Person Identification from the EEG using Nonlinear Signal Classification

M. Poulos; M. Rangoussi; N. Alexandris; A. Evangelou

doi:10.1055/s-0038-1634316

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2002; 41(01): 64-75
DOI: 10.1055/s-0038-1634316

Original Article

Schattauer GmbH

Person Identification from the EEG using Nonlinear Signal Classification

M. Poulos

¹Department of Informatics, University of Piraeus, Greece

,

M. Rangoussi

³Department of Electronics, TEI Piraeus, Greece

,

N. Alexandris

¹Department of Informatics, University of Piraeus, Greece

,

A. Evangelou

²Department of Exp. Physiology, School of Medicine, University of Ioannina, Greece

› Author Affiliations

Abstract

Summary

Objectives: This paper focusses on the person identification problem based on features extracted from the ElectroEncephaloGram (EEG). A bilinear rather than a purely linear model is fitted on the EEG signal, prompted by the existence of non-linear components in the EEG signal – a conjecture already investigated in previous research works. The novelty of the present work lies in the comparison between the linear and the bilinear results, obtained from real field EEG data, aiming towards identification of healthy subjects rather than classification of pathological cases for diagnosis.

Methods: The EEG signal of a, in principle, healthy individual is processed via (non)linear (AR, bilinear) methods and classified by an artificial neural network classifier.

Results: Experiments performed on real field data show that utilization of the bilinear model parameters as features improves correct classification scores at the cost of increased complexity and computations. Results are seen to be statistically significant at the 99.5% level of significance, via the χ² test for contingency.

Conclusions: The results obtained in the present study further corroborate existing research, which shows evidence that the EEG carries individual-specific information, and that it can be successfully exploited for purposes of person identification and authentication.

Keywords

Electroencephalography - pattern recognition - linear models - nonlinear dynamics - neural networks (computer)

Full Text

References

References
1 Davis H, Davis PA. Action potentials of the brain in normal persons and in normal states of cerebral activity. Archives of Neurological Psychiatry 1936; 36: 1214-24.
2 Berger H. Das Elektrenkephalogramm des Menschen. Nova Acta Leopoldina; Bd. 6. Nr. 1938: 38.
3 Anoklin A, Steinlein O, Fisher C, Mao Y. et al. A genetic study of the human low-voltage electroencephalogram. Hum Genet 1992; 90: 99-112.
4 Eischen S, Luckritz J, Polish J. Spectral analysis of EEG from Families. Biol Psycholology 1995; 41: 61-8.
5 Sviderskaya NE, Korol’kova TA. Genetic Features of the spatial organization of the human cerabral cortex. Neurosci Behav Physiol 1995; 25 (Suppl. 05) 370-6.
6 Juel-Nielsen N, Harvand B. The electroencephalogram in uniovular twins brought up apart. Acta Genet (Basel) 1958; 8: 57-64.
7 Lykken DT. Research with twins: the concepts of emergenesis. Psychophysiology 1982; 19: 361-73.
8 Vogel F, Schalt E, Krunger J, Klarich G. Relationship between behavior maturation measured by the “Baum” test and EEG frequency. A pilot study on monozygotic and dizygotic twins. Hum Genet 1982; 62: 60-5.
9 Stassen HH, Bomben G, Propping P. Genetic aspects of the EEG – an investigation into the within-pair similarity of monozygotic and dizygotic twins with a new method of analysis. Electroencephalogr Clin Neurophysiol 1987; 66: 489-501.
10 Poulos M, Rangousi M, Kafetzopoulos E. Person identification via the EEG using computational geometry algorithms. In: Proceedings of the Ninth European Signal Processing (EUSIPCO‘98). Rhodes, Greece: Theodoridis S, Pitas A, Stouraitis N, Kalouptsidis N. (eds). 1998. 4: 2125-8.
11 Poulos M, Rangoussi M, Alexandris N. Neural network based person identification using EEG features. In: Proceedings of the International Conference On Acoustics, Speech, and Signal Processing (ICCASP99). Arizona USA 1999; 2: 2089.
12 Poulos M, Rangoussi M, Chrissicopoulos V, Evangelou A. Person identification based on parametric processing on the EEG. In: Proceedings of the Sixth International Conference on Electronics, Circuits and Systems (ICECS99). Institute of Electrical and Electronics Engineers, Pafos, Cyprus 1999; 1: 283-6.
13 Poulos M, Rangoussi M, Chrissicopoulos V, Evangelou A. Parametric person identification from the EEG using computational geometry. In: Proceedings of the Sixth International Conference on Electronics Circuits and Systems (ICECS99). Institute of Electrical and Electronics Engineers, Pafos, Cyprus 1999; 2: 1005-12.
14 Vogel F. The Genetic basis of the normal (EEG). Hum Genet 1970; 10: 91-114.
15 Buchbaum MS, Gershon ES. Genetic factors in EEG, sleep and evoked potentials. In: Human consciousness and its transformations. Ed. Davidson Phenomen Press; 1978
16 Lennox W, Gibbs E, Gibbs F. The brain-pattern, an hereditary trait. J Hered 1990; 36: 233-43.
17 Plomin R. The role of inheritance in behavior. Science 1990; 248: 183-8.
18 Gibbs FA, Gibbs EL, Lennox WG. Electroencephalographic classification of epileptic patient and control subjects. Arch Neural Psychiatric 1943; 50: 111-28.
19 Hazarika N, Tsoi A, Sergejew A. Nonlinear Considerations in EEG signal Classification. IEEE Transactions on signal Processing 1997; 45: 829-36.
20 Brocket RW. Volterra series and geometric control theory. Automatica 1976; 12: 167-76.
21 Granger CW, Andersen AP. Introduction to bilinear Time series Models. Cottingen; Vandenhoeck-Ruprecht: 1978. a.
22 Anderson CW. Effects of variations in neural network topology and output averaging on the discrimination of mental tasks spontaneous electroencephalogram. Journal of Intelligent Systems 1997; 7: 165-90.
23 Poulos M, Rangoussi M, Alexandris N, Evangelou A. On the use of EEG features towards person identification via neural networks. Medical Informatics & the Internet in Medicine 2001 To be published.
24 Kalcher J, Flotzinger D, Neuper C, Pfurtscheller G. Graz brain-computer interface II. Med Biol Eng Comput 34: 382-8.
25 Pfurtscheller G, Flotzinger D, Kalcher J. Brain-Computer Interface: a new communication device for handicapped persons. Journal of Microcomputer Applications 1993; 16: 293-9.
26 Subba Rao T. On the estimation of bilinear time series models. Bull Inst Int Stat 1977; 41.
27 Gill PE, Murray W, Wright MH. Practical optimization. San Diego: Academic; 1981
28 Kohonen T. Self-Organizing Maps. Berlin, Heidelberg: Springer-Verlag; 1995
29 Sammon JW. A nonlinear mapping for data structure analysis. IEEE Trans Comput 1969; 5: 401-9.
30 Zar JH. Biostatistical Analysis. New Jersey, USA: Prentice-Hall; 1999