Medak College of Engineering and

Technology
Kondapak Village, Siddipet Mandal, Medak District.

BRAIN COMPUTER INTERFACE.

“A technology for the handicaps”

Presenters:

SUBOOHI SHAHEEN
Medak College of engineering and tech
Kondapak Village, Siddipet (M),
Medak District - 502372, Andhra Pradesh, India.
[email protected],

1
 ABSTRACT:

A brain-computer interface is a communication system that does not depend

on the brains normal output pathways of peripheral nerves and muscles. It is a new
communication link between a functioning human brain and the outside world.
These are electronic interfaces with the brain, which has the ability to send and
receive signals from the brain. BMI uses brain activity to command, control,
actuate and communicate with the world directly through brain integration with
peripheral devices and systems. The signals from the brain are taken to the
computer via the implants for data entry without any direct brain intervention. BMI
transforms mental decisions and/or reactions into control signals by analyzing the
bioelectrical brain activity.

While linking the brain directly with machines was once considered science
fiction, advances over the past few years have made it increasingly viable. It is an
area of intense research with almost limitless possibilities. The human brain is the
most complex physical system we know of, and we would have to understand its
operation in great detail to build such a device. An immediate goal of brain-
machine interface study is to provide a way for people with damaged
sensory/motor functions to use their brain to control artificial devices and restore
lost capabilities. By combining the latest developments in computer technology
and hi-tech engineering, paralyzed persons will be able to control a motorized
wheel chair, computer painter, or robotic arm by thought alone. In this era where
drastic diseases are getting common it is a boon if we can develop it to its full
potential. Recent technical and theoretical advances, have demonstrated the
ultimate feasibility of this concept for a wide range of space-based applications.
Besides the clinical purposes such an interface would find immediate applications
in various technology products also.

2
 lives in ways that have been previously
thought possible in only sci-fi movies.
INTRODUCTION:
Brain-Computer Interface (BCI) is a
communication system, which enables the
Millions of dollars are spent by the user to control special computer applications
government of different nations trying to by using only his or her thoughts. These
reincorporate into the society thousands of experiments lend hope that people with
people with severe disabilities. There are spinal injuries will be able to someday use
approximately 200000 cases of spinal cord their brain to control a prosthetic limb, or
injuries – growing at a rate of 11000 new even their own arm. A BMI could, e.g.,
cases per year. Of these new cases 56% are allow a paralyzed patient to convey her/his
in the 16 – 30 age groups, and the recovery intentions to a computer program. But also
rate is 0.7%. Brain Computer Interfaces are applications in which healthy users can
devices to bring an alternative channel of benefit from the direct brain computer
control and communication between people communication are conceivable, e.g., to
severely disabled and the “outside” world. speed up reaction times. The first peripheral
BCIs are intended to enable both the devices were robotic arms. Its approach is
severely motor disabled as well as the based on an artificial neural network that
healthy people to operate electrical devices recognizes and classifies different brain
and applications through conscious mental activation patterns associated with carefully
activity. selected mental tasks.

The Organization of BMI

When we talk about high end BCIs are often divided into three
computing and intelligent interfaces, we just categories: invasive, partially-invasive, and
cannot ignore robotics and artificial non-invasive. When a BCI is labeled as
intelligence. In the near future, most devices invasive, this means that the device is
would be remote/logically controlled. This actually implanted into the brain or head of
technology has the capability to impact our the individual that it is designed for. An
example of an invasive BCI would be a

3
vision BCI, which is implanted into the head
of a blind patient to allow for artificial
vision. Partially-invasive means that certain
parts of the device need to be implanted into
the person’s head while other parts of the
device do not. This allows for better signal
recognition that a normal non-invasive
device, but is often much more dangerous
and expensive. Non-invasive indicates that
the device does not need to penetrate the
skin at all.

Examples of alpha, beta, theta and

delta rhythms.

