Classification of EEG signals using the wavelet transform
Signal Processing
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
Comparison of brain models for active vs. passive perception
Information Sciences: an International Journal
An introduction to variable and feature selection
The Journal of Machine Learning Research
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Rough set based 1-v-1 and 1-v-r approaches to support vector machine multi-classification
Information Sciences: an International Journal
International Journal of Computer Mathematics - Bioinformatics
On detecting nonlinear patterns in discriminant problems
Information Sciences: an International Journal
IEEE Transactions on Fuzzy Systems
On the Complexity of Finite Sequences
IEEE Transactions on Information Theory
Relevant feature selection from EEG signal for mental task classification
PAKDD'12 Proceedings of the 16th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part II
Hi-index | 0.00 |
The Brain Computer Interface provides a channel of communication to physically challenged individuals who have fully or partially lost the power to interact with their surroundings. The strength of a BCI system lies in its ability to determine the appropriate features for a given task and to be able to correctly classify a task amid many other mental tasks. The electroencephalogram (EEG) is a cost effect and efficient means to capture the intent of a person with motor disorder. Wavelet decomposition for feature extraction from EEG is suitable for the analysis of non-linear and non-stationary time series. Hence, Wavelet decomposition of EEG is used in this study to form a feature set. Of the extracted features, a subset of discriminatory and relevant features is selected using ratio of scatter matrices, Chernoff distance measure and linear regression. The performance of different mental tasks using the selected features is compared and evaluated in terms of classification accuracy and the dimension of features. Experimental results on publicly available data show that there is significant improvement in classification accuracies with different feature selection methods. Linear regression performs better in comparison to other two methods and Support Vector Machine requires lesser number of features to build the model.