Performance Evaluation of Discrete Wavelet Transform, and Wavelet Packet Decomposition for Automated Focal and Generalized Epileptic Seizure Detection

In the past decades, wavelet transforms are widely employed for characterizing the electroencephalogram (EEG) signals for automatic diagnosis of epileptic seizure. But few vital issues like the classification of epileptic seizure types from normal EEG signals has not yet been benefited with wavelet transforms. Hence, in this paper, the two major types of wavelet transform, namely discrete wavelet transform (DWT) and wavelet packet decomposition (WPD) are employed for the automatic diagnosis of the epileptic seizure and its types. The publicly available KITS EEG database consisting of three groups namely, normal, focal epilepsy and generalized epilepsy are utilized in this work. Four experimental cases namely (i) normal-generalized epilepsy, (ii) normal-focal epilepsy, (iii) normal-focal-generalized and (iv) normal-epilepsy are used to investigate the proposed approach. Further, this paper attempts to identify the best wavelet function from the commonly used seven wavelet families and the level of decomposition required to analyse the EEG signals. The nine statistical features are extracted from the wavelet coefficients and fed into the support vector machine (SVM) classifier. From the experimental result it was found out that the DWT with rbio1.1 attained the highest classification accuracy for all the experimental cases.

Automated summary

Wavelet transforms have been widely used in characterizing EEG signals for automatic diagnosis of epileptic seizure. In this study, DWT was found to achieve the highest classification accuracy for all experimental cases, demonstrating its effectiveness in this area.