiology; Feature extraction; Fingers; Fingers - physiology; Humans; Imagination - physiology; Models, Neurological; Motor Cortex - physiology; Movement - physiology; Pattern Recognition, Automated; Principal Component Analysis; Reproducibility of Results; Rhythm; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Somatosensory Cortex - physiology; Testing; User-Computer Interface
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2004.826697

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 <self-paced 1s> of "BCI Competition 2003" with a classification accuracy of 84% on the test set.