PROJECT SDMIT CSE
Wednesday, September 5, 2018
Friday, August 31, 2018
Final Year Academic Projects 2017 to 2018
1. Health Care Monitoring System
Youtube Link : https://www.youtube.com/watch?v=7xlDQsKPLQw
2. Soil and Water Quality Testing
3. Vehicle Traffic Monitoring
4. CROP YIELD PREDICTION FOR PADDY
Youtube Link: https://youtu.be/rPCrRcf0fjs
5.Traffic
Sign Classifier and Lane Detection Using Convolutional Neural Network
Youtube Link:https://youtu.be/vtqvqHKzHA0
6.Privacy and security issues in IoT based Smart Home
Youtube Link:
Friday, August 24, 2018
Final year BE Projects Abstract 2016 to 2017
1. Interactive Arboretum Explorer
Abstract: Identification
of plants and commercial promotion of plant species can be achieved by
utilizing information technology based database development; new technology
can help to improve quality and cataloging procedures to organize the
botanical species. Medicinal database management is one of the emerging
trends nowadays. This system helps to identify medicinal use and other
information about medicinal plants. The safety profile of a plant is
maintained in this database which is very useful for appropriate use of
medicinal plant. Some plants consider as important source of nutrition and as
a result of that these plants recommended for their therapeutic values Here,
an attempt is done to enlist various medicinal plants and their recognition
for the benefit of mankind. We develop the educational purpose application
named INTERACIVE ARBORETUM EXPLORER aiming for easy identification of
medicinal plants. Interactive arboretum explorer is an android application in
that user can search for the medicinal plant description using common name of
the plants. The application provides description of medicinal plants
(scientific name, family, genus, part used, medicinal uses) along with the
picture. This application will also recognize the picture of the plant taken
from the user through their android mobile cameras. Added to that the
application will also provide space for the user to add the information of
the medicinal plant if he knew about that plant.
G uide Name : Dr.Thyagaraju G S
1. Interactive Arboretum Explorer
|
Abstract: Identification
of plants and commercial promotion of plant species can be achieved by
utilizing information technology based database development; new technology
can help to improve quality and cataloging procedures to organize the
botanical species. Medicinal database management is one of the emerging
trends nowadays. This system helps to identify medicinal use and other
information about medicinal plants. The safety profile of a plant is
maintained in this database which is very useful for appropriate use of
medicinal plant. Some plants consider as important source of nutrition and as
a result of that these plants recommended for their therapeutic values Here,
an attempt is done to enlist various medicinal plants and their recognition
for the benefit of mankind. We develop the educational purpose application
named INTERACIVE ARBORETUM EXPLORER aiming for easy identification of
medicinal plants. Interactive arboretum explorer is an android application in
that user can search for the medicinal plant description using common name of
the plants. The application provides description of medicinal plants
(scientific name, family, genus, part used, medicinal uses) along with the
picture. This application will also recognize the picture of the plant taken
from the user through their android mobile cameras. Added to that the
application will also provide space for the user to add the information of
the medicinal plant if he knew about that plant.
|
2. Context Aware Intrusion Detection System With Multilevel Security
|
Abstract : Intrusion
detection is the act of detecting unwanted traffic on a network or a device. The
distributed and open structure of cloud computing and services becomes an
attractive target for potential cyber-attacks by intruders. The need to
maintain the security of information or physical property is becoming both
increasingly important and increasingly difficult. In all the frauds taken place criminals
have taken advantage of flaw in the access control systems: the systems do
not grant access by "who we are", but by “what we have”. In our project we used a technology to
verify a "true" individual identity i.e. "biometrics”. To take
the security to the next level we use users
Network access control
via face recognition not only makes hackers virtually impossible to steal
one's password, but also increases the user-friendliness in human-computer
interaction. This approach is greatly useful to protect the user data with
different security levels, and provide multilevel access control and valid
identity authentication. The proposed scheme is effective in multilevel data
security and simultaneously
notifies the
administrator as an intruder tried to access any confidential information.
