INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY

VOLUME 3 ISSUE 2 FEBRUARY 2015 ISSN: 2349 9303

Brain Computer Interface for User Recognition And

Smart Home Control
VIDYA.A
Dept of Electronics & Communication Engineering
Karpagam University, Coimbatore, India.
vidyaannadurai@gmail.com

NANDHA KUMAR.R
Dept of Electronics & Communication Engineering
Karpagam University, Coimbatore, India.
nandhanila69@gmail

Abstract
This project discussed about a brain controlled biometric based on Braincomputer interfaces
(BCI). BCIs are systems that can bypass conventional channels of communication (i.e., muscles and
thoughts) to provide direct communication and control between the human brain and physical devices by
translating different patterns of brain activity into commands in real time. With these commands a biometric
technology can be controlled. The intention of the project work is to develop a
user recognition machine
that can assist the work independent on others.
Here, we are analyzing the brain wave signals. Human brain consists of millions of interconnected
neurons. The patterns of interaction between these neurons are represented as thoughts and emotional states.
According to the human thoughts, this pattern will be changing which in turn produce different electrical
waves. A muscle contraction will also generate a unique electrical signal. All these electrical waves will be
sensed by the brain wave sensor and it will convert the data into packets and transmit through Bluetooth
medium. Level analyzer unit (LAU) will receive the brain wave raw data and it will extract and process the
signal using Mat lab platform. Then the control commands will be transmitted to the robotic module to
process. With this entire system, we can operate the home application according to the human thoughts and
it can be turned by blink muscle contraction.
Index Terms EEG, biometrics, brain rhythms, elicitation protocols.

1 .INTRODUCTION
Electroencephalography (EEG) is a
method used in measuring the electrical activity
of the brain. This activity is generated by billions
of nerve cells, called neurons. Each neuron is
connected to thousands of other neurons. Some of
the connections are excitatory while others are
inhibitory. The signals from other neurons sum up
in the receiving neuron. When this sum exceeds
a certain potential level called a threshold, the
neuron fires nerve impulse. The electrical activity
of a single neuron cannot be measured with scalp
EEG. However, EEG can measure the combined
electrical activity of millions of neurons. The
temporal resolution of EEG is very good:
millisecond or even better.
In the last few years, the notion that
the brain has a default or intrinsic mode of

IJTET2015

functioning has received increasing attention. The

idea derives from observations that a consistent
network of brain regions shows high levels of
activity when no explicit task is performed and
participants are asked simply to rest. The
importance of this putative default mode is
asserted on the basis of the substantial energy
demand associated with such a resting state and of
the suggestion that rest entails a finely tuned
balance between metabolic demand and
regionally regulated blood supply. These
observations, together with the fact that the
default network is more active at rest than it is in
a range of explicit tasks, have led some to suggest
that it reflects an absolute baseline, one that must
be understood and used if we are to develop a
comprehensive picture of brain functioning. Here,
we examine the assumptions that are generally
made in accepting the importance of the default
mode.

89

INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY

VOLUME 3 ISSUE 2 FEBRUARY 2015 ISSN: 2349 9303
2.OVERALLPROJECTOUTLINE
Brain signals have been investigated within
field for more than a century to study brain
diseases like epilepsy, spinal cord injuries. They
are also used in both brain computer and brain
machine interface systems with assistance,
rehabilitative, and entertainment applications.
Despite the broad interest in clinical applications,
the use of brain signals has been only recently
investigated by the scientific community as a
biometric characteristic to be used in automatic
people recognition systems. However, most
commonly used biometrics, such as brain signals
present some peculiarities, not shared by the face,
iris, and fingerprints, with reference, robustness
against spoofing attacks, possibility to perform
continuous identification, intrinsic liveness
detection, and universality.
In this project with a minicomputer RF
Transmitter and Receiver with different input and
output is interfaced. In input section there is brain
wave sensor, transmitter, Level analyzer unit and
the data processing unit.
Here, we are analyzing the brain wave
signals. Human brain consists of millions of
interconnected neurons. The patterns of
interaction between these neurons are represented
as thoughts and emotional states. According to the
human thoughts, this pattern will be changing
which in turn produce different electrical waves.
A muscle contraction will also generate a unique
electrical signal. All these electrical waves will be
sensed by the brain wave sensor and it will
convert the data into packets and transmit through
Bluetooth medium. Level analyzer unit (LAU)
will receive the brain wave raw data and it will
extract and process the signal using Mat lab
platform. Then the control commands will be
transmitted to the robotic module to process. With
this entire system, we can operate the home
application according to the human thoughts and
it can be turned by blink muscle contraction.
When there is a mismatch of the brain wave then
a buzzer sound will be indicated.

