Projects

Parkinson's Care VR System
C# Unity TensorFlow React Flask SVM CNN
Georgetown University H2AI Hackathon: 1st Place Grand Prize & Patient Safety Award
  • Built a VR tool for Parkinson's assessment that tracks movement and voice data using Unity and TensorFlow, achieving 92% accuracy in symptom detection.
  • Connected VR sensors to a Python backend for real-time doctor monitoring with under 100ms latency.
Python React GPT-4 API PyQT5 OpenCV C++ Embedded Systems
PatriotHacks 2024: Triple Winner (Patriot Favorite, Most Likely to be a Startup, Best Cyberpunk Theme)
  • Built a robot that detects and picks up trash, plus a file organizer that uses GPT-4 to categorize files with 95% accuracy.
  • Wrote the code connecting Python vision models to C++ microcontroller firmware for real-time navigation.
Peekabot
Python OpenCV AWS IoT Mediapipe C++ Raspberry Pi IoT Systems
HackOverflow 2024: Best Robot Hack Winner
  • Built a child safety robot using Raspberry Pi and Arduino that tracks toddler movements and alerts parents to dangerous situations.
  • Added pose detection with OpenCV/Mediapipe and live streaming so parents can monitor remotely via AWS IoT.
NaviguideAI
Java Python TensorFlow ResNet Computer Vision PyAudio ESP32
PatriotHacks 2023: Best AI-Powered Hack Winner
  • Built a navigation aid for visually impaired users using ResNet-18 for obstacle detection, achieving 92% accuracy at 127ms inference.
  • Added spatial audio and haptic feedback to guide users through spaces, with 96% successful navigation in testing.
Optimal Path Navigation
Python TensorFlow Hugging Face 3D Mapping Depth Estimation A* Algorithm
  • Built an indoor navigation system that converts 2D images to 3D point clouds using Hugging Face depth estimation models.
  • Used A* pathfinding on 2D occupancy grids to plan safe routes around obstacles in under 5 seconds.
Optical Character Recognition System
Python NumPy Scikit-learn KNN Machine Learning
  • Built a handwritten digit recognizer using KNN, achieving 98.66% accuracy and cutting training time from 26 to 8 minutes.