A NOVEL ALGORITHM DESIGN APPROACH FOR ACQUIRED
SIGNALS IN BRAIN MACHINE INTERFACE
Mamatha.M.N*
Assistant professor
B.M.S.College of Engineering
Department of Instrumentation
Communication
Bangalore mamatha222@yahoo.co.in
ramachandr@gmail.com
Visveswaraya Technological University, Karnataka, INDIA
ABSTRACT
Brain machine interface (BMI) ,a new field of research
helps patients in a locked-in state with minimal eye
movements and no speech and also who have
degenerative disorders (Amyotrophic lateral sclerosis,
multiple sclerosis, muscular dystrophy), brain or spinal
cord injury, or cerebral palsy. Literature survey [1]
shows that BCI systems were semi-automated.
Attempts by researchers changed the design to be fully
automated in few ways [2].The design of a novel
algorithm/hardware to achieve synchronized BCI
system using noninvasive electrodes that acquires
EEG and EOG [3] bio-potentials with high
classification accuracy along with an artifact processor
is the object of this research paper. The technicality of
the paper lies in the design of EOG sensor, which is
not revealed much, rather than its implementation in
an algorithm in acquiring the biopotentials.
The paper is organized as follows: The first part
explains the potential benefits deriving from the use of
additional interfaces conceived as complementary and
auxiliary for BMI as presented in Introduction
Second part reviews different types of non – invasive
man – machine interfaces followed by the design or
the Selected concept consisting of EOG – based BMI,
to be eventually used in combination with interfaces
based on speech recognition , EEG activation and
motion capture and gesture recognition and it may also
be menu driven.
Dr.S.Ramachandran**
Professor
S.J.B.Institute of technology
Department of Electronics and
Bangalore.
can be processed and employed to control
mechanical systems [4] ( e.g. actuators) or
electrical devices ( e.g. electronic
equipment ) is proved in the last section.
KEYWORDS: Brain machine interface
(BMI), EEG,
EOG, Eye wink.
1. INTRODUCTION Medical
electronics has a role to play in every
aspect of health care, be it prevention,
therapy, surgery, pharmalogy,
hospitalization, analysis, prosthetics or
Implants, but its diagnostics can transform
the healthcare in India. Modern electronics
is revolutionizing healthcare like never
before. While bringing superior diagnostic
and therapeutic capabilities, electronic and
semiconductor technologies are also
making healthcare ever more efficient,
accessible and affordable
The availability of the efficient and cheaper
computational resources, and also by the
increasing knowledge and comprehension
about motor dysfunctions [5] stimulated by
the recent findings in the areas of
cardiology, muscle physiology and
neuroscience wherein the evoked bio-
potentials vary with stimulus(auditory,
visual, tactile etc) have provoked the
researchers in the field of biomedical to
develop an interactive hardware (HMI)
which would help patients with neuronal
disorders and would perform the activities
based on the subject’s power of
thought.

The concept developed efficiently tracks the pupil
(eyeball) in real time, based on optical flow and color
predicates, the eye tracking [6] can robustly track a
person’s eye movement. It classifies the rotation of all
viewing directions, detects eye blinking, and recovers
the 3D gaze of the eyes. In , the eyeball detection
operates on the entire iris movement, . It uses the
mean absolute error measurement for eye tracking
movement collection data can be analyzed to
determine the pattern and duration of eye fixations and
the sequence of scan path as a user visually moves his
eyes. The active approaches [8–10] make use of IR
devices for the purposes of pupil tracking based on the
special bright pupil effect. This is a simple and very
accurate approach to pupil detection using the
differential infrared lighting scheme. It is capable of
handling sudden changes between IR and non-IR light
conditions, without changing parameters. However,
the active methods [8–10] require additional resources
in the form of infrared sources and infrared sensors.
In this work, a vision-based eye-movement
for helping the severely handicapped people (to
manipulate the household devices) is presented. We
assume that the possible head poses of the
handicapped people are very limited (severely
handicapped people).
2. METHODOLOGY
Under the front-pose assumption of the face, we may
easily locate the eyes, track the eyes, and then identify
the movement of the eyeball. . In this work, the
Hardware developed makes use of different sensors.
The TE765 sensor detects Eye Ball Position Linked
with EEG; TE916 sensor plots Patients EOG
observation graph monitoring based on the eye ball
position sensor and acquires the signals from evoked
bio-potentials. The Hough transform and radon
transform methods can be made use of for analyzing
the signals. The data is preprocessed to increase signal
to noise ratio prior to extracting the features. An
algorithm with a neural classifier is used and data
retrieved is compared and analyzed .It can also be
transmitted if required to a distant location for further
processing.
Fig[1]: BLOCK DIAGRAM OF BMI
The entire hardware set up (fig 1) worked
out to acquire the biopotentials of the eye
(EOG) and also electroencephalograph
(EEG) [12] which monitors the brainwave
activity from sensors placed on the scalp is
demonstrated. The paper presents the
design of this helmet. The signals
representing the brain activity can
determine epilepsy, hyperactivity and
attention deficit disorder, alcohol /
chemical dependency and other addictive
disorders, traumatic brain injury, sleep
onset disorders and insomnia.
The various regions of the brain do not
emit the same brain wave frequency
simultaneously. A sensor electrode placed
on the scalp would pick up many waves
with different characteristics. This has
presented a great deal of difficulty to
researchers trying to interpret the large
amount of data they receive from even one
recording.. Although none of these waves
is ever emitted alone, the state of
consciousness of the individual may make
one frequency more pronounced than the
others.The electrical activity (rhythm)
of the brain is associated with active
thinking, active attention, and focus on
the outside world or solving concrete
problems.
TE765 EYE BALL POSITION LINKED
WITH EEG
Eyeball sensor senses the position of eye i.e. (Left,
Center, and Right) and has two analog outputs. EEG
sensor acquires evoked potentials depending on the Fig [3]: Eye blink sensor -circuit
person’s emotion. This EEG output is calculated on
derived emotion on a person’s reaction to the
stimulus. The Eyeball position is detected with
reference to the Iris. Harmless 950nm wavelength IR
Transmitter and IR detectors are used to sense the
position of the Eye ball. The Tx, Rx sensors are
positioned in such a way to sense the position of Iris.

