</ Changing the world one commit at a Time >
Hi, I'm Tejas Sheth
M.Sc in Computer Science, University of Southern California
B.Engg in Computer Engineering, University of Mumbai
About Me
I am currently pursuing a Master of Science degree in Computer Science at the University of Southern California, where I have acquired skills in data storage, image recognition, and C#. I have also completed several online courses and certifications in Python, Go, and other programming languages, enhancing my technical knowledge and versatility. With a keen eye on the latest developments in space exploration, I bring a unique blend of technical acumen and celestial curiosity. I am actively seeking opportunities that allow me to apply my skills to projects at the intersection of technology and space.
Education
Experience
Volunteer
‘Color Quest’ - Indie-Platformer GameLead Game Programmer
Jan 2024 - May 2024
- Spearheaded programming and analytics efforts for 'Color Quest,' an indie 2D platformer game inspired by Super Mario Bros. with a unique color-changing twist - Link.
- Developed key C# scripts using Unity 2D, including mechanics for color-changing player and platforms, super power timer countdown bar, jump mechanics, coin and collectible collection, and collision detection for spikes and moving objects, etc.
- This role involved leading the technical development of gameplay features within Unity 2D, ensuring smooth mechanics and optimizing player experience through analytics-driven enhancements.
Technology Stack: Unity Engine, Unity2D, C#, Git and GitHub, Discord, Documentation.
Virtual Human Therapeutics Lab, USC Institute for Creative TechnologiesSoftware Developer
Jan 2024 - Present
- Developed the BattleBuddy application using Unity 3D for iOS app development, developing a custom C# script for implementing long-press functionality and drag-and-drop features for game objects.
- Created a "Favorite Photo" module enabling users to select and view favorite photos within the app.
- Assisted in documentation review and enhancement, engaged in interdisciplinary research on virtual humans' impact on mental and emotional well-being.
Technology Stack: Unity Engine, Unity3D, C#, Tortoise SVN, Jira, Slack, Documentation.
Urban Future’s Data Core, USC Sol Price School of Public PolicySoftware Engineer, Team Lead
Aug 2023 - Dec 2023
- Led a team of 6 in developing a Python web scraping program to extract research data from Google Scholar by professors, resulting in a comprehensive database accessible to students and faculty.
- Implemented agile software development methodologies for efficient project management, overseeing data analysis and visualization to provide actionable insights for public policy and business strategies.
Technology Stack: Python, WebScraping, Selenium, BeautifulSoup4, Database Systems, Google Scholar, Data Analysis, Data Visualization
Mosaic Wellness Pvt. Ltd.Tech Intern
June 2022 - July 2022
- Built a frontend component library to standardize UI elements, facilitating efficient code management and progress tracking.
- Expanded knowledge of the essential fundaments of React.js, TypeScript required to develop an admin panel enhancing internal coordination and streamlining processes.
Technology Stack: ReactJS, Typescript, Storybook, Javascript, Redux, Component Library.
NSP Ites Pvt. Ltd.Machine Learning Intern
July 2021 - January 2022
- Developed Python web scraping tool to boost sales effectiveness and meet client demands efficiently.
- Prototyped WhatsApp Business automation system for faster customer responses, enhancing client satisfaction and streamlining communication.
Technology: Python, WebScraping, Selenium, BeautifulSoup4, WhastApp Automation.
Detection of SQL Injection using Reinforcement LearningTeam Lead Programmer & Researcher
Aug 2022 - May 2023
- Led a 4-person team in engineering a Reinforcement Learning system using Q-Learning to mitigate SQL Injection Attacks, resulting in enhanced security measures and reducing cybersecurity risks.
- Published and presented novel research at conferences in University of Loughborough, London - Link and KJ Somaiya University (KJSIEIT), Mumbai - Link.
Technology: Python, Machine Learning, Reinforcement Learning, WebApp, ReactJS, Research, Documentation.
Reverse Image QueryingLead Programmer & Researcher
Jan 2022 - May 2022
- Redesigned a solution using cosine similarity model to extract similar images with 60%+ accuracy, enhancing image recognition capabilities and facilitating efficient image retrieval.
- Published research in IJRASET Journal with 500+ views - Link, contributing to the academic community.
Technology: Python, Machine Learning, Cosine Similarity, WebApp, ReactJS, Research, Documentation.
Real-time Motion Detection SystemLead Programmer
Aug 2022 - Dec 2022
- Developed a real-time motion detection system using Python and OpenCV to monitor and detect unusual activities captured by a camera feed.
- Implemented algorithms for motion detection and object tracking, enabling the system to identify and track moving objects within the camera's field of view.
- Integrated an alert system to notify users upon detecting motion, enhancing security monitoring capabilities.
Technology: Python, Computer Vision, OpenCV, Documentation.
Mentorship Programby APSIT SKILLS
July 2021 - September 2021
- Managed a group of 10-15 mentees.
- Skills: Communication, Management, Organization.
Internship Programby APSIT SKILLS
June 2020 - August 2020
- Python Specialization Course from Coursera.
- Technology: Python.
Projects
‘Color Quest’ - Indie-Platformer Game
Spearheaded programming and analytics efforts for 'Color Quest,' an indie 2D platformer game inspired by Super Mario Bros. with a unique color-changing twist - Link. • Developed key C# scripts using Unity 2D, including mechanics for color-changing player and platforms, super power timer countdown bar, jump mechanics, coin and collectible collection, and collision detection for spikes and moving objects, etc. • This role involved leading the technical development of gameplay features within Unity 2D, ensuring smooth mechanics and optimizing player experience through analytics-driven enhancements.
Virtual Human Therapeutics Lab, USC Institute for Creative Technologies
Developed the BattleBuddy application using Unity 3D for iOS app development, developing a custom C# script for implementing long-press functionality and drag-and-drop features for game objects. • Created a 'Favorite Photo' module enabling users to select and view favorite photos within the app. • Assisted in documentation review and enhancement, engaged in interdisciplinary research on virtual humans' impact on mental and emotional well-being.
Urban Future’s Data Core, USC Sol Price School of Public Policy
Led a team of 6 in developing a Python web scraping program to extract research data from Google Scholar by professors, resulting in a comprehensive database accessible to students and faculty. • Implemented agile software development methodologies for efficient project management, overseeing data analysis and visualization to provide actionable insights for public policy and business strategies.
Real-time Motion Detection System
Developed a real-time motion detection system using Python and OpenCV to monitor and detect unusual activities captured by a camera feed. • Implemented algorithms for motion detection and object tracking, enabling the system to identify and track moving objects within the camera's field of view.
Detection of SQL Injection Attacks using Reinforcement Learning
SQL injection is the most common web application vulnerability. This vulnerability can be generated unintentionally by software developers during the development phase. Thus, a tool to prevent SQLi Attack to improve the security of the website needs to be implemented.
Reverse Image Querying
We have implemented and improvised a rudimentary yet efficient solution by using the cosine similarity model to extract similar images for the given input image from the user. The model used is explained comprehensively together with visual representations. We have also explored multiple use cases that can be used as commercial products. The resulting web application can be utilised to act as a reverse image search engine as a standalone application or can be embedded as a sub-module in a larger application.
Student Performance Analysis
A Machine Learning model that predicts the marks obtained by a student in their final semester via regression methodology. It is important to find patterns in the student performance to be able to provide the necessary, accurate and timely diagnosis to the student. It also serves as a basic criterion for institutions to monitor the quality of education provided. The model considers factors such as previous academic record, attendance, socioeconomic background, etc.
Cloud-based Note Taking App
A note-taking application using the latest cloud technologies. We solve the problem of slow speed, memory extensive and high cost of allocating resources, even in the cloud by implementing it with asynchronous functions with the concepts of async, await & Promise in TypeScript - React. And, to make it cost-efficient, we make use of serverless technologies
Expense Manager
A Java-based Project for managing day-to-day expenses, allowing the user to keep a track of his/her debited & credited amounts on a daily, monthly, or even yearly basis. Also, to notify user if he/she crosses a threshold amount and thus helping them in maintaining their balance and expenses within set boundaries.
Publications
Detection of SQL Injection Attacks by giving apriori to Q-Learning Agents
The SQL Injection vulnerability can either be unintentional by software developers or an intentional ploy employed by a hacker with malicious intent to exploit sensitive data. With the recent surge in information, there is an innate quest to safeguard this information from falling into the wrong hand leading to data theft, leak of personal data or loss of property. With relational databases like MySQL being the most popular, it allows users to extract any available information without any significant knowledge of databases. With vast information stored in databases warrants attacker’s attention, potentially risking critical confidential information. The premature detection of SQL Injection Attacks will be very helpful in preventing any malicious attempt by an attacker. In this research, we analyze the results of Reinforcement Learning algorithms like Q-Learning on a dataset consisting of potential SQL Injection queries. We intend to provide a Reinforcement Learning solution to minimise the potential threat posed by SQL Injection and give apriori to the model to learn to detect a SQL attack and prevent any unforeseen mishap more quickly and accurately.
A Detailed Evaluation of SQL Injection Attacks, Detection and Prevention
An SQL Injection attack is a database focused attack for programmers that utilise data. It is accomplished by inserting malicious lines of code into the SQL query to alter and modify its meaning, allowing the attacker to gain access to the database or retrieve sensitive data. Many strategies for detecting and preventing such assaults have been developed and suggested. This study provides an in depth examination of 38 publications on approaches for detecting SQL Injection in web applications. This offers a foundation for designing and using efficient SQL Injection, detection and prevention techniques.
Reverse Image Querying
A Research Paper written on 'Reverse Image Quering using Cosine Similarity Model' published in a reputed international journal. We have implemented and improvised a rudimentary yet efficient solution by using the cosine similarity model to extract similar images for the given input image from the user.
Get in Touch
Feel free to contact me either on the following phone number or email address.