Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
Amro Abdrabo, Victor Giurgiutiu · 2024
Read Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge by Amro Abdrabo, Victor Giurgiutiu (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-11644842.txt.
Description
Work led by Amro Abdrabo tested live warning tools for damage in the Z24 bridge in 2024. Bridge health checks need methods that spot odd sensor patterns as data streams in, without prior examples of damage. The study compares five one-class methods that learn what normal bridge data looks like.
A boosted tree method, called XGBoost, did well at picking the small set of traits that matter most. The team also adds a new way to handle drift, as bridge data slowly changes over time. Their drift method uses entropy scores on incoming data states. The authors present the work as an early test of one-class tools on short-term bridge data.
Catalog record
| CREATOR | Amro Abdrabo, Victor Giurgiutiu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |