VISVESVARAYA TECHNOLOGICAL UNIVERSITY

BELAGAVI - 590018
2020–2021

A
Phase 2 Project Report
on
“Face Detection and Recognition for Automatic Attendance
System Using Artificial Intelligence for Real Time
Applications.”
Submitted in the partial fulfillment of the requirement
for the VIII Semester Project - 15ECP85 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by
BHARATH J 1GV16EC007
CHANDANA G 1GV16EC010
KAVYA H N 1GV16EC019
SHUBHA M 1GV16EC056

Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY.
Under the guidance of
Dr. K M Palaniswamy, Professor, ECE Dept.
Mr. Jesudas J, Asst. Professor, ECE Dept.
Department of Electronics and Communication.

Dr.T.Thimmaiah Institute of Technology

Oorguam Post, K.G.F-563120

(Approved by AICTE, New Delhi, Affiliated to VTU-Belagavi,

Approved by Govt. Of Karnataka and ISO 21001-2018
Certified)
Face detection recognition for automatic attendance system using artificial
intelligence for real time applications 2020-21

SYNOPSIS
Face is the crucial part of the human body that uniquely identifies a person. Using the face
characteristics as biometric, the face recognition system can be implemented. The most demanding
task in any organization is attendance marking. In traditional attendance system, the students are
called out by the teachers and their presence or absence is marked accordingly. However, these
traditional techniques are time consuming and tedious. In this project, the Open CV based face
recognition approach has been proposed. This model integrates a camera that captures an input
image, an algorithm for detecting face from an input image, encoding and identifying the face,
marking the attendance in a spreadsheet and converting it into PDF file. The training database is
created by training the system with the faces of the authorized students. The cropped images are
then stored as a database with respective labels. The features are extracted using LBPH algorithm.

8th sem, Dept. of ECE Dr. TTIT KGF ii

 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
on
“Fire Detection Using Surveillance Camera By
Deep Learning Techniques.”
Submitted in the partial fulfillment of the requirement for the VII
. Semester Project - 17ECP75 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by
BHARATH K 1GV17EC004
HARI PRASHANTH B 1GV17EC010
RAKSHITHA S A 1GV17EC033
VIGNESH K 1GV17EC052

Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLGY
Under the Guidance of
Mr. SRINIVAS BABU N.
Assistant Professor,
Department of Electronics and Communication
Engineering

Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY

Oorgaum, Kolar Gold Field - 563120
(Approved by AICTE, New Delhi, Affiliated to VTU-Belgavi,
Approved by Govt. of Karnataka and ISO 21001-2018 Certified)
Fire Detection Using Surveillance Camera By Deep Learning Technology 2020-2021

7th sem, Dept. of ECE, Dr. TTIT, KGF i

Fire Detection Using Surveillance Camera By Deep Learning Technology 2020-2021

SYNOPSIS

The detection of manmade disasters particularly fire is valuable because it causes

many damages in terms of human lives. With the current advancement of the Technologies,
like deep learning models such as convolutional neural networks (CNN) are used. However,
many of the existing research has only been assessed on balanced datasets, which can lead
to the Unsatisfied Results and Mislead Real-World Performances as Fire is a rate and
abnormal real-life event . To verify the effects of existing preprocessing and feature
extraction methods on fire detection when combined with CNN.

The recognition performance and learning time are evaluated by changing the VGG-
19 CNN structure while gradually increasing the convolution layer. In general, the accuracy
is better when image is not preprocessed. Also that the preprocessing method and the feature
extraction method have many benefits in terms of learning speed.

7th sem, Dept. of ECE, Dr. TTIT, KGF vi

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
On
“Printed Circuit Board Fault Detection using
Image Processing in MATLAB”
Submitted in the partial fulfilment of the requirement for the VIII
Semester Project - 17ECP85 for the award of degree of

Bachelor of Engineering
in
Electronics and Communication Engineering
By
CHAITHRA R 1GV17EC006
KANIMOZHI S 1GV17EC013
KESHU MURTHY N 1GV17EC014
TEJAS M 1GV17EC045
Carried out at
Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the guidance of
Mrs. VIJAYA GEETHA R,
Associate Professor,
Department of Electronics and Communication.

