TECHNIACL ANSWERS TO REAL

WORLD PROBLEMS

TEAM 4
TOPIC:REAL TIME FACE MASK DETECTION
 TEAM MEMBERS

• 18MIS0015-SABHARISHVARSHAN GJ
• 18MIS0036-SHRIPATHI C
• 18MIS0299-PRATHAP M
• 18MIS0314 - PUGAZH B
• 18MIS0316-SRINATH G
• 18MIS0384 - HARISH R
• 18MIS0406 - DHIYANESHVAR S
• 18MIS0410 - SIVA SURYA C
• 18MIS0415 - SELVAGANAPATHI B
 COMPARING CONTENT IN A DIGITAL
ASSIGNMENTS OF STUDENTS ACROSS SAME
AND OTHER SLOT STUDENT ASSIGNMENT FILES
(DHIYANESHWAR 18MIS0406)

• PROBLEM STATEMENT:
• Nowadays, the biggest problem for the faculty is the students are Uploading the same documents
for the digital assignments.
• Though the Plagiarism detector can be used to detect the similarities, it compares the documents
with the files or research papers on the internet only so without having the risk of plagiarism
detection on their assignment the students are simply uploading the assignments of a student who
does it by own it is very difficult for the faculties to detect the same documents as every document
has similar content regarding the assignment given and also time consuming.
• for eg. when the document of 5th student is upload by 48th student thereare more no.of documents
in between them if the faculty doesn’t remember then it cannot identified. this can’t be detect by
the plagiarism detector and so as a solution some other thing should be created for comparing the
files of the students uploaded.
• SOLUTION:
• To overcome this issue a new application can be created in which the files are uploaded in a
bulk amount once uploaded it should Tokenize the document then it should remove all the
stop words using NLTK library Then GenSim library is used to find the most relevant
words, line by line.
• This can be done by creating the LDA or LSA of the document then the file is compared
with all other files uploaded one by one using data comparing algorithm and the name of
detected files with more similarities should be detected and displayed with percentage.
• If so the faculty can identify the students with same documents at no time it should also
have the feature of storing the files in the data base once upload so that it can be used to
compare the files with documents uploaded on the other slot or even next year.
 C YB E R S E C U R I T Y B R E A C H E S I N T H E S MA L L ME D I U M
S C A L E C O MPA N I E S A N D T H E NE E D O F I N F O R MAT I O N
S E C U R I T Y A UD I T
( S E LVA G A N A PAT H I B 1 8 M I S 0 4 1 5)

• PROBLEM STATEMENT:
• Cybersecurity is a serious and one of the growing risk for organizations. In the pandemic times
many small and medium scale companies are pushed to use online platforms such as cloud and
moving their daily routine to the online.
• While bigger organizations are capable of doing this in a efficient manner many small and
medium scale companies are still struggling to adopt to the new normal. While pushing all the
day to day activities into the internet small medium scale companies somehow managed to do all
the necessary activities and also opened the way for the new security threats.
• In the pandemic situation many have started working from home it leaded the way for the rise of
many hackers. while most of them are being as beginners the risk they are making to the small
and medium scale companies are high. In order to avoid all we need a good auditing as well as
Management activities.
• SOLUTION:
• In the tackle of the situation we use different efficient and institutional theories to investigate
the influence of security and data breaches and also what are the roles that are needed to audit
this issue in a proper manner.
• As a solution we can try to develop a hypothesis based on the test samples that are gained
from large scale industries and reducing the size of the samples as per the need of the small
and medium size industries.
• From the hypothesis test we can identify the frequency of the data breaches and we will be
documenting what are all the security precautions and incident response they are doing .
• Also it will give the oversight to the upcoming small and medium scale organizations. After
the results we provide implications and areas for future research
 PR OBLEMS IN AS SE SS ING AND P REDICT ING
QUAL ITY OF WATE R
(S IVAS URYA C 18 MIS 0 4 10 )

