Zoya Sumbul Zaheer

Academic

Verbatim text

Zoya Sumbul Zaheer
+923315666421, zoyasumbulzaheer@gmail.com,i180721@nu.edu.pk
Sheesham Road, Sabzazar Colony, Rawalpindi Cantt.
LinkedIn: https://www.linkedin.com/in/zoya-sumbul-zaheer-
3ba202221/
Education
Bachelor of Science (Computer Science)
Major:
Web Development and Software Project Management & Engineering.
APSACS Humayun Road Rawalpindi
F.Sc (Physics, Chemistry, Mathematics)
APSACS Humayun Road Rawalpindi
Matriculation (Physics, Chemistry,Biology)
Projects
Final Project: Machine Learning and Image Processing Lung Disease Application [VGG,MERN]
MILDDA is website that provides early detection and classification of lung diseases into COVID-19, pneumonia,
tuberculosis, and lung cancer. It is an application designed using deep learning and image processing built to assist the
doctors and radiologist in decision making and reducing a large amount of time spent on diagnosis of multiple x-ray
images per day.
Semester Projects:
Pharmacy Management System [MERN]:
Designed a Pharmacy Management System in MERN and developed its all modules.
Sudoku Puzzle Solver:
The objective of this game is to fill a 9×9 grid with digits so that each column, each row, and each of the nine 3×3 sub-
grids that compose the grid (also called "boxes", "blocks", or "regions") contain all of the digits from 1 to 9.
Chess [Python]: A 2D Board game with two players made in Python.
Timetable Scheduler [Python]: Exam Timetable Scgeduler made in Python.
15 Puzzle Problem [C++]: Solved 15 Puzzle Problem.
High Hopes: An Android Application consist of different motivational audios.
3H Smart Builds: An Android Application where customer purchase different building product form nearest vendor.
Advanced Keylogger [Python]: Implemented keylogger using Python which will have a spyware payload.
Inventory Management System [HTML, PHP,SQL, CSS]:
Designed a Pharmacy Management System in PHP language and developed its all modules.
Desktop Screensaver [C++]: ScreenSaver consist of different Shapes done using polymorphism in C++.
Trex Game [Assembly Language]: A 2D game made in Assembly Language.
Notepad Implementation [C++]: Develop a Notepad whose functionality is similar to Microoft Word.
Bricks Layer Game [C++]: A 2D Brick breaker game in C++.
Work Experience
2021 -  2022
Skills & Tools
Professional Skills: Fast Learner, Detail Oriented, Adaptable (work in changing environment), Problem Solving Skills,
Organizational Skills, Able to Build Relationships.
Technical Skills:
C++, C, Python, SQL, HTML, CSS, JavaScript, React, Angular, PHP, UML, Java, Socket
programming, Data Structure, Object Oriented Programming, Multithreading.
Achievements
Certificate from Coursera authorized by different foreign universities(2020): Introduction to HTML5 and CSS3,
Interactivity with JavaScript, Advance styling with Responsive Design, Web Design for Everybody Capstone, Graphic
Design, AI for Everyone, Neural Network and Deep Learning, Programming for Everybody(Getting Started with
Python), Python Data Structure.
Activities
Class Representative throughout degree
Interests
Program Problem Solving
Class of BS (CS)
Final Year
Projects
Accident Detection and Emergency Response System
Almost everyone carries their smartphone with them while driving, and smartphones nowadays
have a lot of sensors present inside them.
Our system makes use of these sensors to detect an accident, and inform relevant authorities about
the exact location of the accident.
The user will sign-up and provide their personal details, along with emergency contacts.
During the trip in case of an accident, it will be detected using the readings on the Accelerometer,
Gyroscope and Microphone present inside the smartphone.
Once an accident has been confirmed, the concerned authorities (helplines and emergency
contacts) will be sent an alert along with the location.
The ambulance portal will be shown the shortest path to the location.
All the people using this app in a nearby radius will be notified of the accident and its location.
The Admin Panel will be able to oversee real-time accidents, along with a history of events.
Statistics will be saved, showing the number of events taken place in particular areas in a given time
selected by Admin user.
The Admin will have access to user’s information to make contact if needed.
Technology Used:
Java, Android Studio, Java Spring Suite 4.0,
Firebase Database, SQLite, MERN Stack
Supervisor Name:
Mr. Bilal Khalid Dar
Group Members:
Fahad Ahmad Siddiqui (I18 – 0590)
Muhammad Saad Minhas (I18 – 0691)
Muntahim Hussain Khan (i18 – 0707)
ADAPT
APT stands for Advanced Persistent Threats. It involves a group of highly experienced cyber
criminals targeting specific sectors to mine data, sabotage or takeover sites and for other nefarious
motives.
With the evolution of more advanced sophisticated attacks, security breaches have become more
complicated posing a great security challenge for companies. Cyber security teams depend on
publicly documented analyses of tools, routines, and behaviors which serve as a reference for the
known tactics, techniques, and procedures (TTPs) to update themselves on the latest findings in the
cybersecurity domain and install defenses against Advanced Persistent Threats (APTs). For
providing such theoretical knowledge of defending against attacks, cyber security experts are
currently manually going through online sources to extract APT relevant information and perform
the threat analysis. AD-APT automates this whole process of web crawling and extracting APT
related information through machine learning making it faster for the cybersecurity experts to
respond to these attacks and saving them from going through the manual work.
Features:
Crawling security blogs and extracting key characteristics relevant to APTs.
Identifying both known and unknown APTs.
Creating APT profiles.
Visual Representation of Data.
Technology Used:
ReactJS, Elastic Search, Express, NodeJS,
Python, PyTorch.
Supervisor Name:
Sir Asim
Co Supervisor:
Sir Omer Beg
Group Members:
Mohammad Ali Mustafa (I18-0619)
Omer Anwar (I18 -0562)
Aniketos: System Vulnerability Scanner
Aniketos is a web application that scans the whole system both internally and externally, and
provides a detailed report of all the vulnerabilities present in the system. Internal scanning includes
the network scan of the organization that provides the details of all the systems connected with the
organization’s internet. It also provides the facility to scan the operating systems of all the devices.
It generates the asset inventory of all the devices showing all the softwares installed in the devices
and also provides port scanning. On the basis of asset inventory and open ports, it provides the
CVEs associated with the devices. In External scanning, we scan for network security, Application
security
and
DNS
Health
of
a
given
domain
and
do
risk
scoring.
Features include:
- Network Scanning to get details of the devices connected.
- Asset inventory scan to get all the assets(softwares) installed in all the devices.
- Port scanning of all the devices connected.
- CVE scan of all the open ports and softwares installed.
- Risk Scoring of all the devices connected.
-Network Security scan of a domain to get the details of open ports and services running.
-External scan to check the application security and DNS health of a given domain.
Technology Used:
Python, Nmap, Java, React,MySQL
Supervisor Name:
Dr. Muhammad Asim
Group Members:
Muhammad Hassan Raza (I18-0424)
Zain-ul-Abideen (I18-0442)
Ahsan Zaheer (I18-0444)
Attack Herald
Attack herald is a Research and Development project aiming to predict cyberattacks generated by
malware before they actually materialize so that they can be prevented from occurring instead of
being flagged after they have occurred. Malware-generated cyberattacks include distributed DDoS,
ransomware and Phishing, etc. Before a piece of malware launches an attack, it is likely to engage in
some pre-attack behavior in preparation for the attack, for example contacting a malicious
Command & Control server(CnC). This pre-attack behavior can be observed on infected hosts or
networks as an evidence trail pointing to possible upcoming attacks.
The initial goal of this project was to first analyze a large amount of malware data from varied
sources to confirm that pre-attack behavior existed and then develop an attack prediction
mechanism that would monitor a host or a complete network for such suspicious behavior to
predict an attack for timely prevention.
This project uses machine learning and empirical data analysis to detect pre-attack behavior of
modern malware, and aims to produce a good quality research publication.
Our end product is a web based tool that will be deployed at an ISP level. Our tool would be
capturing ISP’s network traffic in real time and  the ISP administrator would be able to monitor the
network for any potential cyber-attacks in real time.
Technology Used:
Bash, Flask, Python, Pyshark, React, Sklearn,
Snort, Tensor Flow, Tshark
Supervisor Name:
Dr. Zainab Abaid
Group Members:
Izyan Masood (I18 - 0742)
Omar Anwar (I18 - 0430)
Usama Rashid (I18 - 0673)
Augmented Reality Tactical Simulator
Augmented Reality based tactical training simulator for special forces. The simulation includes a
team of multiple members in various scenarios. Team members will communicate with each other
using call outs, tagging in 3d space, and can view the location of their allies. Each member is part of
the virtual arena connected to a single lobby. A lobby can also have observers analyzing the
performance of players. A player can see a 3D or 2D view of the arena through their device. AR
mesh generation will enable team members to share their 3D views. The simulator will cover
different types of scenarios like rescue operations and arena sweep. Post-training analysis will be
provided through the app where the performance of each player can be analyzed and their
responses to callouts can be judged.
Technology Used:
C#, Unity, ARCore, Photon,
Substance Painter, Adobe Photoshop,
Adobe Aftereffect, 3ds Max
Supervisor Name:
Dr. Adnan Tariq
Group Members:
Rao Ubaid (I18-0504)
Tanzeel Ahmed (I18-0517)
Tayyab Ejaz (I18-0462)
AutoFYP
AutoFYP is for BS students where they are able to perform all their FYP related tasks(FYp group
making, supervisor assigning, uploading all documents of FYP, assigning panels etc). There are three
views of this portal– Student View, Teacher View and Admin/committee View – In student view
students are able to use features like sending requests to other students for FYP groups, sending
requests to teacher for supervision, to view committee announcements, to see teachers propose
FYP ideas, upload the documents and see their marks. In the admin view committee are able to use
features like register students and teachers on the portal, make FYP panels, make announcements
for teachers and students, assign different FYP groups to different panels and set different
weightage to different evaluation forms that committee has created.
while in the teacher view panel members can view the uploaded documents of the students and in
case of missing they can send the reminder email to the students and different panel members can
evaluate the group work and send them the feedback and upload their marks.
Features include:
- Creating different panels for FYPs and assigning them different FYP groups.
- Realtime announcements from FYP committee on the AutoFYP portal.
- Notifying students by sending mails for missing documents.
- Creating the evaluation form of FYP-1 and FYP-2 and setting their weightage.
- Sharing the teachers FYPs ideas with students.
- making student groups and sending requests to teachers for supervision.
Technology Used:
javascript, Nodejs, MERN
stack, Visual Studio
Supervisor Name:
Mr. Saad Salman
Group Members:
Ali Hamza (I18 - 0601)
Mehran Tariq (I18 - 0704)
Muhammad Rashid (I18 - 1583)
Automated Business Intelligence Reporting Solution (ABRS)
The Automated BI reporting solution with the help of three-layered architecture and ELT along with
Power BI will provide the user with business insights. User can also view the current patterns in the
measures with respect to one or multiple dimensions for taking informed decisions.
The source data was dumped into a data lake, to ensure the data sanity. After that business rules
and logics were implemented and surrogate keys were populated, and data was loaded into the
integration layer. Finally depending upon the use cases the aggregated data was stored in the
semantic layer. BI Tool was connected to the semantic layer for the implementation of business
reports and dashboards. These reports are embedded in our pleasing and stylish front-end which
we made on React. Retail data set known as Adventure Works is being used for implementing five
use cases which includes sales, product, purchase/vendor, person and shipment use cases. Most
importantly,
it’s
all
done
on
Big
Data
tools
and
technologies.
Features include:
- The three layered model mentioned above eradicates all data issues and saves time and
CPU/Memory resources as aggregated data is stored in a separate layer.
- Provide the user with business insights
- User can also view the current patterns in the measures with respect to one or multiple
dimensions for taking informed decisions.
- Creation of data pipeline (Data transformation, data cleansing , data integration)
-  Dashboards and reports on Power BI (Easy to understand about patterns)
- Only specific user can log in to view analytics section on website made on react.
Technology Used:
Cloudera, Impala, HiveQL, Hadoop, Power BI,
Java script,  CSS, Bash, SQL, React Framework
Supervisor Name:
Dr. Ejaz Ahmed
Group Members:
Zain Sohail(I17-0016)
Zaeem Ansari(I17-0353)
Hashir Akbar(I17-0080)
Automated Knowledge Graph Construction
for Large Document Collections
Carrying out complex, rich contextualized searches from a large pile of documents is no trivial
matter and if facilitated could be extremely beneficial to the digital humanities domain. Our final
year project, based on the symbolic Artificial Intelligence (AI) field - Knowledge Graph (KG), is a
collaboration with the Goethe University of Frankfurt which has provided us with expert
annotations of a tafsir dataset in TEI/XML format to enable contextualized search with semantics
from historic Islamic literature. Our final year project is divided into three major modules, ontology
(a formal semantic data model) design and evaluation, automated knowledge graph generation
where we had to convert the data with TEI/XML into RDF, and making a web portal to enable users
to run structured queries on the KG. We have used Protégé (A tool to create a knowledge base) for
the first module, Python and Owlready for the second module, and Django for the development of
the web portal.
