Multichannel Classification of Single EEG Trials with Independent Component Analysis
We have previously shown that classification of single-trial electroencephalographic (EEG) recordings is improved by the use of either a multichannel classifier or the best independent component over a single channel classifier. In this paper, we introduce a classifier that makes explicit use of multiple independent components. Two models are compared. The first (“direct”) model uses independent components as time-series inputs, while the second (“indirect”) model remixes the components back to the signal space. The direct model resulted in significantly improved classification rates when applied to two experiments using both monopolar and bipolar settings.
KeywordsIndependent Component Analysis Independent Component Independent Component Analysis Direct Model Signal Space
Unable to display preview. Download preview PDF.
- 1.Jasper, H.H.: The Ten-twenty Electrode Placement of The International Federation. Electroencephalography and Clinical Neurophysiology 10, 371–375 (1958)Google Scholar
- 4.Hyvarinen, A.: Independent Component Analysis by Minimization of Mutual Information. Laboratory of Computer and Information Science. Helsinki University of Technology (1997)Google Scholar
- 8.Wong, D.K.: Multichannel Classification of Brain-wave Representations of Language by Perceptron-based Models and Independent Component Analysis (Ph.D. Dissertation). Stanford University, California, USA (2004)Google Scholar