An Effective Framework for Detecting Epileptic Seizures using CNN and Encrypted EEG Signals

Electroencephalogram (EEG) signals may be used to autonomously diagnose epilepsy, eliminating the requirement for a medical professional’s involvement in the process. A good classification performance is really necessary if you do not want to pass up any possible discoveries. In this piece of research, the authors offer a technique for the automated identification of epilepsy using EEG waves. In order to extract features, the raw EEG signals were first put through a discrete Fourier transform, also known as a DFT, as well as a discrete wavelet transform (DWT). Therefore, researchers have been exploring different methods to improve the accuracy of EEG signal analysis. One such method proposed in this study is the Wavelet Transform based Fourier-Bessel series expansion (WT - FBSE) method. This method utilizes the WT - FBSE spectrum to segment multiple frame-size time-segmented EEG signals using the scale-space boundary detection method. The WT - FBSE technique decomposes the EEG signals into narrow sub-band signals, which are then used to extract various features such as log-energy-entropy (LEnt), line-length (LL), and norm-entropy (NEnt) from different frequency ranges. In order to choose the features that are most important, the relief-F feature ranking approach is applied. This helps to limit the amount of computing work that is required by the models. The study evaluates two time-segmentation approaches and four different frame sizes to analyse the EEG signals and achieves better performance when compared to the existing systems.