Brain Computer interface

INTRODUCTION

Brain Computer interface (BCI) is a

communication system that recognized users’ command
only from his or her brainwaves and reacts according to
them. For this purpose PC and subject is trained. Simple
task can consist of desired motion of an arrow displayed on
the screen only through subject's imaginary of something
(e.g. motion of his or her left or right hand). As the
consequence of imaging process, certain characteristics of
the brainwaves are raised and can be used for user's
command recognition, e.g. motor mu waves (brain waves of
alpha range frequency associated with physical movements
or intention to move).

An Electroencephalogram based Brain-

Computer-Interface (BCI) provides a new communication
channel between the human brain and a computer. Patients
who suffer from severe motor impairments (late stage of
Amyotrophic Lateral Sclerosis (ALS), severe cerebral palsy,
head trauma and spinal injuries) may use such a BCI
system as an alternative form of communication by mental
activity.

The use of EEG signals as a vector of

communication between men and machines represents one
of the current challenges in signal theory research. The
principal element of such a communication system, more

Page | 1
Brain Computer interface
known as “Brain Computer Interface”, is the interpretation
of the EEG signals related to the characteristic parameters
of brain electrical activity.

The role of signal processing is crucial in the

development of a real-time Brain Computer Interface. Until
recently, several improvements have been made in this
area, but none of them have been successful enough to use
them in a real system. The goal of creating more effective
classification algorithms, have focused numerous
investigations in the search of new techniques of feature
extraction.

The main objective of this project is the establishment

of a Time – Frequency method, which allows EEG signal
classification between two given tasks (“geometric figure
rotation” and “mental letter composing”), as well as the
familiarization with the state of the art in time-frequency
and Brain Computer Interface. The extension of this method
to a five-task classification problem will be also considered.

The electrical nature of the human nervous system

has been recognized for more Than a century. It is well
known that the variation of the surface potential
distribution on the scalp reflects functional activities
emerging from the underlying brain [2.1]. This surface
potential variation can be recorded by affixing an array of
electrodes to the scalp, and measuring the voltage between

Page | 2
Brain Computer interface
pairs of these electrodes, which are then filtered, amplified,
and recorded. The resulting data is called the EEG. Fig. 1-1
shows waveforms of a 10 second EEG segment containing
six recording channels, while the recording sites are
illustrated in Fig. 2-2.

Figure 2-1. A segment of a multichannel EEG of an adult

subject during a multiplication task.

Page | 3
Brain Computer interface

Each site has a letter (to identify the lobe) and a number or
another letter to identify the hemisphere
Location. The letters F, T, C, P, and O stand for Frontal,
Temporal, Central, Parietal and Occipital. (Note that there is
no “central”, but this is just used for identification process).
Even numbers (2, 4, 6, and 8) refer to the right hemisphere
and odd numbers (1, 3, 5, and 7) refer to the left
hemisphere. The z refers to an electrode placed on the
midline.
Nasion: point between the forehead and nose.
Inions: Bump at back of skull

Page | 4
Brain Computer interface

System overview

A Brain-Computer Interface (BCI) is a system that

acquires and analyzes neural Signals with the goal of
creating a communication channel directly between the
brain and the computer. Such a channel potentially has
multiple uses.

For example:

• Bioengineering applications: assist devices for disabled

people.
• Human subject monitoring: sleep disorders, neurological
diseases, attention
Monitoring, and/or overall "mental state".

Page | 5
Brain Computer interface
• Neuroscience research: real-time methods for correlating
observable behavior
With recorded neural signals.
• Man – Machine Interaction: Interface devices between
human and computers,
Machines,

For many years, people have speculated that

electroencephalographic (EEG) activity or other measures
of brain function might provide this new channel. Over the
past decade, productive BCI research programs have
begun. Facilitated and encouraged by the new
understanding of brain functions and by the low-cost
computer equipments, these programs have concentrated
mainly in developing new communication and control
technologies for people with severe neuromuscular
disorders. The immediate goal is to provide communication
capabilities so that any subject can control the external
world without using the brain's normal output pathways of
peripheral nerves and muscles.

Nowadays, such activities drive their efforts in:

• Brain (neural) signal acquisition: development of both
invasive and non-invasive
Techniques for high quality signal acquisition.
• Algorithms and processing: advanced machine learning
and signal processing

Page | 6
Brain Computer interface
Algorithms, which take advantage of cheap/fast computing
power (i.e. Moore's
Law2) to enable online real-time processing.
• Underlying neuroscience: a better understanding of the
neural code, the functional
neuro-anatomy, the physiology and how these are related
to perception and
Cognition, enabling signals to be interpreted in the context
of the neurobiology.

Present BCI’s use EEG activity recorded at the

scalp to control cursor movement , Select letters or icons,
or operate a neuroprosthesis. The central element in each
BCI is a translation algorithm that converts
electrophysiological input from the user into output that
controls external devices. BCI operation depends on
effective interaction between two adaptive controllers: the
user who encodes his or her commands in the
electrophysiological input provided to the BCI, and the
computer which recognizes the command contained in the
input and expresses them in the device control. Current
BCI’s have maximum information transfer rates of 5-25
bits/min.
Achievement of greater speed and accuracy depends on
improvements in:
• Signal acquisition: methods for increasing signal-to-noise
ratio (SNR), signal-to interference ratio (S/I)) as well as
optimally combining spatial and temporal

Page | 7
Brain Computer interface
Information.
• Single trial analysis: overcoming noise and interference in
order to avoid
Averaging and maximize bit rate.
• Co-learning: jointly optimizing combined man-machine
system and taking
Advantage of feedback.
• Experimental paradigms for interpretable readable
signals: mapping the task to
The brain state of the user (or vice versa).
• Understanding algorithms and models within the context
of the neurobiology:
Building predictive models having neurophysiologic ally
meaningful parameters
And incorporating physically and biologically meaningful
priors.
The common structure of a Brain Computer Interface is the
following.
1) Signal Acquisition: the EEG signals are obtained from the
brain through invasive
or non-invasive methods (for example, electrodes). After,
the signal is amplified
and sampled.
2) Signal Pre-Processing: once the signals are acquired, it is
necessary to clean
them.
3) Signal Classification: once the signals are cleaned, they
will be processed and

Page | 8
Brain Computer interface
Classified to find out which kind of mental task the subject
is performing.
4) Computer Interaction: once the signals are classified,
they will be used by an
Appropriate algorithm for the development of a certain
application.

BCI common structure.

BRAIN SIGNALS

Brain patterns form wave shapes that are

commonly sinusoidal. Usually, they are measured from
peak to peak and normally range from 0.5 to 100 µV in
amplitude, which is about 100 times lower than ECG
signals. By means of Fourier transform power spectrum
from the raw EEG signal is derived. In power spectrum
contribution of sine waves with different frequencies are

Page | 9
Brain Computer interface
visible. Although the spectrum is continuous, ranging from
0 Hz to one half of sampling frequency, the brain state of
the individual may make certain frequencies more
dominant. Brain waves have been categorized into four
basic groups.

• Beta (>10 Hz)

• Alpha (8-13 Hz)
• Theta (4-8 Hz)
• Delta (0.5-4 Hz)

The best - known and most extensively studied

rhythm of the human brain is the normal alpha rhythm. It
can be usually observed better in the posterior and
occipital regions with typical amplitude about 50 µV (P-P).
Alpha activity is induced by closing the eyes and by
relaxation, and abolished by eye opening or alerting by any
mechanism (thinking, calculating).

BRAIN SIGNALS MEASUREMENT AND

PROCESING

Encephalographic measurements is consisted of

• Electrodes with conductive media

Page | 10
Brain Computer interface
• Amplifiers with filters
• A/D converter

Electrodes read signal from the head surface,

amplifiers bring the microvolt signals into range where they
can be digitalized accurately, converter changes signals
from analog to digital form, and personal computer process
this data.

Electrodes The EEG electrodes and their proper

function are critical for acquiring appropriately high quality
data for interpretation. Many types of electrodes exist,
often with different characteristics. Basically there are
following types of electrodes:

• Disposable (gel-less and pre-gelled types)

• Reusable disc electrodes (gold, silver, stainless steel
or tin)
• Headbands and electrode caps
• Saline-based electrodes
• Needle electrodes

For multichannel montages, electrode caps are

preferred, with number of electrodes installed on this
surface. Commonly used scalp electrodes consist of Ag-
AgCl discs, 1 to 3 mm in diameter, with long flexible leads
that be plugged into an amplifier. AgCl electrodes can
accurately record also very slow changes in potential.

Page | 11
Brain Computer interface
Needle electrodes are used for long time recordings and are
invasively inserted under scalp. In 1958, International
Federation on Electroencephalography and Clinical
Neurophysiology adopted standardization for electrode
placement called 10-20 electrode placement system. This
system standardized physical placement and designations
of electrodes an the scalp. The head is divided into
proportional distances from prominent skull landmarks
(nasion, pre auricural points and inions) to provide
adequate coverage of all regions of the brain. Label 10-20
designates proportional distance on percents between ears
and nose where points for electrodes are chosen. Best
results are in with invasive measurement techniques, where
electrodes are direct on the brain and are scanning only the
small location.

Picture above describes usual electrodes placement

Amplifiers and filters

Page | 12
Brain Computer interface

The signals need to be amplified to make them

compatible with A/D converters. Amplifiers adequate to
measure these signals have to satisfy very specific
requirements. They have to provide amplification selective
to the physiological signal, reject superimposed noise and
interference signals, and guarantee protection from
damages through voltage and current surges for both
patients and electronic equipment. The basic requirements
that a biopotential amplifier has no satisfy are:

• The physiological process to be monitored should

not be influenced in any way by the amplifier.
• The measured signal should not be distorted.
• The amplifier should provide the best possible
separation of signal and interferences.
• The amplifier has to offer protection of the patient
from any hazard of electric shock.
• The amplifier itself has to be protected against
damages that migh result from high input voltages as
they occur during the application of defibrillators or
electrosurgical instrumentation.

