Transacting Multiple Mother Wavelets in Continuous Wavelet Transform for Epilepsy EEG Classification via CNN

Epileptic electroencephalogram (EEG) is one of the most adopted schemes to localize epileptiform discharge via brain signal recordings during seizure, and neurologists typically derive conjectures via ocular assessment. However, such a scheme is time-consuming with immense dependency on scrutinizer's expertise, and thus, automated models are deemed to be the most feasible solutions to this predicament. This paper studies, for the first time, on the impact of transacting multiple mother wavelets (TMMW) on a benchmark signal decomposition algorithm known as Continuous Wavelet Transform (CWT). 1D signals are transformed into 2D scalograms discretely for three mother wavelets, namely `amor', 'bump', and 'mores' first, and then, the such images are categorized with a pre-trained alexnet for classifications. The configured approach finally capitalizes on the repercussions of directing variables, which are adam, rmsprop, sgdm, and four learning rates, i.e., 10(-3), 10(-4), 10(-5), and 10(-6). Simulations are trialed on the renowned Bern-Barcelona dataset for verification. Results imply that deep learning classifier yields better results on morse based images, while the highest segregation is achieved when alexnet is operated on adam at 10(-5), where classification mark up secures 90.4% with parametric values of 87.6%, 843%, and 85.5% for sensitivity, specificity, and specificity f1-score, respectively. This study offers an expanded understanding of the feasibility of mother wavelets on the skeleton of CWT for the classification of epileptic seizures via Convolutional Neural Network (CNN) classifier.