Short description:

This book presents an innovative method of EEG-based feature extraction and classification of seizures using EEG signals. It describes the methodology required for EEG analysis, seizure detection, seizure prediction and seizure classification.

Long description:

This book presents an innovative method of EEG-based feature extraction and classification of seizures using EEG signals. It describes the methodology required for EEG analysis, seizure detection, seizure prediction, and seizure classification. It contains a compilation of techniques described in the literature and emphasizes newly proposed techniques. The book includes a brief discussion of existing methods for epileptic seizure diagnosis and prediction and introduces new efficient methods specifically for seizure prediction.

• Focuses on the mathematical models and machine learning algorithms from a perspective of clinical deployment of EEG-based epileptic seizure prediction


• Discusses recent trends in seizure detection, prediction, and classification methodologies


• Provides engineering solutions to severity or risk analysis of detected seizures at remote places


• Presents wearable solutions to seizure prediction


• Includes details of the use of deep learning for epileptic seizure prediction using EEG

This book acts as a reference for academicians and professionals who are working in the field of computational biomedical engineering and are interested in the domain of EEG-based disease prediction.

Table of Contents:

1: Introduction 2: Electroencephalography 3: Epilepsy Detection 4: Existing Methods for Epileptic Seizure Prediction using Electroencphalegram Signals 5: Epileptic Seizure Prediction with EEG Signal Using Deep Recurrent Neural Network 6: Epileptic Seizure Prediction using Squirrle Atom Search Optimization Algorithm based Deep RNN 7: Contribution of Research and Conclusion