EEG Detection Based on Wavelet Transform and SVM Method

Epilepsy refers to a set of chronic neurologicalsyndromes characterized by transient and unexpected electrical disturbances of the brain. Scalp Electroencephalogram (EEG) is a common test that measures and records the electrical activity of the brain, and is widely used in the detection and analysis of epileptic seizures. However, it is often difficult to identify the subtle changes in the EEG waveform by visual inspection. Then, emerge in large numbers of research for biomedical engineers to develop and implement several intelligent algorithms for the identification of such subtle changes. This paper presents a EEG signal analysis and forecasting technique based on wavelet transform and support vector machine classification method. The main procedure is a dynamic circulation. The technique first train the given datasets, obtain the value of the parameter, then automatically multi-time decompose for a new person's brain signals, predict whether the person has a characteristic wave of epilepsy, add the person's EEG data into the SVM training model if the person has epilepsy abnormal signal, combined withabnormal data before retraining and learning. The method has a very large potential uses, such as application for the initial diagnosis of patients, improving the efficiency for doctors.

[1]  Dragan Djurdjanovic,et al.  Time-frequency distributions in the classification of epilepsy from EEG signals , 2012, Expert Syst. Appl..

[2]  J. Gotman,et al.  Wavelet based automatic seizure detection in intracerebral electroencephalogram , 2003, Clinical Neurophysiology.

[3]  Shuzhi Sam Ge,et al.  Detection of seizures in EEG signal using weighted locally linear embedding and SVM classifier , 2008, 2008 IEEE Conference on Cybernetics and Intelligent Systems.

[4]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  O. Ozdamar,et al.  Wavelet preprocessing for automated neural network detection of EEG spikes , 1995 .

[6]  Ricardo Nuno Vig.  Extraction of' ocular artefacts from EEG using independent component analysis , 1997 .

[7]  Donald C. Wunsch,et al.  Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG , 2000, Neurocomputing.

[8]  Franck Vermet,et al.  Statistical Learning Methods , 2018 .

[9]  Arthur Petrosian,et al.  A comparison of techniques for the prediction of epileptic seizures , 1995, Proceedings Eighth IEEE Symposium on Computer-Based Medical Systems.

[10]  J. Martinerie,et al.  Anticipation of epileptic seizures from standard EEG recordings , 2003, The Lancet.

[11]  B. Litt,et al.  For Personal Use. Only Reproduce with Permission from the Lancet Publishing Group. Review Prediction of Epileptic Seizures Are Seizures Predictable? Prediction of Epileptic Seizures , 2022 .

[12]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[13]  F. Mormann,et al.  Nonlinear EEG analysis in epilepsy: its possible use for interictal focus localization, seizure anticipation, and prevention. , 2001, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[14]  Mukta Dhopeshwarkar,et al.  Prediction of Epileptic Seizure : A Review , 2016 .

[15]  Metin Akay.  Wavelet Feature Extraction from Neurophysiological Signals , 1998 .

[16]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[17]  Kemal Polat,et al.  Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform , 2007, Appl. Math. Comput..

[18]  A. Geva,et al.  Forecasting generalized epileptic seizures from the EEG signal by wavelet analysis and dynamic unsupervised fuzzy clustering , 1998, IEEE Transactions on Biomedical Engineering.

[19]  William J. Williams,et al.  Time-frequency analysis of electrophysiology signals in epilepsy , 1995 .