Page | 13
Brain Computer interface
Artifacts

Among basic evaluation of the EEG traces belongs

scanning for signal distortions called art effects. Usually it is
a sequence with higher amplitude and different shape on
comparison to signal sequences that doesn't suffer by anu
large contamination. The artifact in the recorded EEG may
be either patient- related or technical. Patient - related
artifacts are unwanted physiological signals that may
significantly disturb the EEG. Technical artifacts, such as AC
power line noise, can be decreased by decreasing electrode
impedance and by shorter electrode wires. The most
common EEG artifact sources can be classified in following
way:

Patient related:

• Any minor body movements

• EMG
• ECG (pulse, pace-maker)
• Eye movements
• sweating

Technical

• 50/60 Hz
• Impedance fluctuation

Page | 14
Brain Computer interface
• Cable movements
• Broken wire contacts
• Too much electrode paste or dried pieces
• Low battery

Excluding the artifact segments from the EEG traces

can be managed by the trained experts or automatically.
For better discrimination of different physiological artifacts,
additional electrodes for monitoring eye movement, ECG,
and muscle activity may be important.

In Brain science Institute RIKEN was developed the

ICELAB for signal processing which is describing the picture
below.

The preprocessing tools include: Principal

Component Analysis (PCA), prewhitening, filtering: High
Pass Filtering (HPF), Low Pass Filtering (LPF), Sub band
filters (Butterworth, Chebyshev, Elliptic) with adjustable

Page | 15
Brain Computer interface
order of filters, frequency sub bands and the number of sub
bands.

The post processing tools includes: Deflation and

Reconstruction ("cleaning") of original raw data by
removing undesirable components, noise or artifacts.
Moreover, the ICALAB Toolboxes have flexible and
extendable structure with; the possibility to extend the
toolbox by the users by adding their own algorithms. The
algorithms can perform not only ICA ;but also Second Order
Statistics Blind Source Separation (BSS) Sparse Component
Analysis (SCA), Nonnegative Matrix Factorization (NMF),
Smooth Component Analysis (SmoCA), Factor Analysis (FA)
and any other possible matrix factorization of the form
X=HS+N or Y=WX where H=W+ is a mixing matrix or a
matrix of basis He ICA/BSS algorithms are pure
mathematical formulas, powerful, but rather mechanical
procedures: There is not very much left for the user to do
after the machinery has been optimally implemented. The
successful and efficient use of the ICALAB vectors. Strongly
depends on a priori knowledge, common sense and
appropriate use of the preprocessing and post processing
tools.

Page | 16
Brain Computer interface

STRUCTURE OF BRAIN-COMPUTER INTERFACE

The common structure of a Brain-Computer Interface

is the following:

1) Signal Acquisition: the EEG signals are obtained from the

brain through invasive or non-invasive methods (for
example, electrodes).

2) Signal Pre-Processing: once the signals are acquired, it is

necessary to clean them.

3) Signal Classification: once the signals are cleaned, they

will be processed and classified to find out which kind of
mental task the subject is performing.

4) Computer Interaction: once the signals are classified,

they will be used by an appropriate algorithm for the
development of a certain application.

Page | 17
Brain Computer interface

BRAIN-COMPUTER INTERFACE ARCHITECTURE

The processing unit is subdivided into a preprocessing

unit, responsible for artifact detection, and a feature
extraction and recognition unit that identifies the command
sent by the user to the BCI. The output subsystem

generates an action associated to this command.

Page | 18
Brain Computer interface
Neuropsychological signals used in BCI applications.

Interfaces based on brain signals require on-line

detection of mental states from Spontaneous activity:
different cortical areas are activated while thinking different
things (i.e. a mathematical computation, an imagined arm
movement, a music composition, etc...). The information of
these "mental states" can be recorded with different
methods. Neuropsychological signals can be generated by
one or more of the following three: implanted methods,
evoked potentials (also known as event related potentials),
and operant conditioning. Both evoked potential and
operant conditioning methods are normally externally-
based BCIs as the electrodes are located on the scalp.
Describes the different signals in common use. It may be
noted that some of the described signals fit into multiple
categories. As an example, single neural recordings may
use operant conditioning in order to train neurons for
control or may accept the natural occurring signals for
control. Where this occurs, the signal is described under the
Implanted methods use signals from single or small groups
of neurons in order to control a BCI.

Evoked potentials (EPs) are brain potentials that are

evoked by the occurrence of a sensory stimulus. They are
usually obtained by averaging a number of brief EEG
segments time-registered to a stimulus in a simple task. In
a BCI, EPs may provide control when the BCI application

Page | 19
Brain Computer interface
produces the appropriate stimuli. This paradigm has the
benefit of requiring little to no training to use the BCI at the
cost of having to make users wait for the relevant stimulus
presentation. EPs offer discrete control for almost all users,
as EPs are an inherent response. Operant conditioning is a
method for modifying the behavior (an operant), which
Utilizes contingencies between a discriminative stimulus,
an operant response, and a reinforce to change the
probability of a response occurring again in a given
situation. In the BCI framework, it is used to train the
patients to control their EEG.as it is presented in table
shown in below, several methods use operant conditioning
on spontaneous EEG signals for BCI control. The main
feature of this kind of signals is that it enables continuous
rather than discrete control. This feature may also serve as
a drawback: continuous control is fatiguing for subjects and
fatigue may cause changes in performance since control is
learned.

Page | 20
Brain Computer interface

Common neuropsychological signals used in BCIs

Page | 21
Brain Computer interface
Human BCI research

Invasive BCIs

Invasive BCI research has targeted repairing damaged

sight and providing new functionality to paralyzed people.
Invasive BCIs are implanted directly into the grey matter of
the brain during neurosurgery. As they rest in the grey
matter, invasive devices produce the highest quality signals
of BCI devices but are prone to scar-tissue build-up, causing
the signal to become weaker or even lost as the body
reacts to a foreign object in the brain.

Jens Naumann, a man with acquired blindness, being

interviewed about his vision BCI on CBS's The Early Show

In vision science, direct brain implants have been used

to treat non-congenital (acquired) blindness. One of the first
scientists to come up with a working brain interface to
restore sight was private researcher William Dobelle.

Dobelle's first prototype was implanted into "Jerry," a

man blinded in adulthood, in 1978. A single-array BCI
containing 68 electrodes was implanted onto Jerry’s visual
cortex and succeeded in producing phosphates, the
sensation of seeing light. The system included cameras
mounted on glasses to send signals to the implant. Initially,
the implant allowed Jerry to see shades of grey in a limited
field of vision at a low frame-rate. This also required him to
be hooked up to a two-ton mainframe, but shrinking

Page | 22
Brain Computer interface
electronics and faster computers made his artificial eye
more portable and now enable him to perform simple tasks
unassisted.

Dummy unit illustrating the design of a BrainGate interface

In 2002, Jens Naumann, also blinded in adulthood,

became the first in a series of 16 paying patients to receive
Dobelle’s second generation implant, marking one of the
earliest commercial uses of BCIs. The second generation
device used a more sophisticated implant enabling better
mapping of phosphenes into coherent vision. Phosphenes
are spread out across the visual field in what researchers
call the starry-night effect. Immediately after his implant,
Jens was able to use his imperfectly restored vision to drive
slowly around the parking area of the research institute.

BCIs focusing on motor neuroprosthetics aim to either

restore movement in paralyzed individuals or provide

Page | 23
Brain Computer interface
devices to assist them, such as interfaces with computers
or robot arms.

Researchers at Emory University in Atlanta led by

Philip Kennedy and Roy Bakay were first to install a brain
implant in a human that produced signals of high enough
quality to simulate movement. Their patient, Johnny Ray,
suffered from ‘locked-in syndrome’ after suffering a brain-
stem stroke. Ray’s implant was installed in 1998 and he
lived long enough to start working with the implant,
eventually learning to control a computer cursor.

Tetraplegic Matt Nagle became the first person to

control an artificial hand using a BCI in 2005 as part of the
first nine-month human trial of Cyberkinetics
Neurotechnology’s BrainGate chip-implant. Implanted in
Nagle’s right precentral gyrus (area of the motor cortex for
arm movement), the 96-electrode Brain Gate implant
allowed Nagle to control a robotic arm by thinking about
moving his hand as well as a computer cursor, lights and
TV.

Partially-invasive BCIs

Partially invasive BCI devices are implanted inside the

skull but rest outside the brain rather than within the grey
matter. They produce better resolution signals than non-
invasive BCIs where the bone tissue of the cranium deflects
and deforms signals and have a lower risk of forming scar-
tissue in the brain than fully-invasive BCIs.

Page | 24
Brain Computer interface
Electro cortico graphy (ECoG) measures the electrical
activity of the brain taken from beneath the skull in a
similar way to non-invasive electroencephalography (see
below), but the electrodes are embedded in a thin plastic
pad that is placed above the cortex, beneath the dura
mater. ECoG technologies were first trialed in humans in
2004 by Eric Leuthardt and Daniel Moran from Washington
University in St Louis. In a later trial, the researchers
enabled a teenage boy to play Space Invaders using his
ECoG implant. This research indicates that it is difficult to
produce kinematic BCI devices with more than one
dimension of control using ECoG.

