Optimal EEG Window Size for Neural Seizure Detection

In this paper, different window sizes for EEG signal segmentation are investigated in order to optimize the performance of seizure detection systems. To differentiate between epileptic and non-epileptic epochs, the time axis of the EEG signal is divided into non-overlapping windows. The window period should be long enough for the lapse to be informative but not too long for it to stay stationary. Hence, the KPSS test is used to determine signal stationarity for different window sizes, then the optimal window is chosen such that it corresponds to the smallest number of non-stationary segments in the signal of interest. The seizure detection system is then applied to the piece-wise stationary segments. Compared to the exhaustive examination, it is found that the KPSS test optimal window results in the highest sensitivity.

[1]  P. Phillips,et al.  Testing the null hypothesis of stationarity against the alternative of a unit root: How sure are we that economic time series have a unit root? , 1992 .

[2]  Helge B. D. Sørensen,et al.  Detection of tonic epileptic seizures based on surface electromyography , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[4]  E. Waterhouse,et al.  New horizons in ambulatory electroencephalography , 2003, IEEE Engineering in Medicine and Biology Magazine.

[5]  Hassan Mostafa,et al.  Linear and Nonlinear Feature Extraction for Neural Seizure Detection , 2018, 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS).

[6]  D. Singh,et al.  The Window Size for Classification of Epileptic Seizures based on Analysis of EEG Patterns , 2016 .

[7]  Tamara M.E. Nijsen,et al.  A model of heart rate changes to detect seizures in severe epilepsy , 2006, Seizure.

[8]  Hung T. Nguyen,et al.  Investigation of window size in classification of EEG-emotion signal with wavelet entropy and support vector machine , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  S. Wiebe,et al.  Understanding the burden of epilepsy in Latin America: A systematic review of its prevalence and incidence , 2005, Epilepsy Research.

[10]  Gleb V. Tcheslavski,et al.  Techniques to Assess Stationarity and Gaussianity of EEG: An Overview , 2012 .

[11]  Tao Zhang,et al.  LMD Based Features for the Automatic Seizure Detection of EEG Signals Using SVM , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[12]  Helge B. D. Sørensen,et al.  Evaluation of novel algorithm embedded in a wearable sEMG device for seizure detection , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.