sw-SVM : sensor weighting Support Vector Machines for EEG-based Brain-Computer Interfaces

Abstract : In many machine learning applications, like Brain-Computer Interfaces (BCI), high-dimensional sensor array data are available. Sensor measurements are often highly correlated and Signal to Noise Ratio (SNR) is not homogeneously spread across sensors. Thus, collected data are highly variable and discrimination tasks are challenging. In this work, we focus on sensor weighting as an efficient tool to improve the classification procedure. We present an approach integrating sensor weighting in the classification framework. Sensor weights are considered as hyper-parameters to be learned by a Support Vector Machine (SVM). The resulting sensor weighting SVM (sw-SVM) is designed to satisfy a margin criterion, that is, the generalization error. Experimental studies on two data sets are presented, a P300 data set and an Error Related Potential (ErrP) data set. For the P300 data set (BCI competition III), for which a large number of trials are available, the sw-SVM proves to perform equivalently with respect to the ensemble SVM strategy that won the competition. For the ErrP data set, for which a small number of trials are available, sw-SVM shows superior performances as compared to three state-of-the art approaches. Results suggest that sw-SVM promises to be useful in event-related potentials classification, even with a small number of training trials.
Document type :
Journal articles
Journal of Neural Engineering, IOP Publishing, 2011, 8 (5), pp.056004. <10.1088/1741-2560/8/5/056004>


https://hal.archives-ouvertes.fr/hal-00617810
Contributor : Marco Congedo <>
Submitted on : Tuesday, August 30, 2011 - 3:01:52 PM
Last modification on : Friday, July 1, 2016 - 3:33:25 PM

File

JNE_author.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Nisrine Jrad, Marco Congedo, Ronald Phlypo, Sandra Rousseau, Rémi Flamary, et al.. sw-SVM : sensor weighting Support Vector Machines for EEG-based Brain-Computer Interfaces. Journal of Neural Engineering, IOP Publishing, 2011, 8 (5), pp.056004. <10.1088/1741-2560/8/5/056004>. <hal-00617810>

Export

Share

Metrics

Record views

298

Document downloads

195