Smart Buildings: Water Leakage Detection Using TinyML

Othmane Atanane, Asmaa Mourhir, Nabil Benamar, Marco Zennaro, Luis Hernández-Callejo · 2023

Read Smart Buildings: Water Leakage Detection Using TinyML by Othmane Atanane, Asmaa Mourhir, Nabil Benamar, Marco Zennaro, Luis Hernández-Callejo (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10675406.txt.

Description

Othmane Atanane and colleagues built a tiny learning system in 2023 to catch water leaks. Cities face rising water stress and shortages. Leaks in building pipes waste large amounts silently. Sensors plus on-device learning can spot leaks locally. Local decisions cut delay and central system costs. The team used an existing sound dataset for plastic pipes. Sound clips became image-like patterns for analysis. Five image network designs were adapted through transfer learning. The best model was then shrunk for a small board.

All networks learned to detect leak sounds well. One efficient design scored highest on every measure. Its test accuracy came close to ninety-eight percent. After compression, it ran on an Arduino-class edge device. Inference took about two seconds per check. Memory and storage needs stayed very small. The authors present a near hands-off leak watcher. Real buildings could host such devices widely, they argue.

Catalog record

CREATOROthmane Atanane, Asmaa Mourhir, Nabil Benamar, Marco Zennaro, Luis Hernández-Callejo
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE44 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10675406

Browse the full library · About the Tower of Babel