|
Guide Name :
|
3. Automatic Classification of Alzheimer’s
Disease using Machine Learning
|
Abstract: Alzheimer’s disease, the world’s most common form of dementia, is projected to boom in the coming years. The disease is very financially costly, with a poorly understood cause and no curative treatment. Early diagnosis of Alzheimer’s and its prodromal stage is very important for possible delay of the disease, and there is thus a great deal of interest in the development of new methods for earlier detection. Structural irregularities of the brain are a sensitive feature of the disease (observable on MR images), and one of several known biological markers of the disease. Machine learning models, and maybe particularly techniques from the machine learning branch deep learning, might be able to learn features from high-dimensional data like structural MRI, and thereby enable automatic classification o f Alzheimer’s disease. This report first presents information about Alzheimer’s disease relevant to the task at hand. It then reviews and summarises some of the most important relevant machine learning research from later years. Based upon this information, we design and develop some experiments to investigate the possibility of automatic classification of Alzheimer’s disease from structural MRI, using methods of dimensional reduction and variations in the formulation of the learning task via different schemes of hyper parameter selection, and performed with a deep learning approach. We have also found that the lack o f data is the most hindering problem for further optimization. We also designed a web application to facilitate the use our model by others and classify images. We hope that this report might be used as a starting point for future research into this problem. |
4. Performance
Analysis of Crime Data Processing Based on Apache Pig Framework
|
Abstract : Big data is voluminous and complex collection of data that comes from different sources such as sensors, content posted on social media website, sale purchase transaction etc. Such voluminous data becomes tough to process using ancient processing application. There are various tools and techniques in the market for big data analytics. With continually increasing population, crimes and crime rate analyzing related data is a huge issue for governments to make strategic decisions so as to maintain law and order. This is really necessary to keep the citizens of the country safe from crimes. The best place to look up to find room for improvement is the voluminous raw data that is generated on a regular basis from various sources by applying Big Data Analytics which helps to analyze certain trends that must be discovered, so that law and order can be maintained properly and there is a sense of safety and well-being among the citizens of country. |
Guide Name :
|
5. ENCRYPTING IMAGES USING REVERSIBLE DATA HIDING
|
Abstract :
With
the popularity of sending some important messages to the client source, it is
essential to protect the privacy of data. Under such demands, reversible data
hiding in encrypted images attracts more and more researcher’s attention. In
this project, we propose a novel framework for EI-RDH. It is different from
all previous encryption based frameworks, and here encryption is done with
the text attached to an image and at the end receiver can get the data
without decryption called as data extraction. This framework works on two RDH
methods, including traditional RDH scheme and unified embedding and
scrambling scheme, are adopted to embed watermark in the encrypted image,
which can satisfy different needs on image quality and large embedding
capacity respectively. In this project, we investigated the
problem that as in the case of current data transferring system, there won’t
be much security between the sender and receiver. Because most of the
important information sent by/to the user will be unknown to hackers by interrupting
in network. To solve this there should be a privacy for direct interaction
among the sender and receiver. So we have come up with a solution for all of
the above mentioned problems in our application.
This project has
proposed a Desktop application which was very useful to sending and receiving
data with privacy. By this application sender can be able to embedthe data,
encrypt the image and this isreceived by the particular receiver without any
interruptions. Separable Reversible data hiding in encrypted image is a new
topic drawing attention because of the privacy-preserving requirements from
cloud data management. We proposed by
first encrypting image and then embedding data, protecting it. Thus the data
hider is assure that data in image is protected with a key and the entire
image is encrypted and in that encrypted image, data can be extracted only by
the key know to the receiver. The proposed method can take advantage of all
traditional techniques for plain images and achieve excellent performance
without loss of perfect secrecy.
