MAVI

Created an AI mobile application addressing real life problems for visually impaired people through verbal queries and computer vision.

• GitHub
• Devpost

GT-MAB

• IEEE Paper
• Demo Site

Worked on Miniature Autonomous robotic Blimps (GT-MAB) as flying vehicles for indoor experiments that support research on mobile sensor networks, 3D motion control and human-robot interaction (HRI). The motivation for developing a deep learning approach to localization and tracking is to prove that such a platform could be used for complex tasks in autonomy that could eventually lead to applications such as surveillance of large indoor spaces or assisting with evacuation procedures.

IoT Smart Hedgehog Home

A hedgehog smart house that will allow users to monitor their hedgehog remotely. The smart environment will allow health monitoring features for the hedgehog to be autonomously driven by data collected from a range of sensors. The sensory feedback data provided from the smart environment will be uploaded to a cloud through Amazon Web Services (AWS) and stored in a cloud Relational Database Service (RDS).

The user will be able to interface with the smart environment through a web interface. It will allow for the user to monitor the status of the hedgehog by looking at graphs of certain metrics such as amount of time the hedgehog runs on the wheel and the temperature of his environment in a dashboard interface.

• Demo Site
• GitHub

Monitoring For Distracted Driving

First Place at AuburnHacks 2019

Project that looks at the behavior of a driver to detect if they are distracted. The motivation for this project is to help reduce distracted driving by providing positive reinforcements to drive safe. This idea can be used by companies like insurance companies to predict the risk factor of drivers and reward drivers that are safer. The end result of a tool like this would be safer transportation, especially considering that the leading cause of death for U.S. teens is motor vehicle accidents.

• Demo Site
• GitHub

Bitcoin Price Analyzer

Developed cryptocurrency analyzer using Apache Spark and AWS. The Bitcoin Price Analyzer application was created in order to better characterize and analyze the Bitcoin market. It will more accurately query and analyze historical data in order to make predictions with greater precision regarding the future. Some analysis such as Simple Moving Average (SMA) and Exponential Moving Average (EMA) were performed on historical market data.

• PDF
• GitHub

Mealy/Moore State Machine Simulator

Implemented a basic 1-bit, 2-bit, 3-bit and 4-bit finite state machine simulator in C++ using an adjacency list. It simulates both a Mealy and Moore state machine (choice up to user). The interface is in the form of a raw commandline interface that prints the state of the simulation in a graph or ascii table.

• PDF
• GitHub

2D Discrete Fourier Transorm with Concurrency

Implemented 2D discrete fourier transform using three different methods: Thread, MPI, and Cuda and compared runtimes for each. All three approaches were performed in an HPC cluster at Georgia Tech.

• PDF
• GitHub