Artificial Neural Network Model Using Short-Term Fourier Transform for Epilepsy Seizure Detection

Epilepsy is a neurological illness that can strike anyone at any time in their life. However, a person with epilepsy will experience frequent to uncommon seizures, resulting in death. Electroencephalogram (EEG) signals were used to aid in diagnosing this condition. This paper proposes an Artificial Neural Network (ANN) model to detect epileptic seizures using the five EEG frequency bands (i.e., Delta, Theta, Alpha, Beta, and Gamma) with the help of Short-Term Fourier transform (STFT) and statistical feature extraction. To assess the performance of the model, different performance metrics have been calculated. The model achieved accuracy up to 100% in several cases.