Transfer learning and gated recurrent unit based epileptic seizure detection method

Shuxin Yao; Yanli Zhang

doi:10.1117/12.2627122

14 February 2022 Transfer learning and gated recurrent unit based epileptic seizure detection method

Shuxin Yao, Yanli Zhang

Proceedings Volume 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021); 1216108 (2022) https://doi.org/10.1117/12.2627122
Event: 4th International Conference on Informatics Engineering and Information Science, 2021, Tianjin, China

Abstract

Automatic seizure detection system can greatly reduce the burden of manual diagnosis on epilepsy. In this paper, an epileptic seizure detection method is proposed based on transfer learning of VGGNet-16 and gated recurrent unit network. Evaluated on CHB-MIT EEG dataset, the proposed detection method achieved an average sensitivity of 90.12%, an average specificity of 96.32% and an average accuracy rate of 96.31%. A comparative experiment based on the transfer learning of Resnet50 further demonstrates the good performance of VGGNet-16 in seizure detection

Citation Download Citation

Shuxin Yao and Yanli Zhang "Transfer learning and gated recurrent unit based epileptic seizure detection method", Proc. SPIE 12161, 4th International Conference on Informatics Engineering & Information Science (ICIEIS2021), 1216108 (14 February 2022); https://doi.org/10.1117/12.2627122

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available