BCI COMPONENTS:

A brain-computer interface (BCI) in

its scientific interpretation is a combination
ELECTROENCEPHALOGRAPHY: of several hardware and software
components trying to enable its user to
Electroencephalography (EEG) is a communicate with a computer by
method used in measuring the electrical intentionally altering his or her brain waves.
activity of the brain. The brain generates The hardware consists of an EEG machine
rhythmical potentials which originate in the and a number of electrodes scattered over
individual neurons of the brain. These the subject’s skull. The EEG machine,
potentials get summated as millions of cell which is connected to the electrodes via thin
discharge synchronously and appear as a wires, records the brain-electrical activity of
surface waveform, the recording of which is the subject, yielding a multi-dimensional
known as the electroencephalogram. The (analog or digital) output. The values in each
alpha rhythm is one of the principal dimension (also called channel) represent
components of the EEG and is an indicator the relative differences in the voltage
of the state of alertness of the brain. potential measured at two electrode sites.

The software system has to read,

digitize (in the case of an analog EEG
machine), and preprocess the EEG data
(separately for each channel), “understand”
the subject’s intentions, and generate
appropriate output. To interpret the data, the

4
stream of EEG values is cut into successive
segments, transformed into a standardized
representation, and processed with the help
of a classifier. There are several different
possibilities for the realization of a
classifier; one approach – involving the use
of an artificial neural network (ANN)– has
become the method of choice in recent
years.

An array of microelectrodes.

A BMI based on the classification of Usually small metal-plate electrodes

two mental tasks. The user is thinking task are used in the EEG recording. Neural
number 2 and the BCI classifies it correctly implants can be used to regulate electric
and provides feedback in the form of cursor signals in the brain and restore it to
movement. Now the BMI components are equilibrium. They must be able to move
described as follows: inside the skull with the brain without
causing any damage to the brain. The
1: IMPLANT DEVICE: implant must be chemically inert so that it
doesn’t interact with the hostile environment
The EEG is recorded with electrodes, inside the human body. All these factors
which are placed on the scalp. Electrodes are must be addressed in the case of neural
small plates, which conduct electricity. They implants; otherwise it will stop sending
provide the electrical contact between the useful information after a short period of
skin and the EEG recording apparatus by time.
transforming the ionic current on the skin to
the electrical current in the wires. To
improve the stability of the signal, the outer
layer of the skin called stratum conium
should be at least partly removed under the
electrode. Electrolyte gel is applied between
the electrode and the skin in order to provide
good electrical contact.

5
 Three-dimensional arrays of 3: SPIKE DETECTION:
electrodes are also under development.
These devices are constructed as two- Real time spike detection is an
dimensional sheet and then bent to form 3D important requirement for developing brain
array. These can be constructed using a machine interfaces. Incorporating spike
polymer substrate that is then fitted with detection will allow the BMI to transmit
metal leads. They are difficult to implement, only the action potential waveforms and
but give a much great range of stimulation their respective arrival times instead of the
or sensing than simple ones. sparse, raw signal in its entirety. This
compression reduces the transmitted data
rate per channel, thus increasing the number
of channels that may be monitored
simultaneously. Spike detection can further
reduce the data rate if spike counts are
transmitted instead of spike waveforms.
Block diagram of the neurotrophic Spike detection will also be a necessary first
electrodes for implantation in human step for any future hardware implementation
patients. of an autonomous spike sorter. A hardware
realization of a spike detector in a wireless
2: SIGNAL PROCESSING SECTION: BMI must operate in real-time, be fully
autonomous, and function at realistic signal-
Multichannel Acquisition Systems to- noise ratios (SNRs).
Electrodes interface directly to the non-
inverting opamp inputs on each channel. At 4: SIGNAL ANALYSIS:
this section amplification, initial filtering of
EEG signal and possible artifact removal Feature extraction and classification
takes place. Also A/D conversion is made, of EEG are dealt in this section. In this
i.e. the analog EEG signal is digitized. The stage, certain features are extracted from the
voltage gain improves the signal-to-noise preprocessed and digitized EEG signal. In
ratio (SNR) by reducing the relevance of the simplest form a certain frequency range
electrical noise incurred in later stages. is selected and the amplitude relative to
Processed signals are time-division some reference level measured. Typically
multiplexed and sampled. the features are frequency content of the
EEG signal) can be calculated using, for
example, Fast Fourier Transform (FFT
function). No matter what features are used,
the goal is to form distinct set of features for
each mental task. If the feature sets
representing mental tasks overlap each other
too much, it is very difficult to classify
mental tasks, no matter how good a
classifier is used. On the other hand, if the
feature sets are distinct enough, any
classifier can classify them. The features
extracted in the previous stage are the input
A BMI under design. for the classifier.