|
Guide : Raghavendra Patil
|
6. Mobile healthcare application
|
Abstract : Now a days mobile technology is creating the wonders in the healthcare industry. Mobile healthcare is an important extension of electronic healthcare. It gives providers an opportunity to access the patient’s clinical data and latest medical offerings at any time and place. In the traditional approach the healthcare professionals play the major role. They need to visit the patient for necessary diagnosis and advising. There are two basic problems associated with this approach. Firstly, there is a need for carrying the medical history whenever the patient consults the doctor. Secondly, staffs in the health centres have to keep track of the patients record which is time consuming and requires extra man power. This project demonstrates how healthcare application help doctors to diagnose, monitor, consult and treat common diseases. As healthcare application allow doctors to look up information from the patient’s bedside, this saves time and enables them to provide optimum treatment to the patient. This application enables patients to take more active role in their own healthcare-managing appointments, updating prescriptions, and accessing their health records. When patients take on more responsibility for their own care, their health improves. |
Guide Name : Dr.Thyagaraju G S
|
7. An Android Based
Smart Home Application To Predict Resident Activity
|
Abstract : The smart home refers to domestic
environment that improves the quality of the resident’s life by facilitating
a flexible, comfortable , healthy and safe environment. Internet based home
automation systems become the most popular home automation system in
international markets. Recently , User intention prediction using contextual
data generated by IOT has become an emerging research area in Ubiquitous
Computing Environment. Television ,Mobile ,Healthcare , Smart homes are some
of the applications where the user intension is predicted.
IOT also means that each
object or thing is connected and communicates through the internet without
human intervention , and the ultimate goal of IOT is to enhance the quality
of human life. In recent days the work and life of human
being’s are increasingly busy and complicated with the rapid growth in
communications and information technology. As the economic expansion is
growing rapidly, the standard of living also keeps on rising up and the
people are requiring more living functions. The concept of smart home has
focused the attention of re-searchers. A lot of efforts have been done for
the development of home automation to control that remotely. Smart Home is an
advanced technology to make a house to become intelligent and automated.
Usually, that technology has automation systems for lighting, temperature
control, security and many other functions.
The large number of sensor node wired
connected to the server. This will cause the problem during upgrading the
system and the area network ranges are limited. Wireless communication has
been introduced into a Smart Home system in recent years. In previous work
the device was attached to the wall. The user need go to the device location.
Therefore, this project has purpose predicting user intensions powered by
Android as a user interface device. The AP uses Raspberry Pi. In this project
we are developing an android based smart home mobile application where we are
going to predict user‘s activity by using the contextual data. The parameters
like user id, location & also the status of the device embedded in smart
home are considered for achieving prediction. The hardware devices used in
our project are Raspberry kit, Arduino UNO ,Relay, Rfid reader and reciver,IR
sensor, Temperature and humidity sensor, Force sensor,led,5V bulb. Using
Python programming language the data sets are trained & tested to predict
user‘s activity based on contextual data.
|
Guide Name : Rakshith M D
|
8. HYBRID POSITIONING
OF GIVEN ENTITY
|
Abstract : In the recent years, widespread use of smartphones
increased the popularity of using Location Based Social Network (LBSN) and
Global Positioning System (GPS) for finding the user location. Connected wifi
or Bluetooth can be used to know the next approximate position by tracking
information from the network within the campus. Widespread use of android
mobiles made humans easy to track location.
In this project
“Mahithi” which is an android application that can benefit the users like student, faculty, parent and HOD, to
get the day to day updates of academic details like, attendance status, exam
results, placements, time table and notifications. Using Android, it is an
operating platform for mobile devices such as smart phones, tablet and
computers. The Android platform is a software stack for mobile devices
including an operating system, and key applications. Developers can create
applications for the platform using the android SDK. Mobile apps can have the
compatibility, share ability, immediacy features in effective manner. Faculty
and parents need to continuously monitor the student’s activities in order
for them to be aware of any difficulties the student is facing. Understanding
the student’s problem, fear or confusion will give the faculty a better
understanding the student’s learning difficulties
.
|
Guide Name : Amith K S
|
9. An Android Based
Smart Home Application To Predict Resident Activity
|
Abstract : Water is a limited resource and is essential for
agriculture, industry and for creatures existence on earth including human
beings. Lots of people don’t realize the true importance of drinking enough
water every day. More water are wasted by many uncontrolled way. This problem
is quietly related to poor water allocation, inefficient use, and lack of
adequate and integrated water management. Therefore, efficient use and water
monitoring are potential constraint for home or office water management
system. Internet of Things (IoT) which enables us to build a system without
human interference. In other words IoT is an environment that has the ability
to transfer data over a network without human to human or human to computer
interaction. The IoT allows objects to be sensed and controlled remotely
across existing network infrastructure, creating opportunities for direct
integration between the physical world and computer based system and it
provides more efficiency, accuracy as well as economic benefits. If the projections
and trends towards IoT become reality, it may force a shift in thinking about
the implications and issues in a world where the most common interaction with
the internet comes from passive engagement with connected object rather than
active engagement with content. Five key IoT issue areas are examined to
explore some of the most pressing challenges and questions related to the
technology. These include security, privacy, interoperability and standard,
legal, regulatory and rights, emerging economies and development.
