Support Vector Channel Selection in BCI
Citations Over TimeTop 10% of 2004 papers
Abstract
Designing a brain computer interface (BCI) system one can choose from a variety of features that may be useful for classifying brain activity during a mental task. For the special case of classifying electroencephalogram (EEG) signals we propose the usage of the state of the art feature selection algorithms Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM). These algorithms can provide more accurate solutions than standard filter methods for feature selection. We adapt the methods for the purpose of selecting EEG channels. For a motor imagery paradigm we show that the number of used channels can be reduced significantly without increasing the classification error. The resulting best channels agree well with the expected underlying cortical activity patterns during the mental tasks. Furthermore we show how time dependent task specific information can be visualized.
Related Papers
- → The control of a virtual automatic car based on multiple patterns of motor imagery BCI(2018)37 cited
- → Simultaneous Classification of Multiple Motor Imagery and P300 for Increase in Output Information of Brain–Computer Interface(2014)4 cited
- → Performance Improvement of Motor-Imagery BCI Using Multi-Mental Tasks(2019)2 cited
- → Creation of a high resolution EEG based Brain Computer Interface for classifying motor imagery of daily life activities(2019)2 cited
- Towards a virtual 4-class synchronous BCI using motor prediction and one motor imagery(2008)