An 8051 Micro controller is used to interface this

whole system and gives the display output through
LCD. With this concept the disable patients can help
themselves perform their daily routine only through
their eye ball in walking according to their wish
without any assistance from other people. An 8051 Fig [4]: Eyeball sensor -circuit
Micro controller is used to interface this whole system
and gives the display output through LCD. The use of
ZigBee can be done to transmit and receive the
acquired data which provides highly efficient
connectivity between small packet devices. As a result
of its simplified operations, less complex than a
comparable Bluetooth® device, pricing for Zig-Bee
devices is extremely competitive, with full nodes
available for a fraction of the cost of a Bluetooth®
node.

Sensing elements detects optical muscle

Fig [2]: Working of eyeball sensor
movement continuously and amplified to
give pulse output the elastic strap holds the
sensing element in place vision muscle
movement. The active element in formed
by two metallic electrodes A and B are
placed in a feedback loop of a high
frequency oscillator. When no target in
present the sensor capacitance is low
therefore the oscillator amplitude is small.
When a target the face of the sensor it
increases the capacitance. This increase in
capacitance results in an increased
amplitude of oscillator.

3. PROPOSED-
METHODOLOGY

The methodology is as follows:

Step-1: To check whether the patient is fully/partially
paralyzed with normal eye movements.

Step-2: Mount the sensor strap/belt/helmet on the

scalp/forehead
Step-3: Analyze the type of the eye (Table 1).
Step-4: Acquire the eye movements and the procedure
is repeated for

i) Different patients having the same type (f)

of neuronal abnormality and classify the
signals.
ii) different patients having the different
type of neuronal abnormality and
classify the signals.
Fig [5]: a) Face orientation b) Eye blink c) Eye ball-
centre position d) Eyeball turned left e) Binarized open
eye f) Eye ball defects
4. EXPERIMENTAL RESULTS: To
create mobility, Expression and
communication with outside world for
terminally ill patient for whom only
Eyeball moves.
 Acquired signal from biopac
(simulation) was compared with
the hardware which has been
designed and the data retrieved is
validated by a neurophysician.

Fig [6]: Eye blink signal

(a) (b)

The compact design provides Temporal

Resolution and is easy to use

Fig [7]: Snapshot of the signal acquired

(c) (d) (e) from hardware
 paralyzed
(difficult to On research
analyze)

5. CONCLUSION AND
FUTUREWORK
Even though human brain is
incredibly complex, and the signals
retrieved for processing are unstable,
chaotic, non-linear, non-stationary, non-
Gaussian, asynchronous, noisy and
unpredictable, an attempt is being made to
Fig [8]: Author presenting the concept develop clinical systems for rehabilitation
which investigates the brain activity during
human recognition of characters and
symbols representing directional meaning.
In this work, an effective
algorithm human-machine interface is
proposed. The scheme is an efficient and
accurate method for primitive
identification. Even though EEG-based
BCIs have been implemented as solutions
for patients suffering from various degrees
of body paralysis, The most successful
approach is based on the utilization of
noninvasive electrodes which can eliminate
artifacts by pre-processing the acquired
signals. The design of the transmitter and
receiver with appropriate filters is the
scope of future.
In addition to using EEGs, imaging
techniques such as functional magnetic
resonance imaging (fMRI), which takes
stacks of slices of brain images have been
explored as a new source of brain-derived
signals to drive BCIs to study the activity
of deep brain structures.

