Details
Poster
Presenter(s)
![Keyvan Farhang Razi Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/62121.jpg?h=5b35160a&itok=YQzWrTa0)
Display Name
Keyvan Farhang Razi
- Affiliation
-
AffiliationSwiss Federal institute of Technology Lausanne
- Country
Abstract
A channel selection method correlated to a feature extractor using iEEG signal is proposed to improve the computation efficiency and seizure detection accuracy by reducing the dimension of extracted features and electrode channels. Time-domain features are extracted and ranked to constitute a customized feature subset. Electrode channels are ranked with respect to top four rank features obtained from the feature ranking unit. Then, the number of channels is optimized to reach the highest detection accuracy. The suggested method is tested on seven patients from the Bern University Hospital dataset which reveals high seizure detection performance with remarkably low computation dimension.