Computer-Aided On-line Seizure Detection Using Stockwell Transform

The paper deals with the designing and implementation of a computer-aided system capable to detect seizures by inspecting EEG records. The system is based on modern signal processing tools, which are able to give a time-frequency representation of a signal. Then using time-frequency representation of EEG data, feature extraction and finally classification of neurological disorders is carried out. The application should be treated as a decision support computer system which was designed to help neurologists in detecting seizures. With the help of such a software the time needed for analysing EEG records can be significantly reduced. The research was carried out using real EEG recordings of epileptic patients as well as healthy subjects prepared with the cooperation of the medical staff of the Ward of Neurology and Strokes of the Provincial Hospital of Zielona Gora, Poland.

[1]  Daniel Rivero,et al.  Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks , 2010, Journal of Neuroscience Methods.

[2]  Krzysztof Patan,et al.  Comparison of Time-Frequency Feature Extraction Methods for EEG Signals Classification , 2013, ICAISC.

[3]  Elif Derya Übeyli.  Combined neural network model employing wavelet coefficients for EEG signals classification , 2009, Digit. Signal Process..

[4]  Abdulhamit Subasi,et al.  EEG signal classification using wavelet feature extraction and a mixture of expert model , 2007, Expert Syst. Appl..

[5]  Jacek M. Zurada,et al.  Artificial Intelligence and Soft Computing, 10th International Conference, ICAISC 2010, Zakopane, Poland, June 13-17, 2010, Part I , 2010, International Conference on Artificial Intelligence and Soft Computing.

[6]  Gordon Lightbody,et al.  An evaluation of automated neonatal seizure detection methods , 2005, Clinical Neurophysiology.

[7]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[8]  Lalu Mansinha,et al.  Localization of the complex spectrum: the S transform , 1996, IEEE Trans. Signal Process..

[9]  Clay B. Holroyd,et al.  Detection of synchronized oscillations in the electroencephalogram: an evaluation of methods. , 2004, Psychophysiology.

[10]  Bartosz Krawczyk,et al.  Combined classifier based on feature space partitioning , 2012, Int. J. Appl. Math. Comput. Sci..

[11]  Krzysztof Patan,et al.  Analysis and Classification of EEG Data: An Evaluation of Methods , 2012, ICAISC.

[12]  Richard D. Jones,et al.  Detection of epileptiform discharges in the EEG by a hybrid system comprising mimetic, self-organized artificial neural network, and fuzzy logic stages , 1999, Clinical Neurophysiology.

[13]  A. Tzallas,et al.  Automated Epileptic Seizure Detection Methods: A Review Study , 2012 .

[14]  F. Lippman.  Seizure and epilepsy , 2008 .

[15]  Ewa Swiercz.  Classification in the Gabor time-frequency domain of non-stationary signals embedded in heavy noise with unknown statistical distribution , 2010, Int. J. Appl. Math. Comput. Sci..

[16]  D. Stevanović,et al.  Epilepsy - Histological, Electroencephalographic and Psychological Aspects , 2012 .

[17]  L. Tarassenko,et al.  Linear and non-linear methods for automatic seizure detection in scalp electro-encephalogram recordings , 2002, Medical and Biological Engineering and Computing.

[18]  Przemyslaw Kazienko,et al.  Multi-label classification using error correcting output codes , 2012, Int. J. Appl. Math. Comput. Sci..