SoundFlux is a sound-based fall detection system that uses a deep learning model trained from simulated human falls along with millions of open source sounds, to provide effective, low-cost, unintrusive, and privacy-sensitive peace of mind for the elderly and their loved ones.
We have created an end-to-end solution covering:
- Low cost edge device (non-wearable) for real-time fall detection and response
- State-of-the-art Deep Learning model to classify fall events from spectrogram representation of audio
- Inference done on the edge (no sensitive data transferred to the cloud)
- Unique dataset of simulated falls, collected using a lifelike jointed 165 lb. rescue manikin with human weight distribution
- Cloud portal to manage notifications, and see past fall detection events
Don't miss our capstone demo!
Please watch the live demo the team ran during our final presentation (fast forward to 4:33s on the video to go directly to the demo)