Method of Individual Identification based on Electroencephalogram Analysis
Xuecai Bao
Institute of Information
and Technology, JiangXi
Blue Sky University
Nanchang, China, 330098
lx9782101@163.com
Jinli Wang
Institute of Information
and Technology, JiangXi
Blue Sky University
Nanchang, China, 330098
Jinli986@yahoo.com.cn
Jianfeng Hu
Institute of Information
and Technology, JiangXi
Blue Sky University
Nanchang, China, 330098
huguess@21cn.com
Abstract
Biometric based on Electroencephalogram have
proved to be unique enough between subjects for
applications. A new method on identifying the
individuality of persons by using parametric was used
for identification of motor imagery. In this paper,
autoregressive mode, phase synchronization, Energy
Spectral Density and linear complexity value were
used as EEG features. Neural network was employed
for identification of individual differences. Then,
identification rate was analyzed by different data
length and wave band. The result shows that high
identification ratio was tongue movement and that
perfect accuracy depends on the Paradigm of motor
imagery and wave band.
Keywords: Biometrics , EEG
(electroencephalogram),individual identification,
motor imagery
1. Introduction
Person identification based on biometric measure
unique physical or behavioral characteristics of
individuals, which attempts to establish the identity of
given person out of a closed pool of peoples (one-to N
matching). Some biometrics like speech, iris, face [1],
palm-print [2], have been proposed , but Identity fraud
nowadays is one of the more common criminal
activities and is associated with large costs and serious
security issues. However, using electroencephalogram
(EEG) during imagined activities as a biometric is a
new approach. Since every living and functional
person has a recordable EEG signal, the EEG feature is
universal. Moreover, brain damage is something that
rarely occurs. Finally, it is very hard to fake an EEG
signature or to attack an EEG biometric system[3].
Poulus et al [4] proposed a method using
autoregressive (AR) modelling of EEG signals to
classify an individual as distinct from other
individuals. Palaniappan [5] proposed using VEP (i.e.
stimulus evoked EEG) recorded while the individuals
perceive a single picture. However, this method also
required the individuals to perceive a visual stimulus
and cannot be adapted to persons with Disabilities. In
previous research, it has been shown that motor
imagery classification is a suitable technique for use in
the design of Brain Computer Interfaces (BCIs) to aid
the disabled to communicate or control devices[6,7],
and there are some proofs showing that EEG patterns
are probably unique for individuals.
Therefore,in this paper, mental thoughts are
proposed to identify the individuality of persons.
Several signal processing methods has been used to
find out suitable EEG features as biometrics to classify
individuals by employing a competitive neural
network.
2.Data Description
The dataset of BCI competition 2003 is used in
this investigation. This dataset was provided by Graz
University of Technology. The subject sat in a relaxing
chair with armrests. The task was to perform imagery
left hand or right hand movements according to a cue.
An electrode cap was used to record EEG signals from
positions C3, C4, P3, P4, O1 and O2 defined by the 10
–20 system of electrode placement (as shown in Fig.
1), The data were sampled at 250Hz. The description
data above were filtered between 0.5–100 Hz with a
50-Hz notch filter turned on. To enhance the difference
between these two tasks and reduce the effect of
artifacts, common average reference (CAR) was used
to re-reference it.
2009 International Conference on New Trends in Information and Service Science
978-0-7695-3687-3 2009
U.S. Government Work Not Protected by U.S. Copyright
DOI 10.1109/NISS.2009.44
390
2009 International Conference on New Trends in Information and Service Science
978-0-7695-3687-3 2009
U.S. Government Work Not Protected by U.S. Copyright
DOI 10.1109/NISS.2009.44
390
2009 International Conference on New Trends in Information and Service Science
978-0-7695-3687-3 2009
U.S. Government Work Not Protected by U.S. Copyright
DOI 10.1109/NISS.2009.44
390
2009 International Conference on New Trends in Information and Service Science
978-0-7695-3687-3 2009
U.S. Government Work Not Protected by U.S. Copyright
DOI 10.1109/NISS.2009.44
390
2009 International Conference on New Trends in Information and Service Science
978-0-7695-3687-3 2009
U.S. Government Work Not Protected by U.S. Copyright
DOI 10.1109/NISS.2009.44
390