Updated on: Oct 06, 2021
GPA: 3.83
GPA: 3.61 (Gold medalist)
Java parallel-programming Cloud-computing Finance C# MSSQL Agile JMS docker Kubernetes
Build Framework and services (APIs, microservices & frontend) for Investment Management software to support trading activities
PostgreSQL Go Python3 Flask JavaScript React Redux Agile Gitlab UI-UX
Led the incorporation of Agile development process for slyText - web-based bidirectional messaging service
Developed back-end modules for managing payment gateway, dynamic dispatch queues and smart replies in Go
Migrated front-end to React.js and Redux to improve code maintainability, response time and user feedback mechanism
Developed CI/CD pipelines for back-end (Google go) and front-end (React) using Gitlab
Optimized db performace by 300% by writing efficient queries and using better indexes
MySQL Python3 Django 2.0 React Flux Gitlab Java Android
Taken up the responsibility to develop an end-to-end product to enable international calling and messaging services.
Designed and developed SaaS application to support the product using RESTful architecture by focusing on the security and privacy of the application. Developed a native android application using MVP architecture and data injection concept to enrich the stability and user experience.
Participated in conceptulizing the products being developed at MobileSphere.
OpenCV Android UI-UX Java C
CheckIt Go is a spinoff of an award winning research project. It is a mobile phone based OMR evaluation system to check multiple choice questions. Currently CheckIt Go has more than 5000 users.
Key Features
Assisted for the courses on Machine Learning, Operating Systems, Embedded Systems and Computer Programming. Conducted lab sessions, prepared & graded the assignements & quizes.
Php MySQL Cloud Telephony MATLAB Communication Healthcare
During this fellowship at an incubation center, worked on a healthcare focused startup Kahinee. Kahinee is an interactive voice response system to spread awareness about maternal healthcare, child care, anemia and nutrition through folk music and audio dramas.
The solution/sytem - Kahinee has been designed and fine-tuned after visiting more than 50 vilages, interacting with >100 end users and 50+ medical professionals.
Collaborated with Barakat Bundle and exectuted a pilot in a village named Jhagadia, Gujarat, India.
Personally I enjoyed working with users, interacting with them and coding the software that impected the lifestyle.
Natural Languate Processing Python3 Scikit
Improvised existing extractive text summarization methods such as Luhn's approach and TextRank using more robust features like Word2Vec and TF-IDF
Summarized 4500 online news articles and achieved the accuracy of ROUGE-1(0.4217) and ROUGE-2(0.2024)
Find More about News article Summarization on Github
Robotics & Algorithms Python3 OpenRave
Simulated motions/movements for a Puma robotic arm to move and stack blocks in a desired order in python and openRave
Implemented kinematic, inverse kinematics, biRRT, and data structure to find collision-free movements for a robotic arm
Enabled an algorithm to find solutions for any number of input blocks
Find More about Block world problem implemntation on Github
Php JavaScript Google blockly 24 hours challenge OpenCV
Devised a visual programming platform in a team of 3 to create computer vision applications
Enabled it to perform more than 50 functions of open Computer Vision library
Developed it with JavaScript, python, openCV, Google Blockly, HTML & CSS
Find More about VisionEd on Github
OpenCV CAMSHIFT Viola Jones Algorithm Python
Implemented an extension of Viola Jones algorithm & CAMSHIFT to detect & track multiple faces in Python and OpenCV
Obtained 92% accuracy of with a speed of 46 fps in 1080 FHD video
Explored other face recognition algorithms like Eigenfaces and artificial neural networks to recognize faces
Find More about Face Detection on Github
Linux C
A part of Linux Kernel 2.6.18 was modified in order to implement and evaluate fair share scheduler. In the process, we understood fundamentals of Linux Kernel and scheduling algorithms.
Find More on Github
R. Patel, S. Sanghavi, D. Gupta and M. S. Raval, "CheckIt - A low cost mobile OMR system," TENCON 2015 - 2015 IEEE Region 10 Conference, Macao, 2015, pp. 1-5. doi: 10.1109/TENCON.2015.7372983 [Read]
Abstract: This paper describes CheckIt: a mobile phone based optical mark recognition(OMR) system which is used for automatic checking of the user response sheets. It exploits prior information about the OMR sheet layout, which helps in achieving high speed and accuracy. The system incorporates following interdependent modules: (i) computer vision and image processing; (ii) computer communication and networking; (iii) database and (iv) user interface. The back end is developed in Python and OpenCV library while the front end is made using HTML and Android. The overall system cost is low as; 1. software is developed using open-source technology; 2. it does not necessitate scanning hardware. The desirability and viability aspect of the system development is done based on extensive market survey and after interviewing several stake holders.