Dr. T. Thimmaiah Institute of Technology

Oorgaum Post, K.G.F-563120
(Approved by AICTE, New Delhi, Affiliated to VTU- Belagavi,
Approved by Govt. of Karnataka and ISO 21001-2018 certified)
Printed Circuit Board Fault Detection using Image Processing in MATLAB 2020-2021

SYNOPSIS
Printed circuit board are blooming in current trends in the electronic field where it
is easy to design with less cost. But there are design faults during the manufacturing of
PCBs which may lead to huge losses in production. PCB fault detection is plays vital role;
generally it’s difficult to detect the faults in PCB manually. So many emerging technologies
as came into existence to detect fault in PCBs. Since there are some drawbacks regarding
accuracy and computation cost.

We are using Image processing based technologies which is feasible to the detect
faults in PCBs with much accuracy and get the results faster compared with other
technologies. By using these techniques we can group 14 defects in PCB that are breakout,
pin hole, open circuit, under etch, mouse bite, missing conductor, spur, short, wrong side
hole, conductor to close, spurious copper, excessive short, missing hole, over etch. This
will be easy to analysis the fault and correct them.

We take the standard image and test image and classify the above defects based on
the segmentation process like hole segment, line segment, thin line segment and thick line
segment. Based on this four the 14 defects are classified which make the work easier to
identify the defects. In we use the binary image so we get the exact output in the form of
either level 0 or level 1 by varying the intensity level of RGB the binary image is obtained
in MATLAB. And we use this MATLAB we can use the median filter to remove the noise
from image and it also help to detect the edges of the PCB.

Dept. of ECE, Dr.TTIT, K.G.F. vii

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Phase 2 Project Report
on
“Predicting COVID-19 from Lung Images using Deep
Transfer Learning.”
Submitted in the partial fulfillment of the requirement
for the VIII Semester Project - 17ECP85 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by
DEEKSHITHA N 1GV17EC056
HITESH T N 1GV18EC401
PAVITHRA H V 1GV16EC035
TEJAS N 1GV16EC066

Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY.
Under the guidance of
Mrs. Inbalatha K, Associate Professor,
Department of Electronics and Communication.

Dr.T.Thimmaiah Institute of Technology

Oorguam Post, K.G.F-563120

(Approved by AICTE, New Delhi, Affiliated to VTU-Belagavi,

Approved by Govt. Of Karnataka and ISO 21001-2018
Certified)
Predicting COVID-19 from Lung Images using Deep Transfer Learning 2020-21

SYNOPSIS
The COVID-19 pandemic is causing a major outbreak in more than 150 countries around
the world, having a severe impact on the health and life of many people globally. One of the crucial
steps in fighting COVID-19 is the ability to detect the infected patients early enough, and put them
under special care. Detecting this disease from radiography and radiology images is perhaps one
of the fastest ways to diagnose the patients. Some of the early studies showed specific
abnormalities in the chest radiograms of patients infected with COVID-19. Inspired by earlier
works, we study the application of deep learning models to detect COVID-19 patients from their
chest radiography images. We first prepare a dataset of 5000 Chest X-rays from the publicly
available datasets. Images exhibiting COVID-19 disease presence were identified by board-
certified radiologist.

Transfer learning on a subset of 2000 radiograms was used to train four popular
convolutional neural networks, including ResNet18, ResNet50, SqueezeNet, and DenseNet-121,
to identify COVID-19 disease in the analyzed chest X-ray images. We evaluated these models on
the remaining 3000 images, and most of these networks achieved a sensitivity rate of 98% (± 3%),
while having a specificity rate of around 90%. Besides sensitivity and specificity rates, we also
present the receiver operating characteristic (ROC) curve, precision-recall curve, average
prediction, and confusion matrix of each model. We also used a technique to generate heatmaps
of lung regions potentially infected by COVID-19 and show that the generated heatmaps contain
most of the infected areas annotated by our board-certified radiologist. While the achieved
performance is very encouraging, further analysis is required on a larger set of COVID-19 images,
to have a more reliable estimation of accuracy rates.

