Imperial College London

DrBennyLo

Faculty of MedicineDepartment of Surgery & Cancer

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 0806benny.lo Website

 
 
//

Location

 

B414BBessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Lo,
author = {Lo, BPL and Guo, Y and Zhang, Y and Mursalin, M and Xu, W},
publisher = {IEEE},
title = {Automated epileptic seizure detection by analyzing wearable EEG signals using extended correlation-based feature selection},
url = {http://hdl.handle.net/10044/1/56946},
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Electroencephalogram (EEG)that measures the electrical activity of the brainhasbeen widely employedfordiagnosingepilepsywhich is onekind of brainabnormalities. With theadvancement of low-costwearablebrain-computer interfacedevices,it is possible to monitor EEG forepileptic seizure detectionin daily use. However,it is still challenging to develop seizure classificationalgorithms with a considerable higheraccuracy and lower complexity. In this study, we proposea lightweight method which can reduce the number of features for a multiclass classificationto identify three different seizure statuses(i.e., Healthy, Interictal and Epileptic seizure)throughEEGsignalswith a wearable EEG sensorsusingExtended Correlation-Based Feature Selection(ECFS).More specifically, there are three steps in our proposed approach. Firstly, the EEG signals were segmented into fivefrequency bandsand secondly, we extractthe features while the unnecessary feature space was eliminated by developing the ECFS method.Finally, the features were fed intofive different classification algorithms, including Random Forest, Support Vector Machine, Logistic Model Trees, RBF Networkand Multilayer Perception. Experimental results have shownthatLogistic Model Treesprovides the highest accuracy of97.6% comparing toother classifiers.
AU - Lo,BPL
AU - Guo,Y
AU - Zhang,Y
AU - Mursalin,M
AU - Xu,W
PB - IEEE
TI - Automated epileptic seizure detection by analyzing wearable EEG signals using extended correlation-based feature selection
UR - http://hdl.handle.net/10044/1/56946
ER -