6
The classifier can be anything from a simple In the BMIs based on the operant
linear model to a complex nonlinear neural conditioning approach, feedback training is
network that can be trained to recognize essential for the user to acquire the control
different mental tasks. Nowadays real time of his or her EEG response. The BMIs based
processing is used widely. Real time on the pattern recognition approach and
applications provide an action or an answer using mental tasks do not definitely require
to an external event in a timely and feedback training. However, feedback can
predictable manner. So by using this type of speed up the learning process and improve
system we can get output nearly at the same performance. Cursor control has been the
time it receives input. Telemetry is handled most popular type of feedback in BMIs.
by a wearable computer. The host station Feedback can have many different effects,
accepts the data via either a wireless access some of them beneficial and some harmful.
point or its own dedicated radio card. Feedback used in BMIs has similarities with
biofeedback, especially EEG biofeedback.
5: EXTERNAL DEVICE:

The classifier’s output is the input ADVANTAGES:

for the device control. The device control
simply transforms the classification to a Depending on how the technology is
particular action. The action can be, e.g., an used, there are good and bad effects:
up or down movement of a cursor on the 1. In this era where drastic diseases are
feedback screen or a selection of a letter in a getting common it is a boon if we
writing application. However, if the can develop it to its full potential.
classification was “nothing” or “reject”, no
action is performed, although the user may 2. Also it provides better living, more
be informed about the rejection. It is the features, more advancement in
device that subject produce and control technologies etc.
motion. Examples are robotic arm, thought
controlled wheel chair etc. 3. Linking people via chip implants to
super intelligent machines seems to a
FEEDBACK: natural progression –creating in
effect, super humans.
Real-time feedback can dramatically
improve the performance of a brain– 4. Linking up in this way would allow
machine interface. Feedback is needed for for computer intelligence to be
learning and for control. Real-time feedback hooked more directly into the brain,
can dramatically improve the performance allowing immediate access to the
of a brain–computer interface. In the brain, internet, enabling phenomenal math
feedback normally allows for two corrective capabilities and computer memory.
mechanisms. One is the ‘online’ control and
correction of errors during the execution of a 5. By this humans get gradual co-
movement. The other is learning: the evolution with computers.
gradual adaptation of motor commands,
which takes place after the execution of one CHALLENGES:
or more movements.

7
 1. Connecting to the nervous system
could lead to permanent brain
damage, resulting in the loss of
feelings or movement, or continual
pain.

2. In the networked brain condition –

what will mean to be human?

3. Virus attacks may occur to brain

causing ill effects.

