EFFICIENT CLASSIFICATION USING MULTIPLE MENTAL THOUGHTS
Abstract
Researches in personal identification show that classification using multiple mental thoughts increases complexity and system’s processing time. In this paper, an efficient classification algorithm is proposed to classify an individual using multiple mental thoughts. Features from Electroencephalography (EEG), used as biometric, are extracted using sixth order Autoregressive (AR) model, and Linear Discriminant Analysis (LDA) based classification is performed based on best mental thought combinations. Matlab® simulation results indicate that the proposed algorithm reduces the complexity as well as the processing time that confirms the use of EEG as a biometric for personal identification.References
S. Pankanti, S. Prabhakar and A. K. Jain,
IEEE Trans. PAMI 24, No. 8 (2002) 1010.
J. Wayman, A. Jain, D. Maltoni and D. Maio
(Eds.), Biometric Systems: Technology,
Design and Performance Evaluation,
Springer-Verlag (2004).
A. Samal and P. Iyengar, Automatic
Recognition and Analysis of Human Faces
and Facial Expressions: A Survey, Pattern
Recognition 25, No. 1 (1992) 65.
N. Duta, A. K. Jain and K. V. Mardia, Pattern
Recognition Letters 23, No 4 (2012) 477.
J. Daugman, Recognizing Persons by Their
Iris Patterns, A.K. Jain, R. Bolle, S. Pankanti
(Eds.) : Biometrics: Personal Identification in
Networked Society. Kluwer Academic (1999).
R. Sanchez-Reillo, C. Sanchez-Avila and
Gonzalez-Macros, IEEE Trans. Pattern
Analysis and Machine Intelligence 22, No 10,
(Oct. 2000) 1168.
L. Biel, O. Pettersson, L. Philipson and
P. Wide, IEEE Trans. Instrumentation and
Measurement 50, No 3 (2001) 808.
Hurley, M. D. Nixon and J. Carter, Computer
Vision and Image Understanding 98, No. 3
(2005) 491.
R. Palaniappan and D.P. Mandic, Energy of
Brain Potential Evoked During Visual
Stimulus: A new Biometric, ICANN, LNCS
, Berlin Heidelberg (2005) pp. 735-740
R.B. Paranjape, J. Mahovsky, L. Benedicenti
and Z. Koles, The Electroencephalography
as Biometric, Proc. 2nd Canadian
Conference on Electrical and Computer
Engineering, Toronto, Ontario, Canada
(2001) pp. 1363-1366.
M. Poulos, M. Rangoussi, V. Chrissikopoulos
and A. Evangelou, Parametric Person
Identification from the EEG using
Computational Geometry 2 (1999) pp. 1005–
Nae-Jen Huan and R. Palaniappan, Journal
of Neural Engineering 1 (2004) 142.
Z. A. Keirn and J. I. Aunon, IEEE Trans.
Biomedical Engineering, 37, No. 12 (1990)
pp. 1209-1214.
R. Palaniappan, International Journal of
Information and Communication Engineering
(2006) 222.
R. Palaniappan, Electroencephalogram
Signals from Imagined Activities: A Novel
Biometric Identifier for a Small Population,
IDEAL 2006, LNCS 4224 (2006) pages 604-
R. Shiavi, “Introduction to Applied Statistical
Signal Analysis (2nd edition)â€, Academic
Press, 1999.
R. Palaniappan, P. Paramesran, S. Nishida
and N. Saiwaki, IEEE Trans. Neural System
and Rehabilitation Engineering 10 (2002)
K. Fukunaga, Introduction to Statistical
Pattern Recognition, 2nd Edition. Academic
Press (1990)