Athens, GA., April 27, 2026: Three students from the University of Georgia took first place at UGA Hacks 2026, an annual student-run hackathon that drew more than 500 participants from universities across the region and beyond.
Anisha Dhawan (third year), Stuti Thummala (second year), and Saachi Varshney (third year) earned Best Overall for their project, Guardian Angel, a real-time fall detection system designed to assist seniors and individuals with mobility challenges.
The system detects falls instantly on-device, records a short video for context, and alerts caregivers through multiple channels, including a mobile app, phone call, and Alexa integration. The goal, the team said, is to reduce response time in emergencies where delays can significantly worsen outcomes.
“We wanted to build something that could make a real difference in situations where every second matters,” Dhawan said. “Our goal was to create a system that not only detects a fall, but also helps caregivers respond immediately with the right information.”
The team developed an end-to-end solution using computer vision and edge machine learning tools, including MediaPipe and TensorFlow Lite. The system also features a FastAPI backend for event handling and storage, a Flutter-based mobile application for caregiver alerts and video review, and Alexa integration via AWS Lambda for in-home notifications.
Together, these components allow the system to function in real time and deliver alerts across multiple platforms.
The project highlights how emerging technologies such as artificial intelligence and edge computing can be applied to real-world challenges, particularly in healthcare and safety.
More information about Guardian Angel, including a live demo and technical details, is available on the team’s demo and Devpost pages.
