Testing the Self-Similarity Exponent to Feature Extraction in Motor Imagery Based Brain Computer Interface Systems

A Brain Computer Interface (BCI) system is a tool not requiring any muscle action to transmit information. Acquisition, preprocessing, feature extraction (FE), and classification of electroencephalograph (EEG) signals constitute the main steps of a motor imagery BCI. Among them, FE becomes crucial for BCI, since the underlying EEG knowledge must be properly extracted into a feature vector. Linear approaches have been widely applied to FE in BCI, whereas nonlinear tools are not so common in literature. Thus, the main goal of this paper is to check whether some Hurst exponent and fractal dimension based estimators become valid indicators to FE in motor imagery BCI. The final results obtained were not optimal as expected, which may be due to the fact that the nature of the analyzed EEG signals in these motor imagery tasks were not self-similar enough.

[1]  C. Robinson.  Dynamical Systems: Stability, Symbolic Dynamics, and Chaos , 1994 .

[2]  Pedro J. García-Laencina,et al.  Automatic and Adaptive Classification of Electroencephalographic Signals for Brain Computer Interfaces , 2012, Journal of Medical Systems.

[3]  Pedro J. García-Laencina,et al.  Efficient Automatic Selection and Combination of EEG Features in Least Squares Classifiers for Motor Imagery Brain-Computer Interfaces , 2013, Int. J. Neural Syst..

[4]  Bijaya K. Panigrahi,et al.  A comparative study of wavelet families for EEG signal classification , 2011, Neurocomputing.

[5]  Moritz Grosse-Wentrup,et al.  Critical issues in state-of-the-art brain–computer interface signal processing , 2011, Journal of neural engineering.

[6]  Yan Li,et al.  Monitoring the depth of anaesthesia using Hurst exponent and Bayesian methods , 2014, IET Signal Process..

[7]  Daniela G. Tarniceriu,et al.  Estimating the hurst exponent in motor imagery-based brain computer interface , 2013, 2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD).

[8]  Pedro J. García-Laencina,et al.  Exploring dimensionality reduction of EEG features in motor imagery task classification , 2014, Expert Syst. Appl..

[9]  M. Fernández-Martínez,et al.  Fractal Dimension for Fractal Structures , 2010, 1007.3236.

[10]  T. Aste,et al.  Understanding the source of multifractality in financial markets , 2012, 1201.1535.

[11]  Tomaso Aste,et al.  Non-stationary multifractality in stock returns , 2013 .

[12]  Vicsek,et al.  Multifractality of self-affine fractals. , 1991, Physical review. A, Atomic, molecular, and optical physics.

[13]  C. Peng,et al.  Mosaic organization of DNA nucleotides. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Yangquan Chen,et al.  Multifractional Property Analysis of Human Sleep EEG signals , 2012, Int. J. Bifurc. Chaos.

[15]  H. Berger.  Über das Elektrenkephalogramm des Menschen , 1929, Archiv für Psychiatrie und Nervenkrankheiten.

[16]  L. Pontrjagin,et al.  Sur Une Propriete Metrique de la Dimension , 1932 .

[17]  Bin Deng,et al.  Ordinal Pattern Based Complexity Analysis for EEG Activity Evoked by Manual Acupuncture in Healthy Subjects , 2014, Int. J. Bifurc. Chaos.

[18]  M. Fernández-Martínez,et al.  A note on geometric method-based procedures to calculate the Hurst exponent , 2012 .

[19]  Tomaso Aste,et al.  Scaling behaviors in differently developed markets , 2003 .

[20]  M.M. Moore,et al.  Real-world applications for brain-computer interface technology , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[21]  J. E. T. Segovia,et al.  Some comments on Hurst exponent and the long memory processes on capital markets , 2008 .

[22]  Ladislav Kristoufek,et al.  On Hurst exponent estimation under heavy-tailed distributions , 2010, 1201.4786.

[23]  Fabien Lotte,et al.  Brain-Computer Interfaces: Beyond Medical Applications , 2012, Computer.

[24]  J. E. Trinidad Segovia,et al.  Measuring the self-similarity exponent in Lévy stable processes of financial time series , 2013 .

[25]  Shujuan Geng,et al.  EEG non-linear feature extraction using correlation dimension and Hurst exponent , 2011, Neurological research.

[26]  T. D. Matteo,et al.  Multi-scaling in finance , 2007 .

[27]  J. E. Trinidad Segovia,et al.  An accurate algorithm to calculate the Hurst exponent of self-similar processes , 2014 .

[28]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[29]  Benoit B. Mandelbrot,et al.  Fractals and Scaling in Finance , 1997 .

[30]  Ad Aertsen,et al.  Review of the BCI Competition IV , 2012, Front. Neurosci..

[31]  U. Rajendra Acharya,et al.  Non-linear analysis of EEG signals at various sleep stages , 2005, Comput. Methods Programs Biomed..

[32]  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.