Automated Seizure Detection using Theta Band
Nasmin Jiwani, Ketan Gupta, Neda Afreen
Abstract
The EEG signal is made up of numerous frequency bands that characterize human behaviours like emotion, attentiveness, and sleep status, among others. In order to detect epileptical seizures, categorization based on discrete EEG segments is required. The performance of the theta band in an EEG signal is analyzed with the Short-Time Fourier Transform (STFT). It also analyses different categorization methodologies, demonstrating that some classification algorithms achieve extremely high accuracy. The analysis was done in stages, with STFT, theta frequency band extraction, statistical feature extraction, and then classification using LightGBM and Catboost classifier at the end. STFT is used in this study to extract statistical properties from 2-dimensional data and classify epilepsy in the low frequency range. The proposed LightGBM and CatBoost classifier got 98.33% accuracy.