7th sem, Dept of ECE Dr. TTIT KGF i

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
on
“Defective Coffee Bean Inspection with GA Based GAN
Optimizer Using TensorFlow.”
Submitted in the partial fulfillment of the requirement for the
VIII Semester Project - 17ECP85 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by
DIVYA K K 1GV17EC009
REVANSIDDA 1GV17EC034
SNEHA M 1GV17EC041
YASHASWINI G 1GV17EC055

Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY.
Under the guidance of
Dr. JENITHA A, M.E., Ph.D.,
Associate Professor,
Department of Electronics and Communication.
Dr. T. Thimmaiah Institute of Technology
Oorguam Post, K.G.F-563120

(Approved by AICTE, New Delhi, Affiliated to VTU- Belgavi,

Approved by Govt. Of Karnataka and ISO 21001-2018 Certified)
Defective coffee bean inspection with GA based GAN optimizer using Tensor flow 2020-2021

SYNOPSIS

The quality of a coffee bean is determined by several factors which includes color,
texture and size. This evaluation is done by human inspector, but the decision-making
capabilities of humans are subjected to external influence such as fatigue, environment,
light, emotions, etc. In the process of production of green beans to packaging coffee bean,
the defective bean removal stage is one of most labor-consuming stage to automate this
task, in order to minimize human effort. A deep learning-based defective bean inspection
scheme (DL-DBIS), together with a GAN (generative adversarial network)-structured
automated labeled data augmentation method (GALDAM) is used to automation degree of
bean removal with robotic arms can be further improve for coffee industries.

We proposed a defective bean inspection using deep-learning with CNN classifier,

together with an automated labeled data GAN-structured augmentation method to enhance
the proposed scheme, so that the automation degree of defective bean detection is improved
for coffee industries. We have also used SVM, KNN and Random Forest Classifiers to
detect the defective beans.

8th sem, Dept. of ECE, Dr. TTIT, KGF i

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020-2021

Project Report
on

Convolutional Neural Network For

Human Activity Recognition In Videos: Littering
Activity Detection."
Submitted in the partial fulfilment of the requirement
for the VilI Semester Project - 17ECP85 for the award of degree of

Bachelor of Engineering
in
Electronics and Communication Engineering
by
K DOLLAR SINGH 1GV17ECO58
NAGESH BV 1GV17ECO020
BHARATH BV 1GV17EC003
RAHUL BALU KANBARKAR 1GV17EC032

Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY.
Under the guidance of
Mr. RAJESH KUMAR KAUSHAL
Assistant Professor,
Department of Electronics and Communication.

Dr.T.Thimmaiah nstitute of Technology

Oorguam Post, K.G.F-563120
*

Convolutional Neural Network for Human Activity Recognition in Videos:

Littering Activity Detection_ 2020-2021

SYNOPSIS
The earth is what we all have in common. Many people have forgotten how to
walk lightly on the earth as its other creatures do. Various organizations and individual

volunteers focused on multidimensional work and solutions to stop humans from filling
the world with trash. Litter has the potential to harm human health, safety, welfare, as

well as the environment. The mass production of disposable goods also produced a

growing mountain of waste. The environment can be kept clean and hygienic only
through human activities. In this project, a technique to recognize humans littering is
proposed and the activity is detected.

A convolutional neural network is used to resolve and extract the patterns

from video framework and validate with the threshold to make a decision. In this

technique, various sample videos are validated and persons with and without littering
activities are identified.

PROBLEM STATEMENT
1) Environmental pollution due to litters created by humans.
2) Unable to monitor activities of large number of people at the same time.

Dept. of ECE Dr. TTITK.G.F

 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
On
“Depression Detection From Social Network Data Using Machine
Learning Techniques”
Submitted in the partial fulfilment of the requirement for the VIII
Semester Project phase 2 - 17EC85 for the award of degree of
Bachelor of Engineering
In
Electronics and Communication Engineering
By
S LAVANYA 1GV17EC035
VENILA B N 1GV17EC050
FELSY FLORANCE W 1GV17EC400
ISHWARYA R 1GV17EC402
Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the Guidance of
Dr.T.Bhuvanendhiran
Associate Professor,
Department of Electronics and Communication.

Dr. T. Thimmaiah Institute of Technology

Oorgaum Post, K.G.F-563120
VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
On
“BITCOIN PRICE PREDICTION USING MACHINE
LEARNING TECHNIQUE ”
Submitted in the partial fulfilment of the requirement for the VIII
Semester Project - 17ECP85 for the award of degree of

Bachelor of Engineering
in
Electronics and Communication Engineering
By
MAMATHA N 1GV17EC016
PREETHI T 1GV17EC026
SIRISHA SHREE NAGATHI S 1GV17EC014
THEJENDRA K E 1GV17EC045
Carried out at
Dr . T. THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the guidance of
Mr, SHASHIKIRAN .S
Associate Professor,
Department of Electronics and Communication.

Dr. T. Thimmaiah Institute of Technology

Oorgaum Post, K.G.F
K.G.F-563120

(Approved by AICTE, New Delhi, Affiliated to VTU

VTU- Belagavi,
Approved by Govt. of Karnataka and ISO 21001-2018
21001 certified)
Bitcoin Price Prediction Using Machine Learning Techniques 2020-2021

SYNOPSIS
With the introduction of Bitcoin in the year 2008 as the first practical decentralized crypto
currency, the interest in crypto currencies and their underlying technology, Block chain,
has skyrocketed. Their promise of security, anonymity, and lack of a central controlling
authority make them ideal for users who value their privacy. Academic research on
machine learning, Block chain technology, and their intersection have increased
significantly in recent years. Specifically, one of the interest areas for researchers is te
possibility of predicting the future prices of these crypto currencies using supervised
machine learning techniques.

In this project, we investigate their ability to make one day ahead price prediction
of several popular crypto currencies using five widely used time-series prediction models.
These models are designed by optimizing model parameters, such as activation functions,
before settling on the final models presented in this project. Finally, we report the
performance of each time-series prediction model measured by its mean squared error and
accuracy in price movement direction prediction.

Dept. of ECE, Dr.TTIT, K.G.F. iv

 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI-590018
2020-2021

A
Project Report
On
“Deep Learning for Recognizing Human Activities Using
Motions of Skeleton Joints”
Submitted in the partial fulfilment of the requirement
for the VIII Semester Project – 15ECP85 for the award of degree of
Bachelor of Engineering
In
Electronics and Communication Engineering
By
MANIVANNAN S 1GV15EC027
REENASHREE R 1GV16EC043
SUCHITRA G 1GV16EC061
DEVAIYANI R 1GV16EC071

Carried at
Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the guidance of
Prof. Ruckmani Divakaran (Dean Administration)
Mrs. Nandini G N Asst. Professor
Dept. of ECE, Dr. TTIT, KGF

Dr. T.Thimmaiah Institute of Technology

Oorgaum Post,K.G.F-563120
Deep learning for recognizing human activities using motions of skeleton joints. 2020-21

SYNOPSIS

With advances in consumer electronics, demands have increase for greater

granularity in differentiating and analysing human daily activities. Moreover, the potential of
machine learning, and especially deep learning, has become apparent as research proceeds in
applications such as monitoring the physically challenged people and surveillance for detection
of suspicious people and objects left in public places. Although some techniques have been
developed for Human Action Recognition (HAR) using wearable sensors, these devices can
place unnecessary mental and physical discomfort on people, especially children and the
elderly. Therefore, research has focused on image-based HAR, placing it on the front line of
developments in consumer electronics. This technique proposes an intelligent human action
recognition system which can automatically recognize the human daily activities from depth
sensors using human skeleton information, combining the techniques of image processing and
deep learning. Moreover, due to low computational cost and high accuracy outcomes, an
approach using skeleton information has proven very promising, and can be utilized without
any restrictions on environments or domain structures. Therefore, this technique discusses the
development of an effective skeleton information based HAR which can be used as an
embedded system. The experiments are performed using two famous public datasets of human
daily activities.

8t hsem Dept of ECE Dr. TTIT K G F ii

 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI-590018
2020-2021

A
Phase 2 Project Report
on
“Grading of Harvested Mangoes based on Quality Evaluation
and Maturity Prediction using Machine Learning Technique”
Submitted in the partial fulfillment of the requirement for the VIII
Semester Project Phase 2 – 17ECP85 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by
MOHAMMED SHOAIB 1GV17EC018
MOHAN BABU M 1GV17EC019
PAWAN 1GV17EC022
SAJJAD AHMED A 1GV17EC036
Carried out at
Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the guidance of
Ms. Mohana C, M. Tech,
Asst. Professor,
Department of Electronics and Communication.

