Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Enhancing EEG Signals Classification using LSTM-CNN Architecture
  • +1
  • Swaleh Omari,
  • Michael Kimwele,
  • Akeem Olowolayemo,
  • Dennis Kaburu
Swaleh Omari
Jomo Kenyatta University of Agriculture and Technology

Corresponding Author:[email protected]

Author Profile
Michael Kimwele
Jomo Kenyatta University of Agriculture and Technology
Author Profile
Akeem Olowolayemo
International Islamic University Malaysia
Author Profile
Dennis Kaburu
Jomo Kenyatta University of Agriculture and Technology College of Engineering and Technology
Author Profile

Abstract

Epilepsy is a condition that disrupts normal brain function and sometimes leads to seizures, unusual sensations, and temporary loss of awareness. Electroencephalograph (EEG) records are commonly used for diagnosing epilepsy, but traditional analysis is subjective and prone to misclassification. Previous studies applied Deep Learning (DL) techniques to improve EEG classification, but their performance has been limited due to dynamic and non-stationary nature of EEG structure. In this paper, we propose a multi-channel EEG classification model called LConvNet, which combines Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) for capturing temporal dependencies. The model is trained using open source secondary EEG data from Temple University Hospital (TUH) to distinguish between epileptic and healthy EEG signals. Our model achieved an impressive accuracy of 97%, surpassing existing EEG classification models used in similar tasks such as EEGNet, DeepConvNet and ShallowConvNet that had 86%, 96% and 78% respectively. Furthermore, our model demonstrated impressive performance in terms of trainability, scalability and parameter efficiency during additional evaluations.
02 Jun 2023Submitted to Engineering Reports
21 Jun 2023Submission Checks Completed
21 Jun 2023Assigned to Editor
25 Jun 2023Review(s) Completed, Editorial Evaluation Pending
07 Jul 2023Reviewer(s) Assigned
25 Jul 2023Editorial Decision: Revise Minor
17 Aug 20231st Revision Received
18 Aug 2023Submission Checks Completed
18 Aug 2023Assigned to Editor
18 Aug 2023Review(s) Completed, Editorial Evaluation Pending
31 Aug 2023Reviewer(s) Assigned
16 Oct 2023Editorial Decision: Revise Minor
04 Nov 20232nd Revision Received
06 Nov 2023Submission Checks Completed
06 Nov 2023Assigned to Editor
06 Nov 2023Review(s) Completed, Editorial Evaluation Pending
08 Nov 2023Reviewer(s) Assigned
09 Nov 2023Editorial Decision: Revise Minor
16 Nov 20233rd Revision Received
20 Nov 2023Submission Checks Completed
20 Nov 2023Assigned to Editor
20 Nov 2023Review(s) Completed, Editorial Evaluation Pending
21 Nov 2023Editorial Decision: Accept