Brain signatures: A modality for biometric authentication

Author

Hema, C.R. ; Paulraj, M.P. ; Kaur, Harkirenjit

Author_Institution

Sch. of Mechatron. Eng., Univ. Malaysia Perlis, Arau

fYear

2008

fDate

1-3 Dec. 2008

Firstpage

1

Lastpage

4

Abstract

In this paper we investigate the use of brain signatures as a possible biometric authentication technique. Research on brain EEG signals has shown that individuals exhibit unique brain patterns for similar tasks. In this paper we use brain EEG signals recorded during the performance of three mental tasks to identify six individuals. PSD features using Welch algorithm is extracted from the EEG Beta waves. A feed forward neural classifier is used to identify the six individuals. The performance of the neural network is appreciable with an average accuracy of 94.4 to 97.5%. Results validate the usage of brain signatures as a possible modality for biometric verification.

Keywords

biometrics (access control); digital signatures; electroencephalography; medical signal processing; neural nets; EEG Beta waves; Welch algorithm; biometric authentication technique; brain EEG signals; brain signatures; feed forward neural classifier; neural network; Authentication; Bioinformatics; Biological neural networks; Biometrics; Electrodes; Electroencephalography; Feeds; Fingerprint recognition; Neurons; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronic Design, 2008. ICED 2008. International Conference on

Conference_Location

Penang

Print_ISBN

978-1-4244-2315-6

Electronic_ISBN

978-1-4244-2315-6

Type

conf

DOI

10.1109/ICED.2008.4786753

Filename

4786753