Dr. T. Thimmaiah Institute of Technology

Oorgaum Post, K.G.F-563120.
(Approved by AICTE, New Delhi, Affiliated to VTU- Belagavi,
Approved by Govt. of Karnataka and ISO 21001-2018 certified)
Grading of Harvested Mangoes based on Quality Evaluation and Maturity Prediction 2020-21
using Machine Learning Techniques

SYNOPSIS
It is very important to do proper Grading of fruits to increase the profit of Agriculture.
Nowadays sorting of the fruits like Mango, Banana, Dates and Grapes is performed
manually, for this getting adequate manual expert during the period is difficult. This process
is time and money consuming also face problem like inconsistency, inaccuracy,
inefficiency, lack of objectivity and it is labor intensive process. By using Machine Vision
Technique, Several Image Processing Techniques are applied to collect features which are
sensitive to Maturity and Quality. For Maturity prediction SVR (Support Vector
Regression) technique, for estimation of Quality MADM (Multi Attribute Decision
Making) is adopted. Finally, Fuzzy Incremental Learning Algorithm has been used for
Grading of Mangoes.

In this system mangoes are graded in three types like Green Mango, Yellow Mango
and Red Mango which are based on machine learning method. This system considers RGB
values, size and shape of mangoes. Posterior analysis is used to obtain good probability.
This helps to train system to detect appropriate maturity of mangoes. This experiment is
conducted based on Naive Bayes to compare the performance of both based on accuracy
and defective pixels. From the previous system, this system gives the more accuracy as
posterior analysis is used. Here we are going to use MATLAB Tool version R2018a.

Dept of ECE, Dr. TTIT, KGF. iv

 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A
Project Report
on

“A DEEP LEARNING TECHNIQUE FOR IMAGE

BASED PLANT DISEASE DETECTION AND CROP
YIELD PREDICTION”
Submitted in the partial fulfillment of the requirement
for the VIII Semester Project - 17ECP75 for the award of degree of
Bachelor of Engineering
in
Electronics and Communication Engineering
by,
POOJA SREE K 1GV17EC023
PREETHI P 1GV17EC025
RACHEL RHEMA RICHARD 1GV17EC030
SUVEDITTA B 1GV17EC043

Carried at

Dr.T. THIMMAIAH INSTITUTE OF TECHNOLOGY

Under the guidance of
Mrs. MANJUSHREE K CHAVAN
Asst Prof., Dept. of ECE, Dr.TTIT., K.G.F

Dr.T. Thimmaiah Institute of Technology Oorgaum Post,

K.G.F-563120 (Approved by AICTE, New Delhi, affiliated to VTU-
Belagavi, Approved by Govt. Of Karnataka and ISO 21001-2018 Certified)
A Deep Learning Technique for Image Based Plant Disease Detection and Crop Yield Prediction 2020-21

SYNOPSIS
Modern technologies have given human society the ability to produce enough food,
yet food security remains threatened by a number of factors including climate change, plant
diseases and others. Plant diseases are not only a threat to food security at the global scale,
but can also have disastrous consequences for farmers whose livelihood depends on healthy
crops. Crops yield prediction is of great importance to global food production. Seed
companies need to predict the performance of new hybrids in various environments to breed
for better varieties. Farmers and growers also benefit from yield production to make financial
decisions and suitable varieties to crop to be used for the food production.

Various efforts have been developed to prevent crop loss due to diseases. It is
generally accepted that deep learning technique have recently been successfully applied in
detecting the diseases in plants, predicting and checking the yields, yield difference of corn
hybrids from genotype and environment data. This means that existing method for plant
diseases detection and crop yield prediction is simply observed by experts through naked eye.
This causes huge economic loss for farmers. But we propose a technique on deep learning
which uses different classification on plant leaf diseases and also crop yield prediction.
Digital camera or similar devices are used to take images of different types of leaves and then
those are used to identify the affected areas in leaves.