Light Reactive Imaging BCI devices are still in the

realm of theory. These would involve implanting a laser
inside the skull. The laser would be trained on a single
neuron and the neuron's reflectance measured by a
separate sensor. When the neuron fires, the laser light
pattern and wavelengths it reflects would change slightly.
This would allow researchers to monitor single neurons but
require less contact with tissue and reduce the risk of scar-
tissue build-up.

This signal can be either subdural or epidural, but is

not taken from within the brain parenchyma itself. It has not
been studied extensively until recently due to the limited
access of subjects. Currently, the only manner to acquire
the signal for study is through the use of patients requiring

Page | 25
Brain Computer interface
invasive monitoring for localization and resection of an
epileptogenic focus.

ECoG is a very promising intermediate BCI modality

because it has higher spatial resolution, better signal-to-
noise ratio, wider frequency range, and lesser training
requirements than scalp-recorded EEG, and at the same
time has lower technical difficulty, lower clinical risk, and
probably superior long-term stability than intracortical
single-neuron recording. This feature profile and recent
evidence of the high level of control with minimal training
requirements shows potential for real world application for
people with motor disabilities.

Non-invasive BCIs

As well as invasive experiments, there have also been

experiments in humans using non-invasive neuroimaging
technologies as interfaces. Signals recorded in this way
have been used to power muscle implants and restore
partial movement in an experimental volunteer. Although
they are easy to wear, non-invasive implants produce poor
signal resolution because the skull dampens signals,
dispersing and blurring the electromagnetic waves created
by the neurons. Although the waves can still be detected it
is more difficult to determine the area of the brain that
created them or the actions of individual neurons.

Animal BCI research

Page | 26
Brain Computer interface
Several laboratories have managed to record signals
from monkey and rat cerebral cortexes in order to operate
BCIs to carry out movement. Monkeys have navigated
computer cursors on screen and commanded robotic arms
to perform simple tasks simply by thinking about the task
and without any motor output. Other research on cats has
decoded visual signals.

Early work

Studies that developed algorithms to reconstruct

movements from motor cortex neurons, which control
movement, date back to the 1970s. Work by groups led by
Schmidt, Fetz and Baker in the 1970s established that
monkeys could quickly learn to voluntarily control the firing
rate of individual neurons in the primary motor cortex via
closed-loop operant conditioning, a training method using
punishment and rewards.

In the 1980s, Apostolos Georgopoulos at Johns

Hopkins University found a mathematical relationship
between the electrical responses of single motor-cortex
neurons in rhesus macaque monkeys and the direction that
monkeys moved their arms (based on a cosine function).
He also found that dispersed groups of neurons in different
areas of the brain collectively controlled motor commands
but was only able to record the firings of neurons in one
area at a time because of technical limitations imposed by
his equipment.

Page | 27
Brain Computer interface
There has been rapid development in BCIs since the
mid-1990s. Several groups have been able to capture
complex brain motor centre signals using recordings from
neural ensembles (groups of neurons) and use these to
control external devices, including research groups led by
Richard Andersen, John Donohue, Phillip Kennedy, Miguel
Nicolelis, and Andrew Schwartz.

Prominent research successes

Phillip Kennedy and colleagues built the first

intracortical brain-computer interface by implanting
neurotrophic-cone electrodes into monkeys.

Yang Dan and colleagues' recordings of cat vision

using a BCI implanted in the lateral geniculate nucleus (top
row: original image; bottom row: recording)

In 1999, researchers led by Yang Dan at University of

California, Berkeley decoded neuronal firings to reproduce
images seen by cats. The team used an array of electrodes
embedded in the thalamus (which integrates all of the

Page | 28
Brain Computer interface
brain’s sensory input) of sharp-eyed cats. Researchers
targeted 177 brain cells in the thalamus lateral geniculate
nucleus area, which decodes signals from the retina. The
cats were shown eight short movies, and their neuron
firings were recorded. Using mathematical filters, the
researchers decoded the signals to generate movies of
what the cats saw and were able to reconstruct
recognizable scenes and moving objects. Similar results in
humans have been since then achieved by researchers in
Japan (see below).

Miguel Nicolelis has been a prominent proponent of

using multiple electrodes spread over a greater area of the
brain to obtain neuronal signals to drive a BCI. Such neural
ensembles are said to reduce the variability in output
produced by single electrodes, which could make it difficult
to operate a BCI.

After conducting initial studies in rats during the

1990s, Nicolelis and his colleagues developed BCIs that
decoded brain activity in owl monkeys and used the
devices to reproduce monkey movements in robotic arms.
Monkeys have advanced reaching and grasping abilities
and good hand manipulation skills, making them ideal test
subjects for this kind of work.

By 2000, the group succeeded in building a BCI that

reproduced owl monkey movements while the monkey
operated a joystick or reached for food. The BCI operated in

Page | 29
Brain Computer interface
real time and could also control a separate robot remotely
over Internet protocol. But the monkeys could not see the
arm moving and did not receive any feedback, a so-called
open-loop BCI.

