A Review automated system for diagnosis and detection of epilepsy brain disorder using deep hybrid based leaning approaches

DOI

10.2991/978-94-6463-738-0_19How to use a DOI?

Keywords

Epilepsy; Deep Learning; Electroencephalogram; Convolutional Neural Network; Recurrent Neural Network; Non-Invasive Monitoring; Seizure Detection; Diagnostic Accuracy

Abstract

Frequently occurring seizures are a hallmark of epilepsy, a persistent brain illness. Standard diagnostic modalities, such as electroencephalograms (EEG), magnetic resonance imaging (MRI), and clinical examinations, have limitations in terms of efficacy, spatial resolution, invasiveness, cost, and interpretative reliability. These problems can result in incorrect diagnoses and delayed treatment, which ultimately affect patient outcomes and quality of life. New approaches to improving the precision, effectiveness, and non-invasiveness of epilepsy diagnosis and treatment have been made possible by recent developments in deep learning. In order to maximize the diagnostic performance of epilepsy, we develop a combination deep learning model in this research using EEG data that integrates Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Using CNNs to record spatial information and RNNs to examine temporal correlations using the EEG data, the model offers a comprehensive method for spotting seizure-related patterns. Using advanced mathematical approaches, this paper describes a procedure that involved substantial data pre-processing, including noise removal, normalization, and augmentation, and ended with feature extraction. The model is trained and validated on a large, varied collection of EEG recordings and produces high accuracy, precision, recall, and F1-scores. The findings show that the model may identify low levels of epileptic activity that are missed by conventional methods, lowering the risk of misdiagnosis and allowing for early action guarantee.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kamal Kumar
AU  - Gagandeep
PY  - 2025
DA  - 2025/06/22
TI  - A Review automated system for diagnosis and detection of epilepsy brain disorder using deep hybrid based leaning approaches
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 229
EP  - 244
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_19
DO  - 10.2991/978-94-6463-738-0_19
ID  - Kumar2025
ER  -