• PROBLEM STATEMENT:
• Considering water tanks which stores ground water for domestic use and for small scale
agriculture purpose in different areas across different states in India, it is very huge task to
assess and predict the water quality.
• As the data is very huge it becomes quite difficult to handle the data and analysis the water
quality based on contaminants by the union water resources ministry. There are numerous
contaminants that pollute or degrade the quality of water.
• Water I different areas across different states could have been got contaminated because of
various chemical substances and wastes. It is difficult task for department of drinking water
and sanitation under union water resources ministry to conduct surveys region wise to
collect the data for prediction and assessing the water quality.
• SOLUTION:
• This problem can be solved using data mining. Data mining deals with data preprocessing,
algorithms like The Naïve Bayes classifier is one of the simplest approaches to the
classification task that is still capable of providing reasonable accuracy and data visualization.
• An web application which helps to collect data, clean data, classify data, assess and predict the
water quality of different areas across different states is the solution.
• The main idea is to develop web based application using python and flask implementing naïve
Bayes algorithm to address the water pollution problem (for instance of our dataset we
considered the ground water which are stored in tanks of different areas across different states
in India which consists of contaminants like Iron ,Salinity, Fluoride, Arsenic, Nitrate), taking
these contaminants as quality parameters we assess and predict the water quality
 SEC UR ITY P ROBLEMS IN THE ONL INE C ARD
TRANS ACTION
(HARIS H R 1 8 MIS 0 38 4 )

• PROBLEM STATEMENT:
• The main problem here is the name of Card-present-transaction is derived from presentation of
the card to the merchant by the card holder, at the time of transaction. This means that any online
payment via internet.
• In a Card Payment transaction, the card information is sent to the payment gateway and after
verification, the gateway will send the transaction authorization to the merchant along with a
receipt to the card holder.
• In such this transaction, in case of fraud by customer, the merchant is not liable of the losses
because of the payment gateway authorization. The important thing in Card-present-transaction
is PIN AND CVV number. We should solve the problem and reduce the frauds in the business as
it affects many trades and transactions as people fear of doing transactions using their credit and
debit cards.
• SOLUTION:
• We can solve the problem by creating and implementing a most securing payment during
the online shopping which may reduce the fraud business using credit card.
• We can get the e-sign of the card owner and provide e-sign facility and setup an OTP
receiving technology to their mobile at the end to proceed the transaction successfully by
implementing this with the use of RSA algorithm which ensures that the keys, in the above
illustration, are as secure as possible by this we can reduce fraud by providing esign of the
card owner and at the end of the transaction the owner receives the OTP to their mobile
number and then only the payment will successfully completed.
• So in this way the fraud business may reduce and also may promote the users to use cards
for transactions.
 HARMFUL ATTACKS ON THE C RITICAL DATA
S HARED VIA EM AIL
(PUGHAZH B 1 8M IS 03 1 4)

• PROBLEM STATEMENT:
• The main problem is many harmful attacks are attempted and gets succeeded in taking the critical
data.
• E-mail is now widely used as a means of communication by many people. It is a type of text
messaging service that allows users to exchange personal information, notifications, transactions, and
bank account information, among other things.
• These are critical data that must be safeguarded from harmful attempts. However, security and
protection of email communication remains a difficult task. Several algorithms have been proposed to
solve these security concerns .
• We encrypt the message before transmitting it using an application interface and decrypt the
encrypted message at the receiver end by using one of these cryptographic algorithms, such as AES,
DES, Blowfish, etc.
• SOLUTION:
• This problem can be rectified by creating a system which undergoes the following steps. At first
from the sender side The message is typed by the user and attachments are attached if any.
• it then takes it in the form of bytes . The bytes is then encrypted using the algorithm what sender
chooses from AES, DES, Blowfish, ARC2, ARC4,etc.
• The encrypted bytes is converted in to hexadecimal and then it is sent to the user via SMTP server
using their email address as an encrypted mail. Now from the receiver side The received encrypted
hexadecimal message is again converted to bytes.
• The email content and attachments are then decrypted using the decryption method of the same
algorithm which is used for encryption . The bytes is converted to UTF-8 decrypted text, thus giving
us the original message sent by the sender.by this we can safeguarded from harmful attempts.
 SOCIAL DISTANCING DETECTION
(SHRIPATHI C 18MIS0036)

• PROBLEM STATEMENT:
• The distance between people to mitigate the impact of this coronavirus
pandemic Social-distancing is an important way to slow down the spread of
infectious diseases. People are asked to limit their interactions with each other,
reducing the chances of the disease being spread with physical or close contact.
• SOLUTION:
• Social distancing detection using deep learning to evaluate the distance
between people to mitigate the impact of this coronavirus pandemic. The
detection tool was developed to alert people to maintain a safe distance with
each other by evaluating a video feed. The video frame from the camera was
used as input, and the opensource object detection
 LANE DETECTION
(PRATHAP M 18MIS0299)

