AUTOMATION USING BRAIN COMPUTER

INTERFACE TECHNOLOGY

A PROJECT REPORT

Submitted by

S HAMEED ASMATH - 210419115013

SAI DINESH R S – 210419115041

In partial fulfillment for the award of the degree

Of
BACHELOR OF TECHNOLOGY

IN

MECHATRONICS ENGINEERING

CHENNAI INSTITUTE OF TECHNOLOGY (AUTONOMOUS)

(Affliated to Anna University, Chennai-600069)

ANNA UNIVERSITY : CHENNAI 600 025

APRIL 2023
 ANNA UNIVERSITY : CHENNAI 600 025

BONAFIDE CERTIFICATE

Certified that this project report “AUTOMATION USING BRAIN COMPUTER

INTERFACE ” is the bonafide work of “SAI DINESH R S (210419115041) ,

HAMEED ASMATH S (210419115013) who carried out the project work under

my supervision.

Submitted for University viva voice examination held on ………………………….

at Chennai Institute of Technology, Chennai-600069.
 ACKNOWLEDGEMENT

It is our first and foremost duty to express our heartily gratitude and
allegiance to our beloved chairman Shri. P SRIRAM for being our
inspiration throughout the entire period of course.

We would like to thank our Principal Dr. A RAMESH Ph.D., for his
constructive criticism towards improving our project.

We would like to extend our faithful thanks to Mr. SHANUMUGASELVAM

Ph.D.,Head of the Department, Mechatronics Engineering for his sustained
help, guidance, and inspiration in doing this project and making this a
successful one.

We would like to thank our guide Mr. P S GOKUL M.TECH., for his
guidance and for giving entire support to us in doing this project. We also
thank him for giving his innovative ideas.

We would like to express our heartfelt gratitude to all the faculty and
supporting staff of the Mechatronics Engineering Department for the help
they extended for the completion of the project.

This project is dedicated to our parents and friends who were with us during
the tough times by extending their full support to us
 ABSTRACT

The Brain computer Interfaced automation is used to help the paralysed people

to operate all kinds of home appliances . This will make a revolutionary change as

the device are indirectly connected to the human brain and can be switched based

on their moods or electrical activities of neurons which has some threshold value .

This project will give the equal abilities of normal humans automation like motion

detection , image sensing etc. but with help of brain signals. Since there are various

kinds of researches are going on to trace the activities of brain and its full

potential , These kinds of automation are just basics of that research , which can

give the ability to control any kind of device with their brain signals . These

automation does not involve any physical muscle moment, These are purely

dependent on pattern waves of brain like sleep pattern, Rapid Eye Movement

(REM) , blinking of eyes. The physically challenged people can also use this

devices to operate their device. Technology can make people lives quality and

proves even paralysed people can also control devices like normal peoples . This

project involves receiving brain signals of human brain and processing it using

DSP ( Digital signal processing ) and converting this analog signal to digital signal

using ADC converter circuit and then transmitting it to microprocessor and

transmitting the signal to relays to switch the output devices

 CONTENTS

S. NO PARTICULARS PAGE NO.

Acknowledgement..............................................................3
Abstract...............................................................................4
Contents............................................................................. 5
List of Figures..................................................................... 7
List of Tables.......................................................................8
1. Introduction......................................................................... 9
1.1. Background......................................................................... 9
1.2 Team Members..................................................................10
1.3 Project Management......................................................... 10
1.4 Literature Review...............................................................11
1.5 Block Diagram................................................................... 13
1.6 Bio Signals and its Types................................................... 13
1.7 Brain Computer Interface...................................................15
1.71 Flow Map Description…………………………………15
1.72 Process Map Description………………………………16
1.8 Electroencephalography………………………………….17
1.9 Components of BCI………………………………………18
2. Literature Review…………………………………………18
 2.1 Brain computer interface Technology……………………19
2.1.1 Abstract………………………………………………21
2.1.2 Methodology…………………………………………21
2.2 Brain Waves sensor………………………………………21
2.2.1 Abstract………………………………………………21.
2.2.2 Methodology………………………………………….22
2.3 Sensors of detection of Brain signals……………………..24
2.3.1 Abstract……………………………………………….24
2.3.2 Methodology………………………………………….25
3. Methodology………………………………………………26
3.1 Types of Electrode........................................................................26
3.1.1 Invasive Type……………………………...26
3.1.2 Non Invasive Type………………………...26

