Leave-one-out authentication of persons using 40 Hz EEG oscillations

It has been shown previously that recognizing persons using 40 Hz electroencephalogram (EEG) oscillations is possible. In the method, features were computed from the Visual Evoked Potential (VEP) signals recorded from 61 electrodes while subjects perceived a picture. Here, two modifications have bee...

Full description

Bibliographic Details
Main Authors: Ravi, , KVR, Palaniappan, , R
Format: Article
Published: 2005
Subjects:
Online Access:http://shdl.mmu.edu.my/2328/
_version_ 1848790026989600768
author Ravi, , KVR
Palaniappan, , R
author_facet Ravi, , KVR
Palaniappan, , R
author_sort Ravi, , KVR
building MMU Institutional Repository
collection Online Access
description It has been shown previously that recognizing persons using 40 Hz electroencephalogram (EEG) oscillations is possible. In the method, features were computed from the Visual Evoked Potential (VEP) signals recorded from 61 electrodes while subjects perceived a picture. Here, two modifications have been proposed to improve the classification performance: Principal Component Analysis (PCA) to reduce the noise and background EEG effects from the VEP signals and normalization. Two classifiers were used: Simplified Fuzzy ARTMAP (SFA), and k-Nearest Neighbor (kNN). The experimental results using 800 VEP signals from 20 subjects with leave-one-out cross validation strategy showed that PCA and normalization improved the classification performance for both the classifiers. The best classification performance of 95.25% obtained using the improved method shows that 40 Hz EEG oscillations are suitable for use as biometrics.
first_indexed 2025-11-14T18:06:05Z
format Article
id mmu-2328
institution Multimedia University
institution_category Local University
last_indexed 2025-11-14T18:06:05Z
publishDate 2005
recordtype eprints
repository_type Digital Repository
spelling mmu-23282011-08-24T01:56:20Z http://shdl.mmu.edu.my/2328/ Leave-one-out authentication of persons using 40 Hz EEG oscillations Ravi, , KVR Palaniappan, , R QA75.5-76.95 Electronic computers. Computer science It has been shown previously that recognizing persons using 40 Hz electroencephalogram (EEG) oscillations is possible. In the method, features were computed from the Visual Evoked Potential (VEP) signals recorded from 61 electrodes while subjects perceived a picture. Here, two modifications have been proposed to improve the classification performance: Principal Component Analysis (PCA) to reduce the noise and background EEG effects from the VEP signals and normalization. Two classifiers were used: Simplified Fuzzy ARTMAP (SFA), and k-Nearest Neighbor (kNN). The experimental results using 800 VEP signals from 20 subjects with leave-one-out cross validation strategy showed that PCA and normalization improved the classification performance for both the classifiers. The best classification performance of 95.25% obtained using the improved method shows that 40 Hz EEG oscillations are suitable for use as biometrics. 2005 Article NonPeerReviewed Ravi, , KVR and Palaniappan, , R (2005) Leave-one-out authentication of persons using 40 Hz EEG oscillations. Eurocon 2005: The International Conference on Computer as a Tool, Vol 1 and 2 , Proceedings. pp. 1386-1389.
spellingShingle QA75.5-76.95 Electronic computers. Computer science
Ravi, , KVR
Palaniappan, , R
Leave-one-out authentication of persons using 40 Hz EEG oscillations
title Leave-one-out authentication of persons using 40 Hz EEG oscillations
title_full Leave-one-out authentication of persons using 40 Hz EEG oscillations
title_fullStr Leave-one-out authentication of persons using 40 Hz EEG oscillations
title_full_unstemmed Leave-one-out authentication of persons using 40 Hz EEG oscillations
title_short Leave-one-out authentication of persons using 40 Hz EEG oscillations
title_sort leave-one-out authentication of persons using 40 hz eeg oscillations
topic QA75.5-76.95 Electronic computers. Computer science
url http://shdl.mmu.edu.my/2328/