• PROBLEM STATEMENT:
• Road traffic accidents are one of the problems that are risking people's lives.
Many lane departure accidents especially on high-way roads are due to driver’s
inattention or incompetence or drowsiness.
• Therefore it is needed to save the considerable number of lives by warning the
driver of imminent danger.
• In many highway traffic accidents, the main cause is straight line detection. Car
accidents caused by unintentional run off road have become an important topic
within worldwide accident research activities
• SOLUTION:
• Computer vision is a technology that can enable cars to make sense of their
surroundings. It is a branch of artificial intelligence that enables software to
understand the content of an image and video.
• Modern computer vision has come a long way due to the advances in deep
learning, which enables it to recognize different objects in images by
examining and comparing millions of examples and cleaning the visual
patterns that define each object.
 DEVELOP MENT OF S MART E-HEALTH S YSTE M FOR
COVID-1 9 PANDE MIC
(SRI NATH G 18 MI S0 3 16 )

• PROBLEM STATEMENT:
• Now a days it is very contagious to go to hospital for corona virus. There are
many issues people can get infected with the virus easily if they do not follow
proper safety measurement.
• No a day's going hospital is risky for older people due to corona pandemic. It
is safe if people can get treatment plan of doctors staying at home is very safe.
• The communication between doctor and the patient is very important. The
more the patient describe the problem clearly the more doctor can find the core
problem of the disease.
• SOLUTION:
• Real-time online Doctor Patient interaction and prescription are the main
features.
• Increasing popularity of online systems and to avoid time waste, distance
people will easily take advantage of this it. The doctors are specialized and
highly professional in their field.
• Website has also blog, shop site where doctor post different health issue to
make awareness among the society and patient can buy their medicine as well.
 REAL TIME FACE MASK DETECTION
(SABHARISHVARSHAN G J 18MIS0015)

• PROBLEM STATEMENT:
• The present scenario of COVID-19 demands an efficient face mask detection application.
As colleges, airports, hospitals, and offices where chances of spread of COVID-19 through
contagion are relatively higher .
• If anyone is found to be without a face mask, beep alert will be generated. As all the
workplaces are opening. The number of cases of COVID-19 are still getting registered
throughout the country.
• If everyone follows the safety measures, then it can come to an end. Hence to ensure that
people wear masks while coming to work we hope this module will help in detecting it.
Reports indicate that wearing face masks while at work clearly reduces the risk of
transmission.
• SOLUTION:
• A hybrid model using deep and classical machine learning for detecting face mask will be presented.
A dataset is used to build this face mask detector using Python, OpenCV, and TensorFlow and Keras
.
• While entering the place everyone should scan their face and then enter ensuring they have a mask
with them.
• If anyone is found to be without a face mask, beep alert will be generated. A hybrid model using
deep and classical machine learning for detecting face mask will be presented.
• A dataset is used to build this face mask detector using Python, OpenCV, and TensorFlow and
Keras. While entering the place everyone should scan their face and then enter ensuring they have a
mask with them. If anyone is found to be without a face mask, beep alert will be generated.
 REASONS FOR CHOOSING REAL TIME
FACE MASK DETECTION.

• Technology Used: Python, OpenCV, and TensorFlow and Keras.

• Usage: This technology can be used on Live Video camera. With further
improvements this can be integrated with CCTV camera to detect and identify
people without masks.
• Cost: This model is particularly resource efficient when comes to deployment
and also it can be employed for safety.
• Scope: This technique can be merged with embedded application systems at
public places such as airports, train stations, workplaces and schools to ensure
subordination to the guidelines for public safety.
 TOOLS & METHODS

• TOOLS & FRAMEWORKS NEEDED:

• Scikit Learn
• Tensor Flow
• Keras
• OpenCV
• MobileNet
• Methods:
• Data set Collection , Data pre-processing , Training & Testing Model ,Detect Face Mask Using
OpenCV
• We have devised a smart framework for detecting facemask in real-time in this project.
THANK YOU