TABLE 1

TYPE OF EYE POSITION RESULT

ANALYSIS
But fMRI-based BCIs are not suitable for
Normal and Left Achieved
subjects for prolong usage and those who
disabled (eye Centre(reference
suffer from temporal delays of several
movement ) Right
seconds which again is a disadvantage.
normal)
Segregating A robotic hand controlled by the
each eye and power of thought can also be thought off.
Squint Unable to reference to be
analyze provided
Paralyzed Depends on the 6. REFERENCES
part of the organ
[1] Birbaumer, N. (2006) Brain–computer-interface [9] Millán, J. del R., Ferrez, P., Buttfield,
research: coming of age. Clin. Neurophysiology. 117, A. (2006) Non Invasive Brain-Machine
479–483 Interfaces, ESA Ariadna Study 05/6402,
[2] McCarthy, R. A. and Warrington, E. K. CognitiveESA Contract 19708/06/NL/HE
neuropsychology: a clinical introduction, Academic Press, San
Diego, 1990. [10] Carmena, J.M., Lebedev, M.A., Crist,
R.E., O’Doherty, J.E., Santucci, D.M.,
[3] S Venkataramanan, Pranay Prabhat, Shubhodeep RoyDimitrov, D.F., Patil, P.G., Henriquez,
Choudhury, Harshal B Nemade, and J S Sahambi, “BiomedicalC.S., Nicolelis, M.A. (2003) Learning to
Instrumentation based on Electrooculogram (EOG) Signalcontrol a brain–machine interface for
Processing and Application to a Hospital Alarm System reaching and grasping by primates.
Proceedings of ICISIP 2005, pp 535-540. PlosBiology, Vol 1 (2), pp.193-208

[4] Carpi, F., De Rossi, D. (2006) Non Invasive Brain-Machine[11] Hochberg, L.R.,Serruya, M.D., Friehs,
Interfaces, ESA Ariadna Study 05/6402, ESA Contract G.M., Mukand, J.A., Saleh, M. Caplan,
19706/06/NL/HE A.H., Branner, A., Chen, D. Penn, R.D.,
and Donoghue, J.P. (2006). Neuronal
[5]) Kubler A, Kotchoubey B, Kaiser J, Wolpaw JR, Birbaumer ensemble control of prosthetic devices by a
N. Brain-computer communication: unlocking the locked in.human with tetraplegia. Nature 442, 164-
Psychol Bull. 2001; 127:358–375. 171.
[6] T. D’Orazio, M. Leo, P. Spagnolo, and C.
[12]N. Birbaumer, “Breaking the silence:
Guaragnella, “A neural system for eye detection in a
Brain-computer interfaces(BCI) for
driver vigilance application,” in Proceedings of the 7th
communication and motor control,”
International IEEE Conference on Intelligent
Pyschophysiology, vol.
Transportation Systems (ITS ’04), pp. 320–325,
43, pp. 517-532, 2006.
Washington, DC, USA, October 2004.
[13] J. Kalcher, D. Flotzinger, Ch. Neuper,
S. Golly, and G. Pfurtscheller,“Graz brain-
[7] K. F. Van Orden, T.-P. Jung, and S. Makeig,
computer interface II: towards
“Combined eye activity measures accurately estimate
communication between humans and
changes in sustained visual task performance,”
computers based on online classification of
Biological Psychology, vol. 52, no. 3, pp. 221–240,
three different EEG patterns,” Med. Biol.
2000.
Eng. Comp., vol. 34, pp. 382–388,Sep.
1996
[8] R. Shaw, E. Crisman, A. Loomis, and Z.
[14] [9] Farwell, L.A. & Donchin, E.
Laszewski, “The eye wink control interface: using the
(1988) Talking Off the Top of Your Head:
computer to provide the severely disabled with
Toward a Mental Prosthesis Utilizing
increased flexibility and comfort,” in Proceedings of
Event Related Brain
the 3rd Annual IEEE Symposium on Computer- Based
Potentials, Electroenceph. Clin.
Medical Systems (CBMS ’90), pp. 105–111, Chapel
Neurophysiol. 70, 510–523
Hill, NC, USA, June 1990.
 Dr. S. Ramachandran has wide academic as well
ABOUT THE AUTHORS
Mamatha. M. N. received her M.E. degree in
Electronics from University of Bangalore in 1999.
She received her B.E. degree in Instrumentation
from Mysore University in 1993. Presently, she is
working as an assistant professor in B. M. S.
College of engineering, Visveswaraya
Technological University. She is presently doing a
Ph. D. Research in Vinayaka Missions University,
Salem, Tamilnadu. Her areas of interest are
biomedical instrumentation and transducers. She
has presented papers in national and International
Conferences.
as industrial experience for over 30 years,
having worked as Professor in various
engineering colleges as well as design
engineer in industries. Prior to this, he has
been with the Indian Institute of Technology,
Madras. He has industrial and teaching
experience, having worked both in India and
USA, designing systems and
teaching/guiding students and practicing
engineers based on FPGAs and
Microprocessors. His research interests
include developing algorithms, architectures
and implementations on FPGAs/ASICs for
Video Processing, DSP applications,
reconfigurable computing, open loop control
systems, etc. He has a number of papers in
International Journals and Conferences. He is
the recipient of the Best Design Award at
VLSI Design 2000, International Conference
held at Calcutta, India and the Best Paper
Award of the Session at WMSCI 2006,
Orlando, Florida, USA. He has completed a
video course on Digital VLSI System Design
at the Indian Institute of Technology Madras,
India for broadcast on TV by National
Programme on Technology on Enhanced
Learning (NPTEL). He has also written a
book on Digital VLSI Systems Design,
published by Springer Verlag, Netherlands
(www.springer.com).