Our web portal provides the following features:
-
SPARQL Endpoint (enables users to query a knowledge base via the SPARQL language)
-
Browsing of Tafsir Al-Tabari
-
Advance Search from Tafsir Al-Tabari
Technology Used:
Python, Protégé, GraphDB, Owlready,
SPARQL, Django, JavaScript, HTML, CSS, XML
Supervisor Name:
Dr Amna Basharat
Group Members:
Rafay Rashed (I18 - 0549)
Talha Ahmed (I18 - 0658)
Zaid Saeed (I18 - 0506)
AutomateIt
A Home automation software to control the appliances at one’s home using Urdu voice command
or application-based input. The system is responsible for controlling some features of home
appliances not just by an android app but also with voice which can be heard either from the app or
the microphone device installed. Turning appliances on or off, changing the AC temperature,
changing TV channels or playing the next/previous song. All this can be controlled by one’s voice or
using the app.
Features include:
-
The system is compatible with multiple accents, gender voices and synonymous words.
-
There is a mobile application in which a user can speak in Urdu to control all the appliances.
-
There is a microphone device installed so that a person could speak directly into it rather
than speaking in front of the mobile application.
There is also a feature of controlling the appliances by non-voice input as well i.e., touch on buttons
in mobile application.
Technology Used:
Raspberry Pi, React Native, Jupyter Notebook,
Google Colab, MongoDB, Python, Go Lang
Supervisor Name:
Mr. Umair Arshad
Group Members:
Sameet Asadullah (I18 - 0479)
Aysha Noor (I18 - 0591)
Tayyab Ali (I18 - 0531)
AuxVision
“AuxVision – Assisted Vision for the Visually Impaired” aims to change the lives of the visually
impaired by enabling them to navigate autonomously in indoor environments. To accomplish this
task, we rely on hardware components such as different sensors to perceive the environment. All of
this has been combined to make a wearable device. Our sensors include the following:
-
Ultrasonic sensor.
-
Stereo camera.
Using these sensors, we scan the environment around the individual, identify the types of objects in
the vicinity and at what distance they are to the person through depth estimation with stereo
cameras. In case of potential collision, the user is informed through data from ultrasonic sensor so
they can alter their direction of movement. For object detection we are using deep learning model.
All of this information is converted from textual format to speech for the person to interpret. This
allows them to make an informed decision as to what they want to do.
Technology Used:
Python, Raspberry Pi, OpenCV
PyTorch, TensorFlow
Supervisor Name:
Dr. Zohaib Iqbal
Group Members:
Ali Asghar (I18 - 0475)
Affan Arif (I18 - 0484)
Buraq Khan (I18 - 0800)
Baby Neuron
Baby Neuron focuses on visually pleasing and engaging 3D environments to keep the children’s
attentions captivated all the time while making them interact with certain stage objects, materials
and the environment, solve puzzles and recall patterns from memory! Baby Neuron also comprises
of a 2D version of the same 3D game to do a fair comparison between the learning outcomes of the
both games. We have created four games for our FYP. The first two games were the Card matching
in which children were supposed to remember the objects behind the cards in the pairs of two. This
was developed in both 2D and 3D dimensions.  The subsequent two games were a pathfinder game
known as Memory Jog where the player is supposed to remember the pattern of highlighting blocks
and repeat the pattern at multiple levels. The games include many modes such as Normal Mode,
Timed Mode and Free Mode. Other than that the gamification elements include:
- Scores
- Avatar Skins
- Levels
-Player Lives
- Multiplayer Highest Levels
- Highest Level
Technology Used:
C#, Unity, Visual Studio, Firebase
GitHub, Visual Studio
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Momin Salar (I18 - 0574)
Shahnoor Haider (I18 - 0460)
Umair Anwar (I18 - 0500)
ClickFix
ClickFix is being made, whilst keeping in mind the perspective of Handymen and people who want
to get their home accessories fixed. There are two views of this app – Handyman View and
Customer View. Customers can take pictures of the defective home appliance, and our app would
identify the type of the object, and as a result, it will display the list of relevant handymen. In
contrast, if customers are not comfortable taking and uploading the picture, they can manually
select the type of service they want, and again as a result, a similar list of relevant handymen would
be displayed. The core competency of our app is that we have provided a quote system; the
handyman and customer can negotiate the price before finalizing the deal. This feature helps the
customer to get better deals at the best market price. We are also providing a real-time location
tracking feature for the customer, so the customer can easily track the progress of the ongoing
deal. From looking at the handyman's perspective, they can easily find job opportunities using only
a mobile app. They do not have to wander the streets to find a job; They would get employment.
Features include:
-       Near Real-time image classification to classify the defective item.
-       Quote System to get a market-competitive rate to get things fixed.
-       Chat Messages, both handymen and customers can chat with each other.
-       Recommendation System, for the customer, to enjoy the best service.
Technology Used:
Flutter, Firebase, Tensor flow,
OpenCV, Adobe XD, Android Studio
Supervisor Name:
Mr. Asif Naeem
Group Members:
Hamza Ijaz (i18 - 0522)
Hadia Chaudhary (i18 - 0577)
Haroon Ali (i18 - 0737)
Covitector
Covitector is a first ever non-invasive, rapid, free of cost platform to detect Covid through the input
of a forced cough sound. Cough Sound is the only single feature that every Covid Positive or Covid
Negative patient can experience, where other symptoms like loss of taste or loss of smell is not
experienced by all patients. Covitector uses a mix of Deep Learning Techniques to produce some of
the very complex models to understand the inter-connectivity and correlation of features from
MFCCs and Delta MFCCs, to form a complex algorithm to diagnose people. There were 6 models
trained and tested on different data samples that are openly available, conjuring a total of 98.4% on
CoughVid and 100% on Coswara and Virufy-Covid Datasets.
A ReactJs application backed by Flask, Google Firebase is built to aid people with a web application,
where they can record, upload, check daily statistics of Covid Cases across the globe; google-maps-
api integrated with the web app helps customers get live update of Covid-positive cases in their
vicinity.
Features include:
- Recording their Audio Sounds - Uploading pre-recorded Audio Sounds. -Applying Silence Removal
- Applying Cough Detection Algorithm
- Computing MFCCs  and Delta MFCCs
- Majority Voting on the cough sound and notifying the results.
- Data Scraping from worldometers website for Daily Statistics
- Integration of google-maps-api to produce live update of covid positive cases in vicinity
Technology Used:
DLTS, Python, ReactJS,
Colab, Flask, Firebase, Google Maps Api
Supervisor Name:
Mr. Umair Arshad
Co-Supervisor Name:
Mr Salman Ijaz (PhD Researcher at NTNU, Norway)
Group Members:
Omer Ihtizaz (I18-0404)
Faaira Ahmed (I18-0423)
DeepDub
DeepDub is an engine which can translate videos from one language to another - it dubs the human
speech and also alters the lips of the actor so that it seems like they are speaking in the dubbed
language. It comprises of a pipeline of Deep Learning and Machine Learning models which work
together to produce the results. It is built to be modular from the ground up; it is easy to swap out
modules for other modules, and to add more languages. To demonstrate the power of this engine,
users can record themselves speaking some words and see themselves being dubbed, using the
“Echo” app. To show the applications of the DeepDub in the industry, users can edit videos
according to their desire, using the “Showup” app.
Features include:
- Extensive Language Support (German, Chinese, Urdu, Hindi, and Turkish, to English).
- Useful side-products of this engine are that it can caption a video and also produce a translated
subtitles file (.SRT file)
- The Echo App (Live demonstration)
- The Showup App (Video editing app with DeepDub integration)
Technology Used:
Python, PyTorch, FastAPI, Django, ReactJS
Supervisor Name:
Dr Mirza Omer Beg
Group Members:
AbdUrRehman Subhani (I18 - 0732)
Saad Ahmed Bazaz (I18 - 0621)
DeepScene
DeepScene is a research project aimed towards developing a novel solution for visualizing virtual 3D
animated scenes using text or speech. This allows the user to create 3D scenes as they please. Its
applications include helping content creators in story-boarding, helping students visualize problems
and ideas and can potentially be used by architects to map out building sites and visualize interior
design concepts.
In essence, our engine can play at the intersection of natural languages and real world objects. To
meet the use cases in different domains, we don’t intend it to be an end to end pipeline but just a
core which can be used for different tasks via transfer learning techniques.
We achieve this by creating a scene graph from text or verbal input and pass that graph to a graph
convolutional neural network for an edge classification task. This enables us to classify the graph
edges based on distance and direction class predictions and place the new entities into the scene
accordingly. And to bring life to the scene we further predict animations of the generated entities
as-well.
Our main contributions include creating scene graphs from text, creating a playground environment
to save training examples and animating the 3D scenes.
Technology Used:
Python, C#, Unity, ,
Supervisor Name:
Dr Omer Beg
Group Members:
Syed Zohair Abbas Hadi (I18-0671)
Abdul Mannan (I18-0577)
Hamza Maqsood (I18-0744)
Doc express
Doc express is basically an Android plus web Application which help organization in organizing the
records and files also requests are handled in a well-organized way. It improves the working
efficiency of the office, with this application we can easily track the documents. We are able to
generate reports so we can see the progress of the department. Employee that want to initiate a
new application for a specific applicant will forward it to other departments for verification. After
verification application will be accepted or rejected. Applicant can see the progress of their
application. They can also see the department in which their application is currently present. Also,
they
can
check
whether
their
application
is
accepted
or
rejected.
Features include:
- Defined tracking route (can be changed later)
Calculation of expected number of days to process the file/document
Current state of document
Searching of documents
Configuration and installation of central server and database system
SMS alerts to end users/clients
Check in and check out of documents
Daily summary report
Technology Used:
Oracle, Java, Php, SQL, Next Js, React
Android Studio
Supervisor Name:
Dr. Muhammad Ejaz
Group Members:
Muhammad Haris Khan (I17 - 0209)
Muhammad Arshad Habib (I17 - 0208)
Khilat Mehdi (I17 - 0296)
eCampus
e-Campus aims to provide a cashless transactions ecosystem for an organization, which in our case
is university, by providing a blockchain based payment solution that benefits faculty, staff and
students alike. We aim to make the campus cashless and hustle free. Using our system any
transaction in the university at any level will be done without cash, simply by using our developed
app. The app will allow proceeding for different transactions between any two entities of the
system. In the blockchain based private network, each entity of the organization will have defined
roles. The system will make the transactions fast, traceable and will provide a maintenance free
self-driven system. The system will also reduce the financial resources as there is no need to install
more atm machines even if the number of students is increased every year.
Features include:
- All kinds of transactions within the well-defined ecosystem (University)
- Maintained history
- Deposition and withdrawal of physical currency
- Balance visible to user at all times
- Real time transaction and updates.
- Immutability, Transparency, Traceability, Documentation
\
Technology Used:
React, Node, Ethereum, Android Studio, Solidity
Supervisor Name:
Ms. Hina Binte Haq
Group Members:
Ahsan Ali Abbasi (I17 - 0306)
Sameed Ansari (I18 - 0539)
Shahzeb Malik (I18 - 0611)
Explainable Ai For Hate Speech Detection For Urdu
In this day and age of social media, information spreads very quickly through blogs, discussion
forums, videos, posts, images etc. The rate at which the data is generated and consumed has
brought about numerous issues; Hate Speech being one of them. It is a relatively new concept and
lacks a universal definition. It covers a wide variety of content such as hate against race, ethnicity,
gender, sexual orientation, religion, nationality etc. The social media users indulging in such
practices believe that they are practicing their freedom of speech. However, content used to target
a certain group of people and defame them or destroy their repute, due to certain personal beliefs,
cannot be considered as freedom of speech. Hate speech and hate crimes are connected. Majority
of the present AI models are all black box models. This means that as a user we cannot determine
why a model gave a certain result. Our Explainable AI models classify the text into
Hate/Offensive/Neutral speech and alongside provides explanations which are easily understood by
a layman. A user can enter their own text to check for any hate or offensive speech. Also, a user can
enter a UserHandle of a twitter profile. It will scrape the most recent tweets, segregate them into
Urdu, Roman Urdu and English tweets, and provide results on each language separately. The results
are shown in the form of charts, feature highlights, word clouds and textual explanation. The main
focus of work is in Urdu language which is an under resourced language.
Technology Used:
Python, Tensorflow, Keras, Pytorch, Kaggle,
Jupyter Notebooks, Shap, Lime, Google Collab
Supervisor Name:
Mr. Umair Arshad & Doc. Omer Beg
Group Members:
Maria Yasir (I18-0454)
Maaz Asad (I18-474)
Rizwan Haidar (I18-0536)
ForestFellow
The forest fellow web application is being made, with the motivation of reducing deforestation and
promoting efficient afforestation. The application provides benefits to both individual plant
enthusiasts who want to do some good to our environment and to professional foresters by making
their work more efficient and automated. Individuals can use the application to check the species of
the plant beforehand and recommendations for plantation. On the other hand, the professionals
can use the application for checking deforestation in an area or analyze growth of the forest by
providing satellite images.
