File(s) under permanent embargo
EEG-based person verification using multi-sphere SVDD and UBM
conference contribution
posted on 2013-01-01, 00:00 authored by Phuoc NguyenPhuoc Nguyen, D Tran, T Le, X Huang, W MaThe use of brain-wave patterns extracted from electroencephalography (EEG) brain signals for person verification has been investigated recently. The challenge is that the EEG signals are noisy due to low conductivity of the human skull and the EEG data have unknown distribution. We propose a multi-sphere support vector data description (MSSVDD) method to reduce noise and to provide a mixture of hyperspheres that can describe the EEG data distribution. We also propose a MSSVDD universal background model (UBM) to model impostors in person verification. Experimental results show that our proposed methods achieved lower verification error rates than other verification methods.
History
Event
Knowledge Discovery and Data Mining. Conference (17th : 2013 : Gold Coast, Qld.)Volume
7818Series
Knowledge Discovery and Data Mining ConferencePagination
289 - 300Publisher
SpringerLocation
Gold Coast, Qld.Place of publication
Berlin, GermanyPublisher DOI
Start date
2013-04-14End date
2013-04-17ISSN
0302-9743eISSN
1611-3349ISBN-13
9783642374524Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2013, Springer-Verlag Berlin HeidelbergEditor/Contributor(s)
J Pei, V Tseng, L Cao, H Motoda, G XuTitle of proceedings
PAKDD 2013 : Proceedings of the 17th Pacific-Asia Conference on Knowledge Discovery and Data MiningUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC