A BCI motor imagery experiment based on parametric feature extraction and Fisher Criterion

An EEG-based classification method in the time domain is proposed to identify left and right hand motor imagery as part of a brain-computer interface (BCI) experiment. The feature vector is formed by sixth order autoregressive coefficients (AR) or sixth order adaptive autoregressive coefficients (AAR) representing EEG signals obtained from C3 and C4 channels, according to the EEG 10-20 standard. The signal is analyzed considering 1 second windows with a 50% overlapping. A feature selection process based on the Fisher Criterion (FC) removes irrelevant or noisy information. A Linear Discriminant Analysis (LDA) is applied to both cases: feature vectors formed with the total number of coefficients, and feature vectors formed with coefficients corresponding to larger Fisher Ratio. Classification results obtained using two AR methods, Burg and Levinson-Durbin, and one AAR LMS are presented.

[1]  G. Pfurtscheller,et al.  A criterion for adaptive autoregressive models , 2000, Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143).

[2]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[3]  Lin Liu,et al.  A Research Combining Spatial Filter with Autoregressive Model for EEG Feature Extraction , 2010 .

[4]  Bao-Guo Xu,et al.  Pattern Recognition of Motor Imagery EEG using Wavelet Transform , 2008 .

[5]  Bin He,et al.  A wavelet-based time–frequency analysis approach for classification of motor imagery for brain–computer interface applications , 2005, Journal of neural engineering.

[6]  Seung Kee Han,et al.  Single Trial Discrimination between Right and Left Hand Movement-Related EEG Activity , 2004, International Conference on Computational Science.

[7]  Cheng-Lin Liu,et al.  Feature Selection by Combining Fisher Criterion and Principal Feature Analysis , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[8]  R. Palaniappan,et al.  Identifying Individuality Using Mental Task Based Brain Computer Interface , 2005, 2005 3rd International Conference on Intelligent Sensing and Information Processing.

[9]  J Pardey,et al.  A review of parametric modelling techniques for EEG analysis. , 1996, Medical engineering & physics.

[10]  Ramaswamy Palaniappan,et al.  Neural network classification of autoregressive features from electroencephalogram signals for brain–computer interface design , 2004, Journal of neural engineering.

[11]  Aiguo Song,et al.  Algorithm of Imagined Left-Right Hand Movement Classification Based on Wavelet Transform and AR Parameter Model , 2007, 2007 1st International Conference on Bioinformatics and Biomedical Engineering.

[12]  Rabab K Ward,et al.  A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals , 2007, Journal of neural engineering.

[13]  Jonathan R Wolpaw,et al.  Sensorimotor rhythm-based brain–computer interface (BCI): model order selection for autoregressive spectral analysis , 2008, Journal of neural engineering.

[14]  Carlos Guerrero-Mosquera,et al.  New feature extraction approach for epileptic EEG signal detection using time-frequency distributions , 2010, Medical & Biological Engineering & Computing.

[15]  Gert Pfurtscheller,et al.  Characterization of four-class motor imagery EEG data for the BCI-competition 2005 , 2005, Journal of neural engineering.