Elderly · Frontier
Bathroom Hazard Forensics: Chronic Leak & Wet-Floor Risk Mapping
Finds hidden dampness in bathroom walls and recurring wet patches on walking paths.
Plausible physics, early work — shown honestly as an experiment.
How it works
Water changes how WiFi waves travel through walls and floors — a damp patch slows and weakens the signal in one fixed spot. Because a leak grows slowly in the same place, the system can separate it from everyday changes and point to it on the floorplan.
In the physics: Water ingress into drywall/subfloor raises local eps_r from ~2 toward 10-30+, adding picosecond-to-nanosecond excess delays on wall-penetrating paths and increasing attenuation (sigma). A chronic leak is a spatially fixed, monotonically growing dielectric anomaly — the exact complement of motion sensing, and it sits on the same hardware.
See it work
This is real pipeline output for Elderly, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
ESP32-wall dataset for wall-path characterization; own-hardware controlled wetting of a drywall test panel and subfloor section with graduated water volumes, tracking CIR delay drift vs. moisture meter ground truth over 3 weeks.
Who it is for
For senior-housing property operators and insurers: 'The same $100 room kit that watches for falls also finds the leak that causes them — moisture and slip-zone maps from the resident's own WiFi.'
runtime Runs today in LatentField 2.0 as fall_detect
The matching solution
Complete first-room estimateAging-in-Place Guardian3 nodes · ~$130 parts · 60 min Request kit, subscribe, or set up →Compatible DIY hardware options
15 min · beginner
60 min · intermediate