Hey, I'm Harry Cheng

1st Place & Audience’s Choice @ UC Berkeley AI Hackathon

pFoG

pFoG is a wearable medical aid device that tackles Freezing of Gait (FOG) in people with Parkinson's disease. When FOG is detected, the device sends a targeted muscle stimulation to the frozen leg, helping the patient resume walking.

It comes with a web interface that eases data collection and labeling, and lets users fine-tune a model on their own walking data.

The pFoG wearable device
The pFoG prototype: an Arduino-driven wearable that reads gait data and triggers stimulation.

How it works#

The pFoG web interface for collecting and labeling walking data
The web interface for collecting, labeling, and training on walking data.

1 of 2: The pFoG web interface for collecting and labeling walking data

Features#

  • Real-time FOG detection using machine learning
  • Targeted muscle stimulation for gait recovery
  • Web interface for data collection and labeling
  • Model selection and personalization (fine-tuning)

Awards#

  • 1st Place, Social Wellness Track at UC Berkeley AI Hackathon 2025
  • Hacker's Choice Award at UC Berkeley AI Hackathon 2025

Tech stack#

  • React
  • Next.js
  • Tailwind CSS
  • Python
  • Flask
  • Arduino
  • Machine Learning
  • TensorFlow