Application of Deep Learning and WT-SST in Localization of Epileptogenic Zone Using Epileptic EEG Signals

Focal and non-focal Electroencephalogram (EEG) signals have proved to be effective techniques for identifying areas in the brain that are affected by epileptic seizures, known as epileptogenic zones. The detection of location focal EEG time seizure occurrence vital information help doctors treat seizures using a surgical method. This paper proposed computer-aided (CAD) system detecting classifying manual process is time-consuming, prone error, tedious. technique employs time-frequency features, statistical, nonlinear approaches form robust features extraction technique. Four classification were proposed. (1). Combined hybrid with Support Vector Machine (Hybrid-SVM) (2). Discrete Wavelet Transform Deep Learning Network (DWT-DNN) (3). DNN (Hybrid-DNN) an optimized model. Lastly, (4). A newly Synchrosqueezing Transform-Deep Convolutional Neural (WTSST-DCNN). Prior feeding classifiers, statistical analyses, including t-tests, deployed obtain relevant significant at each approach. feature suitable smart Internet Medical Things (IoMT) devices performance parameters accuracy, sensitivity, specificity higher than recently related works value 99.7%, 99.5%, 99.7% respectively.