Features include:
 Detecting land features in an area from satellite images
 Finding Specie information of plant from leaf images
 Detecting and visualization of deforestation in an area from satellite images
 Analysis and visualization of forest growth in an area from satellite images
Getting plant recommendation for a specific city
Technology Used:
Python, TensorFlow, PyTorch,
OpenCV, Flask, MySQL, Anaconda
Supervisor Name:
Ma’am Amna Irum
Group Members:
Abdul Wahab (I18-0617)
Ahmer Ejaz (I18 - 0620)
Kamran Ahmed (I18 - 678)
GoCart
GoCart is an automated shopping cart with the aim to make shopping a hassle-free and simple
experience for both the consumer and the shop employees by utilizing a combination of IoT and
AI.
It will allow cashier-less checkout using an integration of radio-frequency identification (RFID)
and image recognition using deep learning, with a very simple user interface so it is
understandable and easy to use for all kinds of users.
Features include:
Radio Frequency Identification
Image Recognition
Web Application
Technology Used:
Python, Raspberry Pi, Flask, ReactJS, Github,MySQL,
Yolov5,Roboflow, Visual Studio Code
Supervisor Name:
Dr. Adnan Tariq
Group Members:
Aleezeh Usman (I18-0529)
Moiz Muzahir (I18-0786)
Areesha Tahir (I18-1655)
Haath Ki Baat
HaathkiBaat is a mobile application that will be built to assist deaf people for understanding
conversations with hearing people and vice versa. It will take Urdu speech as input and convert it
Features include:
-Taking Input from the mic button
-Sign Language will be displayed on screen using an avatar.
Technology Used:
PyTorch, React Native, JS, Python, Blender, Django
Supervisor Name:
Mr. Saad Salman
Group Members:
Zeeshan Ikram (I18 - 0660)
Sundus Khalid (I18 - 0666)
Hate Speech Inspector
Hate Speech Inspector is an analytical web app that takes tweets from Twitter on runtime and
detects whether the tweet includes Racism, Sexism, Islamophobia, General Hate, and No Hate
Speech.
After
all
of
this,
it
visually
represents
the
tweets.
Features include:
- Watch all the labeled tweets in the form of 3 different charts. You can select your own choice, The
charts are Bar Chart, Pie Chart, Radar Chart
- Search tweets by Keyword, you can search tweets by entering any keyword on the search bar and
check how many tweets contain any type of hate we mentioned before.
- Search tweets by Username, you can search tweets on the basis of username as well. Just set the
“Search by Username” on the dropdown and write Twitter username on the same search bar. You
will get how many tweets are labeled in categories.
- View all tweets, the tweets can be checked by going to another page.
Technology Used:
Adobe XD, Python, React, PyTorch, Flask
Supervisor Name:
Dr. Mehreen Alam
Group Members:
Taha Ahmad Mirza (I17 - 0197)
Shehryar Tariq (I17 - 0198)
Muhammad Haris Bilal (I17 - 0264)
Hazri
Hazri consists of a mobile application for teachers to mark attendance in classrooms using their
phone cameras and facial recognition, and also web views for students and administrators.
Students can upload individual pictures of their face while registering, and they can enroll for
classes. Administrators can create classes, assign teachers to these classes, and download the
attendance of classes.
Hazri also provides improved results of facial recognition in low lighting conditions and in low
resolution images.
Features include:
-
Teachers marking attendance
-
Administrators creating classes
-
Administrators downloding class attendance
-
Students enrolling in classes
Students uploading a picture of their face for reference comparison later on during each class
Technology Used:
Flutter, Firebase, Tensorflow lite
Supervisor Name:
Ms. Noor ul Ain
Group Members:
Rabbia Sajjad (I18-0422)
Khadija Bahsir (I18-0718)
Haider Zia (I17-0161)
Hospital Aid
HospitalAid is a real-time video analysis and alert generating system. It is a multi-platform
application that aims to assist hospitals by removing the need for manual oversight of patients and
hospital staff. It will monitor the hospital environment through the camera feed, notice various
abnormalities/incidents and alert appropriate personnel to address the situation.
Detecting an anomaly will be done purely through Computer Vision & ML, by performing real-time
analysis of the live video feed coming in from the hospital’s existing surveillance infrastructure. Our
system will have various deep learning models that will be trained to notice particular types of
anomalies. Alerts will be sent to hospital staff via a mobile app (which will act as a pager), and
incident statistics will be reported to the hospital administration through a web portal.
HospitalAid's features include:
- Face Mask Detection
- Empty Reception/Nursing Station Monitoring
- Social Distancing Detection
- Fainting Detection
- Choking Detection
- Drowsiness Detection
Technology Used:
Python, PyTorch, TensorFlow, Keras, ReactJS,
React Native, Firebase, Flask, GitHub.
Supervisor Name:
Mr. S. Muhammad H. Mustafa
Group Members:
Hassan Shahzad (I18 - 0441)
Sana Ali Khan (I18 - 0439)
Idea Market
Idea Market is a web application that allows you to turn your ideas into valuable assets. It makes
the use of a custom Blockchain to protect the ownership of Ideas. It also has its own in-app coins
and an automated auction system to enable the bidding process for transaction of ideas and their
transfer of ownership. In order to make use of the application, the seller or owner of the idea needs
to propose their idea. Once they propose their idea, it is added to a list of pending ideas along with
its similarity score. The similarity score is a measure of uniqueness of the idea in the Blockchain and
it is calculated by an NLP module of our project. Now if the idea is unique in context of our
Blockchain, it would be added to the Blockchain, else it would be rejected. Once it is added, the
owner can enable bidding on the idea and the buyers can bid on the idea. In the end, the highest
bidder would be selected as the final buyer of the idea and the ownership of idea would be given to
him
in
exchange
for
some
coins.
Features include:
Proposal of an Idea.
Finding the similarity score of an Idea.
Approval or disapproval of Idea.
Transferring the ownership of an Idea in exchange for some coins.
Technology Used:
Angular.js, Blockchain, Go,
MySQL, Python, Visual Studio code
Supervisor Name:
Dr. Ehtesham Zahoor (FYP-1)
Dr. Muhammad Asim (FYP-2)
Group Members:
Abubakar Mughal (I18 - 0681)
Fatima Maryam (I18 - 1573)
Wasif Ali Shah (I18 - 1567)
Iinterview
The iInterview web application is being made, whilst keeping the perspective of the candidates
applying for a job and the hiring agency which posted the job. There are two views of this app –
Candidate View and Admin View – the former is for the candidate to use the features provided by
our web application to browse all posted jobs, apply for any job that they desire, give an interview
for that particular job and then view the results of the given interview. The latter is for the admin,
who can post, update or remove jobs. At any given time, they can also view the list of all the
candidates applying for the job and can also view their scores and interviews.
Features include:
-
Real time assessment of given interviews taking three different factors into account i.e. facial
expressions, vocal fluency and response accuracy.
-
A recommended list of candidates shortlisted for the admin.
-
Preventing candidates from  giving multiple interviews for the same job.
Admin can view the interviews themselves and not just rely on the scores given by the system.
Technology Used:
Python, JavaScript, Flask, MySQL, Visual Studio
Supervisor Name:
Ma’am Amna Irum
Group Members:
AbuBakr Idrees (I17 - 0130)
Hashim Mazhar (I18 - 0618)
Abdul Hadi (I18 - 1575)
Insider Threat Detection
Threats to data and security don’t always start on the outside, most of the time it’s actors within
the organizations who carry out malicious and sophisticated acts. Within an organization, every
employee is capable of accessing a wide range of information which unintentionally or intentionally
can put the organization in danger.  Our software is capable of detecting activities that can lead to
such malicious acts i.e. monitoring applications as well as complete directories, tracking data
movements, detecting IP/MAC spoofing, tracking shell usage, logging connection information to
external devices, detecting privilege escalation and providing a user friendly dashboard. Moreover,
our application is running as a hidden service in the background. It also supports a rule-based
reasoning
module
capable
of
detecting
insider
threats
before
they
occur.
Features include:
-Storing logs locally while connection to server is severed.
-Detecting
any
change
in
IP
or
MAC
address.
-Dynamically monitoring directories and their subdirectories for any change.
-Tracking
shell
access
and
usage.
-Detecting insertion of any external device and copying data to the external device.
-Two-admin
authentication
for
greater
security
on
the
admin
dashboard.
-Rule based inference engine capable of using the logs to generate critical alerts.
-Using encryption while communicating data to the server.
Technology Used:
C#, .Net core framework , ReactJS, SqlLite,
Supervisor Name:
Dr. Muhammad Asim
Group Members:
Adan Abbas (I18-0401)
Ayesha Gul (I18-0467)
Laiba Khurram (I18-1562)
Machine Learning and Imaging processing based Lung diseases detection
application (MILDDA)
We made an application that detects lung diseases such as COVID-19, pneumonia, lung cancer and,
tuberculosis using chest x-rays. The radiologists can upload medical  images. The images are then
processed and cleaned first, then they are passed through an optimized Visual Geometry Group
(VGG) which then classifies the images into diseases. The probability of a given disease is also
shown to give an accuracy measure. This system helps point out the critical cases in a particular
class/disease. This system also makes the detection of Covid-19 faster. This system be there to help
the doctors and radiologists as they will make the final decision for the patient. This system also
detects the severity of each disease and classifies it into mild, moderate and severe.
Features include:
-Detection of lung disease such as lung cancer, pneumonia, tuberculosis, COVID-19.
-Detection of the severity of each disease classified into mild, moderate and severe.
-Upload reports, prescription and patient history.
-View reports, prescription and patient history.
Technology Used:
Python, React, TensorfLow,
4.6, Visual Studio
Supervisor Name:
Mr. Bilal Khalid Dar
Group Members:
Fizza Asif (I18 - 0790)
Abeer Aqeel (I18 - 0636)
Zoya Sumbhul (I18 - 0721)
Medi-Eye
Medi-Eye is a web and mobile devices-based monitoring software, which uses live camera footage
to observe the premises of medical institutes and alert the respective authorities of any suspicious
or threatening activity that may occur. It aims to replace the physical labour stationed for security
monitoring with a highly accurate and low-response-time digital system to enhance security
protocol.
Our system has the following six major features:
1. Parking/Waiting Area Monitoring:
Checking for free parking spaces.
2. Employee Attendance:
Attendance will be recorded as the employees enter the premises of the institute.
3. Aggressive Behavior Detection:
Any violent actions (fighting, pushing etc.) will be reported.
4. Prohibited Actions Detection:
Certain actions are not permissible in some areas for example smoking in hospital hallways.
5. Weapons Detection:
Checking if someone is wielding an object that can cause possible harm to a person or property.
Isolation Ward Monitoring:
Ensuring no unauthorized personnel enters the ward.
Technology Used:
Python, , React, Java, Github, Firebase,
Pycharm IDE, Visual Studio Code, Visual Studio, OpenCV
Supervisor Name:
Mr. S. Muhammad H. Mustafa
Group Members:
Azka Khurram (I18 - 0461)
Abeera Fatima (I18 - 0411)
MimicBot
MimicBot is a real time voice cloning & text-to-speech application that allows you to clone your
own or some other voice of your choosing, using an audio clip of mere 10 seconds. It can then
convert any text to speech that you provide to it, in the cloned voice. MimicBot is a web
application, which gives the user 3 types of input options for the voice. A user can either Browse a
file, they can Record their own voice, or they can even select a YouTube video URL for the voice.
Then, the user can input any length of text that they want to clone and the application will speak it
out
for
them.
Features include:
- Voice cloning
Works for Roman Urdu
Text to speech
Browse/Select file from your system for input.
Record your voice for input.
Select a YouTube URL for voice input.
Allows you to save the cloned output audio.
Technology Used:
Python, Flask, Visual Studio Code
Supervisor Name:
Mr. Umair Arshad
Group Members:
Faraz Ahmed (I18 - 0468)
Pawan Kumar (I18 - 0715)
Awaiz Hussain (I18 - 1593)
My Health Passport
A digital encrypted medical health wallet is being created; this wallet contains verified health
records of a user. These health records can be verified by scanning a QR code. There are three
actors involved in this project:
The user:
User can view list of tests and authorized labs. User can also request for a QR code for their
health record.
The verifier:
Verifier can scan QR code provided by the user to check the verification of the health record,
verifier also issues a list of tests required by the user.
The issuer:
The issuer can create and delete test records.
The project is backed up by blockchain, this enables higher security of the health records. Since
blockchain provides decentralization hence the project will be free from the control and
interference of a single authority.