3.2 BCI Three sub-Types................................................................... 27

3.3 Basic Components of Brain Component System.........................31
3.4 Signal Range of EEG.................................................................. 35
3.5 NEURO SKY MINDWAVE MOBILE SENSOR ……………38
4. Implementation………………………………………….......40
4.1 Open BCI..................................................................................... 40
4.2 Muse ............................................................................................41
4.3 Melon...........................................................................................42
4.4 Application of Brain Computer Interface....................................47
4.5 Neurospeller…………………………………………….…...47
4.6 Operator Monitoring Application……………………….…..48
4.7 Forensics Lie Detection…………………………….……….49
4.8 Entertainment……………………………………….…….....50
4.9 Health…………………………………………..……………51
5. Conclusion………………………………………………….. 53
Features of BCI……………………………………….47
References..........................................................................49
 LIST OF FIGURES

FIG NO. PARTICULARS PAGE NO.

1.5 Block diagram of Smart BrainWave sensor… 13

1.5.1 Process Flow Map 16
1.5.2 NeuroFeedBack 18
1.5.3 Electrode Position 25
1.5.4 Signal Range of EEG 29
1.5.5 Systematic approach of process 31
1.6.1 EMOTIV 33
1.6.2 OpenBCI 34
1.6 Mose…………………………………………….35
1.7 Melon……………………………………………37
1.8 Zigbee Module …………………………………38
1.9 Microcontroller…………………………………39
1.7 Neurospellar…………………………………….41
1.8 Operator Monitoring System……………………42
1.9 Entertainment……………………………………44
1.10 Health……………………………………………45
1.11 Benefits of BCI………………………………….47
 LIST OF TABLES

TABLE NO. PARTICULARS PAGE NO.

1. Comparison of EEG Bands 30

2. Components of BCI… 18
3. Systematic approach of the process 31
 CHAPTER 1
INTRODUCTION

1.1 Background

Though the recent developments of science and technology has drastically

changed the way a normal person lives his life , there are certain groups of people
who have not been able to be benefit from this development. On particular
paralysed people with have limited mobility are still living a miserable life.

These Brain computer interfaced automation aims to provide control over

devices to operate using the brain waves and their neural activity
Human brain controls body function, such as heart activity,movement, speech, but
also thinking itself, memory or emotion perception
Brain activity could be measured by the neurologic examination method
–electroencephalography (EEG). The principle of this method is capturing
electric potential. If the central nervous system is damaged, some body functions
may be restricted. Brain computer interface systems could offer these people
improved communication and
independence.
Recent developments in BCI technology may see such hands-free control
method realised. A BCI is a communication and control system in which the
thoughts of the human mind
are translated into real-world interaction without the use of the common neural
pathways and muscles.

EXAMPLE
 users of the BCI system can switch a light or change TV channels using only
their imagination and without any physicalmovement. Recent advances in the human
brain and BCIresearch reveal that BCI-based devices and technologies can play a
significant role in the future [1] – [4]

1.2 Team Members

For this project two of us have worked together. Followings are the names
and College roll number of ours.

1. SAI DINESH R S – 2104219115041

2. HAMEED ASMATH S – 210419115013

1.3 Project Management

This project constituted mechanical design as its major part as well as embedded
system design. So the work had to be divided accordingly.
 1.5 BLOCK DIAGRAM

FIG 1.5 BLOCK DIAGRAM OF BCI INTERFACE

1.6 BASIC PROCESS DESCRIPTION :

1.6.1 BIO SIGNALS AND ITS TYPES

Biological signals, or biosignals, are space, time, or space-time records of a

biological event such as a beating heart or a contracting muscle. The electrical,
chemical, and mechanical activity that occurs during this biological event often
produces signals that can be measured and analyzed.
 FIG 1.6.1 TYPES OF BIO SIGNALS

There are various kinds of bio signals :

● Electromyogram (EMG)

● electroneurogram (ENG)

● electrocardiogram (ECG)

● electrooculogram (EOG)

● Galvanic skin response

● Magneto encephalography (MEG)

● electroencephalogram (EEG)

FIG 1.6.2 BRAIN IMAGING

1.7 BRAIN COMPUTER INTERFACE :

Communication using Thoughts of Brain (EEG) without using any Muscle

control, Especially for Severely Paralyzed people

A brain-computer interface (BCI) is a computer-based system that

acquires brain signals, analyzes them, and translates them into commands that are
relayed to an output device to carry out a desired action. In principle, any type of
brain signal could be used to control a BCI system.

1.7.1 PROCESS FLOW MAP:

FIG 1.7.1 PROCESS FLOW MAP

1.7.2 FLOW MAP DESCRIPTION :

The brain wave signals which are transmitted from the brain are received
by sensor where the first stage of the flow process starts which is called Signal
Acquisition
Then the signal is pre-processed and features are extracted and classification
and translation process occurs
Then the suitable application is interfaced and the command is executed and
the Feedback is passed to the user.

FIG 1.7.2 BIO SIGNAL

1.8 ELECTROENCEPHALOGRAPHY:

Electroencephalography (EEG) is the recording of electrical activity

along the scalp. EEG measures voltage fluctuations resulting from ionic current
flows within the neurons of the brain
German physiologist and psychiatrist Hans Berger (1873–1941) recorded the first
human EEG in 1924
 1.8.1 NEUROFEEDBACK :

Neurofeedback is direct training of brain function, by which the brain learns

to function more efficiently.
Neurofeedback is used to teach children with ADHD how to calm and
concentrate
 FIG 1.8.1 NEURO FEEDBACK FLOW MAP
1.9 COMPONENTS OF BCI :

A BCI generally consists of three main components :

1. A Signal acquisition module which consist of electrode and Filtering equipment
and amplifier
2. A Signal processing module (ASIC, DSP)
3. A control module (Microcontroller and driver )

FIG 1.9.1 PROCESS FLOW MAP OF BCI

 CHAPTER 2
LITERATURE REVIEW

2.1Brain computer interface Technology

2.1.1 ABSTRACT :

BCI’s provide these users with communication channels that do not

depend on peripheral nerves and muscles. This article summarizes the first
international meeting devoted to BCI research and development. Current BCI’s use
electroencephalographic (EEG) activity recorded at the scalp or single-unit activity
recorded from within cortex to control cursor movement, select letters or icons, or
operate a neuro prosthesis. 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 BCI which recognizes the
commands contained in the input and expresses them in device control. Current
BCI’s have maximum information transfer rates of 5–25 b/min. Achievement of
greater speed and accuracy depends on improvements in signal processing,
translation algorithms, and user training. These improvements depend on increased
interdisciplinary cooperation between neuroscientists, engineers, computer
programmers, psychologists, and rehabilitation specialists, and on adoption and
widespread application of objective methods for evaluating alternative methods.
The practical use of BCI technology depends on the development of appropriate
applications, identification of appropriate user groups, and careful attention to the
needs and desires of individual users. BCI research and development will also
benefit from greater emphasis on peer-reviewed publications
2.1.2 METHODOLOGY

The goal of signal analysis in a BCI system is to maximize the signal-to-noise

ratio (SNR) of the EEG or single-unit features that carry the user’s messages and
commands. To achieve this goal, consideration of the major sources of noise is
essential [44]. Noise has both non neural sources (e.g., eye movements, EMG,
60-Hz line noise) and neural sources (e.g., EEG features other than those used for
communication). Noise detection and discrimination problems are greatest when
the characteristics of the noise are similar in frequency, time or amplitude to those
of the desired signal. For example, eye movements are of greater concern than
EMG when a slow cortical potential is the BCI input feature because eye
movements and slow potentials have overlapping frequency ranges. For the same
reason, EMG is of greater concern than eye movements when a rhythm is the input
feature. In the laboratory particularly, it is important to record enough information
(e.g., topographical and spectral distributions) to permit discrimination between
signal and noise. Non-neural noise such as EMG is of particular concern because a
user’s control over it can readily masquerade as actual EEG control. Non-neural
noise produced by reflex activity may occur even in users who lack all voluntary
muscle control. In this case, the non neural noise will not support communication,
but can degrade BCI performance by reducing the SNR. It is also important to
distinguish between different neural features. The visual rhythm is a source of
noise when the rhythm is the feature being used for communication. While
appropriate temporal and spatial filtering methods can help make such distinctions,
signals from different sources might well have similar frequency spectra and
similar spatial distributions (e.g., [45]). If non neural and neural noise can be
detected online, in the course of BCI operation, its impact on operation can be
greatly reduced or eliminated. For example, in a BCI driven by slow cortical
potentials, input contaminated by eye movements can be rejected [3]. This
approach can also induce the user to reduce the production of such noise.

2.2 BRAIN WAVE SENSOR :

2.2.1 ABSTRACT :
Electroencephalograph(EEG)is regularly used as a part of a combination
coherent fields. Shockingly, business devices are overall amazingly exorbitant,
costing an expansive number of dollars. Starting late, devices costing under $200
have been made open.
The Think Gear Aisc Model (TGAM) chip , made by Neurosky Inc., is
starting now the base exorbitant business EEG device, costing under $100. The
paper presents how to control mind waves and examining cerebrum information
for doing some usable things in regular day to day existence with this
information. Mind information is gathered by a headset with terminals and
some EEG hardware. The implementation of the Virtual Reality (VR) on game is
practical for in various fields, especially in the field of Education. The
implementation of a mobile based VR game is example where the players of game
feel as in the real world. However, the VR game has the weakness on limited
interaction of their player with the virtual environment created by the game.
Currently, the interactions pass through the buttons on mobile phone and joysticks.
For this reason, this research investigates the alternative media to control the
virtual environment of the game using brain sensor. The prototype was created
using “mindwave neurosky” as brain sensor and thingkgear as sensor drive to
construct the experiment of mobile based virtual reality math game. This research
tests three modes signal including meditation, attention and beta signal. A
meditation signal was taken when the player open and close the eye. While
attention and beta signals were taken when the player focuses
2.2.2 METHODOLOGY :
The principal thing to note is that each time that I wore my headset it took
me no less than 15 minutes to interface. As per my applications, the gadget
wasn't sitting appropriately on my head. I needed to alter it all the time on my
make a beeline for get a legitimate flag. Possibly I have an extremely bizarre
head, yet this same issue additionally happened to my companions who attempted
it on. Possibly they have an abnormal head too… I believe it's spare to state
the EEG headsets should be set painstakingly to get appropriate signs. With the
smallest removal EEG-wave movement can be adjusted. So in this manner it is
better that the gadget is a tiny bit critical when you put it on your head. At any rate
that is the manner by which it should work. We've found that the level of
mental control over the flag differs from individual to individual. The most
sensible trial of the gadget's authenticity would be a correlation with a therapeutic
gradeEEG. While we have not possessed the capacity to test this ourselves,
NeuroSky has distributed the consequences of such a correlation. Their
discoveries propose that the NeuroSky chip conveys a similar Flag.
Obviously, NeuroSky has a huge stake in a positive result for this kind of test.
The procurement of mind waves signs will be completed with a headset. In
this thought 2 distinct assortments of headsets are utilized. One is made with
a quick TGAM module (57600baud transmission rate) and one is made by
adjusting a business Mindflex headset which likewise uses a moderate TGAM
module (9600baud transmission rate). Both headsets sends cerebrum wave
signals by means of bluetooth. The quick headset is utilized to send signs to any
Android cell phone utilizing an open source application called Brainwaves
Visualiser which can be found at Google Play store for nothing out of pocket. This
application can demonstrate us bright graphical observing of mind flags on
real-time. It is utilized to screen real-time cerebrum action. The other slower
headset is custom worked for transmitting real-time brainwave signs to an
Arduino processor which can process and send to a PC over USB. These signs can
be observed on PC screen on real-time representation or can be spared to a
document to be prepared later as sessions. The real-time plotting and realistic
checking is accomplished by a program called BrainGrapher which is
composed in Processing programming. The session recording of the signs to a
document can be completed by means of any terminal program, for example,
TeraTerm or Terminal.exe. These sessions are spared to a content log document in
CSV arrange for later preparing in Excel tables and outlining for
examination.
Another system is built for the implementation of actual usage of brain
signals to remotely control a mechanical device. As in figure 1 For the purpose, a
dc motor with a fan is used to demonstrate the actual controlling of the device
remotely with brain signals. The motor speed of the fan is controlled using brain
signals (more specifically the Attention values) which shows the level of
concentration and focusedness of the brain activity. The more you concentrate
or get focused, the more motor speed. Simply this experiment shows that you
can actually control the speed of a motor with your brain. The system circuit
for the experiment is as follows: Cut down repeat (Delta, theta, alpha)
brainwaves should be more present in the midst of thought, while the higher (Beta,
Gamma) cerebrum waves should be more present in the midst of the fixation
mind entertainments. In figure 2 you can see the midpoints of each wave between
each errand. If you consider what I had expected, this did not look good. As
demonstrated by this data my cerebrum was more thought about, also more
connected with in the midst
of my appearance task.
2.2 WIRELESS SENSOR FOR BRAIN ACTIVITY

2.3.1 ABSTRACT :
Over the last decade, the area of electroencephalography (EEG) witnessed a
progressive move from high-end large measurement devices, relying on accurate
construction and providing high sensitivity, to miniature hardware, more
specifically wireless wearable EEG devices. While accurate, traditional EEG
systems need a complex structure and long periods of application time, unwittingly
causing discomfort and distress on the users. Given their size and price, aside from
their lower sensitivity and narrower spectrum band(s), wearable EEG devices may
be used regularly by individuals for continuous collection of user data from
non-medical environments. This allows their usage for diverse, nontraditional,
non-medical applications, including cognition, BCI, education, and gaming. Given
the reduced need for standardization or accuracy, the area remains a rather incipient
one, mostly driven by the emergence of new devices that represent the critical link
of the innovation chain. In this context, the aim of this study is to provide a holistic
assessment of the consumer-grade EEG devices for cognition, BCI, education, and
gaming, based on the existing products, the success of their underlying
technologies, as benchmarked by the undertaken studies, and their integration with
current applications across the four areas. Beyond establishing a reference point,
this review also provides the critical and necessary systematic guidance for
non-medical EEG research and development efforts at the start of their
investigation.
2.3.2 Methodology :

The paper aims to critically review the market of EEG consumer-level products
and their suitability and prior usage within studies relating to brain activity. The
discussion will focus in particular on the nature of the EEG signals recorded, the
type of research that has been conducted and, where available, the performance of
the consumer-grade device versus the medical-grade devices. In the context of
virtual and augmented reality, assisted living, motor and neural-supportive devices,
and IoT development, the requirements for EEG products are constantly evolving,
both to make full use of the technological progress and the increasing customer
demands. From an effectiveness and privacy perspective, these technologies are
becoming more secure.
 CHAPTER – 3
METHODOLOGY

3.1 TYPES OF BCI ELECTRODES :

Depending on the number of electrodes and its types , the brain computer
interface sensor electrode are classified into two types . they are
1. Invasive type
2. Non Invasive type

3.1.1 INVASIVE TYPE :

These are the electrodes which are involved attaching electrodes directly to
the brain tissue . These kinds of electrodes are most commonly used in hospitals
to conduct surgery as they need to sense the brain signals more accurately
The patients brain gradually adapts its signals to be sent through the
electrodes’ And the signals are received by the concern operating feedback
system

Fig 3.1.1 Invasive type

3.1.2 NON INVASIVE TYPE :

FIG 3.1.2. NON INVASIVE TYPE

These involves putting electrodes on the scalp of the patient and taking
readings from it like a helmet the electrode covers all the parts of the head to get
different signals
Non-Invasive Brain Computer Interfaces means electrodes are emplaced on
the surface of the skull to record changes in EEG state. The signal, which is
producing has the weakest values in spite of this, the non-invasive BCI is the
safest and easiest way to record EEG [2]. The schema of brain computer interface
system
These electrodes are most important while taking the accurate brain signals .
A small error leads to improper detection of signals and lacks in accuracy and
precision. Even though the size of electrode is compactable.
It should be maintained in a quite high state and under ambient normal room
temperature , excess heat can make the circuit shorting.
 3.2 THREE BCI SUB-TYPES :

• Active BCI:

“An active BCI is a BCI which derives its outputs from brain activity which is

directly consciously controlled by the user, independently from external events, for
controlling an application.”

FIG 3.2.1 ACTIVE BCI

• Reactive BCI:

“A reactive BCI is a BCI which derives its outputs from brain activity
arising in reaction to external stimulation, which is indirectly modulated by the
 user for controlling an application.”

FIG 3.2.2 REACTIVE BCI

• Passive BCI:

“A passive BCI is a BCI which derives its outputs from arbitrary brain
activity without the purpose of voluntary control, for enriching a human-computer
interaction with implicit information.”
 fig 3.2.2 Passive BCI

3.2.1 VOLUME CONDUCTION :

Fig 3.2.1 volume conduction

● Neural activity is conducted through the brain volume to the scalp and sensors by
Volume conduction
● Volume conductor models that are commonly used to describe the EEG and
MEG neglect holes in the skull, lesions, the ventricles, and anisotropic
conductivity of the skull. To determine the influence of these features,
simulations were carried out using the finite element method.
 3.3 BASIC COMPONENTS OF BRAIN COMPUTER INTERFACE :

ELECTRODE POSITIONS :

FIG 3.3.1 ELECTRODE POSITIONS

These are basic electrodes which are used most frequently . This style is used
to cover the head. So that signals can be referred easily by the electrodes. This
major consist of 10 to 20 electrode system . They are various kinds of electrodes
 FIG 3.3.2 ELECTRODES

There are various sensor strip material available which decides the
accuracy of the measurements . Since there are high demand for semi conductors
, the rate of this electrode increases , as it fully depends upon the semiconductor
materials for its construction
EEG sensors are placed on a participant's head, then the electrodes
non-invasively detect brainwaves from the subject. EEG sensors can record up
to several thousands of snapshots of the electrical activity generated in the brain
within a single second.
EEG neurofeedback machines, also called EEG biofeedback machines,
are EEG systems that allow a subject to see their brain activity in real-time.
During this type of EEG monitoring, the EEG machine is synced to a computer or
a cloud device, and the subject's brain waves are displayed on a computer screen.
EEG machines — which include portable EEG machines, ambulatory EEG
machines and EEG neurofeedback machines or EEG biofeedback machines —
are monitoring devices used for EEG recordings. EEG stands for

FIG 3.3.3 PINS

electroencephalography, the non-invasive method of monitoring the brain’s

electrical signals.
 FIG 3.3.4 SPRING LOADED PINS

Most of these devices contain electrodes, amplifiers, filters and an analog to

digital converter. Wireless or portable EEG machines contain a battery, while
wired EEG machines will be hooked up directly to a computer.

An ambulatory EEG machine is used during an extended EEG reading. Often

used to diagnose sleep disorders or seizure disorders, ambulatory EEGs record for
up to 72 hours while traditional EEG tests record for 1-2 hours.
3.4 SIGNAL RANGE OF EEG :
 FIG 3.3.6 SIGNAL CHIP

3.4.1 COMPARISON OF EEG BANDS :

3.4.1.1 SYSTEMATIC APPROACH OF PROCESS :

FIG 3.3.7 SYSTEMATIC PROCESS MAP

 The electrodes is placed on the subject’s head and some of amplifiers are
also used to amplify the signal coming out from the sensor and to process it .
The amplification of signals, defined as an increase in the intensity of a
signal through networks of intracellular reactions, is considered one of the
essential properties in many cell signal pathways. Then ADC converters are used
to convert analog signal to digital signal , then the signal is passed to the
oscilloscope and then it returns as EEG graph on the given paper .

AVAILABLE SOFTWARE TOOLS :

● Opensig
● BCI2000
● EEGLAB
● Open VIBE
● BCILAB

AVAILABLE HAND BANDS :

● Neurosky
● Emotiv
● Open bci
● Muse
● Melon
● Biopack

3.4 NEURO SKY MINDWAVE MOBILE SENSOR :

These are headbands which are majorly used till now. It consists of three
essential components . they are
● EEG electrode
● TGAM module
● Battery module
● Bluetooth module
● Ear clip

Neuro sky is one of the most promising semiconductor company which can
manufacture quality sensors and other electrical and electronic equipments
FIG 3.4 NEURO SENSOR

3.4.1 SPECIFICATIONS:

POC
14 EEG channels + 2 references 1channel locations:
AF3, F7, F3, FC5,
T7, P7, O1, O2, P8, T8, FC6, F4, F8, AF4
Insight
5 EEG channels +
2 references Signals
5 channels:
AF3, AF4, T7, T8, Pz

CHAPTER 4
IMPLEMENTATION

4.1 OPEN BCI :

FIG 4.1 8 and 16 EEG channel

●

4.2 MUSE :
Muse is a wearable device in the form of a headband that senses the electrical
rhythms of the brain (EEG). The headband is coupled with a smartphone app
(Calm) that monitors the user's brain electrical activity and gives immediate
feedback so that a “calm” or meditative pattern can be achieved.
These are hair band sensors in which appears closed to the head , It has
unique and different design to isolate from his competitor . It sends the signal via
Bluetooth module to arduino or any other micro controller.
Thus microcontroller undergoes signl conditioning on MATLAB , various
signal are correctly processed and noise are removed

FIG 4.2.1 MUSE

4.3 MELON :

Melon measures this global electrical activity by placing three electrodes on the
forehead region, with the primary electrode on FP1.
Melon is a handy device with an EEG-sensor, which allows users to monitor
current brain activity of the user. It’s intended to work in conjunction with iOS or
Android phones and tablets.
The manufacturer of Melon markets it as a gadget for daily use, which allows its
users to obtain statics about brain waves activity in different situations. Unlike
many similar devices, it offers really light weight and convenient design.
 4.3.1 BIOPAC MEDICAL GRADE EEG :

EEG machines are used for diagnosing a variety of neurologic diseases,

such as epilepsy, convulsive disorders, brain death, cerebrovascular lesions,
ischaemia, and problems associated with trauma. The brain generates
rhythmical potentials, which originate in the individual neurons of the brain.
Modern EEG monitors use computers to analyse and generate large amounts
of electroencephalographic data, which are processed and displayed in various
formats. EEG electrodes give high skin contact impedance as compared with
ECG electrodes. EEG preamplifiers are generally designed to have a very high
value of input impedance to take care of high electrode impedance.

FIG 4.3.1 MEDICAL EEG

Standard 10-20 EEG Placement.
Available in small ,Medium and Large size.
4.3.2 ZIGBEE MODULE :
Zigbee is a standards-based wireless technology developed to enable
low-cost, low-power wireless machine-to-machine (M2M) and internet of
things (IoT) networks. Zigbee is for low-data rate, low-power applications and is
an open standard.
FIG 4.3.2 ZIGBEE MODULE

4.3.3 MICROCONTROLLERS :

Arduino consists of both a physical programmable circuit board (often

referred to as a microcontroller) and a piece of software, or IDE (Integrated
Development Environment) that runs on your computer, used to write and upload
computer code to the physical board.
Arduino boards are able to read inputs - light on a sensor, a finger on a
button, or a Twitter message - and turn it into an output - activating a motor,
turning on an LED, publishing something online. You can tell your board what to
do by sending a set of instructions to the microcontroller on the board.
 FIG 4.3.3
ARDUINO

4.3.4 BREADBOARD :

A breadboard (sometimes called a plugblock) is used for building

temporary circuits. It is useful to designers because it allows components to be
removed and replaced easily.

There are two major types of breadboards; these are solder and solderless
boards. Solder boards are boards you have to solder components onto (per the
name). These are most of your standard circuit boards, and if you flip one over
you'll notice that all of the connections are soldered to the board itself.
 FIG 4.3.3.1 BREADBOARD

4.3.4 JUMPER WIRES :

Commonly refers to as a "Jumper", "Jumper Bar", or "Terminal Block

Jumper"
It is a short length or conductor (commonly copper)that is used to connect
two or more points in a electrical circuit. Very commonly used in industrial
control panels.

Jumper wires typically come in three versions: male-to-male,

male-to-female and female-to-female. The difference between each is in the end
point of the wire. Male ends have a pin protruding and can plug into things, while
female ends do not and are used to plug things into.
FIG 4.3.4 JUMPER WIRES AND ITS TYPES
 4.4 APPLICATIONS OF BRAIN COMPUTER INTERFACE :

Several disabilities can be easily overshaded by them . these includes ,

Tetraplegia
Locked in syndrome

FIG 4.4.1 MEDICAL APPLICATION

4.5 NEUROSPELLER :
4.6 OPERATOR MONITORING APPLICATIONS :

The operator monitoring is the process in which operator is monitored

using camera and using computer vision , his facial movements also helps to
track with his brain functions . These applications are majorly used in gamming
industry , virtual Reality and Augmented Reality
FIG 4.6.1 CAR CONTROL
 FIG4.6.1 FATIGUE ANALYSIS

4.7 FORENSICS LIE DETECTION :

 These are used to detect lies using brain signals which are used in forensics
department. Telling lies will generate different wave signals . They are also used
in brain finger printing as the result they can analyse the individual thinking
pattern and make predictions that what may think next by using previous brain
prints record,
through which we can analyse the Trust assessment , how much the individual
thinks that his decision has more weights

4.8 ENTERTAINMENT :
4.9 HEALTH :
4.9.1 ROAD MAP FOR
DESIGNING BCI INTERFACED TECHNOLOGY:
 CHAPTER 5

CONCLUSION

5.1 FEATURES OF BCI :

• Can detect multiple mental states simultaneously

• Reference electrode on Ear clip to remove ambient noises

• IP involves noise cancellation and signal amplification

• Provides EMG feature for Eye Blink detection

It can also predict the upcoming brain waves pattern with help of a deep
learning model
Which can be implemented in future
Nowadays advanced digital marketing strategies use neuro marketing
techniques in which these techniques directly attack the psychological part to
prime the emotions and make persons to buy the product using some
advertisements…
It includes visible colour , efficient design and sounds.

SUPPORTED PLATFORM AND DEVELOPMENT TOOLS :

REFERENCE :

[1] S. S. Mader and M. Windelspecht, Human biology (12th ed.). New

York, NY: McGraw-Hill, 2012.

[2] H.S. Anupama, N.K. Cauveryand and G.M. Lingaraju, (2012, May).
Brain computer interface and its types – a study. International Journal
of Advances in Engineering & Technology. 3(2). pp. 739-745. Available:
http://www.e-ijaet.org/volume-3-issue-2.html

[3] S. Xie and W. Meng, Biomechatronics in medical rehabilitation. New

York, NY: Springer Berlin Heidelberg, 2017.

[4] B. HE, Neural engineering (2nd ed.). New York: Springer, 2013.

[5] (2016, November 21). EEG Measures of Cognition. Available:

https://hvmn.com/biohacker-guide/cognition/eeg-measures-of-cognition

[6] S. Siuly, Y. Li and Y. Zhang, EEG signal analysis and classification.

New York, NY: Springer Berlin Heidelberg, 2017.

[7] 5 Types Of Brain Waves Frequencies: Gamma, Beta, Alpha, Theta,

Delta [online], Available: https://mentalhealthdaily.com/2014/04/15/5-
types-of-brain-waves-frequencies-gamma-beta-alpha-theta-delta/

[8] Ch. S. Nam, A. Nijholt and F. Lotte, Brain-computer interfaces

handbook: technological and theoretical advances. Boca Raton: Taylor
& Francis, CRC Press, 2018.

[9] J. R. Wolpaw and E. Winter, Brain-computer interfaces: principles and

practice. New York: Oxford University Press, 2012.

[10] D. P. Subha, P. K. Joseph, R. Acharya U and Ch. Min Lim. (2010). EEG
Signal Analysis: A Survey. Journal of Medical Systems. [Online]. 34(2).
pp. 195-212. Available: http://link.springer.com/10.1007/s10916-008-
9231-z

[11] N. Thi, H. Hanh and H. Van Tuan, “Identification of some brain waves
signal and applications,” in 12th IEEE Conference on Industrial
Electronics and Applications, 2017, pp. 1415-1420

[12] D. Ming, Y. Xi, M. Zhang, H. Qi, L. Cheng, B. Wan, and L. Li,

“Electroencephalograph Signal Processing Method of Motor Imaginary
Potential for Attention Level Classification”, International Conference
of the IEEE on Engineering in Medicine and Biology Society, pp. 4347-
4351, 2009.

[13] W. Kilmesch, H. Schimke, and G. Pfurtscheller, “Alpha frequency,

cognitive load and memory performance,” Brain Topography, vol. 5, pp.
241-251, 1993