Wavelet Packet-Based Feature Extraction for Brain-Computer Interfaces

A novel feature extraction method of spontaneous electroencephalogram (EEG) signals for brain-computer interfaces (BCIs) is explored. The method takes the wavelet packet transform (WPT) as an analysis tool and utilizes two kinds of information. Firstly, EEG signals are transformed into wavelet packet coefficients by the WPT. And then average coefficient values and average power values of certain subbands are computed, which form initial features. Finally, part of average coefficient values and part of average power values with larger Fisher indexes are combined to form the feature vector. Compared with previous feature extraction methods, the proposed approach can lead to higher classification accuracy.

[1]  Reza Derakhshani,et al.  On classifiability of wavelet features for EEG-based brain-computer interfaces , 2009, 2009 International Joint Conference on Neural Networks.

[2]  G.E. Birch,et al.  Comparison of Using Mono-Polar and Bipolar Electroencephalogram (EEG) Electrodes for Detection of Right and Left Hand Movements in a Self-Paced Brain Computer Interface (BCI) , 2007, 2007 Canadian Conference on Electrical and Computer Engineering.

[3]  Xiaorong Gao,et al.  An auditory BCI using voluntary mental response , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[4]  Mingtian Zhou,et al.  Feature Extraction and Parameters Selection of Classification Model on Brain-Computer Interface , 2007, 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering.

[5]  Wu Xiaopei,et al.  Motor imagery EEG detection by empirical mode decomposition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[6]  Yan Tang,et al.  Research of Brain-Computer Interface Based on the Time-Frequency-Spatial Filter , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[7]  Wang Shou-yong.  Feature Extraction Using Best Wavelet Packet Transform , 2003 .

[8]  Abbas Erfanian,et al.  An on-line BCI for control of hand grasp sequence and holding using adaptive probabilistic neural network , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Girijesh Prasad,et al.  Continuous EEG classification for a self-paced BCI , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[10]  R. Nagarajan,et al.  Appraising human emotions using Time Frequency Analysis based EEG alpha band features , 2009, 2009 Innovative Technologies in Intelligent Systems and Industrial Applications.