Technology Used:
Ethereum, MetaMask, React Js,
React Native, Node js, Visual Studio Code
Supervisor Name:
Dr. Shujaat Hussain
Co-Advisor Name:
Memoona J.Anwar
Group Members:
Eyman Farooq(I18-0445)
Areebba Maqsood(I18-0472)
Sophia Syed(I18-0835)
NavPal
NavPal is an AR based android application that provides an interface for user to facilitate them with
the navigation during traversal inside the building. It will provide both the on-premises and off-
premises navigation. Its features are mentioned below:
High Level Features: -
 On-Premise Directed Live Navigation: User will be able to select a destination inside the
building. Then the application will help the user reach the destination by providing live
navigation inside the 3D model of the building and guiding them along the way. User needs to
be present inside the building to use this feature
 Off-Premise Find Shortest Paths: User will be able to find shortest path between a starting
location and a destination inside the model while being off premise i.e. user does not need to
be present inside the building.
 Off-Premise Open World Traversal: User will be able to see the 3D model of the building and be
able to navigate in it with the help of joystick and touch controls.
Event Management: User will be able to navigate inside any events that are happening inside the
building
Technology Used:
C#, Unity, Blender, Android,
Visual Studio
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Hasan Mustafa (I17 - 0167)
Hatim Bin Hammad (I17 - 0032)
Taha Ur Rahman (I17 - 0263)
Notefy - Video Lecture Summarization
Notefy is a web-based solution in which deep learning algorithms are being used to compile a
solution to assist students in their learning phases. Notefy extracts important points based on
lecture audio and lecture visuals as well. In other words, this app is an updated version of
abstractive summary which considers important video frames along with the audio. Previously work
is done on these two factors separately, in the last few years very efficient models are trained for
speech recognition and text summarization. In addition to this different model are trained for
processing video frames. Notefy leverages both of these models and prepare an ultimate solution
based on them. Assisting students in their learning is a major goal of Notefy.
Features include:
Users will be able to log in and create accounts.
Multiple uploading options for the video lectures, e.g., upload, drive, link for online video, etc.
Users will have option to generate notes of their uploaded lectures.
User’s history will be maintained, so if they have converted any notes before they will be saved in
their account.
Users will be allowed to download, share and also to make changes to their notes.
Users will also be able to preview their uploaded lectures and generated notes.
}}}}}
Technology Used:
Python, React, Express, Flask,
OpenCV, MongoDB, NGROK
Supervisor Name:
Ms. Amna Irum
Group Members:
Muhammad Haseeb (k18 - 1070)
Muhammad Athar (I18 - 0692)
Syed Murtaza Hassan (I15 - 0486)
Online Digital Advertisement Marketplace (ODAM)
ODAM is a web-based application developed in MERN stack for remotely controlling and uploading
ad campaigns on Digital Billboards using Raspberry PIs and electron JS application. Three different
applications are developed – Portfolio Website, Client Application and Admin Application – to cater
to the needs of our project. The Front-end applications are developed using Next.js framework. The
client application will allow new users to view the geographically dispersed and different billboards
that are available for booking. The billboards are tagged on Google Maps to ease the process of
search. The selected billboard will show the time during a day when it is available for booking and
what price will be charged for a selected period of time. The remote access and control of content
on the digital billboard is implemented using Raspberry PI. The Raspberry PI will not only run
Electron.js for display of content but also send a regular pulse to check the live status of the said
billboard. The admin will approve an ad campaign before it can be run on the billboard. The
installed IP camera on the billboard will take the live feed of the traffic and run an object detection
module to detect different vehicles and humans. The resultant data will be saved and will be
showed as an analytics to the target customer. The Super Admin will have control over all the CRUD
operations relating to new admin, billboards, advertisements and hirers. The interoperability of
different independent modules is managed by Node.js main server. We have used Amazon S3
bucket for uploading of Ad Videos and images.
Technology Used:
Node.js, Next.js, Express.js, MongoDB, Flask,
Raspberry Pi, AWS, Electron.js
Supervisor Name:
Dr. Mohammad Adnan Tariq
Group Members:
Abdul Waheed (i18 - 0535)
Muzammil Shakir (i18 - 0645)
Zohaib Khalid (i18 - 1565)
Overhaulin’ – A Blockchain-Based Auto Auction System
Overhaulin is being made, while keeping the perspective of a customer as a buyer/seller, admin
perspective for managing car data, and maintenance perspective for managing car repair log. There
are three views of this app – Customer View, Admin View, and Maintenance Admin View. Our
system will help facilitate customers looking to buy or sell a car. A seller can post ads to sell a car
and buyers can bid openly against one another, with each subsequent bid required to be higher
than the previous bid. Bidding will be open for a certain time after that car will be sold to the
highest bidder. Immutability of each bid will be registered to make the tracking and verification of
bidding history easier; this bidding process should be done using smart contracts, The use of smart
contracts ensures that sensitive information is validated and protected ensuring data security.
Moreover, the blockchain-based solution would enable the auctioneer to directly connect with
many potential bidders without intermediaries. No bid cancellation’ feature was enabled to ensure
a fraud-free Auction. Customers will also be facilitated through a car recommendation system, to
cater to their unique needs. He can also search for the different cars of their own choice. The
maintenance/accident log of the car will be stored on the blockchain to help customers verify the
repair history of the car. And for the admin view, he will be responsible for adding the car data to
the blockchain also it facilitates the admin to generate a sale receipt, approve ads posted by
customers, start bidding and stop bidding also he can announce a bid winner.
Technology Used:
React, Node, Express, MongoDB, Web3.0,
Solidity, Ganache Ethereum Blockchain
Supervisor Name:
Ma’am Hina Binte Haq
Group Members:
M. Osama Rafique (I18 - 0639)
Sardar Shahnawaz Mazhar (I18 - 0699)
Waseem Shehbaz (I18 - 0746)
P2C HD-Wallet
Our main focus was to study and proposed a reliable digital wallet which ensure privacy and
security. This is an R&D project in which we did qualitative research on different crypto wallets to
check how they works and what methods and techniques they use. We extracted data from these
wallets and build our wallet upon it.
As the primary function of a wallet is to generate keys, and manage them. We utilized the
deterministic approach to generate keys from a single seed. We used electrum-based support to
our wallet and used 10 servers to maximize the security. We selected the main server by checking
for the heaviest blockchain.
We basically worked with the ethereum blockchain and used ethers to make transactions. We did
the inter & intra wallet testing to check its behaviour. We also compared our wallet with the
existing wallets.
Technology Used:
React, Node js, Web3, Ethereum Blockchain,
Visual Studio Code, Oracle Cloud
Supervisor Name:
Mr. Jawad Hassan
Group Members:
Hamza Khalid (I18 - 0421)
Mubashir Ahmed (I18 - 0481)
Farrukh Raza (I18 - 0680)
PAnalysis
PAnalysis is web application designed to analyze the personality of social media users by analyzing
their profiles.The application is able to build intelligent scrappers and bots to scrape data at a high
speed. The users of the application will also be able to scrape and analyze a specific profile just by
providing the profile and the platform. The application will then provide them with the results and
a complete analysis of the profile. There is also a feature in the application for the subscribers to
bulk analyze many profiles for comparison purposes. This feature will be useful to analyze all the
applicants for a job and compare and find the best person for the job. The output generated by the
application is in the form of graphs, reports, and pdfs depending upon the type of scraping
performed by the user. For bulk analysis, a graph is making it easy to compare the outputs and get
to a concrete conclusion while reports and pdfs are enhancing the graphs and present the
information
gathered
in
an
easy-to-understand
way.
Features include:
Accurate Analysis of User's personality
Software as a service model for frictionless usage
Text analysis from Roman Urdu and English
Analysis using user-uploaded images
Output results in the form of graphs, reports, and pdfs
Technology Used:
Python, aws, MySql, Selenium, Flask, jinja
, Deep Learning
Supervisor Name:
Mr. Umair Arshad
Group Members:
Muhammad Asim (I18 - 0508)
Haris Manzoor (I18 - 0428)
QuratulAin (I18 - 0524)
Parking Reservation System
A smart parking reservation system which aids the user in booking a spot and reserves that spot on
the vehicle's license plate by recognizing it using OCR techniques. Cameras will be installed at the
parking lot which will monitor the parking spots and detect whether a vehicle is parked or not and
will validate the parked vehicle by reading its license plate and comparing it with the booked spots’
license plate. If an incorrect vehicle is parked, then the system will inform the user to move their
vehicle otherwise a fine would be charged. An online payment system would also be available for
the user to pay their fines and fee for the booked spot. The communication between the system
and the front-end would be in real time.
The system would have two applications, an android application for users and a web application for
the admin. The user via their android app would be able to view the parking spots, book an
available spot, unbook their spot if not parked yet, edit their profile, get their current fee and pay
their due amount. The admin via their web app would also be able to view the parking lot, book an
available spot, view and edit the information of all the booked users as well as the registered users,
assign some special spots such as spots for disable people and get the required reports of the
system such as a graph for booking trends, a table with real time current information about the
parking lot, a chart for the most booked spot etc.
Technology Used:
Android Studio, openCV, javascript,
reactJs, Firebase, python
Supervisor Name:
Mr. Bilal Khalid Dar
Group Members:
Mujtaba Farooq (I18 - 0685)
Zarak Jehan (I18 - 0256)
Messam Ali (I16 - 0041)
Path Visualization
An android app for visually impaired and blind people for the visualization of the path and notify
the user about the detections in its way. This app utilized the device camera which detects the
obstacles in its way like the potholes, vehicles, pedestrian, pole, fire hydrants etc. Furthermore, an
estimated distance from the camera to the obstacles was also calculated with the help of the
average height of the obstacles. This app uses Speech-To-Text and Text-to-Speech feature to
communicate with user. Different datasets are merged and trained on Yolov3 model. The working
of the app is that first the user would login to the app using his voice and the app would start a live
feed using the camera and the results of the model will be displayed on the camera and focal length
formula is used to calculate the distance using the average height of the objects in its way and the
app would notify the user about the path.
Features include:
-Realtime detection of objects using Yolov3 Model and Django restframework API to pass upload
results to the server and Volley multipart request to fetch the data from the server in the app.
-Distance Estimation using focal Length formula.
-App use Speech-to-Text and Text-to-Speech feature.
Technology Used:
Deep Learning (Yolov3), OpenCV, pytorch, TensorFlow,
Keras, Python, Django Rest framework, PyCharm,
Android Studio, Postman, Git
Supervisor Name:
Mr. Saad Salman
Group Members:
Mohammad Wasique Sheikh (I17 - 0117)
Arbab Tufail (I15 - 0136)
Penetrato
Penetrato, which is an automated penetration testing tool, is being designed with the aim of
reducing the time and cost involved in the process of penetration testing.
It is common practice for IT companies to do penetration tests of their networks from time to time,
in order to get information about existing vulnerabilities in their system, and to protect the critical
infrastructure. With each update in their softwares, companies have to repeat this whole step again
so that no vulnerabilities are opened with the integration of new modules. All of these tests cost a
lot of money as well as time because once the penetration test is completed, the step of report
generation takes a long time as well. All of this makes this system not feasible due to huge time and
cost involvement.
Our tool will help solve this problem by automating the whole process of penetration testing
including report generation. With this tool you can simply initiate the process at night, let the tool
do its work without any supervision and view the results generated by it in the morning. This not
only will solve the issue of cost but also will save you from time wastage.
Another feature of penetrato is that it is very easy to use and any user even with very basic
knowledge of IT can use it due to its extremely easy interface.
Technology Used:
React JS, Go lang, Nmap, Metasploit, Masscan, Docker
Supervisor Name:
Dr. Muhammad Asima
Group Members:
Ali Imran (I18-0847)
Nauman Aziz (I18-1561)
Aitzaz Ahmad (I18-0589)
Pest Recognition of Images using Deep Learning
Our project focuses on using various deep learning techniques on images of a variety of pests to
come up with an effective model to classify images of pest. This project has direct significance in
the field of agriculture where tones of crops are wasted just because farmers can’t recognize and
prevent pest attacks on their crops. According to research (At Least 40% Global Crops Lost to Pests
Every Year: FAO, n.d.) 40% of the global crops are annually wasted to pests amounting to around
€69 billions of economic loss that is enough to feed around 1 billion people annually.
We discovered a dataset of labelled pest images called IP102 (Wu et al., 2019) which comprises
more than 75000 images of 102 classes of pests.
During FYP-1, we focused on developing a model that classifies the images of pests in the IP102
dataset and used different feature extraction, data pre- processing and deep learning techniques to
prepare our dataset and train it to come up with a base line model. Then we fine-tuned our model
and performed data augmentation techniques to increase its accuracy in FYP-2. We then embedded
the best model as a TFLite model into an iOS mobile application using Swift.
