Title :
Non-invasive classification of cortical activities for brain computer interface: A variable selection approach
Author :
Besserve, Michel ; Martinerie, Jacques ; Garnero, Line
Author_Institution :
Lab. Neurosciences Cognitive et Imagerie Cerebrale, Univ Paris, Paris
Abstract :
We propose to carry out a classification method for electro-encepfialographic signals (EEG), using the activities of cortical sources estimated with an EEG inverse problem. To overcome the difficulties caused by the high number of sources (approximately 10000), we use a multivariate variable selection algorithm: the zero norm Support Vector Machine (L0-SVM). This technique allows to extract a small subset of sources, which are the most useful to allow for the discrimination of the mental states. The whole approach is applied to an asynchronous Brain Computer Interface (BCI) experiment from our lab. It outperforms a method based on the direct measurement of EEG electrodes´ activities.
Keywords :
electroencephalography; handicapped aids; medical computing; support vector machines; EEG electrode activity; brain computer interface; cortical activity; electroencephalographic signals; selection algorithm; zero-norm support vector machine; Brain computer interfaces; Classification algorithms; Electroencephalography; Image analysis; Input variables; Inverse problems; Performance analysis; Spatial resolution; Support vector machine classification; Support vector machines; Brain Computer Interface; EEG; Inverse problem; Support Vector Machine;
Conference_Titel :
Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on
Conference_Location :
Paris
Print_ISBN :
978-1-4244-2002-5
Electronic_ISBN :
978-1-4244-2003-2
DOI :
10.1109/ISBI.2008.4541183