Other various applications are

Mental Mouse Applications in technology
products, e.g., a mobile phone attachment
that allows a physically challenged user to
dial a phone number without touching it or
speaking into it. System lets you speak
APPLICATIONS: without saying a word In effective
construction of unmanned systems, in space
The BMI technologies of today can missions, defense areas etc. NASA and
be broken into three major areas: DARPA has used this technology
effectively. Communication over internet
1. Auditory and visual prosthesis can be modified.
- Cochlear implants
- Brainstem implants LATEST INFORMATION ABOUT BCI:
- Synthetic vision
- Artificial silicon retina The world's first commercial effort at
a patient-ready brain computer interface is
2. Functional-neuromuscular stimulation on display over at CeBIT 2010. Intended for
(FNS) patients suffering from locked-in syndrome
- FNS systems are in experimental use in and other communication-impairing
cases where spinal cord damage or a stroke conditions, the Intendix from Guger
has severed the link between brain and the Technologies allows users to input text
peripheral nervous system. They can use using only their brains. Intendix works using
brain to control their own limbs by this an EEG-sensitive cap that measures brain
system. activity that is focused in a particular way.
You simply watch a grid of letters that
3. Prosthetic limb control flashes on the screen, focusing on the letter
- Thought controlled motorized wheel chair. you want to type. When the letter you want
- Thought controlled prosthetic arm for lights up, your brainwaves jump ever so
amputee. slightly, allowing the EEG to determine
- Various neuroprosthetic devices. what to type. Guger Technologies claims
that the interface is simple enough that users

8
can utilize it relatively well after just ten New findings by a team of
minutes of training. University of Maryland researchers may
lead to new, non-invasive technologies for
Brain control headset for gamers: portable brain-computer interface systems.
Such technologies potentially could allow
people with disabilities or paralysis to
Gamers will soon be able to interact with operate a robotic arm, motorized wheelchair
the virtual world using their thoughts and or other prosthetic device using a headset
emotions alone. A neuro-headset which with scalp sensors that send signals from the
brain to the device.
interprets the interaction of neurons in the
brain. The brain is made up of about 100
billion nerve cells, or neurons, which emit
an electrical impulse when interacting. The
headset implements a technology known as
non-invasive electroencephalography (EEG)
to read the neural activity. The Epoc
technology can be used to give authentic
facial expressions to avatars of gamers in
virtual worlds. For example, if the player
smiles, winks, grimaces the headset can
detect the expression and translate it to the
avatar in game.

FUTURE EXPANSION:

A new thought-communication
device might soon help severely disabled
people get their independence by allowing
them to steer a wheelchair with their mind.
Mind-machine interfaces will be available in
the near future, and several methods hold
promise for implanting information. .
Linking people via chip implants to super
intelligent machines seems to a natural
progression –creating in effect, super
humans. These cyborgs will be one step
Non-invasive brain-computer interface ahead of humans. And just as humans have
technology: always valued themselves above other forms
of life, it is likely that cyborgs look down on
humans who have yet to ‘evolve’.

9
 Will people want to have their heads
opened and wired? Technology moves in REFERENCES:
light speed now. In that accelerated future,
today’s hot neural interface could become 1. www.news.bbc.co.uk/2/hi/technolog
tomorrow’s neuro trash. Will you need to y/7254078.stm.
learn any math if you can call up a computer
merely by your thoughts? Thought 2. www.sciencedaily.com/realeases/200
communication will place telephones firmly 9/10/091006102637
in the history books.
3. www.tomshardware

4. www.medicalnewstoday.com

5. www.popci.com/.../worlds-first-
commercial-brain-computer-
interface.

And some image and data’s are with

the help of the prominent site i.e.
Google, etc.

CONCLUSION:

Cultures may have diverse ethics, but

regardless, individual liberties and human
life are always valued over and above
machines. What happens when humans
merge with machines? The question is not
what will the computer be like in the future,
but instead, what will we be like? What kind
of people are we becoming?

BMI’s will have the ability to give

people back their vision and hearing. They
will also change the way a person looks at
the world. Someday these devices might be
more common than keyboards. Is someone
with a synthetic eye, less a person than
someone without? Shall we process signals
like ultraviolet, X-rays, or ultrasounds as
robots do? These questions will not be
answered in the near future, but at some
time they will have to be answered. What an
interesting day that will be.

10