Vivek Maskara

GRA at The Luminosity Lab, ASU | Ex Senior Software Engineer, Zeta | Volunteer, Wikimedia Foundation

Arizona State University

Hello!

I am currently pursuing my Masters in Computer Science from Arizona State University. I completed my bachelor’s in Software Engineering from Delhi Technological University. I love writing code, developing apps and creating websites.

As a full stack Software Engineer at Zeta, I helped in building a suite of products for digitizing office cafeterias used by ~700 corporates and attributing to 1 million+ monthly transactions. With strong Computer Science fundamentals and experience across multiple engineering verticals, I always tend to bring a unique perspective when solving business problems.

I have been associated with the Wikimedia Foundation as a volunteer for the past 3 years, contributing to their Wikimedia Commons Android app.

Interests

Artificial Intelligence
Computer Vision
Android app development

Education

Master of Science, Computer Science, 2021
Arizona State University
Bachelor of Technology, Software Engineering, 2016
Delhi Technological University - New Delhi, India

Experience

Graduate Research Assistant

The Luminosity Lab, ASU

Mar 2020 – Present Tempe, Arizona

Responsibilities include:

Developing a machine learning model for detection of Neuroblastoma using histopathological images for PCH hospital.
Researched and built the MVC for indoor parking automation using YOLO and DeepSort for real time vehicle tracking.
Contributed to the backend for ASU’s end to end PPE response network for producing and delivering medical supplies.
Built a Customer 360 dashboard for Bank of West using Neo4J graph database, Flask backend and React for frontend.
Published a gamified supply chain management learning app funded by USAID, ShipShape for iOS and Android.

Senior Software Engineer

Zeta, Directi

Jun 2016 – Nov 2019 Bangalore, India

Built NFC based contactless payments & custom ordering solution for POS attributing to 1 million+ monthly transactions.
Contributed to over 20+ projects in Zeta spanning across Android, Raspberry Pi and backend microservices.
Responsible for optimizing query performance for PostgreSQL and building throughput and service health monitoring dashboards using Grafana and Kibana.

Recent Posts

Using Weighted Random Sampler in PyTorch

Sometimes there are scenarios where you have way lesser number of samples for some of the classes where as other classes have lots of samples. In such a scenario, you don’t want a training batch to be contain samples just from a few of the classes with lots of samples.

Last updated on Nov 19, 2021 2 min read Deep Learning, Pytorch

Using Weighted Random Sampler in PyTorch

Handling corrupted data in Pytorch Dataloader

Recently, while working on a video dataset, I noticed that some of the videos contained a few corrupted frames. While running the training, my dataloader used to return an incorrect shaped tensor since it was not able to read the corrupted frame.

Last updated on Oct 31, 2021 1 min read Deep Learning, Pytorch

Handling corrupted data in Pytorch Dataloader

Analyzing Bike Sharing Demand

Recently, I worked on an assignment to analyze the data from bikesharing system to predict its demand. In this post, we will see how the given data can be analyzed using statistical machine learning methods.

Last updated on Feb 12, 2021 10 min read Data Science

Analyzing Bike Sharing Demand

Overview of programmatically managing AWS Infrastructure

If your application uses just a handful of cloud resources, you can easily manage it using the GUI(Graphical User Interface) based console. As the complexity of your system increases, the underlying infrastructure also grows, and managing it manually becomes a nightmare.

Last updated on Sep 27, 2021 13 min read Software Development

Overview of programmatically managing AWS Infrastructure

Tabular Synthetic Data Generation using CTGAN

In this post we will talk about generating synthetic data from tabular data using Generative adversarial networks(GANs). We will be using the default implementation of CTGAN [1] model. Introduction In the last post on GANs we saw how to generate synthetic data on Synthea dataset.

Last updated on Dec 18, 2020 3 min read Deep Learning, GANs

Tabular Synthetic Data Generation using CTGAN

Projects

English Vocabulary Builder for GRE, TOEFL & IELTS

Learn new English words every day! The app has 1000s of pictures with cartoons from Mickey Bach. Mickey Bach was producing Word-A-Day cartoons from the 1940’s to about 1985 for the pleasure of people who wanted to improve their vocabulary skills.

Download for Android

English Vocabulary Builder for GRE, TOEFL & IELTS

Helium Monitor

Electron based cross platform menu-bar app for monitoring earnings from helium miner

Code Download for macOS

Helium Monitor

Data Viz: San Diego Burritos

The project uses zoomable circle packing visualization below shows the burritos and their ratings in San Diego.

Data Viz: San Diego Burritos

Data Viz: Trump Approval Ratings

This project uses a pair of visualizations to promote opposing viewpoints using the same base dataset

Data Viz: Trump Approval Ratings

Data Viz: Mystery at the Wildlife

This project was done as part of CSE 578 course. The primary goal of this project is to identify reasons behind the decline in the population of the Rose-crested Blue Pipit bird in the city of Mistford.

Code Slides Video

Data Viz: Mystery at the Wildlife

Wikimedia Commons

An open-source app allowing the Wikimedia community to contribute content to Wikimedia Commons.

Code Download for Android

Wikimedia Commons

Spaced

AR App for Zeta’s design meetup 2019

View iOS app View Android app

Spaced

ShipShape

A gamified approach to educate on supply chain skills in an engaging manner.

Download for iOS Download for Android

ShipShape

Ppe Response

A decentralized production network to print, sterilize and deliver personal protective equipment (PPE) for those on the front lines of the coronavirus response.

Ppe Response

Zeta

Contributed in building products for Zeta Express, an end to end solution for digitizing cafeterias

View Android app

Zeta

Recent Publications

Early Pleistocene faunivorous hominins were not kleptoparasitic, and this impacted the evolution of human anatomy and socio‑ecology

Humans are unique in their diet, physiology and socio‑reproductive behavior compared to other primates. They are also unique in the …

Certification

Neural Networks and Deep Learning

Coursera Jul 2020

Course on Neural Networks by DeepLearningAI

See certificate

TensorFlow in Practice Specialization

Coursera Mar 2020

Introduction course on using Tensorflow

See certificate

Convolutional Neural Networks

Coursera Feb 2020

Course on CNN by DeepLearningAI

See certificate