We utilize two stages namely, training stage and testing stage. The first stage is image
procurement, image pre processing, and DNN based preparing and the second stage is image
procurement, image pre processing, classification and diseases distinguishing proof and crop
yield prediction. For experimentation reason we will utilize plant village datasets. To develop
this model Anaconda tool is used, as available tools are present and Python is the language
used for coding the proposed method.

7th sem,Dept of ECE,Dr TTIT,KGF ii

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020–2021

A Project Report
On
“An Efficient IoT Based Covid-19 Monitoring
System Using CNN Classifier”
Submitted in the partial fulfilment of the requirement
for the VIII Semester Project Phase 17ECP85 for the award of degree of

Bachelor of Engineering
In
Electronics and Communication Engineering
By
Priyanka D 1GV17EC027
Priyanka S 1GV17EC029
Vinutha S 1GV17EC053
Chandrakala V 1GV17EC057
Carried at
Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY
Oorgaum, K.G.F-563120

Under the Guidance of

Mr. Jesudas J, Assistant Professor,
Department of ECE, Dr.T.T.I.T, K.G.F.

Dr.T.THIMMAIAH INSTITUTE OF TECHNOLOGY

(Formerly Golden Valley Institute of Technology)
Department of Electronics and Communication Engineering
Kolar Gold Fields – 563120.
An Efficient IoT Based COVID-19 Monitoring System Using CNN Classifier 2020-2021

SYNOPSIS
As we are aware of the current pandemic situation that is Covid-19 which is spreading
all over the world. Covid-19 spreads mainly by droplets produced as a result of coughing or
sneezing of Covid-19 infected person, it can also spread from contact with infected surfaces
or objects. Any person who comes into close contact with someone who has Covid-19 is at
increased risk of becoming infected themselves.

As it is spreading widely it is difficult to get the report on required time, hence to

detect Covid-19 “Positive or Negative” within 30minutes of time we are using an efficient
IoT based Covid-19 Monitoring System Using CNN Classifier. In this process we are using
sensors such as heart rate sensor, temperature sensor, and respiratory sensor to collect data
from a person and it is transmitted wirelessly with the help of ESP8266 module and the data
is received by using Arduino. These data are being processed using MATLAB and CNN
Classifier is used to predict the result whether it is “Positive or Negative” based on this result,
best accuracy and efficiency is achieved.

Dept. Of ECE, Dr.T.T.I.T, K.G.F. Page ii

VISVESVARAYA TECHNOLOGICAL UNIVERSITY
BELAGAVI - 590018
2020-2021

A
Project Report
on
“VLSI Implementation of Turbo codes for LTE Systems”
Submitted in the partial fulfilment of the requirement for the VIII
Semester Project – 17ECP85 for the award of degree of

Bachelor of Engineering
in
Electronics and Communication Engineering
by
SINDHU G 1GV17EC039
SPANDANA K. N. 1GV17EC042
V. PRACHI BOHRA 1 GV17EC049
WAJIHA SULTANA 1GV17EC054

Carried at
Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY
Under the Guidance of
Prof. VIJAYA BHARATHI M
HOD, Assoc. Prof. Dept. of E & C,

Dr. T. THIMMAIAH INSTITUTE OF TECHNOLOGY

Oorguam Post, K.G.F- 563120

(Approved by AICTE, New Delhi, Affiliated to VTU-Belagavi,

Approved by Govt. Of Karnataka and ISO 21001-2018 Certified)
VLSI Implementation of Turbo Codes for LTE Systems 2020-2021

SYNOPSIS

Communication is act of transmission of information. Everyone in the world experiences

the need to receive information almost continuously. For communication to be successful,
it is essential that sender and receiver understands a common language.
When signal is transmitted there are 3 sources of transmission errors, they are: Signal bit
errors, burst errors and erasure. Errors in signal may lead to miscommunication between
systems. So, error correction is required to retrieve the original message. In order to detect
and correct the errors, turbo codes are used.
Turbo encoder and decoder is designed using the Verilog HDL Language. Turbo decoding
is time consuming process. So, the SOVA Algorithm gives high throughput and less
complexity output.
Xilinx Vivado 2020.2. tool is used which achieves simulation and synthesis of proposed
turbo encoder and decoder.

Dept. of ECE Dr. TTIT K.G.F ii