Diagram of the BCI developed by Miguel Nicolelis and

colleagues for use on Rhesus monkeys

Later experiments by Nicolelis using rhesus monkeys,

succeeded in closing the feedback loop and reproduced
monkey reaching and grasping movements in a robot arm.
With their deeply cleft and furrowed brains, rhesus monkeys
are considered to be better models for human
neurophysiology than owl monkeys. The monkeys were
trained to reach and grasp objects on a computer screen by
manipulating a joystick while corresponding movements by
a robot arm were hidden. The monkeys were later shown
the robot directly and learned to control it by viewing its
movements. The BCI used velocity predictions to control
reaching movements and simultaneously predicted hand
gripping force.

Other labs that develop BCIs and algorithms that

decode neuron signals include John Donohue from Brown

Page | 30
Brain Computer interface
University, Andrew Schwartz from the University of
Pittsburgh and Richard Andersen from Caltech. These
researchers were able to produce working BCIs even though
they recorded signals from far fewer neurons than Nicolelis
(15–30 neurons versus 50–200 neurons).

Donoghue's group reported training rhesus monkeys

to use a BCI to track visual targets on a computer screen
with or without assistance of a joystick (closed-loop BCI).
Schwartz's group created a BCI for three-dimensional
tracking in virtual reality and also reproduced BCI control in
a robotic arm. The group created headlines when they
demonstrated that a monkey could feed itself pieces of
zucchini using a robotic arm controlled by the animal's own
brain signals.

Andersen's group used recordings of premovement

activity from the posterior parietal cortex in their BCI,
including signals created when experimental animals
anticipated receiving a reward.

In addition to predicting kinematic and kinetic

parameters of limb movements, BCIs that predict
electromyography or electrical activity of muscles are being
developed. Such BCIs could be used to restore mobility in
paralyzed limbs by electrically stimulating muscles.

Commercialization and companies

Page | 31
Brain Computer interface
John Donoghue and fellow researchers founded Cyber
kinetics. Now listed on a US stock exchange and known as
Cyber kinetic Neurotechnology Inc, the company markets
its electrode arrays under the Brain Gate product name
and has set the development of practical BCIs for humans
as its major goal. The Brain Gate is based on the Utah Array
developed by Dick Norman.

Philip Kennedy founded Neural Signals in 1987 to

develop BCIs that would allow paralyzed patients to
communicate with the outside world and control external
devices. As well as an invasive BCI, the company also sells
an implant to restore speech. Neural Signals' Brain
Communicator BCI device uses glass cones containing
microelectrodes coated with proteins to encourage the
electrodes to bind to neurons.

Although 16 paying patients were treated using

William Dobelle's vision BCI, new implants ceased within a
year of Do belle’s death in 2004. A company controlled by
Dobelle, Avery Biomedical Devices, and Stony Brook
University is continuing development of the implant, which
has not yet received FDA approval for human implantation.

Ambient, at a TI developer’s conference in early 2008,

demoed a product they have in development call The
Audeo. The Audio is being developed to create a human-
computer interface for communication without the need of
physical motor control or speech production. Using signal

Page | 32
Brain Computer interface
processing, unpronounced speech representing the thought
of the mind can be translated from intercepted neurological
signals.

Mind ball is a product developed and commercialized

by Interactive Productline in which players compete to
control a ball's movement across a table by becoming more
relaxed and focused. Interactive Product line is a Swedish
company whose objective is to develop and sell easy
understandable EEG products that train the ability to relax
and focus.

There are three main consumer-devices commercial-

competitors in this area .which are going to launch such
devices primarily for g aiming- and pc-users.

Cell-culture BCIs

Researchers have built devices to interface with neural

cells and entire neural networks in cultures outside animals.
As well as furthering research on animal implantable
devices, experiments on cultured neural tissue have
focused on building problem-solving networks, constructing
basic computers and manipulating robotic devices.
Research into techniques for stimulating and recording from
individual neurons grown on semiconductor chips is
sometimes referred to as neuroelectronics or neurochips.

Page | 33
Brain Computer interface

World first: Neurotic developed by Caltech researchers

Jerome Pine and Michael Maher

Development of the first working neurotic was claimed

by a Caltech team led by Jerome Pine and Michael Maher in
1997.The Caltech chip had room for 16 neurons.

In 2003, a team led by Theodore Berger at the

University of Southern California started work on a
neurochip designed to function as an artificial or prosthetic
hippocampus. The neurochip was designed to function in
rat brains and is intended as a prototype for the eventual
development of higher-brain prosthesis. The hippocampus
was chosen because it is thought to be the most ordered
and structured part of the brain and is the most studied
area. Its function is to encode experiences for storage as
long-term memories elsewhere in the brain.