In this real time
IoT system, A tank containing water is immersed with pH,temperature and
turbidity sensors for water quality
measurement,FSR sensor for water leakage detection and LED sensors for
determining the water level. These sensors measure the corresponding values
in the water. Since the outputs of the pH sensors are analog in nature and
this is converted to digital by Raspberry pi using ADC. System uses LAN for
communication with the control centre. These continuously read values are
stored in the repository. This process is displayed on LCD screen by
Raspberry Pi 3 and also the data can be accessed through website. The IoT
system provides the advantage of improved efficiency, accuracy and low price.
|
Guide Name : Arjun K
|
10. Cloud BASED WEB
APPLICATION TO CONDUCT MOCK CAMPUS TEST
|
Abstract
In this project
“CLOUD BASED WEB APPLICATION TO CONDUCT MOCK CAMPUS TEST”,Microsoft visual
studio is used for the development.It is an integrated development
enivironment which is used to develop computer programs for Microsoft
Windows, as well as web sites, web apps, web services and mobile apps. The
question of the entrance examination system are programmed and visually
displayed on the system’s screen in an
interactive form using visual studio. The student answers the question on the
computer system,immediately the question is marked and notified.The
result of the examination is also
displayed at the end of the examination which goes a long way to lessen the fears of students that they were
marked in the examination. This entrance examination system is designed to
assist university administration examination in attaining a standardized
sample,and as such the psychological implication of such a design is very
important.
This Web
Application provides facility to take online e-examination worldwide. It save
the time as it allows number of students to give the exam at a time and
displays the results of the exam when exam is completed, so no need to wait
for the result. It is automatically generated by the server. Administrator
&Coordinator has a priv ilege to create, modify and delete the test
papers and its particular questions. User can register to exam system, login
and give the exam with his specific id, and can see the results as well. The
Mock test System is an innovation in the context of College, and Academic
Institutes etc. This project will boot transparency of the examinations,and
provide opportunity for publishing results immediately after the test.Apart
from these facilities,large number of participants may sit for the test
simultaneously which will save the time. The answers are evaluated and the
marks obtained are stored in the database while the examiner can get the
results immediately from the system.
|
Guide Name : Dr.Thyagaraju G S
|
11. Museum Guide - BLE Beacon based Car Museum Prototype
Application
|
Abstract : Recent years have seen a confluence of two major trends – the increase of mobile devices such as smart phones as the primary access point to networked information and the rise of social media platforms that connect people. The capability to provide the users with added value services through low-power and low-cost smart objects is very attractive in many fields. In this project we try to provide information at the users finger tips by implementing these techniques. We propose Bluetooth with low energy functionality architecture to improve the experience of the user. Taking into account these considerations, it could be possible to design and develop a smart system able to improve the user experience in a museum. The huge collection of variety of artifacts in the museum is made available to be viewed easily by the viewers at the museum along with the detailed description of the object which can be accessed through this app on their Smartphone. The technique is implemented with the help of BLE Beacons which is a small device that sends out signals to nearby smart phones and tablets containing a small amount of data. The app detects the object through these signals and displays information about the object
A museum is an institution that cares for
a collection of artifacts and other objects. Bluetooth Low Energy(BLE) beacon
is a hardware transmitter that broadcasts their identifier to nearby portable
electronic devices. The developed app detects the object with the help of BLE
beacon and displays the information about the object. As a museum is an
institution that cares for a collection of artifacts and other objects of
artistic, cultural, historical, or scientific importance we have focused on
providing the museum with a smart guide. The problem investigated here is on
visiting a vintage museum, it is common for a visitor to have very less
information about the collection of objects there
|
Guide Name : H Manoj T Gadiyar
|
12. NEWS CRAWLER Distributed Crawler to curate filtered news
content
|
Abstract :
A Web crawler,
also called a spider, is an Internet Bot that systematically browses the
World Wide Web, typically for the purpose of Web Indexing. It is a system for
the bulk downloading of web pages. Web crawlers are used for a variety of
purposes. Most prominently, they are one of the main components of web search
engines, systems that assemble a corpus of web pages, index them, and allow
users to issue queries against the index and find the web pages that match
the queries. We propose to develop a distributed web crawler application to
curate filtered news content. Broad web search engines as well as many more
specialized search tools rely on web crawlers to acquire large collections of
pages for indexing and analysis. Search engines are used to extract valuable
Information from the internet. We
present the software architecture of the system, discuss the performance
bottlenecks, and describe efficient techniques for achieving high performance.
