Time Series Feature Evaluation in Discriminating Preictal EEG States

Statistical discrimination of states in the preictal EEG is attempted using a large number of measures from linear and nonlinear time series analysis. The measures are organized in two categories: correlation measures, such as autocorrelation and mutual information at specific lags and new measures derived from oscillations of the EEG time series, such as mean oscillation peak and mean oscillation period. All measures are computed on successive segments of multichannel EEG windows selected from early, intermediate and late preictal states from four epochs. Hypothesis tests applied for each channel and epoch showed good discrimination of the preictal states and allowed for the selection of optimal measures. These optimal measures, together with other standard measures (skewness, kurtosis, largest Lyapunov exponent) formed the feature set for feature-based clustering and the feature-subset selection procedure showed that the best preictal state classification was obtained with the same optimal features.

[1]  Alberto Prieto,et al.  Computational intelligence and bioinspired systems , 2007, Neurocomputing.

[2]  Andreas Schulze-Bonhage,et al.  Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction. , 2006, Chaos.

[3]  I. Osorio,et al.  Controlled test for predictive power of Lyapunov exponents: their inability to predict epileptic seizures. , 2004, Chaos.

[4]  A. Kraskov,et al.  On the predictability of epileptic seizures , 2005, Clinical Neurophysiology.

[5]  A. Schulze-Bonhage,et al.  Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic , 2004 .

[6]  G. Darbellay.  An estimator of the mutual information based on a criterion for independence , 1999 .

[7]  Holger Kantz,et al.  Practical implementation of nonlinear time series methods: The TISEAN package. , 1998, Chaos.

[8]  Sun I. Kim,et al.  Mutifractal Analysis of Electroencephalogram Time Series in Humans , 2005, IWANN.

[9]  Piotr J. Franaszczuk,et al.  Signal complexity and synchrony of epileptic seizures: is there an identifiable preictal period? , 2005, Clinical Neurophysiology.

[10]  M. Besserve,et al.  Towards a proper estimation of phase synchronization from time series , 2006, Journal of Neuroscience Methods.

[11]  S. Kochen,et al.  Discriminating preictal from interictal states by using coherence measures , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[12]  J. Velazquez,et al.  EEG nonstationarity during intracranially recorded seizures: statistical and dynamical analysis , 2005, Clinical Neurophysiology.

[13]  F. Mormann,et al.  Epileptic seizures are preceded by a decrease in synchronization , 2003, Epilepsy Research.

[14]  K. Tsakalis,et al.  Long-term prospective on-line real-time seizure prediction , 2005, Clinical Neurophysiology.

[15]  Dimitris Kugiumtzis,et al.  LINEAR AND NONLINEAR ANALYSIS OF EEG FOR THE PREDICTION OF EPILEPTIC SEIZURES , 2000 .

[16]  M. Paluš,et al.  Synchronization and Information Flow in EEGs of Epileptic Patients , 2001 .

[17]  David W. Aha,et al.  A Comparative Evaluation of Sequential Feature Selection Algorithms , 1995, AISTATS.

[18]  A. Kehagias,et al.  Statistical analysis of the extreme values of stress time series from the Portevin-Le Châtelier effect. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Werner Ebeling,et al.  Entropy and Complexity Analysis of Intracranially recorded EEG , 2004, Int. J. Bifurc. Chaos.

[20]  C. Stam,et al.  Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field , 2005, Clinical Neurophysiology.

[21]  J. Velazquez,et al.  Brain, behaviour and mathematics: Are we using the right approaches? , 2005 .