Page | 34
Brain Computer interface
Thomas Demarest at the University of Florida used a
culture of 25,000 neurons taken from a rat's brain to fly an
F-22 fighter jet aircraft simulator. After collection, the
cortical neurons were cultured in a Petri dish and rapidly
began to reconnect themselves to form a living neural
network. The cells were arranged over a grid of 60
electrodes and used to control the pitch and yaw functions
of the simulator. The study's focus was on understanding
how the human brain performs and learns computational
tasks at a cellular level.

Mental Task Classification for Brain Computer

Interface Applications

Mental task classification by recognizing

Electroencephalographic (EEG) patterns is an important and
challenging biomedical signal processing problem. Such
classification can be utilized to enable a patient to
communicate without any overt physical movement. This is
done just by the computer processing of the patient’s brain
waves as can be seen in the block diagram of Figure 1.
Developments of faster digital computers and better EEG
devices have motivated many researchers to work on BCI
systems.

So far the accuracy of classification has been one of

the main pitfalls of the developed BCI systems which
directly affect the decisions made as the BCI output. This
accuracy is affected by the quality of EEG signal and the

Page | 35
Brain Computer interface
processing algorithms. The processing algorithms include
preprocessing, feature extraction and feature classification.
In our previous research the effect of different feature
extraction algorithms and different number of EEG channels
[4] on classification accuracy was investigated. In the
current work, the effects of different types of classifiers on
the accuracy of classification are investigated and
compared. Density models. In the present research, the
classification of mental tasks using the Purdue University
EEG dataset and the EEG

Dataset from Department of Medical Informatics,

University of Technology Graz are investigated. Both
datasets are known and well established datasets in the BCI
field and are accessible from internet. Autoregressive (AR)
and adaptive autoregressive coefficients (AAR) were
extracted from the EEG windows for all classifiers. These
extracted features were inputted to the next stage of BCI,
which is the classifier. The same extracted features for all
classifiers facilitated the comparison of classifiers
efficiencies. The main focus was on investigation

The main focus was on investigation and comparison

of feed forward neural network, Bayesian quadratic,
Bayesian network, Fisher linear classifier and Hidden
Markov Models (HMM) in mental task classification. These
classifiers are known methods in the machine learning
literature. The classifiers are intentionally chosen to cover
both linear and nonlinear methods. The Gaussian mixture

Page | 36
Brain Computer interface
model is represented as a Bayesian network and this is the
first time that such a classifier is used for the EEG signal
classification [7].

We trained the Bayesian network and Hidden Markov

model using expectation maximization (EM) algorithm.
Mixture models are a type of density models. They are
comprised of a number of component functions that in our
case were Gaussians. These component functions are
combined to provide a multimodal density.

Figure1. Flow of the methodology

Military applications

The United States military has begun to explore

possible applications of BCIs beginning in 2008 to enhance
troop performance as well as a possible development by
adversaries. As one report concluded,

Page | 37
Brain Computer interface
The most successful implementation of invasive
interfaces has occurred in medical applications in which
nerve signals are used as the mechanism for information
transfer. Adversarial actions using this approach to
implement enhanced, specialized sensory functions could
be possible in limited form now, and with developing
capability in the future. Such threat potential would be
limited to adversaries with access to advanced medical
technology.

BCI ANDIT'S APPLICATIONS

In the context of BCI, EEG signals are mainly analyzed

in time, frequency, and time-frequency domains. Most of
the research groups work in the frequency domain and
extract the information characterizing mental activities
from the nonparametric and parametric spectral
representations of EEG. Also joint spectral properties of the
EEG components are analyzed do detecting particular
emotional states. The relationship between the time
courses of the signals coming from different electrodes
serves as an indication of motor activities. Useful
information can alos be extracted from particular brain
configurations that can be interpreted in terms of brain
states.

Time-frequency and time-scale representations of EEG

signals were exploited for finding those neuronal groups

Page | 38
Brain Computer interface
that synchronize their activity as a response to a particular
stimulus. From that above considerations it can be stated
that mental activities, when mapped onto the time-
frequency representation of EEG signals, display a picture
that illustrates the cooperative activity consists in analyzing
the joint time-frequency-space correlations between the
components of an EEG signal.

The Brain Communicator is well-suited for patients

who are severely paralyzed or locked-in, and who therefore
have very limited options in their communications with
others, such as ALS (Amyotrophic Lateral Sclerosis) patients
on a ventilator. Patients must be cognitively intact with no
history of epilepsy.

There are many applications that are still in

developement but also some of them are quite useful. At
Graz University of technology was developed BCI that uses
oscillatory EEG signals, recorded during specific mental
activity, as input and provides a control option by its
output. The obtained output signals are presently evaluated
for different purposes, such as cursor control, selection of
letters or words, or control of a prosthesis or orthosis. They
are already working on Direct Brain Interface that
recognizes voluntary activity within the brain and can be
used to control assistive technologies without requiring any
physical movement. This technology uses the

Page | 39
Brain Computer interface
electrocorticogram (ECoG), recorded from implanted
electrodes which are placed directly on the cortex.

