About-me

I'm Vyom Unadkat

I am a computer science graduate student at USC
And I really love Machine Learning and animation.

I like to dismantle things and see from inside how things work. This curious nature has helped me become a good problem solver. The first big thrill was when I dismantled my computer and assembled it back again (It still works!). My first big introduction to playing with a computer was with animation and VFX. I was 12 and I used to shoot short clips and edit them on Adobe After Effects for hours. I loved doing that and even considered film making as a career for a short time.

The second part of my story with computers was when I was introduced to programming. I loved the idea of learning a language that machines could understand. The first language I introduced myself with was C. Currently, my favourite language is Python. I like working on projects related to Machine Learning and Data Science. I get very happy to see the impact they have on society and how businesses and human life benefits from it.

Name: Vyom Unadkat

Age: 24

Email: me@vyomunadkat.com

City: Los Angeles, USA

Design & Code

My Skills

Python

95%

Java

80%

SQL

95%

JavaScript

70%

Swift

90%

HTML/CSS

85%

React Native

75%

Tensorflow

80%

experience & education

My Resume

June 2021 - Aug 2021

Business Technology Solutions Associate - Intern

ZS Associates, Evanston, IL, US

• Automated manual process of obtaining data from multiple vendors by establishing channels improving efficiency by 25%.
• Created a cloud based Datawarehouse on Snowflake for Data Analysis.

my-history
March 2021 - Dec 2021

Student Researcher

Neurosurgery Dept., Keck School of Medicine, USC

• Designed a pipeline to extract key features from a video to predict if surgery would be successful.
• Publication - Vyom Unadkat, Dhiraj J Pangal, Guillaume Kugener, et al. Machine Learning Analysis of Intraoperative Video Without the Use of Code, 2021 Congress of Neurological Surgeons Annual Meeting. (Submitted).

my-history
Dec 2020 - Apr 2021

Student Researcher

Melady Lab, USC

• Worked as a Researcher and developed iOS app integrated ML model to anticipate surgical candidacy based on burn images.
• Publication - S. Huang, S. Rambhatla, L. Trinh, M. Zhang, B. Long, M. Dong, V. Unadkat, H. Yenikomshian et al. DL4Burn: Burn Surgical Candidacy Prediction using Multimodal Deep Learning, AMIA 2021 Annual Symposium. (Submitted).

my-history
Aug 2018 - Dec 2018

ML Engineer - Intern

3D POST

• Created a runtime surveillance and analysis module.
• Solved the Spaghetti problem in 3D printing by developing a Raspberry Pi module with a web cam.
• Compared layers of the product to be printed and detected flaws using Image Processing.
• Reduced the material wastage and production time by detecting discrepancies while the product is being printed.

my-history
June 2018 - Aug 2018

Decision Science Analyst - Intern

Quantiphi Analytics

• Performed video and audio alignment for multiple languages based on clips to be censored for Viacom US.
• Pre-processing on video clips to set the same frame rate, resolution, remove noises, detect the intro and credits in a video.
• Employed algorithms to divide a movie into a number of clips based on camera cuts and changing scenes.
• Incorporated Image Classification and Video Encoding algorithms for generating feature vectors of videos.
• Detected the clips to be deleted or censored based on content of the video using feature Vectors.

my-history
Jan 2017 - Jan 2018

ML Engineer - Intern

CoveVenture

• Worked on a project called MySA (My Social Analytical Score).
• Crawled online activities to retrieve data, analyze and perform sentiment analysis to assign a score to each user.
• Developed an iOS application by integrating ML for MySA..

my-history
Jan 2020 - Dec 2021

University of Southern California

Master's Degree | Los Angeles

Relevant coursework:
Foundations of Artificial Intelligence
Machine Learning for Data Science
Database Systems
Analysis of Algorithms
Software Engineering
Security Systems

my-history
June 2015 - May 2019

University of Mumbai

D.J. Sanghvi College of Engineering
Bachelor's Degree | Mumbai

Relevant coursework:
Data Structure and Algorithm Analysis
Data Mining and Business Intelligence
Cloud Computing
Intelligent Systems
Image Processing
Big Data Analytics
Database Management Systems

my-history
Download Resume

Projects Completed

Lines Of Code

Pizzas

Coffee Cups

Let's See My Work

My Portfolio

  • All
  • Software Development
  • Artificial Intelligence
  • Machine Learning
my-work
MySA-My Social Analytical Score

By crawling one’s online
activities, the system provides
the user with a social score–
just like a credit score.
This score can be referred to
take measures should there be online identify thefts.
View on Github
check youtube video
my-work
Timer App

A basic timer app built using Swift 3.
Default time set at 4 mins.
Features to add and subtract
10 seconds from timer.
View on Github
my-work
Automated Censorship System

Let us say there is a company wanting to air shows across the globe but are experiencing vagaries of varied censorship norms. Facing difficulty in manually editing the part to be censored, this project automates the manual work and provides a solution to map the audios in multiple languages with the video in accordance to the censored scenes.
View on Github
my-work
Deep Learning for financial predictions

Compared the accuracy in predicting prices of different stocks like Adobe, Facebook, Apple after an RNN-LSTM model was trained for a timestamp of 20 and 60 days.
View on Github
my-work
Search Algorithms

Used BFS, UCS, and A* algorithms to solve a problem statement.
View on Github
my-work
To do app

A to do app built using Swift 3. Can add tasks and delete as soon as done.
View on Github
check youtube video
my-work
Poke dex App

A poke dex iOS app. List of all the pokemons read from a csv file. Can search the pokemon based on the user's input.
my-work
Times Table App

An iOS based mobile times table app. The values can be changed with the help of a slider.
View on Github
my-work
Intelligent traffic management and violation detection system

Trained a You only look once (YOLO): Real – Time Object Detection System using Darknet to detect Cars, Buses, Motorbikes, Trucks, Autos. Jumping red light, standing ahead the white line are some of the violations that can be detected.
View on Github
my-work
Mini Go Game

Developed a 5x5 go game playing agent which plays against a random player, greedy player, aggressive player and alpha beta player(depth <=2 branching factor 10) both as black and as white player. Winning accuracy of over 93%

View on Github
my-work
Intelligent System for Weather and Congestion probing

This project determines the effect of weather on traffic using models like RNN-LSTM and ARIMA to acquire an estimation of the time taken to travel between two places by considering weather conditions.
View on Github
my-work
Neural Network for handwritten digit detection

Implemented a neural network from scratch using only numpy to detect handwritten digits using the MNIST dataset. Accuracy of over 98% achieved.
View on Github

What Love I Do

My Hobbies

Swimming

I have been swimming since I was 5 or 6. There is nothing more refreshing than going for a swim.

Programming

I get a sense of satisfaction by developing softwares that have a social impact on all of our lives.

VFX and animation

I like making short clips and editing them which tells a story and brings out the creativity in me.

Books and Research

My work

blog
  • JAN 2019 / BOOK
Learning Swift-ly

As the name suggests, this book will take you on a learning spree to help you know this programming language. It includes all the concepts you need to know to hit the ground running...

Read More
blog
  • SEPT 2019 / RESEARCH PAPER
Intelligent Traffic Management System

Urbanization has presented opportunities of progress which has attracted people from rural areas to the cities thus leading to mass migration...

Read More
blog
  • OCT 2018 / REVIEW PAPER
A Review Approach For Detecting Distracted Driver

Distracted driving causes a great loss of life as well as money. According to the National Highway Traffic Safety Administration (NHTSA), in 2015 alone...

Read More
blog
  • DEC 2018 / RESEARCH PAPER
Automated System for Detecting Distracted Driver

There has always been a safety issue while driving and this issue is of utmost importance with the increasing amount of accidents due to car crashing or distracted driving....

Read More
blog
  • DEC 2018 / RESEARCH PAPER
Deep Learning for Financial Prediction

Finance is one of the main pillars on which an economy grows. Having a precise understanding of how the financial market works corroborates greater monetary returns...

Read More
blog
  • DEC 18 / RESEARCH PAPER
Intelligent System for Weather Prediction

The emergence of deep learning techniques in the recent years coupled with the wide accessibility of colossal weather observations has inspired many researchers....

Read More
blog
  • OCT 18 / RESEARCH PAPER
Stock Price Trend Prediction Using Multiple Linear Regression

Stock markets are major institutions where trades are made daily having their worth in millions and billions on a daily basis. Some consider as a fast way to fill up their pockets whereas some have a traditional approach to invest in a company and reap long term benefits...

Read More
  • JAN 18 / BLOG
djinit.ai

The data science club of our undergrad college where we motivated juniors and students to pursue the field of data science by taking lectures and seminars...

Read More

Get In Touch

Contact Me

Address

Los Angeles

USA

Email

me@vyomunadkat.com

vunadkat@usc.edu

Message me

m.me/vyomunadkat97

Message me on facebook

Send Message