Creative CV

About

Hello! I am Parth Goel. Machine Learning Engineer, Software Developer and Researcher.

Experienced Artificial Intelligence and Software Developer with a demonstrated history of working in the Artificial Intelligence research field. Skilled in Python, Java, R, Android Development, Typsecript, C and C++. Strong media and communication professional with a Masters in the field of CS with ML/AI concentration from Rutgers University.

Basic Information

Age:

23

Email:

goel.parth210@gmail.com

Phone:

+1 279-234-9356

Address:

54 Handy Street, New Brunswick, NJ, U.S.A

Language:

English, Hindi

Technical Skills

Python

100%

C++

100%

C

100%

Java

90%

R

80%

Typescript

80%

MySQL

90%

PostgreSQL

90%

Android Development

90%

Node

70%

React

75%

Preact

85%

Ojet

100%

Flask

60%

MacOS

90%

Windows

100%

Linux

85%

Jira

95%

GitHub

95%

Photoshop

85%

PySpark

95%

Tkinter

75%

Education

2021 - 2023

Master's Degree

Master's of Science

Rutgers University

CGPA: 4.0

Majoring in Computer Science with concentration in Machine Learning / Artificial Intelligence.

2017 - 2021

Bachelor's Degree

Bachelor of Technology

Manipal University Jaipur

CGPA: 8.55

Majoring in Computer Science and Engineering

2015 - 2017

High School

Central Board of Secondary Education

Ahlcon Public School

Percentage: 85%

Majoring in Non-Medical Science stream

Work Experience

Jan 2021 - Present

Rutgers University

Teaching Assistant, Grader and Proctor

Took recitations as a TA for undergrad courses; Discrete Maths - 2, and Algorithms courses.
Worked as a Grader for undergrad courses; Operating Systems, Data Management for DS, Algorithms, Software Engineering and Numerical Analysis Computing courses.
Proctored final exams for the Math department and Discrete Maths - 2 course.

May 2022 - Aug 2022

Oracle

Software Engineer Intern

Interned as a Full Stack Developer in the Applications Development Team (OCI).
Worked on the latest technologies; Ojet and Helidon to create a Generic Service Microservice for the internal members of the organization.
Initially developed an interface for the OCI vault for the users to store and manage their secrets but later plans to onboard other OCI tenancies as well.

Jan 2021 - May 2021

Capgemini

Senior Analyst Intern

Interned as a Java Full Stack Node + React Developer to create a web app to track both mental and physical health of the users.
The web app enabled the users to schedule appointments with verified doctors.
It also enabled the Doctors to schedule their availability for appointments.

Mar 2020 - Aug 2020

NEU, with Prof. Stavros Tripakis

Research Intern

Found equivalence in Neural Nets using SMT solvers which achieved great results.
This opened a gateway for creating shallower Neural Nets saving both computation power and time.
Threshold error value was found by experiments for 2 Neural Nets to be equivalent.

Dec 2019 - Jan 2020

IIT-KGP, with Prof. Sudip Misra

Research Intern

Worked on 10+ major and minor projects on Algorithms, Image Processing and Computer Vision.
Found which image compression algorithm gives the best compression results with least loss in quality.
Developed a Navigation System for the Visually Challenged people using Object Detection and Triangular Similarity.

Oct 2018 - Dec 2018

FunEduLearn

Android App Developer Intern

Developed a fun/learn gaming mobile app for kids using native Android.
Kids could give quizzes in a friendly competition manner to learn better following their friend's progress in the leaderboard.
Backend was written in Java and XML was used for frontend.

Projects

Patient Monitoring using Activity Recognition

• Developed a continuous monitoring system for patients in a team of 7, using CNN-LSTM to record and track all their activities. The model was trained on 6 activities, utilizing the data generated on Unity 3D and a web-app was built.

Sketch to Colored Facial Images using CGANS

• Converted facial sketches to coloured images using GAN models trained on FS2K and CUHK datasets

• Implemented and compared, state of the art research papers like Pix2pix, Sketch2face and Cycle GANs in a team of 3.

Siamese Neural Network Facial Recognition Implementation

• Constructed the Siamese Neural Network for one-shot image recognition.

• Employed the Neural Network to design a facial recognition system.

Mathematical Equation Solver using SNN

• Implemented a Mathematical Equation Solver using Spiking Neural Networks. The users could click a photo of their equation and send it to our algorthm.

• The model then identified all the Mathematical digits and symbols and return the solved value for the user.

Navigation System for Visually Challenged People

• Created an interactive and user-friendly navigation system for visually challenged people.

• Used pre-trained SSD 512 resnet50 v1 coco model for object detection and triangular similarity for distance calculation.

Single to Multiple Profile Generation of a Face using CGANs

• Designed a Conditional GANs algorithm, which generated images of multiple profiles (0, 45, 135 & 180 degrees) of a face when given the centre profile (90) image as input. A GUI using Tkinter was created for user-friendly experience.

• The main idea behind this project was to help in criminal and missing person identification.

Imitation Game

• Designed an algorithm using Convolutional Neural Networks to help the agent find it's way out of a maze.

• There were several agents coded using A star algorithm in python, which the CNN had to imitate.

Marksheet Scanning Android App

• Created an intelligent marksheet scanning DBMS. It allows users to scan the exam marksheet using an android app. This app reads and identifies the registration number and scores on the marksheet and stores them in a database side-by-side.

• The project was implemented during examinations at Manipal University Jaipur.

Intellectually Organised Crime Records

• Built a portal for the police, where photographs of missing and wanted people can be uploaded.

• These photographs combined with CCTVs installed throughout the country are used for identification. Once identified, their location is sent to the nearest police station.

Red Black Trees

• A red-black tree is a special kind of self-balancing binary search tree where each node has an extra bit (red or black).

• In this project we attempt to implement the red-black tree and investigate its efficiency by analyzing time and space complexity with the help of a user interface.

MujConnect Android App

• Developed an android app to allow users to register for different clubs at Manipal University Jaipur, which can be found on Google Play Store. To enable smooth administrative handling, a sister app was also designed, which was handed directly to the admins.

• This app was used at Manipal University Jaipur during the academic year 2018-19.

QR code Scanning Attendance System

• Assembled an attendance system that allows users to scan the QR code on their ACM ID cards to mark and check their attendance.

• The project was used during the classes of ACM Student Chapter at Manipal University Jaipur during the academic year 2018-19.

Library Management System

• Developed a library Management system which allowed the users to keep track of all the books in their library.

• The project was built using React.

Conversion of 2-D images into Multi-view Images of Bone Using Deep Learning

Published in Computer Methods in Biomechanics & Biomedical Engineering: Imaging & Visualization Journal Volume 9, 2021 - Issue 1.

Group Activity Recognition using Synthetic Data Generated on Unity 3D

Trained and tested state-of-the-art research algorithms like Actor-Transformer and Composer on simulated data generated using Unity 3D, to see if they give comparable results as compared to real data.

Conversion of 2-D images into 3-D Images of Bone Using Deep Learning

This is an extension of my research publication. In this project we designed a computer vision algorithm to estimate a 3D view of bones from a single 2D image.

Published Articles

Research

Journal

Conversion of 2-D Images into Multi-view Images of Bone using Deep Learning

Advancement in technology has changed the viewpoint of the public towards the medical field. Patients believe in the correct diagnosis of a deformity/defect improper functioning before the commencement of actual treatment...

Blog

Medium

A-Z Guide on how to run your Python/Machine Learning code on Android

As we all know, Machine Learning (ML)/Artificial Intelligence (AI) has taken the world of computer science by a storm. Everyone in the computer science community, irrespective of their specialization has started to learn about or use ML or AI in some form or the other...

Blog

Medium

Single to Multiple Profile Generation of a Face using Conditional GANs

The aim of this project is solely to aid the police in searching for the missing or wanted people, or maybe have some fun among our peers. The basic idea of this project is to implement an image translation model for generating....

Blog

Medium

Patient Monitoring System: CNN-LSTM model trained on Unity 3D simulated data

Human Activity Recognition (HAR) is the process of predicting the activity of a person based on a trace of their movement using a camera. The main goal of this blog is to develop a project which recognizes the patterns...