There are two choices. One is the patented

Neurotrophic Electrode, whereby the electrode tip is
implanted 5mm under the surface of the brain and the
outer end is attached to amplifiers and FM transmitters
located on the skull, under the scalp. No wires or batteries
are used. Power is provided by a power induction system
similar to your toothbrush holder that charges the
toothbrush overnight. This implantation requires major
surgery lasting about 10 hours. The neural signals are
transmitted to and processed by a computer to activate a
switch or drive a cursor and hence provide communication.
The other option is to implant a patented conductive skull
screw that does not enter the brain. It records from local
field potentials over the surface of the cortex, rather like a
very pricise EEG (electroencephalogram). These signals can
be used to activate a switch and hence provide
communication.

Before implantation, the subject undergoes a

functional MRI. This determines if there is brain activity
even when there is no movement. The implant target is
thus chosen. The system is also used at surgery to guide
the surgeon onto target for accurate implantation. The
Army is also interested in using BCI to make faster
responses possible for figter pilots. The combination of EEG

Page | 40
Brain Computer interface
signals and artifacts combine to create a signal that can be
used to fly a virtual plane. One can imagine that the
military would have multiple uses for a system that speeds
up response times in areas as tactical maneuvering and
even targeting and firing weapons. Currently, the main
focus of Air Force research is for Alternative Control
Technology (ACT). The goal of the ACT program is to enable
communication with computers while the computer users’
hands are busy with other tasks.

Page | 41
Brain Computer interface
Present and Future

The practical use of BCI technology depends on an

interdisciplinary cooperation between neuroscientists,
engineers, computer programmers, psychologists, and
Rehabilitation specialists, in order to develop appropriate
applications, to identify appropriate users groups, and to
pay careful attention to the needs and desires of Individual
users.

The prospects for controlling computers through

neural signals are indeed Difficult to judge because the field
of research is still in its infancy. Much progress has been
made in taking advantage of the power of personal
computers to perform the operations needed to recognize
patterns in biological impulses, but the search for new and
more useful signals still continues.

If the advances of the 21st century match the strides

of the past few decades, direct neural communication
between humans and computers may ultimately mature
and find widespread use. Perhaps newly purchased
computers will one day arrive with biological signal sensors
and thought-recognition software built in, just as keyboard
and mouse are commonly found on today's units.

Page | 42
Brain Computer interface

Page | 43
Brain Computer interface

CONCLUSION

As we can see there are many useful applications of

brain computer interface. It can be very helpful for people
with moving disabilities as human - machine interface. But
it can be also used for control of human body muscles.
There are also many possibilities in military domain. Last
are are the applications for making our lives easier. So one
day maybe all people are wearing bci-caps and using hands
only for eating. Or even without caps but with implants
right in CNS.To bring this in reality it has to been d

The role of signal processing is crucial in the

development of a real-time Brain Computer Interface. Until
recently, several improvements have been made in this
area, but none of them has been entirely successful. The
goal of creating more effective classification algorithms,
have focused numerous investigations in the search of new
techniques of feature extraction. A BCI has to be useful for
a wide variety of tasks, for instance, when a BCI is used as
the main control device for a handicapped individual. In this
study, signals from five different tasks were used as the
basis for tests. Among the five tasks, multiplication problem
solving, geometric figure rotation, mental letter composing,
visual counting, and A baseline task where the subject was
instructed to think about nothing in particular, two
(“rotation” and “letter”) had been problematic in a previous

Page | 44
Brain Computer interface
classification method based on autoregressive models. The
discovery of a new method founded on Time Frequency
Representations was of vital importance not only for these
two tasks, but also for future research.

Page | 45
Brain Computer interface

BIBILOGRAPHY

J.R. Wolpaw, D.J. McFarland, G.W. Neat, and C.A. Forneris.

"An EEG-based
Brain-computer interface for cursor control". Electroenceph.
Clan. Neurophysiology. v.78, pp. 252—258, 1991.

G. Pfurtscheller, J. Kalcher, Ch. Neuper, D. Flotzinger, and

M. Pregenzer, "On-line EEG classification during externally-
paced hand movements using a neural network
basedClassify er", Electroenceph. Cline. Neurophysiol.",
v.99, pp. 416—425, 1996.

J.M. Belsh and P.L. Schiffman (editors), Amyotrophic lateral

sclerosis: diagnosis
and management for the clinician, Future Publishing Co.,
Inc., Armonk, NY, 1996.
[N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iversen, B.
Kotchoubey, A. Kubler, J. Perelmouter, E. Taub, H. Flor. "A
Spelling Device for the Paralysed". Nature, v.398, pp. 297—
298, 1999.

S. Lin, Y. Tsai, and C Liou, "Conscious mental tasks and their

EEG signals",
Medical and Biol. Engineering and Comput., v.31, pp. 421—
425, 1993.

Page | 46
Brain Computer interface

Page | 47