Federated learning based fire detection method using local MobileNet
Sridhar Panneerselvam, Senthil Kumar Thangavel, Vidya Sagar Ponnam, Sudhakar Sengan · 2024
Read Federated learning based fire detection method using local MobileNet by Sridhar Panneerselvam, Senthil Kumar Thangavel, Vidya Sagar Ponnam, Sudhakar Sengan (2024) 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-11621580.txt.
Description
Sridhar Panneerselvam and co-authors build a fire-spotting system that learns across sites without pooling their images. Forest and indoor fires call for fast, sharp detection, yet models trained in one place can stumble in another. Their method, IOFireNet, trains a shared model through federated learning, so each site keeps its data and sends only model updates.
Images first pass through a filter that strips noise, then a clustering step splits fire from non-fire zones pixel by pixel. A light mobile network handles the heavy lifting on site, flagging spread, severity, and the area at risk for early warnings. In tests, the system topped ninety-eight percent accuracy at spotting fires and beat four well-known image networks, while its zoning step beat older segmentation tools.
Catalog record
| CREATOR | Sridhar Panneerselvam, Senthil Kumar Thangavel, Vidya Sagar Ponnam, Sudhakar Sengan |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |