Enhanced Active Segment Selection for Single-Trial EEG Classification

In this study, an electroencephalogram (EEG) analysis system is proposed for single-trial classification of both motor imagery (MI) and finger-lifting EEG data. Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system mainly consists of three procedures; enhanced active segment selection, feature extraction, and classification. In addition to the original use of continuous wavelet transform (CWT) and Student 2-sample t statistics, the two-dimensional (2D) anisotropic Gaussian filter further refines the selection of active segments. The multiresolution fractal features are then extracted from wavelet data by using proposed modified fractal dimension. Finally, the support vector machine (SVM) is used for classification. Compared to original active segment selection, with several popular features and classifier on both the MI and finger-lifting data from 2 data sets, the results indicate that the proposed method is promising in EEG classification.

[1]  Pierre Flor-Henry,et al.  EEG Analysis of Male to Female Transsexuals: Discriminant Function and Source Analysis , 2010, Clinical EEG and neuroscience.

[2]  H. Jasper,et al.  The ten-twenty electrode system of the International Federation. The International Federation of Clinical Neurophysiology. , 1999, Electroencephalography and clinical neurophysiology. Supplement.

[3]  N. Nicolaou,et al.  The Use of Permutation Entropy to Characterize Sleep Electroencephalograms , 2011, Clinical EEG and neuroscience.

[4]  Chao-Hung Lin,et al.  Wavelet-based envelope features with automatic EOG artifact removal: Application to single-trial EEG data , 2012, Expert Syst. Appl..

[5]  Wei-Yen Hsu,et al.  Wavelet-based fractal features with active segment selection: Application to single-trial EEG data , 2007, Journal of Neuroscience Methods.

[6]  E.R. Cuspineda Bravo,et al.  Noninvasive Multimodal Neuroimaging for Rasmussen Encephalopathy Surgery: Simultaneous EEG-fMRI Recording , 2010, Clinical EEG and neuroscience.

[7]  Wei-Yen Hsu,et al.  Unsupervised fuzzy c-means clustering for motor imagery EEG recognition , 2011 .

[8]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[9]  G. Lightbody,et al.  A comparison of quantitative EEG features for neonatal seizure detection , 2008, Clinical Neurophysiology.

[10]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[11]  Wei-Yen Hsu,et al.  EEG-based motor imagery analysis using weighted wavelet transform features , 2009, Journal of Neuroscience Methods.

[12]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[13]  G. Pfurtscheller,et al.  EEG-based discrimination between imagination of right and left hand movement. , 1997, Electroencephalography and clinical neurophysiology.

[14]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  HsuWei-Yen.  Improved watershed transform for tumor segmentation , 2012 .

[16]  Hojjat Adeli,et al.  Fuzzy Synchronization Likelihood with Application to Attention-Deficit/Hyperactivity Disorder , 2011, Clinical EEG and neuroscience.

[17]  Yu-Chuan Li,et al.  Application of Multiscale Amplitude Modulation Features and Fuzzy C-Means to Brain–Computer Interface , 2012, Clinical EEG and neuroscience.

[18]  Wei Yen Hsu,et al.  Application of Competitive Hopfield Neural Network to Brain-Computer Interface Systems , 2012, Int. J. Neural Syst..

[19]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[20]  Barak A. Pearlmutter,et al.  Linear Spatial Integration for Single-Trial Detection in Encephalography , 2002, NeuroImage.

[21]  WEI-YEN HSU,et al.  Analytic differential approach for robust registration of rat brain histological images , 2011, Microscopy research and technique.

[22]  P. de Chazal,et al.  Parametric models and spectral analysis for classification in brain-computer interfaces , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[23]  Wei-Yen Hsu,et al.  Continuous EEG Signal Analysis for Asynchronous BCI Application , 2011, Int. J. Neural Syst..

[24]  V. Samar,et al.  Time–Frequency Analysis of Single-Sweep Event-Related Potentials by Means of Fast Wavelet Transform , 1999, Brain and Language.

[25]  B. Mandelbrot.  Fractal Geometry of Nature , 1984 .

[26]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[27]  Wei-Yen Hsu,et al.  Improved watershed transform for tumor segmentation: Application to mammogram image compression , 2012, Expert Syst. Appl..

[28]  Wei-Yen Hsu,et al.  Automatic seamless mosaicing of microscopic images: enhancing appearance with colour degradation compensation and wavelet‐based blending , 2008, Journal of microscopy.

[29]  G Pfurtscheller,et al.  Estimating the Mutual Information of an EEG-based Brain-Computer Interface , 2002, Biomedizinische Technik. Biomedical engineering.

[30]  Wei-Yen Hsu,et al.  Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification , 2012, Expert Syst. Appl..

[31]  J. Brickmann.  B. Mandelbrot: The Fractal Geometry of Nature, Freeman and Co., San Francisco 1982. 460 Seiten, Preis: £ 22,75. , 1985 .

[32]  J R Wolpaw,et al.  Spatial filter selection for EEG-based communication. , 1997, Electroencephalography and clinical neurophysiology.

[33]  Wei-Yen Hsu,et al.  EEG-based motor imagery classification using neuro-fuzzy prediction and wavelet fractal features , 2010, Journal of Neuroscience Methods.

[34]  Ahmet Ademoglu,et al.  Simultaneous EEG/fMRI Analysis of the Resonance Phenomena in Steady-State Visual Evoked Responses , 2011, Clinical EEG and neuroscience.

[35]  Wei-Yen Hsu,et al.  EEG-based motor imagery classification using enhanced active segment selection and adaptive classifier , 2011, Comput. Biol. Medicine.

[36]  Chongxun Zheng,et al.  Decreased Delta Event-Related Synchronization in Patients with Early Vascular Dementia , 2011, Clinical EEG and neuroscience.