A Novel Hybrid Attentive Convolutional Autoencoder (HACA) Framework for Enhanced Epileptic Seizure Detection

Epilepsy, a prevalent neurological disorder, requires accurate and efficient seizure detection for timely intervention. This study presents a Hybrid Attentive Convolutional Autoen-coder (HACA) framework designed to address challenges in EEG signal processing for seizure detection. The proposed metho...

Full description

Saved in:
Bibliographic Details
Published in:International journal of advanced computer science & applications Vol. 16; no. 2
Main Authors: Vaddi, Venkata Narayana, Sikha, Madhu Babu, Kodali, Prakash
Format: Journal Article
Language:English
Published: West Yorkshire Science and Information (SAI) Organization Limited 2025
Subjects:
Accuracy
Classification
Computer science
Convulsions & seizures
Datasets
Deep learning
Electroencephalography
Entropy
Epilepsy
Feature extraction
Neural networks
Neurological diseases
Neurological disorders
Real time
Seizures
Signal processing
Signal reconstruction
Wavelet transforms
ISSN:2158-107X, 2156-5570
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Epilepsy, a prevalent neurological disorder, requires accurate and efficient seizure detection for timely intervention. This study presents a Hybrid Attentive Convolutional Autoen-coder (HACA) framework designed to address challenges in EEG signal processing for seizure detection. The proposed method integrates signal reconstruction, innovative feature extraction, and attention mechanisms to focus on seizure-critical patterns. Compared to conventional CNN- and RNN-based approaches, HACA demonstrates superior performance by enhancing feature representation and reducing redundant computations. The proposed HACA framework achieved 99.4% accuracy, 99.6%sensitivity, and 99.2% specificity on the CHB-MIT dataset. Moreover, the training time is reduced by 40%, which makes the model more relevant for real-time applications and portable seizure monitoring systems.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2158-107X
2156-5570
DOI:10.14569/IJACSA.2025.01602127