Figure 1.Block diagram

3. HARDWARE PROTOTYPE
3.1. Elicitation of Brain Responses
Since the earliest applications of EEG
signals, particular interest has been shown in the
study of cerebral activity during a state of rest, due
mainly to the simplicity of the acquisition process.

IJTET2015

90

INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY

VOLUME 3 ISSUE 2 FEBRUARY 2015 ISSN: 2349 9303
Therefore, the resting state protocol, with eyes
closed or open, has been widely studied for
different purposes. Within this paradigm the
enrolled subjects are typically seated in a
comfortable chair with both arms resting, in a
dimly lit or completely dark room. Generally,
external sounds and noise are minimized to favor
the relaxed of the subjects. Participants are asked
to perform few minutes of resting state with eyes
closed or eyes open, avoiding any focusing or
concentration, but staying awake and alert. Brain
activity during resting state without performing
any task carries interesting information as
3.2. EEG SIGNAL BASED RECOGNITION
contained in EEG specific patterns .Eyes closed
SYSTEMS
and eyes open resting conditions are usually
employed in EEG research processes related to
The use of brain activity as user identifier is
global arousal and focal activation .Moreover,
suggested by its general role in controlling the
EEG patterns have shown significant differences,
functioning of the whole body, the cognitive
specially related to the spectral analysis, between
processing, and the response to external stimuli. In
rest and several cognitive tasks, and even
this regard, memory mechanisms (experience),
between different cognitive tasks themselves,
personality correlates, and anatomo -physiological
involving distinct neural systems. In order tinfer
factors contribute generating individual specific
about the properties of neural activation in the
traits. Some promising results have been obtained
involved brain regions, match logical and spatial
employing different EEG acquisition protocols,
cognitive operation have been considered in the
involving both resting conditions with closed or
development of suitable acquisition protocols.
open eyes, response to specific stimuli, like visual
Changes in neuronal activation patterns due to
stimuli, and execution of real or imagined body
specific components of mental calculation tasks
movements. Since the recognition performance of
can be observed from the analysis of each
a biometric system in general, and of an EEG
frequency band, as they seem to be related to
based system in particular, depends on the proper
oscillatory activity of different neural networks. In
design of the acquisition protocol, on the feature
this regard, different studies for baseline estimates,
selection approach, and on the classification
although they represent different processes related
algorithm, in this Section the afore mentioned
to global arousal and focal activation .Moreover,
issues will be considered to compare the state of
EEG patterns have shown significant differences,
the art EEG based biometric systems. Databases
specially related to the spectral analysis, between
structures will also be taken into account.
rest and several cognitive tasks, and even between
different cognitive tasks themselves, involving
distinct neural systems. In order to infer about the
properties of neural activation in the involved brain
Delta 0.54Hz: Delta rhythm is a predominant
oscillatory activity in EEGs recorded during the so
called deep or slow wave sleep (SWS). In this
regions, math, logical, and spatial cognitive
stage, Delta waves usually have relatively large
operations have been considered in the
amplitudes (75 200V) and show strong
development of suitable acquisition protocols.
coherence all over the scalp. In newborns, slow
Changes in neuronal activation patterns due to
Delta rhythms predominate. An increase in Delta
specific components of mental calculation tasks
EEG activity during the performance of a mental
can be observed from the analysis of each
task has shown to be related to an increase in
frequency band, as they seem to be related to
subjects attention to internal processing.
oscillatory activity of different neural networks.