The News Crawler designed at the end of the project is a distributed web
crawler that curates filtered news content from all available sources. The
availability of multiple news outlets with bundles of data including
misleading headlines requires an analysis to be performed beforehand for
sentiment. The future scope of this
News crawler would be: In the design
of a Recommendation Engine using machine learning, where a keyword or root
can be used to recommend for various categories of requirements. It can also be used in extracting vast
information for comparison operations, for examples comparison between
objects, products or people
|
Guide Name : Saraswathi
|
13. An Optimized Map Reduce
Framework for Small Files: A case Study Of Weather Data
|
Abstract :
Large amount of data is being generated from different social media
around us. Every digital processes and social media produces large amount of
data. New skills are needed to harness this large amount of data. So Hadoop
came into existence to handle, manipulate and store those collected data from
all around the world.
Hadoop is an open source implementation framework which is widely used
because of its ease of programming, scalability and availability. The core of
Hadoop consists of a storage part known as Hadoop Distributed File System
(HDFS). Hadoop ecosystem consists of Mapreduce, Hive, Pig,
Sqoop, ZooKeeper. With the explosive development of cloud computing,
business and scientific applications increasingly take the advantage of
hadoop. The sizes of files stored and processed in Hadoop
are not bound to very large files anymore. Large amount of small files are
also generated in internet. Hadoop has a default
block size of 64MB. Small files are the ones whose size is very lesser than
the hadoop block size. However, Hadoop cannot provide a stable and efficient
approach for storage and also processing levels. To solve these problems and to
provide increased efficiency of managing small files in hadoop, we tried to
provide an approach. There are already two types of approaches. One is the
normal hadoop processing which is inefficient and the other is Hadoop archive
which is comparatively more efficient than the normal hadoop approach but it
is necessary to find more efficient approach to handle small files. So here
we use sequence file approach in which the data are converted into sequence
files and then processed to get better efficiency than Hadoop and Hadoop
Archive approaches.
|
Guide Name : Prof Guruprasad M S
|
14.Design and
Development of IoT based Smart Application For Garbage Monitoring and
Notifying
|
Abstract : Smart Application for waste management is proposed here is to
implement a smarter way of conventional waste management using smart sensors
to gather fill-level data, presence of garbage around the dustbin, and send
it to servers in real time. In this
proposed System there are multiple dustbins located throughout the city or
the Campus,these dustbins are provided with low cost embedded device,
ultrasonicsensor, which helps in tracking the level of the garbage bins and
each dustbin is located using GPS module so that it is easy to identify which
garbage bin is full. When the level reaches the threshold limit, the
Raspberry Pi will transmit the level along with its location. These details
can be accessed by the concern authorities from their place with the help of
Internet and an immediate action can be made to clean the dustbins.
|
Guide Name : Prof. Arjun K
|
15. SMART IOT WEB
APPLICATION TO RECOGNIZE AND MONITOR PLANT CONDITIONS
|
Abstract : Agriculture plays
very important role in human life and it has become a much more than simply
means to feed ever growing population. It is very important where in more
than 70% of population depends on agriculture in India. Plant plays very
important role in biological field and plant disease effect humans directly
or indirectly by health or economically. In our project we use IOT technology
and role of IOT technology in monitoring plant requirement and conditions.
The system can provide new way to access agriculture information for the
farm. One of the major challenges of the agriculture is the proper monitoring
of the soil health, the environment and adjusting the irrigation. In this project we have described the
development of web application that gives user or a farmer the capability to
identify plants requirements and helps to know its current condition.
