Method of identifying individuals using VEP signals and neural network

Author

Palaniappan, R.

Author_Institution

Fac. of Inf. Sci. & Technol., Multimedia Univ., Melaka, Malaysia

Volume

151

Issue

1

fYear

2004

Firstpage

16

Lastpage

20

Abstract

A method of identifying individuals using visual-evoked-potential (VEP) signals and a neural network (NN) is proposed. In the approach, a backpropagation (BP) NN is trained to identify individuals using the gamma-band (30-50 Hz) spectral power ratio of VEP signals extracted from 61 electrodes located on the scalp of the brain. The gamma-band spectral-power ratio is computed using a zero-phase Butterworth digital filter and Parseval´s time-frequency equivalence theorem. NN classification gives an average of 99.06% across 400 test VEP patterns from 20 individuals using a 10-fold cross-validation scheme. This shows promise for the approach to be developed further as a biometric identification system.

Keywords

Butterworth filters; backpropagation; biomedical electrodes; biometrics (access control); equivalence classes; feature extraction; neural nets; signal classification; visual evoked potentials; 30 to 50 Hz; BP NN; Parseval time-frequency equivalence theorem; VEP patterns; VEP signals; backpropagation neural network; biometric identification system; cross-validation; feature extraction; gamma-band spectral power ratio; individual-identification; scalp located electrodes; signal classification; visual-evoked-potential signals; zero-phase Butterworth digital filter;

fLanguage

English

Journal_Title

Science, Measurement and Technology, IEE Proceedings -

Publisher

iet

ISSN

1350-2344

Type

jour

DOI

10.1049/ip-smt:20040003

Filename

1262435