Paper Contents
Abstract
Epilepsy is the second most common brain disease after migraines. Automatic detection can significantly enhance the quality of life for patients with epileptic seizures. Current seizure detection approaches based on EEG suffer from many difficulties in practice. EEGs are non-stationary signals and seizures display different patterns in different individuals and recording sessions. Furthermore, the EEG data contains additional kinds of noise that might impact the accuracy of detecting epileptic seizures. As solutions to these problems, I present a deep learning based method that automatically picks up the discriminative EEG characteristics of epileptic seizures. In particular, time-series EEG data are first partitioned into a stream of non-overlapped epochs in order to demonstrate the correlation between successive data samples, and second, high-level representations of normal and epileptic EEG patterns are learned using an LSTM Network
Copyright
Copyright © 2025 Mrs. S. Kaviya. This is an open access article distributed under the Creative Commons Attribution License.