Technology Used:
Python, TensorFlow, TFLite, OpenCV,
PIL, Swift, Kaggle
Supervisor Name:
Dr Labiba Fahad
Group Members:
Muhammad Abdullah (I18-0416)
Muhammad Abdul Rehman Shah (I18-1566)
Physics AR
Physics AR is an Augmented Reality based application by which students of Secondary Level can do
their lab experiments of Physics using just their Android phones. When the user opens the app, a
list of experiments available will be shown to the student. The apparatus for the chosen practical
will be displayed to the student, 3D simulation of step by step practical will be shown. Students can
also change the sizes, weights, etc. of the tools involved in the practical like the direction of laser,
force applied etc. The measurements will be updated according to the data updated by the student.
For example, he can change the weight of unknown object on the force table in vector addition of
forces, also he can change the weight of unknown object on the meter rule while visualizing the
principle
of
moments.
Student Panel Features:
Pick and view available experiments in Classroom Mode.
Post questions and doubts.
Attempt assessments in Quiz Mode.
Teacher Panel Features:
Give access to students of experiments.
Schedule Quizzes and give access to students.
Push Notifications for student interaction.
Sort and answer queries posted by students
Technology Used:
Unity, Blender, Android Studio
Supervisor Name:
Ms. Noor Ul Ain
Group Members:
Ayesha Khan (I17 - 0313)
Saad Rasheed (I18 - 0556)
Sheryar Ali (I18 - 0452)
PlanteafX
PlanteafX is an automatic plant leaf disease detection system in which you just have to take the
picture of the diseased area of your plant from your gallery as well as from your camera. Then you
just have to tap on the predict button and our state-of-the-art pre trained model will predict the
disease
of
the
plant.
Features include:
-Our app can predict the diseases of Apple, Orange, Wheat, rice, jamun, lemon, potato, Tomato,
Mango and many more species as well.
-Our app can predict the disease within seconds so that timely precautionary measures can be
taken to prevent the spread of disease.
-Our app’s interface is easy to use and user friendly such that anyone can use it.
Technology Used:
Kaggle, python, android studio, Tensorflow, java
Supervisor Name:
Dr. Labiba Fahad
Group Members:
Masood Ahmad (I18- 0755)
Haseeb Ahmad (I18- 1579)
Muhammad Zargham Masood (I18- 0464)
Sawari
Sawari, a decentralized ride-hailing application through block chain so that the power comes back
to the people where it actually belongs. Middleman is removed and so the huge tax we pay for that.
Both the passenger and driver will be connected directly to each other. This will be open
governance. This app will help the drivers earn more and the customers to travel at reasonable
prices. Also given the transparency in the amount, this is an amazing earning opportunity for jobless
people, they will be more encouraged to do something that they are fully paid for instead of paying
commission on one fourth of their hard work.
Features include:
- Register as a new passenger or driver in the app through contact number and firebase
authentication.
- Enables passengers to enter their location, car type and destination.
- Enables both the passenger and driver to see their route after the ride starts.
- Transactions are saved in a blockchain that provides transparency.
- Payment is displayed at the start and end of the ride.
Technology Used:
Flutter, Dart, Ethereum, Firebase, Android Studio
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Ghufran Ahmad (I18 - 0532)
Bilal Ahmed (I18 - 0555)
Zoha Jaleel (I18 - 0722)
SceneGen
An AI based thermal imaging system in which we have imported real time maps in unity and we are
doing simulation. It’s an application in which user can select different terrains, targets and the
simulation works when the rocket hits the target object. In this application the user can select the
speed of simulation and IR images. Basically the need of this application is to create the dataset
from different views and different angles and after creating the dataset, and object detection
model is trained using YOLO V5. After training the model, it will be tested in NESCOM using real
time
simulators.
Features include:
-
Customizing/Selecting the terrain
-
Selecting the target
-
Applying IR effects
-
Performing the simulation
-
Collecting dataset
-
Training Object detection model
Performing real time target detection
Technology Used:
C#, Unity3D, Photoshop, 3Dsmax, Python,
OpenCV, Pytorch
Supervisor Name:
Dr. Hammad Majeed
Group Members:
Shabih Ul Hassan (I18 - 0640)
Muhammad Abbad (I18 - 0471)
Hamza Amin (I18 - 0550)
Scribbling Speech
Scribbling Speech is an application for young children and is made for their edutainment purposes.
It is a creative application that allows a user to use a Drawing Canvas to an extended set of
possibilities. It converts your speech input to Drawings and its subsequent Animations for both the
entertainment of the user and enhancing their learning on how a particular object is made. Why
Speech? Because we, especially children, imagine the world in spatial constellations. It is easier for
them to just say what they want to draw/learn to draw. Several other features are also there that
allow user to save their above said drawings, re watch, learn and redraw either via speech or
manually.
Features include:
- Creating and Animating drawings from real time speech input for edutainment purposes.
- Teacher Mode to go beyond and further and teach and learn anything in imagination on a canvas.
- AutoComplete feature to assist a user when drawing manually.
- Watching previous and newer animations for recreational or learning purposes.
- Predictor Mode to predict the drawings of user with speech and visual output.
- Magic Painter for creativity on the canvas with special feature to change color at each stroke.
Technology Used:
React JS, P5.js, Processing 4.0,
Tensorflow.js, Visual Studio Code
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Syed Murtaza Hassnain Naqvi (I18 - 0595)
Saifullah Dar (I18 - 0599)
Sorooj Shehryar (I18 - 0503)
SEAMZO
A social media marketplace for digital content creators/collectors to post their content and
monetize it. They can socialize, engage and make their arts, photos, and articles shareable through
posts. These posts will be tradeable on the SeamZo Marketplace. Through a fully decentralized
approach, we will ensure to make SeamZo trustable and transparent. Every valuable activity on
SeamZo will live on the blockchain. Minting nfts(Non-fungible tokens) against posts would ensure
that the work of small content creators is protected. Posts can be made available to SeamZo
Marketplace through NFTs. These assets can then be sold and bought.
Features include:
You can like and comment on other user’s posts.
You can make your post tradeable by minting an nft against it.
You can buy and sell your nfts.
The ease of use would enable layman to delve into the world of nfts and cryptocurrency.
Technology Used:
React Native, EOS, Firebase
Supervisor Name:
Sir Adnan Tariq
Group Members:
Mahrukh Waqar (I18 - 0403)
Wajeeha Malik (I18 - 1587)
Arsalan Tayyab (I17 - 0039)
Secure Ballot
two views of this app – User View and Admin View – the former is for the users to use the features
provided by our app to cast vote and see the results for the election. To view the results, it is
compulsory for user to cast the vote. The latter is for the admin and officers, who will add
candidates of election, add the user who are eligible for casting vote, manage election and view
results. The casted vote will be stored in blockchain, to have transparency, immutability and
decentralization.
Features include:
 Casting a vote.
 Realtime results from blockchain.
 Admin adds the employees for election commission.
 Employees add the candidates for the election of the year.
Employees add the user who are eligible to cast vote.
Technology Used:
Dart, Flutter, Solidity, Ganache,
Firebase, Android Studio, Ethereum
Supervisor Name:
Mr. Zeeshan Qaiser
Group Members:
Aimen Zara (I18 - 0559)
Laiba Imran (I18 - 0477)
Sadia Saad (I18 - 0698)
Smart Grocery
Our Project is based on the idea of ordering groceries online through Urdu Speech Recognition as
well as making a user profile for further saving the user’s most frequently ordered items and
categorizing edible items that would be safe or unsafe for the user (in case of any health issues).
In our project for Urdu speech recognition, we will have to train and develop an Urdu based speech
recognition model by first using multiple voice recordings as datasets and mapping them out with
their corresponding English text by transcribing them. The problem that we discovered was that
Urdu doesn't have a global recognition as a language despite there being 70 million native speakers.
So, by enabling Urdu Speech we would be promoting an application that has the ability to
understand what a native Urdu speaker is trying to order.
The next feature is Auto Generation, for this we will have to collect data of a user’s recent
purchases as well as their frequently bought items, next after collecting a sufficient amount of data,
a grocery list will be generated which matches the user profile. The objective of this is to minimize
the amount of time a user takes to select every grocery item on their shopping list. So, generating a
grocery list will help users order groceries with less effort and time. Also, to facilitate the users
more, Smart Categorization will help users be shown only edible products that would be medically
safe for the user based on their health requirements. The problem that we discovered was that,
most people cannot differentiate edible items that would be medically safe or unsafe for them,
they would tend to ignore labels on food items or even general research on a particular item. So,
smart categorization would allow for users to be displayed edible items that are safe for them.
Technology Used:
Flutter, Google Firebase, Librosa, Torch, Google
Search API, Beautiful Soup, Python, Google Colab
Supervisor Name:
Dr. Shujaat Hussain
Group Members:
Shujaa Marwat (I18 - 0432)
Kamal Qureshi (I18 - 0438)
Areesha Maqsood (I18 - 0600)
SmartBot
An interactive AI chat bot known as “SmartBot” is being made to streamline the whole admission
process of FAST NU Islamabad and to clear all those queries that arise in the minds of students
when applying for an admission. SmartBot will be intelligent enough to understand and answer all
those queries that will be asked by students may it be in English or in Roman Urdu. This System will
be a web-based application having an interface where students can write their queries and our chat
bot will use built-in artificial intelligence to answer the queries. Our chat bot will be able to make
friendly conversations, respond to different queries, answers frequently asked questions.
Features include:
- Admission related queries including how to apply, admission criteria, entry tests and much more.
- Answering basic queries regarding (fee structure, location, campuses, programs offered, ranking).
- Handling queries regarding (Aggregate Calculation and GPA Calculation).
- Answering queries regarding facilities at FAST NUCES like transportation, events, sports etc.
Technology Used:
RASA, TensorFlow, Python, GPT, React js, FIGMA, Scrapy
Supervisor Name:
Dr Mehreen Alam
Group Members:
Muhammad Umair Dastagir (I16 - 0343)
Farman Hasnain (I17 - 0366)
Ali Naqi (I17 - 0076)
SMARTSalah
SMARTSalah will perform the task of activity recognition by using smartwatch sensors. The watch is
tied to the wrist, and the sensors will record the tri-axial coordinates of the person performing
Salah. The basic steps that will be recorded are Long-Standing (Qayam), Bowing (Raku), Short
Standing (Qouma), 1st Prostration (Sajda-I), Short Sitting (Jalsa), 2nd Prostration (Sajda-II), Long
Sitting (Tashahud).  The recording of all steps of the prayer gives us a pattern of Salah performed
through which our system will tell whether the performed steps and Salah are correct and
complete or not. The correctness of Salah depends upon the performance of each posture and the
sequencing of postures which tells that performed Rakah is correct. If all the rakah including
postures are correct and complete, this means that Salah is complete. The AI based mobile
application will show the Salah profile to the person which contains all the statistics of the
performed Salah.
Features include:
Average time spent on each posture of Salah i-e Qayam, Ruku, Sajda, Jalsa, and Tashahud. Time
spent on each Rakah of performed Salah.Tells the user about any missed rakah or any extra prayed
rakah. Tells the performer if he has missed any posture within the rakah and similarly if he
performed any extra posture. Identify the missed Salah of the performer on daily, weekly, and
monthly bases. SMARTSalah maintains the count of Farz and Sunnah in a day also and enlightens
the user about how much sunnah he/she is offering alongside Farz Salah. The application also
creates the provision of routine day supplications for the performer to recite while using this app.
Technology Used:
C, Python, Flask, PyCharm, Heroku, Java
4.6, Android Studio, Firebase Tizen Studio
Supervisor Name:
Dr. Amna Basharat
Co-Supervisor Name:
Dr. Asma Ahmed
Group Members:
Mahnoor Raza (I18 - 0571)
Bushra Fatima (I18 - 0566)
Maha Riaz (I18 - 1652)
Social Media Investigator
Misinformation, inaccurate, or misleading information is being used by many as a tool to achieve a
political and narrative wins. Social Media Investigator is a tool that is used to identify the fake
trends used for spreading misinformation on social media platforms. It performs deep analysis and
generates a report which includes all the proof that how a particular trend contains information
that is based on incorrect facts. Social Media Investigator is connected with Twitter through
“Tweepy” and handles the real-time data. The user can search a trend in the web dashboard, check
the location of individual posts in a trend, check for the most influential post in a trend, the
sentiment of a trend, check for bots in a trend, and create a counter-trend using Social Media
Investigator.
Features include:
- Sentiment of a Trend.
- Location of each individual post in a Trend.
- Most influential post in a Trend.
- Bots Identification in a Trend.
- Countering the negative sentiment trend using Text generation.
Web Dashboard implemented using MERN Stack
Technology Used:
Python, KendoReact, MUI, React, Flask, MongoDB
Supervisor Name:
Dr. Atif Jilani
Group Members:
Omar Hayat (I18-0511)
Muhammad Hassan (I18-0523)
Ahmed Shabib (I18-0720)
ThreatGator: A Threat Intelligence Platform
Cyber Threat Intelligence (CTI) lies under the domain of cybersecurity and focuses on the retrieval
as well as analysis of data about potential and current attacks that pose a threat to an
organization’s assets or the organization itself. A Threat Intelligence Platform (TIP) is a software
that manages threat intelligence data by gathering, aggregating and organizing the data from
various sources and multiple formats.
ThreatGator, our proposed version of a TIP, performs curation of threat data from heterogeneous
sources such as social media and blogposts, and presents the derived, actionable threat intelligence
specific to each user’s organization.
Furthermore,  ThreatGator provides additional privileges to an organization’s admin, allowing them
to manage the organization’s assets and edit reports, on top of the functionalities provided to other
users
in
the
organization.
ThreatGator’s features include:
1. Aggregation of intelligence from multiple sources
2. Compilation and normalization of data
3. Filtration and prioritization of threats
4. Correlation of data based on entities in STIX format and their visualization
5. An interactive, user friendly dashboard designed to best portray the gathered intelligence
Technology Used:
Java, Spring Boot, Python, Elasticsearch
Kafka, MySQL, React Bootstrap
Supervisor Name:
Dr. Muhammad Asim
Group Members:
Zaynab Batool Reza (I18 - 0419)
Hurriya Nasir (I18 - 0597)
Muhammad Adil Fayyaz (I18 - 0613)
Travel Planning Mobile App and Data Visualization Web Tool
PlanitPK is a mobile and web-based application that functions as an intelligent tourist
guidance system. It does this using data mining and machine learning techniques to streamline and
simplify the process of travel planning, help users create an itinerary that connects multiple points-
of-interest, give personalized and customized suggestions, as well as provide data analytics and
data visualization for administrators.
Features include:
● Create and view photo albums for your planned trips
● Comprehensive trip planning i.e., selecting multiple destinations, finding hotels and other
accommodations, analyzing potential costs and budgeting, as well as activities to do when in
the selected destinations
● Live weather information
● Google Maps for navigation
● Administrator dashboard which allows third parties to advertise travel packages and hotels
● Data visualization showcasing graphical representation of trends based on Android app usage
● Recommender system to predict destinations based on user preferences and/or usage history
Text-based Travel Assistant that provides info on locations, hotels, and activities within the app
Technology Used:
Android Studio, Java, Python, React
JS, Material UI, Firebase, RASA
Supervisor Name:
Mr. Bilal Khalid Dar
Group Members:
Rafae Raza (I17 - 0224)
Usman Ahmed (I17 - 0151)
Naseer-ud-Din (I18 - 0407)
TravelBuddy
A cross-platform travel application which connects tourists with travel guides from all parts of
tourists with common travel preferences can connect with each other and plan their adventure
together. A user can register as both a tourist or a travel guide. The social platform is moderated
through a RNN-based deep learning model which is used to detect hateful/abusive language.
Features include:
hourly charges.
- A social platform for tourists with posts, comments and chat group options.
- Emergency services option for tourists to guide them to their nearest hospitals, petrol stations,
police stations or bus stations from their current location on a single click.
- Automatic post/chat moderation through a DL-based classification model for detecting
hateful/abusive language.
Technology Used:
React Native, Firebase, Flask,
Tensorflow, Python, Javascript
Supervisor Name:
Mr. Umair Arshad
Group Members:
M. Nabeel Noor Khan (I18 - 0469)
M. Zulkifal Khan (I18 - 0495)
Saqib Zeb (I18 - 0656)
Urdu Audio Miner
Urdu Audio Miner is a web based application to search for a word or phrase through Urdu audio
files. Searching manually through audio files for a word or phrase is time consuming and tiring
work. Automating this task can save a lot of time. Urdu Audio Miner provides the timestamps, after
searching, where word was spoken so user can easily play audio from that point. Along with the
searching functionality user also can check if audio file contains offensive language or not, and one
can also download the transcription of audio file.
Features include:
-
Searching for a word or phrase in audio files
-
Detecting offensive language in audio files
-
Either upload the audio files or provide a YouTube video link.
-
Provide word or phrase to be searched in Roman Urdu, recording through microphone or by
uploading an audio file containing that word.
-
Get the timestamps where phrase occurred and play audio file from that specific time.
-
Transcribing Urdu audio files
Downloading transcription in text format
Technology Used:
Kaldi, Python, Scikit-learn, Javascript, NLTK, Flask,
UrduHack, PyAudio, Spacy, Google Colab
Supervisor Name:
Mr. Umair Arshad
Group Members:
Humayun Afzal (I18 - 0738)
Abdullah Shahid (I18 - 0526)
Hafiz Muhammad Talha (I18 - 0513)
Urdu Assistant
Urdu Assistant is a personal voice assistant for mobile devices. It understands Urdu language and
responds to it. The responsibility of this assistant is to control the basic functionalities of the mobile
device using voice commands.
There are a lot of use cases of our voice assistant, some of them are:
-
If you have preoccupied hands, you can simply trigger the voice assistant to perform any
function you like.
-
If you ever get stuck in an emergency, voice assistant can really get you help!
-
While driving, you can control your device without even looking at it.
Urdu Assistant can perform the following tasks:
-
Dial your contacts.
-
Send Messages.
-
Open Apps.
-
Control your Wi-Fi, Bluetooth, Mobile Data etc.
-
Sets Alarm.
-
Sets Reminders.
Control Volume, Torch and Brightness.
Technology Used:
TensorFlow, Android Studio,
Google Cloud, Jupyter Notebook
Supervisor Name:
Mr. Umair Arshad
Group Members:
Abdullah Naveed (I18 - 0654)
Abdul Rafay (I18 - 0726)
Abdullah Ihsan (I18 - 1654)
Technology Used:
Python, keras, jupyter notebook,
pycharm, tensorflow, pytorch
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Iqra Aziz (I18 – 0491)
Tehreem Khawar (I18 – 0489)
Hafsa (I18 – 0405)
It can help debug deep learning models faster and better.
what features it is learning.
trained. This technique is transparent and can tell us at train time how well a model is trained and
We generate heat maps with our explainability model to understand and depict how well a model is
however, VGGis an improvement of AlexNet with 38 layers and better feature extraction.
standard forcomparison of their performances. AlexNet has 20 layers and is not that well trained,
AlexNet. Boththese models are trained on ImageNet dataset and therefore, it gives a good
for  thistask  of  explainability  by  comparing  and  analyzing  their  performances  are  VGG-16 and
exactlywhat a deep learning model is learning and how well it is trained. The models we are using
generate  heat  maps  by  back  propagating  relevance's  through  which  we  can  understand
learning  models. The  technique  we  are  using  is  layer-wise  relevance  propagation – to
DeepBug is a research and development project specifically related to Explainability of deep
DeepBug
Voice Controlled Self Driving Car (VCSDCar)
VSCD aims to assist in the growth of self-driving technology by creating a self-driving car that
supports user provided multi-lingual instructions. Our AI has the preliminary capabilities to drive on
the road without user instructions.
Additionally, The AI is also be able to support maneuver interventions by the user in the form of
vocal commands and make appropriate decisions keeping in view the traffic laws.  Currently, there
is support for 7 commands in English and Urdu. These commands are
English Commands:
start, stop, turn left, turn right, change lane, speed up, speed down
Urdu Commands:
chalo, ruk jao, dayein muro, bayein muro, lane badlo, ahista chalo, tez chalo.
Technology Used:
Python, tensorflow, keras, opencv,
pysounds, librosa, raspberry pi
Supervisor Name:
Mr. Umair Arshad
Group Members:
Usama Munim (I18 - 0616)
Piyush (I18 - 0650)
Shahab Ul Hassan (I18 - 0731)
VRun
One player plays the game. The player has a Mobile VR headset on. The movement of the player is detected by
the phone and registered on the screen. The player moves forward by jogging, turns left or right by moving their
head left or right. The player needs to run in order to outrun the enemy (Monster) chasing them. There will be
hurdles in the player's path that the player will overcome by jumping/crouching. If the player is unable to outrun
the enemy, they will be caught. If the player is unable to jump/crouch an obstacle, their score will be deducted
and the monster will get closer to them.The player will jog, jump and crouch in real life, these motions will be
detected by the sensors in his phone. The player's motion will be mirrored by his character in the game. The
player’s speed will also be imitated in the game, if the player runs faster the distance covered on the track will be
faster and the scene will move faster and if the player slows down or stops the scene will also slow down or stop.
The player must outrun the monster. That's not all though, the player must also dodge obstacles in their path. The
player will have to maintain a certain speed to outrun the monster. For the obstacles the player will either have to
jump or crouch. The player will also be expected to turn left or right to change his direction. The player will either
have to run a set distance or for a set amount of time for the run to be complete and to escape the
monster.Rewards will be given for completing challenges. If a user completes their target distance in a target
time, they will receive an award. If a user is able to reach their target weight in their set time, they will receive an
award. There will be a weekly/daily challenge for all the players and the ones who perform best will be given
special ranking and rewards.This project’s scope is based on high-end mobile phones that can support VR
accessories. It is targeted towards people who have little to no motivation to practice physical activities and
cannot find time in their schedule to go out for a run or to a gym. It is also aimed at people who wish to workout
but can’t afford gym memberships, treadmills or expensive indoor workout applications. This application can be
used for a well varied workout experience that is fun, immersive and most importantly affordable.
Technology Used:
C#, Unity, Blender, Visual Studio, Firebase, Bridge, XCode
Supervisor Name:
Mr. Hassan Mustafa
Group Members:
Nameira Khalid Rana (I18 - 0695)
Syed Muhammad Tayyab Abbas (I18 - 0417)
Talha Mustafa  (I18 - 0573)
Web Application Firewall (Webalcazar)
WebAlcazar is going to be a Web Application Firewall that will filter, monitor, and block malicious
payloads coming to a website. For this purpose, we are going to be using a front end with
interactive features for the user. Since our project progress is mostly based on the back end side
due to algorithms and ML-based signature matching, this is why our use cases are not covering the
whole aspect of our project.  Henceforth, our second use case which is Change Policy will be
covering 70% of our project.
This use case will have a protection policy for every web-based attack such as SQLi, XSS, XXE, etc.
These policies are divided among the iterations as shown in the iteration plan. To host our web
application firewall, we have set up an apache web server hosted in the virtual environment of the
Linux server.
Furthermore, our firewall is going to need a data set like payloads in order to train the model. We
have spent a specific amount of time collecting the data for every web-based attack. We are going
to use a local database for our firewall since it will help negate the amount of time delay and
internet access for the users. For this purpose, we are going to use a SQL database. The front end
developed in this iteration is done by using React framework. For our back end, we are using
Django.
Technology Used:
React (Redux), Django
(REST API Python Framework), Jupyter Notebook
Supervisor Name:
Mr. Zeeshan Qaiser
Group Members:
Muhammad Abubakar (I18-0449)
Hamza Malik (I18- 0502)
Syed Umer Ali (I180627)
WicketToWicket
WicketToWicket is an AI empowered customized-cricket-highlights-generating and analysis
platform. Our product aims to improve an individual player performance as well as collective
strategies of teams, and facilitates critical decisions in the game of cricket by revolutionizing
traditional cricket coaching and analysis methods while making them robust through Deep Learning
techniques. Our application primarily uses YOLOV5 Deep Learning architecture to classify a
particular frame of pitch that corresponds to the start of a bowling delivery, then labels the
trimmed bowls with bowl by bowl commentary and match summary, and performs further analysis
Features include:
 Cricket Highlights on Demand
 Player Coaching
Team (i.e. Playing Eleven) Selector
Technology Used:
Python, Pytorch, MySQL, JavaScript, AJAX, JQuery,
Bootstrap, PHP, Visual Studio, PyCharm, Jupyter
Supervisor Name:
Mr. Syed Muhammad H. Mustafa
Group Members:
Zoha Fatima (I18 - 0565)
Abdullah Ansar (I18 - 0446)
Saram Atif (I18 - 0659)
Route and Safety Awareness
Route and Safety Awareness app is being made, whilst keeping the perspective of inexperienced
drivers and their safety. There is one view of the app - Driver View - the view is for the drivers to
use the features provided by our app to view the detected traffic signboard, check the history of all
passed traffic signs, and get the real-time voice alert whenever the signboard is detected. Traffic
signboards include 42 signs i.e. warning signs, speed limit signs, and stop signs. Real-time signboard
detection is performed using the You Only Look Once i.e. YOLOV5 algorithm and classification using
Convolutional Neural Network i.e. CNN.
Features include:
- Capture traffic signboards in real-time
- Detect traffic signboards: including warning signs, speed limit signs, and stop sign
- Classify traffic signboards: including warning signs, speed limit signs, and stop sign
- Generate voice alert whenever a  signboard is detected
- Display the history of all passed signboards to the driver
Technology Used:
Python, Java, Xml,  Android Studio, Visual Studio Code,
Jupyter Notebook, Raspberry pi
Supervisor Name:
Mr. Umair Arshad
Group Members:
Amna Arshad (i18 - 0563)
Iram Bashir (i18 - 0456)
High Achievers
Class of BS (CS)
Abdul Mannan (18I-0557)
Before coming to FAST, I was reminded time and again that this institution would make me work
harder than I’d ever done before. I chose to study here because I knew it would be a new challenge
for me and in being so, would help me grow into the kind of person I wanted to be. It was an
expectation.
Now, at the end of this long journey that still manages to feel short, I can safely say that I held the
right expectation. In my time here, I’ve changed as a person in ways that I’d never imagined. I’ve
grown past my expectations. Of course, it wasn’t easy. This has also been the most challenging
period of my life in all aspects. But, thanks to the people I was able to meet and the opportunities
offered by FAST (academic, extracurricular, and career), I’ve made it this far.
One of the most significant ways in which FAST has changed my life is in the exposure it gave me to
the different directions in which my career can go. I came here with the sole aim to become a game
developer, but through the curriculum, I learned about the possibilities in research and academia,
low-level systems, software design, and the list goes on. I am now much clearer about what I want
to do, and why, thanks to my experiences here.
Lastly and most importantly, the people and the sense of community one finds here are what have
made the struggle bearable and even more rewarding. I tried my best to work with as many people
as I possibly could, finding myself in a new group for almost every course or assignment. As a result,
I’ve found people that are there for me in times of need, and whom I relate with deeply. For this,
and everything else, I am thankful!
Adan Abbas (18I-0401)
My journey at FAST NUCES began in Fall 2018, never realizing how wonderful and life changing the
next 4 years of my life would be.
FAST NUCES wasn't my first choice for a computer science degree. In fact, coming from a military
college, I had only aimed at joining the army. I never considered what I actually had to do in life,
what I was made to do, and what all I was capable of doing. I never evaluated my aptitude. But
after 4 years, I can proudly assert that this is what was always meant for me, this is where my stars
shine bright.
When I first joined FAST, I was clueless about what was going to happen. To this day I remember
the sleepless nights, long bus journeys and the grueling assessments in the form of assignments,
quizzes and projects that being a freshman I had to endure. The only thing that was able to keep
me going was the fact that I was learning what I loved and I was learning it where it was taught
best. To be a student at FAST, one does not have to be an extraordinary person or a genius. All it
takes is perseverance, dedication and a strong conviction that you can do it.
Being at FAST provides everyone a chance to do something at which they excel other than bookish
literature only. I was given an opportunity to be a part of the winning team at NaSCon ‘19 for the
bug catcher competition. I was also the winner of speed programming and the runner up at the bug
catcher event for IntraFAST 2019. I was also blessed with multiple opportunities to take part in boot
machine learning in the summer of 2019.
From being a freshman who had no clue about what was going to happen to him, to being a soon-
to-graduate engineer who is already employed, it has been a truly rewarding journey for which I
would be forever thankful to Allah Almighty and my Alma Mater.
Hamza Ijaz (18I-0522)
Who knew that when I came to FAST for just graduating in four years, I'd be putting this down as
called my mother, and told her that I am not going to make it here. That was because my class was
full of intelligent or exceptional kids, it was like an MIT or a Harvard classroom for me at that time,
something I wasn't prepared for at the time. I was merely listening to a podcast amongst my fellow
students and lecturers. Because I was unable to respond to the lecturer's question due to lack of
knowledge. The secondary issue was the language barrier; my classmates were so used to speaking
English that they might have believed speaking Urdu is not admissible at FAST. Whether you accept
it or not, this object makes you feel inadequate. That feeling of inadequacy drove me to think about
dropping out of university. However, as is customary, your parents' assistance is invaluable. I
ultimately made it through here. I didn't make many friends in the beginning. But, fortunately, I was
able to form a decent group of friends until the middle of my first semester; the common thread
that held us together was that we were all unsure of what to do here. I didn't mind the burden
FAST was putting on me because I joined knowing that the next four years of my life would be
the second semester. And in our class, CGPA was directly proportionate to respect and popularity.
As a result, a declining CGPA signifies a declining level of respect among friends. Our sections were
rearranged after the second semester, and I was assigned to a new section, which marked the
beginning of my academic excellence. In the third semester, I obtained a gold medal and a 4.0
SGPA, as well as a significant increase in my CGPA and esteem. The third to eighth semesters gave
me the best years of my life. My entire friend group was transformed, or should I say
revolutionized, for the better. I concentrated on developing my personality, communication skills,
emotional intelligence, and academic intelligence during this time. I began to be more outgoing,
attending university events and interacting with individuals from my junior, current, and senior
batches. In that time, I can say that I have made memories that will last until my last breath. To
conclude my summary, I would like to remind anyone reading this that I witnessed both success
and failure here. I witnessed how people change when they need you; those pals who didn't help
you when you needed them will come for you when you're in your golden period, you should
always help them, never hold grudges. Whatever you are; you owe it to Allah and your parents'
prayers. People do smug for achieving high grades, but I didn’t. I'll never forget the feeling of
inferiority I had when I first arrived at FAST due to my classmates' arrogance and unwillingness to
help; for others not to have the same experience, stay humble and attempt to help everyone.
Humayun Afzal (18I-0738)
Having a passion for Computer Science, programming and technology even before I was in grade 9,
receiving the admission letter for FAST NUCES was like a dream come true. Like many other fellow
batch mates, I felt a little nervous on my first day at university, yet it is still one of the unforgettable
days of my life. Within a week, I had made many amazing friends. No doubt life at FAST was tough
at the beginning. As compared to college, we were studying a lot of new content each week, had to
meet deadlines for assignments, be ready for quizzes, and work on projects. But I think that this
workload was only to make us realize that we all are capable of doing more than what we thought
we can do. Only the sky is the limit.
During Covid, studying from home was a big challenge but I got used to it eventually. I am grateful
to all my instructors who always guided me whenever I needed help during online and in-person
classes. Within my 4 years at FAST, the administration made several improvements in the university
to facilitate students like the One Stop service, improved playing grounds, new student societies,
new research labs, buddy program, facilities for online teaching, and many more.
I enjoyed the seminars and workshops conducted by the FAST Computing Society related to
emerging topics in Computer Science. I had the opportunity to hear from CEOs of many well-known
had amazing memories of them. During my time at FAST, I met many talented people with diverse
interests and hobbies. Besides CS courses, I got the chance to study many business related courses
like marketing, technology management, and entrepreneurship. FAST NUCES encourages and
supports new entrepreneurs which is amazing.
Now that within few weeks I will be graduating from FAST, it looks like time has passed swiftly.
Maybe because we had around 3-4 semesters online. The things I learned from instructors, friends,
and even the people from administration, will remain with me throughout my life.
Hurriya Nasir (18I-0597)
I still remember my admission test day at FAST. As I walked down the corridors, I got a feeling that I
will return to this place again for sure and here I am finally in my last semester at FAST.
I would describe my first few days at FAST as extremely stressful. I was not used to such long
lectures packed with all the new things I had to learn instantly and going back home so late. I felt
overwhelmed with all the assignments coming one after another, surprise quizzes, lab task
submissions and the dreaded presentations.  At times I wanted to give up because I had never
faced such difficulties ever in my life. However, after a couple of weeks things started to get better
for me. I figured out how to manage all the course work and started making friends which created
this acceptance towards the fact that how different university life is from A levels. I eventually
started believing in “We either make ourselves miserable, or we make ourselves strong. The
amount of work is the same”.
I have realized that joining FAST was actually the best for me. These 4 years have changed me for
good and I can clearly feel that I am a different person now. My university has taught me to be
more confident, take up challenges, work hard, work in teams and help out others. I truly feel
blessed and tremendously thankful to be taught by competent Instructors and guided by the best
mentors.
Apart from academics I had such a memorable time at FAST. I will always cherish the memories of
these 4 years from enjoying the Final Year Trip, attending events like Nascon and Adventure Gala,
winning the virtual escape room, being part of the décor team for welcome ’19, taking the role of a
teacher’s assistant, coming to university during summers for an internship at AIM Lab, taking batch
photos, having lunch with friends at the cafeteria, to just simply singing along with the jamming
sessions at the hill on a random day.
It feels so unreal that soon I will be leaving this place and everything will just turn into bitter sweet
memories. But my journey here does not end as this institution will continue to impact my life
positively and has made me believe that I can achieve anything.
Iqra Aziz (18I-0491)
On my first visit to FAST, on the day of my entry test, mesmerized by the fountain amidst the green
gardens, I had no idea what an experience it was going to become and what a memorable part of
my life. However, no matter how much you plan for your life to be a certain way, God always has a
better plan – and my journey at FAST National University was just that, God’s better plan for me.
In FAST, just like its name suggests, your life becomes a little too fast paced. It’s like a roller coaster
ride: you jump in, take a seat, fasten your seat belt, and the rest is just a rush of adrenaline,
pounding heartbeat, and a bumpy ride – all for the endgame, the computer science degree.
From roaming the corridors of these buildings with zero clues, to now having an ambition to raise
the roof higher, what a journey it has been. Life at fast is a deal, a very well drafted one at that; in
focus. It’s all about perseverance here. You may have moments when you want to skip a class, or
miss an assignment, or take a day off or even just give up, but if you continue through all that,
headstrong, persistent, then one day, you might end up with something to show for it.
I never knew I’d end up here in CS, especially having done my O-levels and A-levels with biology as
the major, and even after coming here, it didn’t click at first, and strangely, PF became the enigma I
ran from right in the beginning. However, life is nothing but moments of realization, and the
moment I knew I was at the right place and path, the moment I knew this was it, was in a very
boring OOP class – I just had an epiphany, maybe it was all the constructors we were studying but I
knew this was exactly where I belonged, my life’s constructor.
Make it past the initial obstacles with enough focus and hard work, and I believe, somewhere along
the way, life at FAST just becomes a little easier, a little more bearable. On the one side, you may be
outnumbered by your submission deadlines at times, the FYP takes a toll on your health, teacher
assistance becomes too hectic and there may be too much happening, all with a GPA and image to
maintain, but on the plus side, FAST offers you great opportunities, gives you room for growth, and
people here, both staff and students are great. I still feel like I’m lost sometimes, but at least I know
I’m lost in the right direction. God really blessed me with this one.
Mohammad Ali Mustafa (18I-0619)
Life is a journey that consists of several milestones, selecting a university, and a field of study is one
of the most significant of these milestones. For me, it took me the entirety of A levels to be
completely satisfied with what field I wanted to pick. This also made the choice of opting for CS
FAST was a completely unique experience for me. It had students from diverse backgrounds making
an environment I was not accustomed to. This made it exciting and isolating at the same time. Like
many students here, my first year was very challenging. FAST has a demanding education system
for sure. But personally, I feel like it was the university’s method of training its students for real
world scenarios. Many of the deadlines often coincided with each other as well. This made it
necessary for you to allocate proper time for each of your tasks. It helped us understand the
importance of thinking. Thinking about what we value for ourselves, thinking about how we want
to plan on doing our assignments, thinking about the balance between education and our co-
curricular activities.
Being unsatisfied with my second semester, I vowed to improve my performance and spend more
time thinking about and planning my actions. I had a simple goal of improving my SGPA every
semester, making sure that I never get less than what I got in the previous one. Alhamdulillah, I
succeeded in doing that, eventually earning a silver medal in my second last semester as well.
For me, the faculty separated FAST from other institutes. As the CR of my class, I had to interact
with the teachers more than others, humanizing them for me. From the HoD of our department
personally handling our batch’s shuffling during the epidemic, to the director overlooking
everything in the campus and interacting with the student body, to having teachers from the 3rd
semesters still asking about their student’s well-being. Acts like these made me appreciate the
faculty a lot.
Looking back at my journey, with only a few months left here, I feel like I could have done some
things better, but I am still content with my experience. The growth I managed to achieve in this
grateful to FAST. I am certainly proud of what some of my fellow batchmates have already
managed to achieve and I believe most of them will excel in all the milestones they have yet to
reach in their lives.
Momin Salar (18I-0574)
At the time of writing this, I am thinking to myself; is this really it? Is this really the last month of my
time here, in this beautifully gathered shoulder to shoulder buildings, or rather ‘departments’ that
we call FAST? Is this really an end to all the torturous bombardment of quizzes, assignments,
projects, warnings, TA work that would amass to a size of the Everest itself, if stacked upon? Is this
really an end to a mix of emotional engagements, damages, build ups, butterflies and the treadmill
of new connections not just confined within this university – or for a lack of better words, the
joyous social life? Is this really the last time I will be anxiously holding my fingers back from opening
FLEX for a new entry in my ‘judgement book’ after a freshly announced “XYZ finals are up”? Is this
really the last time I will load up my car, with the goons I call friends, the goons I hold so dear,
without any prior planning just because we felt like filling our void with freshly cooked Chow Mein
at the top of a mountain or by the side of a long, beautiful street? Is this really it?
For a moment, my heart stops to express the need of freezing time, right here, right now – and take
a good, long, look back, owing to the fact that none of this is replaceable, extendable, expendable
or better yet, forgettable. It is the epitome of what life without political, binding responsibility feels
like with the added relentless intensity by none other than our dearest: FAST. I might sound
condescending taking into account the tone of words I have used when it comes to FAST, however,
little does any outsider know the love attached to them. If I were to explain this relationship, it
would be of those two siblings that would describe each other the worst but love each other the
best.
On that note, I’ll end this by just stating one of the best memories FAST has provided me with; the
time when I walked on the stage in the auditorium with my head held high, itching to turn around
and see the reaction of my parents on how proud they would be with that 4.0 medal hanging
around my neck. I would be lying if I said I expected the level of pride they had or the level of
satisfaction I would have achieved… This is only something you get to fully immerse yourself in,
when you’ve finally experienced it, Alhamdulillah. Please aim for this moment, you will not regret it
InshaAllah 
Muhammad Adil Fayyaz (18I-0613)
Change never comes easy. Especially, when you’re about to take the first step down a professional
path. Goodbyes are said to old friends and greetings to new ones. Unfamiliar faces are met with
new smiles. Opportunities missed and indecisions rekindled. There is a lot in play, so much to look
forward to, yet much is lost at the same time. And, no matter how inevitable and anticipated this
change might seem, you are never ready for it.
I remember walking into class on the first day, wearing a cloak of doubt and fear. Who knew what
to expect? Despite the positive reputation of a FAST alumnus, there was an un-motivating word
around that was not for the books. The first two semesters here were difficult to manage and keep
up with. The coursework was overwhelming, and the timings were tiring. At one point, it became
difficult to even take out time for myself and my family. However, I was gratefully able to pull
through without letting any of it impact my grades. Yet, I still hadn’t felt in place or that this was a
fit for me. As the circumstances kept changing, soon enough later, I planned to drop out and make
a transfer elsewhere. It didn’t work out. And today, I’m glad that it didn’t.
Over these past four years at FAST, one of my biggest takeaways is the connections I have had a
chance to build. By surrounding myself with the right people, who shared the same energy,
motivation, and goals as I did, I allowed myself to be more expressive and proactive. I feel this is
what university life is all about. Your technical skills cannot be valued if your interpersonal skills are
not impressive. And that is why this is the best time to invest in yourself and in the people who
bring out the best in you.
To anyone reading this who might feel intimidated by those apparently ahead of them, it may
sound cliché, but no one has it easy.  Studies can take a toll on any one of us. And while that may be
stressful at times, don’t let it overshadow the great memories you make here and don’t forget that
everyone has their own journey, there is no set standard and no defined timeline. We’ll all get to
the destinations we are meant to reach, but it is also important to savor and enjoy the journey.  So
celebrate your moments of joy. Cheers!
Nabeel Danish (18I-0579)
academics, but also holistically as a person. As I write my graduating note for this high-achiever
directory, I am going through a wonderful journey of memories and learning that has made me who
I am today.
I always had my aim set on doing Computer Science, and everyone I knew advised me to go to the
very best university that has excelled in this field for decades. With a word of caution that the
academic life at NUCES is going to be tough and enduring, I set out on my journey despite everyone
saying that you won’t be able to get a good GPA or enjoy your university life as everyone else does.
My four years here allowed me to hone my work ethic and gives me this great confidence that not
only I can survive in a place competitive than I have known before, but I can also excel there. With
the constant support of my parents, my friends, and some of the best teachers from the university,
I managed to consistently ace my studies. Managing my work-life balance allowed me to learn to
work hard and stay focused on my goals.
Participating in the Google Summer of Codes 2021 Program and managing that alongside my
university academics have been the highlights of my time here, and it showcases not only my
capacity to work hard and endure for long but to stay committed and consistent in my
performance. This is something that I could only learn from NUCES, and I will always be thankful for
this.
Noman Aziz (18I-1561)
Joining FAST was my own decision which I do not regret upto this day. I still remember everyone
saying from my college days that “It is very difficult to survive in FAST”, but no matter how hard it
got, I did not give up.
Looking down the road, I now realize that every challenge and difficulty I faced, it not only helped
me to expand my skills or groom myself, but also, it helped me to understand the fact that nothing
is impossible, you only have to have dedication and firm belief in yourself.
Apart from academics, during my life at FAST, I got to interact with different kinds of people, made
some friends along the way, lost a few and oftentimes I indulged myself in sports. I also had the
opportunity to become Teacher Assistant two times which led me to understand how things work
at the teacher's end.
This university helped me reach the place I am today, I have nothing but love for this institution.
Apart from that, every decision that I took was part of Allah’s plan for me which made me shape
into the person that I am today.
Rao Ubaid Ullah (18I-0504)
My journey at FAST started when I first heard about the name “FAST” in one of the motivational
lectures held at my college. As a computer enthusiast from the beginning, I wanted to choose the
Computer Science. It was then, that I decided it was FAST I want to study in.
At the start, a couple of semesters were hard since I had to become used to the semester system
and the workload of FAST. Even though I had a head start since I had done programming in a few
languages before, still that wasn’t good enough to make me a high achiever. In the beginning, I
thought getting an A in my programming courses is good enough, I just didn’t aim high. But it took
me 5 semesters to realize that it’s actually possible to score all As’ and all that one need is
consistency and not taking any of the course for granted. If I get the opportunity to advise my
juniors, I would say the same thing.
“You all can become high achievers, Aim high and Work Hard! Believe me, you can do it too!”
The ground for learning was very intuitive and teachers always had our back by pointing us in the
right direction. The thing that I liked about the education environment the most was that, unlike
other universities, we were given the bare minimum of information regarding our tasks and
assignment. We had to figure most of the things out on our own. This might have made things
difficult for most of the students but I always liked the challenge. Yeah, it did become stressful
sometimes and did cost me some all-nighters, but in the end, it was worth it. The effort required to
complete those tasks when delivered properly had a great learning impact on us. As a guy working
in an industry, I see myself standing out among students from other universities.
Regarding side activities, it has been slightly unfortunate for my batch. We only got to see 1
NASCON before 2022 due to COVID. But even then, that one event was very fun. I did participate in
a lot of the events and never had such an amazing experience before. In the 7th semester, we also
had our final year trip. That was such a great experience for me as well since it was the first time for
me to visit all those northern areas and spend such quality time knowing my classmates.
All of these are the memories I cannot forget ever and I really want to thank FAST for bringing all of
us together and providing such a beautiful and educative environment for us.
Sameet Asadullah (18I-0479)
I still remember my first day, sitting in the wrong classroom, waiting for the instructor to come, and
now taking my last few lectures in this university. Who knew the time would fly so fast, giving me
the best memories of my life. From playing games to making games, from using software to making
software, from a neural network in human brain to making my own neural network to think, this
four-year time period has taught me a lot.
It is never easy to bear the load of a lot of quizzes, assignments, and multiple projects at the end of
each semester. You never enter in the classroom without thinking that there could an un-
announced quiz today. But all of this transforms you in a way that by the end you are willing to face
any hurdle that comes in your way. It changes you from a young weak teenager to a strong
graduated man, and that is all what matters in the future life to come.
It has been a great experience here in FAST, probably the best experience that I will ever get in my
life. A friendly environment, kind faculty, beautiful sports, cozy grounds, fun concerts, and a lot
more. I will never be able to forget all of it. I will miss it all.
Sometimes I used to regret coming to FAST because of its academic burden, but now after
spending all this time and getting a touch of all these industries and companies out there, I consider
it the best decision of my life to come here. This is what God chose for me and then helped me get
on the top of it to be a medal holder. I will always thank God, the faculty, my friends, my parents to
shape me into what I am today!
Sana Ali Khan (18I-0439)
I never planned on coming to FAST, or even studying Computer Science – I applied on a whim and only came
here by chance. But almost four years later, I can thankfully say I don’t have any regrets.
When you come to FAST, everyone tells you about the extreme difficulty in surviving here: the tough studies,
hard schedule, lack of relaxation and so on. This all sounded very daunting to me then, but now I realise that
through these measures, university instills in you some very valuable qualities: a habit and appreciation for
hard work and a dedication to performing consistently.
Nothing feels better than realizing your hard work paid off and being a medalist in FAST is something that
makes me very proud of myself and all the work I have put in it. It is a great achievement to have good
grades and medals, but it is a much better thing to have a good work ethic and being hard-working and
responsible – these are the things that FAST teaches you, and that will ultimately benefit you in whatever
you do in your future.
My batch is in a unique position because we got to view FAST change a lot – from creating new departments,
to constructing a new building, developing a rich social life at university and much more. In my first
semester, university felt very small with nothing to do except study. Then almost two years passed under
lockdown – but so many things changed once the university was finally open again and back to normal. It’s a
marvel to look at our university now and see how much it has grown, and will continue to grow inshallah.
Even though I did not get the usual university experience due to the pandemic, I can still look back on the
last four years with pride and pleasure. It was very tough at times, but alhamdullilah for all the amazing
teachers I’ve had and all my friends who made university a good experience for me. I’m graduating soon
knowing that I have gained a lot from university and am ready to progress into the next phase of my life.
FAST is definitely not easy, but anyone can learn and grow a lot from being there.
Zaynab Batool Reza (18I-0419)
27th August, 2018. The first day of my first semester at FAST. That day is still etched clearly in my
memory, the nervousness and excitement I felt. Sure, I knew these next four years would be huge.
Little did I know then, however, exactly what I was in for.
As students of computer science, much of our lives revolve around 0 and 1. The binary of good or
bad, black and white, on and off. The four years I’ve spent at FAST however, cannot be summarized
in a single word or a single verdict. It has been a journey of growth, learning and unlearning, despair
and also hope. Moments of laughing so hard that I cannot breathe, of legs burning as I climb up the
unending stairs with barely a minute till class starts, of staring in horror at the marks for an exam I
thought went well, of trying to stay awake in an 8:30am class as my eyes burned, of silently
thanking Allah for getting high marks in a different exam, or of sitting in the corridor waiting for a
teacher while on an hour of sleep. All of these moments, and so many more, bundled together and
tied with the vibrant crimson ribbon that represents the road of my last four years, are what
encapsulate my journey at FAST.
During these last few years, yes, I have learned a lot about CS, about programming languages and
OOP, Data Structures, and other subjects. But I have also learned so much more about myself.
About who I am and what I am capable of. I have learned about people, and about life. I found
teachers, who were not only skilled in teaching their subject material, but who mentored us and
taught us about being better people and about navigating life. I found friends, who pushed me and
inspired me to be the best version of myself every single day, who I found standing by my side on
the days even I couldn’t stand my own presence.
Not every day of this degree was easy. In fact, the right words would be that barely any day was -
easy. There were a lot of sleepless nights, hours spent debugging code and crying sessions involved.
But as the end of my time here approaches, I find myself without any regrets. Every single moment
I’ve spent here has been worth it. For all the friends I’ve gained, the skills I’ve learnt, the
experiences I’ve had. For the new version of myself I have discovered. There is so much that FAST
has given me that will stay with me for the rest of my life, and for that, I am forever grateful.
PosiƟon Holder
Class of BS (CS)
Medal Holders of Bachelor of Science (Computer Science)
Batch 2018
S.No Roll-No
Name
Fall-18 Spring-19 Fall-19 Spring-20 Fall-20 Spring-21 Fall-21
1.
18I-0557
Abdul Mannan Ahmed
-
-
Silver
-
-
-
Bronze
2.
18I-0411
Abeera Fatima
-
-
-
-
Silver
-
-
3.
18I-0401
Adan Abbas
-
-
-
-
-
-
Bronze
4.
18I-0522
Hamza Ijaz
-
-
Gold
-
Gold
Bronze
Gold
5.
18I-0737
Haroon Ali
-
-
-
-
Bronze
-
Bronze
5.
18I-0738
Humayun Afzal
-
-
-
-
-
Silver
-
6.
18I-0597
Hurriya Nasir
Silver
Silver
-
-
Gold
-
Silver
7.
18I-0491
Iqra Aziz
-
-
-
-
-
-
Gold
8.
18I-0619
Mohammad Ali Mustafa
-
-
-
-
-
-
Silver
9.
18I-0574
Momin Salar
-
-
Bronze
-
-
-
Gold
10.
18I-0613
Muhammad Adil Fayyaz
Bronze
Silver
Gold
-
Gold
Silver
Gold
11.
18I-0632
Muhammad Bin Laiq
-
-
Silver
-
-
-
-
12.
18I-0436
Muhammad Farjad Ilyas
Gold
Gold
Gold
-
-
Gold
Gold
13.
18I-0579
Nabeel Danish
Gold
Silver
Gold
-
Silver
-
-
14.
18I-1561
Noman Aziz
-
-
-
-
-
-
Bronze
15.
18I-0504
Rao Ubaid Ullah
-
-
-
-
-
Silver
Silver
16.
18I-0479
Sameet Asadullah
-
-
Gold
-
-
-
-
17.
18I-0439
Sana Ali Khan
-
Gold
-
-
Silver
Silver
Gold
18.
18I-0419
Zaynab Batool Reza
-
Bronze
Silver
-
Gold
Gold
Gold

AI enrichment