Development of an automated transformer-based text analysis framework for monitoring fire door defects in buildings
Seunghyeon Wang · 2025
Read Development of an automated transformer-based text analysis framework for monitoring fire door defects in buildings by Seunghyeon Wang (2025) 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-12708815.txt.
Description
Seunghyeon Wang, writing alone, builds a text analysis system that flags fire door defects in buildings from written reports. The 2025 study addresses a safety gap: faulty fire doors let smoke and flame spread, putting residents at risk. Inspectors' notes hold the clues, but reading them at scale is slow.
Wang compares five transformer language models, each tuned in many variants, for sorting defect reports by type. One model, RoBERTa, won with strong scores across defect kinds such as frame gaps, seal faults, and hardware faults. It also beat a large set of classic and neural rival models. Automated sorting could help managers spot and fix door faults faster across housing stock. The work joins language AI with a concrete building safety task.
Catalog record
| CREATOR | Seunghyeon Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |