IRJET- Human Emotions Detection using Brain Wave Signals

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 06 | June 2018 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 501
Human Emotions Detection using Brain Wave Signals
Viraj Yadav1, Pradeep Shinde2, Nilima Patil3, Akshaya Thorat4
1,2,3,4Department of computer Engineering, JSPM’s Jayawantrao Sawant College of Engineering, Pune
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – Here we focal point on issues and challenges
of research project that was designed to assess the different
human emotions through Electroencephalogram (EEG).
EEGcapacity isnoninvasiveand reasonablypriced,andhavea
very high sensitivity to receive information about the
internal (endogenous) changes of brain state, and offer a
very high time resolution inthe millisecond range. Because
of the latter possessions, these data are particularly suited
for study on brain mechanisms of cognitive-emotional
information processing which occurs in the millisecond
range. Ithasbeenwellknownthatspecificcorticalandsub-
corticalbrain systemis utilizedandhavebeendifferentiated
by regional electrical activities according to the associated
emotional states. There are important challenge we face
while rising efficient EEG signal emotion thanks are: (i)
designing a set of rules to stimulate unique emotion than
multiple emotions, (ii) extend a efficient algorithm for
removing noises and artifact from the EEG signal, (iii)
utilize the appropriate and efficient artificial intelligence
technique to classify the emotions. In addition, emotional
activities of the brain causes difference EEG characteristics
waves, it has been attempted to examine the brain activity
related to emotion through analyzing EEG.
KeyWords-- Electroencephalogram(EEG), DWT, Brain
Computer Interface (BCI).
1. INTRODUCTION
Emotions are a great asset in communication and a
key element in social interactions. They can be used as
deviceforsignaling, direct thought, inspiring and control-
ling interactions. The connections can happen through
vote commands, visually, using gesture recognitionandat
present in the field of science directly with the human
brain.
Too much or too less emotions can effect rational
thoughts and also presentation. Emotion plays a serious
role in rational and intelligent behavior. Since long it is
arguedthatemotional intellectisabetterpredictorthanIQ
for measure how successful a person is in his life time.
When we are happy, our insight is biased at selecting
happy events, equally for negative emotions. Similarly,
while creation decisions, users are often influenced by
their affective states. Reading a text while experience a
negatively valence emotional state often leads to very
dissimilar explanation than evaluation the same text as in
a positive state. Feeling is an omnipresent and main factor
in human life. Measuring emotion from brain activity is a
comparatively original method. Popular the doldrums
heavily changes as per the wayof communication.
EEG is a recording of the brains electrical activity, in
most cases made from electrodes over the surface of the
scalp. The neuron components producing thecurrents are
the dendrites, axons and cell bodies. The architecture of
the brain is not standardized but varies with dissimilar
location. Thus the EEG can vary depending on the location
of the recording electrodes. EEG gamut contain
characteristic waveforms which fall in 4 frequency bands
viz alpha (8-13 Hz), beta (13-30 Hz), theta (4-8 Hz) and
delta(¡ than 4 Hz).
2. Problem Definition and Objective
Nonverbal information appearing in human facial
expressions, gestures, and voice plays an important role in
human communication. Especially, by using information of
emotion and/or affection the people can communicate with
each other more smoothly. In order to achieve this smooth
communication we first need to discover the emotions of a
human being.
Human emotion detection till now was a mostly carried
out on the basis of facial recognition, thermal immagiary of
brain, blood volume pressure etc. All these methods are not
much effective. In order to predict the correct emotion the
most effective way is analyzing human brain signal. In this
project we focus on predicting the accuratehuman emotions
with the help of EEG headgear. Here we aim on providing
mobility to the subject and parallely monitoring the brain
signals and making the project dynamic one.
Objective:
1. Enables an individual to analyse their emotions.
2. Raw data is collected from EEG headgear and
delivered to the server via Bluetooth.
3. This raw data is filtered using Feature Extraction,
WaveletTransform,Feature ReductionandEmotion
Classification.

3. System Architecture
Fig -1: Block Diagram of System
Description:
Electroencephalography (EEG) is an electrophysiological
monitoring technique to record electrical activity of the
brain.
3.1. Noise fall:
Noise lessening is the procedure of removing
noise as of a signal. All signal dealing out devices, both
analog and digital, have traits that craft them disposed
to noise.
3.2. Data:
Live data: Run Time monitor EEG signals from
EEG Device.
3.3. Feature Extraction:
Feature extraction starts from an initial set of
measured data and builds derived values(features)
intended to be revealing and non-redundant,
facilitating the next scholarship and generalization
steps, and in some cases leading to better human
interpretations.
3.4. Feature Classification:
A pattern credit technique that is used to
categorize a huge figure of data into different classes.
3.5. Emotion:
This module will represent emotionalstate ofhuman.
4. Algorithm
4.1. DWT Algorithm:
The discrete wavelet transform (DWT) algorithms have a
firm position in processing of signals in several areas of
research and industry. As DWT provides both octave-scale
frequency and spatial timing of the analyzed signal, it is
constantly used to solve and treat more and more advanced
problems.
The discrete wavelet transform (DWT)isanimplementation
of the wavelet transform using a discrete set of the wavelet
scales and translations obeying some defined rules. In other
words, this transform decomposes the signal into mutually
orthogonal set of wavelets,whichisthemaindifference from
the continuous wavelet transform (CWT), or its
implementationforthediscretetimeseriessometimescalled
discrete-time continuous wavelet transform (DT-CWT).
The wavelet can be constructed from a scaling function
which describes its scaling properties. The restriction that
the scaling functions must be orthogonal to its discrete
translations implies some mathematical conditions on
them which are mentioned everywhere, e.g. the dilation
equation,
Where S is a scaling factor. Moreover, the area between
the function must be normalized and scaling function must
be orthogonal to its integer translations, i.e.
Following steps are performed for compression :
a) Load the image which is compressed.
b) Applying the transform-The compressionalgorithm
starts by transforming the image from data space to
wavelet space. This is done on several levels.
c) Chossing the threshold- neglectall thewaveletcoefficients
that fall below a certain threshold.Weselectourthreshold in
such a way as to preserve a certain percent of the total
coefficients - this is known as ‖quantile‖ thresholding.
4.2. KNN Algorithm:
KNN can be used for both classification and regression
predictive problems. However, it is more widely used
in classification problems in the industry. To evaluate
any technique we generally look at 3 important
aspects:

1. Ease to interpret output.
2. Calculation time.
3. Predictive Power.
Here is step by step on how to compute K-nearest
neighbors KNN algorithm:
Determine parameter K = number of nearest
neighbors.
Calculate the distance between the query-instanceand
all the training samples.
Sort the distance and determine nearest neighbors
based on the K-th minimum distance.
4.3. SVM Algorithm:
If you want to relate the two, an SVM might be used to
perform image classification. For example, given an
input image, the classificationtaskistodecidewhether
an image is a cat or a dog. The image, before being
input into the SVM might have gone through some
image processing filters so thatsomefeaturesmightbe
extracted such as edges, color and shape.
SVM is fundamentally a binaryclassificationalgorithm.
It falls under the umbrella of machine learning.
5. Advantage
1. User Friendly
2. Wireless EEG Signal Acquisition.
3. Mobility.
6. Outcome
1. The main aim of our project is to identifythehuman
emotions by using cost effective means.
2. The other focus is to provide mobility to the user
while he/she is capturing the brain waves.
3. The system captures the brainwaves of the subject
and processes it to predict the correct emotion.
4. The result is the human emotion displayed in the
form of an emoji and the graphs which displays the
brainwave attributes.
7. Application
1. Medical applications:
Healthcarefieldhasavarietyofapplicationsthat
couldtakeadvantageofbrainsignals in all linked
phasesincluding avoidance,detection,diagnosis,
rehabilitation and restoration.
2. Games and entertainment:
Entertainment and gaming applications have
opened the market for non-medical brain
computer interfaces. Various games are
accessible like in where helicopters are made to
fly to any point in either a 2D or 3D virtual world.
combine the features ofexistinggameswithbrain
controllingcapabilitieshasbeensubjecttomany
researches such as which tend to provide a
multi-brain activity experience. The video game
is called Brain Arena. The players can join a
collaborative or competitive football game by
means of two BCIs. They can score goals by
imagining left or right hand movements.
3. Neuromarketing and advertisement:
Marketing field has also been an interest for
BCI researches. The research in haveexplained
the benefits of using EEG valuation for TV
advertisements related to both commercial and
followingfields. BCIbasedassessmentmeasures
the generated attention connected watching
activity. On the other hand, the researchers of
haveconsidered the impact of another cognitive
function in neuromarketing field.Theyhavebeen
involved in estimating the memorization of TV
advertisements thus providing another method
for advertising evaluation.
4. Educational and self-regulation:
Neurofeedback is a promising approach for
enhancing brain performance via target human
being brain activity intonation. It invades the
educational systems, which utilizes brain
electrical signals to determine the degree of
lucidity of studied information. Personalized
interaction to each learner is recognized
according to the resultant responseexperienced.
Learning to self-regulate through noninvasive
BCI have also been studied. It provides a mean
forimproving cognitivetherapeutic approaches.
5. Smart Environment:
Smart Environments such as smart
houses,workplaces or transportations could also
exploit brain computer interfaces in offering
additional safety, luxuryandphysiological control
to humans daily life. They are also expected to

witness cooperation between Internet Of Things
(IOT) and BCI technologies.
8. Screen Shot:
1. HAPPY:
2. SAD:
9. CONCLUSION
The emotion recognition from the EEG signal, and also
the findings of effectual data recordingfromphysiological
signal, feature extraction , data reduction, mark
categorization throughSVM,realtime applicationsandthe
scope for futureresearch.
10. Future Scope
1. Using advanced algorithms for prediction of emotions.
2. PC games where the player can control the game based on
his/her thoughts.
3. To identify if the patient will suffer from
subconsciousness.
4. Brain controlled wheelchair.
5. Brain controlled robotic arm.
11. REFERENCES
[1] Ali S. AlMejrad Biomedical Technology
Department, College of Applied Medical Sciences
King Saud University, “Human Emotions Detection
using Brain Wave Signals: A Challenging”,
European Journal of Scientific Research ISSN 1450-
216X Vol.44 No.4 (2010), pp.640-659
[2] Kanwisher N, McDermott J, and Chun M.M, 1997.“The
fusiform face area: a module in human extrastriate cortex
specialized for face perception”, Journal ofNeuroscience, 17,
pp,4302- 4311.
[3] Haxby J.V, Hoffman E.A, and Gobbini M.I, 2000.“The
distributed neural system for face perception”, Trends
Cognitive Neuroscience, 4, pp, 223-233.
[4] Picard R.W, Vyzas E, and Healey J, 2001. “Towards
Machine Emotional Intelligence: Analysis of Affective
Physiological State”, IEEE Transactions on Pattern Analysis
and Machine Intelligence, 23(10), pp, 1175- 1191.
[5] Dr. R.Newport, Human Social Interaction perspectives
from neuroscience,
www.psychology.nottingham.ac.uk/staff/rwn.
[6] Marcel S, Jose del and R.Millan, 2006. “Person
Authentication Using Brainwaves (EEG) and Maximum A
Posteriori Model Adaptation”, IEEE Trans on Pattern
Analysis and Machine Intelligence, Special issue on
Biometrics, pp, 1-7.
[7] M. Murugappan, N. Ramachandran and Y. Sazali,
"Classification of human emotion from EEG using
discretewavelet transform," Journal of Biomedical Science
and Engineering, vol. 3, pp. 390, 2010.
[8] Dexon T.L, Livezey G.T, 1996. “Wavelet- Based Feature
Extraction for EEG Classification”, IEEEProceonEMBS,3,pp,
1003-1004.
[9] Jenkins J.M, Oatley K, and Stein NL, 1998. “Human
Emotions”, A reader Balck Well Publisher.
[10] Blinswska K.J, Durka P.J, 1994. “Application of wavelet
transform and matching pursuit to the time- varying EEG
signals” Proce, of conference on artificial neural networksin
engineering, USA, pp, 535-540.

IRJET- Human Emotions Detection using Brain Wave Signals

More Related Content

What's hot

Similar to IRJET- Human Emotions Detection using Brain Wave Signals

More from IRJET Journal

Recently uploaded

IRJET- Human Emotions Detection using Brain Wave Signals