Automated Detection of Epileptic Seizure using FBSE-EWT method from EEG signals

Analyzing the brain signals generated by brain neurons can help identify the severe chronic neurological condition known as epilepsy. To interact with human organs and produce signals, neurons are intricately connected to one another. Electroencephalogram (EEG) media are generally used for the recording of these brain impulses. These signals are highly data-intensive, complicated, noisy, non-linear, and non-stationary. Therefore, it is difficult to detect seizures and learn about the brain. However, they may fail to classify correctly due to complex data. In this study, the `Fourier Bessel' series expansion-based empirical wavelet transform (FBSE-EWT) is used to first decompose the EEG data into sub-bands. The five best-performing ensemble learning classifiers such as Na\"ive Bayes, SVM, RF, XG Boost, and CNN are given here as a result of experiments using the obtained ranked features on various classifiers.