IJTET2015

91

INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY

VOLUME 3 ISSUE 2 FEBRUARY 2015 ISSN: 2349 9303
Theta 4 8Hz: In human scalp EEG, changes in
Motor
Theta rhythm are very difficult to detect without
the help of computational methods from raw EEG
Software requirements:
traces. If EEG power in a resting condition is
Compiler(KEIL IDE)
compared with a test condition, an increased
Orcad design
activity in the Theta sub band is observed, which is
Programmers(Flash Magic)
known as Theta-band power synchronization. In
Languages: Embedded c
particular, Theta-band power increases in response
MATLAB
to memory demands, electively reflecting the
successful encoding of new information.
Applications:
Bio metric applications
Alpha 8 14Hz: The oscillatory Alpha band
Online verified applications
activity is the most dominant rhythm which
Home applications
emerges in normal subjects, most pronounced in
Mobile applications
the parieto-occipital region. It is manifested by a
Voting applications
peak in frequency spectrum. The Alpha brain
oscillations may present amplitudes large enough
CONCLUSION
to be clearly seen in raw EEG traces acquired in
The system can be used in
specific mental states
several places like banks, hospitals, labs and other
sophisticated
automated
systems,
which
Beta 14 30Hz: Phase synchrony in Beta
dramatically reduce the hazard of unauthorized
frequency band is enhanced for consciously
entry. Evidence can be given to the security
perceived stimuli [17], and detectable mainly from
department if any robbery issue occurs. The
the involved cortical areas, including somato
system can However, most commonly used
sensory, frontal, parietal and motor regions,
biometrics, such as brain signals present some
depending on the performed task. Specifically,
peculiarities, not shared by the face, iris, and
Beta activity is characteristic for the states of
fingerprints, with reference, robustness against
increased alertness and focused attention.
spoofing attacks, possibility to perform
Continuous identification.
Gamma over 30Hz: Neuronal synchronization in
In future, EEG measurement using brain
the Gamma band is considered important for the
computer
interface is Possible to measure the
transient functional integration of neural activity
electrical signals of the brain for authentication
across brain areas, which represent various
and smart home control with high accuracy.
functions involving active information processing,
e.g., recognition of sensory stimuli, and the onset
REFERENCES
of voluntary movements. Gamma components are
difficult to record by scalp electrodes and their
[1] E. Basar, Brain Function and Oscillations:
Integrative Brain Function.Neurophysiology and
Cognitive Processes (Springer series in
frequency usually does not exceed 45Hz .
synergetics).Berlin, Germany: Springer-Verlag,
Components up to 100Hz, or even higher, may be
1999.
registered in electrocorticogram (ECoG).
Hardware requirements:
ARM lpc2148
Brain wave sensor
Alaram unit
LCD display
Switches
Gsm modem
Light

IJTET2015

[2] G. Dornhege, J. d. R. Millan, T. Hinterberger,

D. McFarland, andK.-R. M oller, Towards
Brain-Computing
Interfacing.
Cambridge,
MA,USA: MIT Press, 2007.
[3] J. R. Wolpaw and E. W. Wolpaw,
Event-Related Brain Potentials: Methods, Theory,
and Applications. Hoboken, NJ, USA: Wiley,

92

INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY

VOLUME 3 ISSUE 2 FEBRUARY 2015 ISSN: 2349 9303
2000.
[4] J. M. Carmena, Becoming bionic, IEEE
Spectr., vol. 49, no. 3,pp. 2429, Mar. 2012.,
which [5] H. H. Stassen, Computerized
recognition of persons by EEG spectral
patterns, Electroencephalogr. Clin.Neurophysiol.,
vol. 49, nos. 12,pp. 190194, 1980.
[6] P. Campisi, D. La Rocca, and G. Scarano,
EEG for automatic personrecognition, IEEE
Comput., vol. 45, no. 7, pp. 8789, Jul. 2012.
[7] J. Berkhout and D. O. Walter, Temporal
stability and individual differences in the human
EEG: An analysis of variance of spectral
values, IEEE Trans. Biomed. Eng., vol. 15, no. 3,
pp. 165168, Jul. 1968.
[8] H. Van Dis, M. Corner, R. Dapper, G.
Hanewald, and H. Kok, Individualdifferences in
the
human
electroencephalogram
during
quietwakefulness,
Electroencephalogr.
Clin.Neurophysiol., vol. 47, no. 1,pp. 8794,
1979.

IJTET2015

93