Main objectives of
our project are- To measure completely different soil and climatic parameters
through respective sensors. This monitored information is collected with the
help of raspberry pi& to get a good low-price and versatile answer for
condition observation and in the farm. Main outcomes of project arehere the
plant conditions are checked whether it is normal or abnormal. If abnormal
conditions are detected necessary action has to be taken.
|
Guide Name : Dr.Thyagaraju G S
|
16. IoT based automatic student attendance monitoring and
notifying system
|
Abstract: Today
students‟ (class) attendance is become more important part for any
organizations/institutions. Recording and monitoring of class attendance is
an area of administration that can require significant amounts of time and
effort in a school/university environment, largely due to the amount of time
required in lectures to get the necessary information. To solve this problem
we are using RFID technology. RFID technology can be a powerful tool in
helping to manage student„s attendance throughout the working school day and
also enhance classroom security. RFID
technology has been applied to solve problems where it is necessary to take
automatically record the movements and locations of students in a classroom
of school/university environment. RFID is a technology that allows for a tag
affixed on identity card to communicate wirelessly with a reader, in order
for the tag‟s identifier to be retrieved.
|
Guide Name : Chandrappa S
|
17. Automatic Time Table Generator
|
Abstract: The manual system of preparing time
table in colleges with large number of students is very time consuming and
usually ends up with various classes clashing either at same room or with
same teachers having more than one class at a time. These are just due to common human errors
which are very difficult to prevent in processes such as these. To overcome
these problems people usually taking the previous year’s timetable and
modifying it but still it is a tedious job to incorporate changes. To overcome all these problems, we propose
to make an automated system. The system will take various inputs like details
of students, subjects and class rooms and teachers available, depending upon
these inputs it will generate a possible time table, making optimal
utilization of all resources in a way that will best suit any of constraints
or college rules. List of subjects may
include electives as well as core subjects. The case is similar to schools
and other educational institutions. So our aim is to develop a general
purpose which can efficiently generate optimal solutions.
|
Guide Name : Saritha M
|
18. Vehicle Tracking and Theft Detection System using MQTT on
IOT
|
Abstract: At the present time, the rate of
crime is increasing rapidly, because it is a kind of evident from the actual
fact that vehicle thefts became a matter of routine. Particularly these
vehicles may incur huge losses on the part of the amount invested on these
vehicles. To overcome this problem, there are numerous technologies are
available in the market which provides the protection from thefts. The main
purpose of this project is to notify the vehicle owner, when the vehicle is
moved/theft from the parking area and to monitor the movement of the vehicle
in real time. Raspberry pi 3 board connected with SIM908 GPS module will be
placed in the vehicle. GPS module receives the signal and provides the data
in NMEA format. Out of several messages, GPRMC message will be sent from the
board to the cloud. GPRMC message type has several information like latitude,
longitude, speed, time etc. Onc e the Vehicle is parked, ‘Set
Location’ button should be pressed in the web page, which saves the parking
area location. If somebody tries to move the vehicle from the parking area,
the GPS data will be different than that of previously saved location, which
triggers an SOUND ALERT notification in the web page. Mean time the Vehicle
can be monitored on the Map on Web page.
|
Guide Name : H Manoj T
|
19. Weather monitoring and sending the information to
registered user
|
Abstract: Weather
monitoring plays an important role in human life, so the collection of information
about the temporal dynamics of weather changes is very important. In any
industry during certain hazards it is very important to monitor weather. The
system proposed in this paper is an advanced solution for monitoring the
weather conditions at a particular place and make the information visible
anywhere in the world. The technology behind this is Internet of Things
(IoT), which is an advanced and efficient solution for connecting the things
to the internet and to connect the entire world of things in a network. Here
things might be whatever like electronic gadgets, sensors and automotive
electronic equipment. The system deals with monitoring and controlling the
environmental conditions like temperature, relative humidity and CO level
with sensors and sends the information to the web page and then plot the
sensor data as graphical statistics. The data updated from the implemented
system can be accessible in the internet from anywhere in the world.
|
Guide Name : Aswitha A
|
Subscribe to:
Posts (Atom)
Final year Academic Projects 2016-17
1.Context Aware Intruder Detection System With Multi-level Security Youtube link: 2. Performance Analysis o...
