A Novel Approach for Epilepsy Detection Using Time–frequency Localized Bi-Orthogonal Wavelet Filter

Identification of seizure using electroencephalogram (EEG) signal is crucial to detect diseases like epilepsy. Manual epilepsy detection is time consuming and prone to errors. Various techniques have been developed to get quick and accurate results for epilepsy detection. We propose a novel approach to detect epileptic seizure using bi-orthogonal wavelet filters. The bi-orthogonal wavelet filters divide the EEG signal into different sub-bands. Then different features, i.e., Shannon entropy (ShEn), Renyi entropy (RenEn), fractal dimension (FD), energy and fuzzy entropy (FE) are extracted from the sub-bands. The [Formula: see text]-values of the features are used to evaluate the discriminating ability of the features. These features are given as input to the support vector machine (SVM). The EEG signals are then classified into the following classes: (i) normal versus seizure, (ii) seizure-free versus seizure, (iii) normal versus seizure-free versus seizure, and (iv) normal versus seizure-free. We have used two independent datasets: a public dataset for training and validation of the model, and a private dataset for evaluating the model’s performance. The ten-fold cross-validation method is used here to reduce the chances of over fitting. The SVM classifier yielded 100% accuracy in discriminating both seizure-free and normal patients for public dataset, and inter-ictal and ictal for private dataset. It also gave very good classification accuracies for the other classification problems for both the datasets. The proposed method is ready for the clinical trial to be tested with huge databases before the actual practical usage.