Support vector regression model for the prediction of buildings’ maximum seismic response based on real monitoring data
Dongwang Tao, Shizhe Fang, Haixu Liu, Jianqi Lu, Jiang Wang, Qiang Ma · 2024
Read Support vector regression model for the prediction of buildings’ maximum seismic response based on real monitoring data by Dongwang Tao, Shizhe Fang, Haixu Liu, Jianqi Lu, Jiang Wang, Qiang Ma (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-11612228.txt.
Description
Dongwang Tao and co-authors predict how far buildings drift in earthquakes using real monitoring records, in a 2024 study. The peak drift ratio is a key clue to damage, yet most prediction models train on simulations or lab models, not real buildings. The team used the largest public set of true building responses, with 41 features per record. They trained a support vector regression model on all features, then a leaner one on the ten most useful.
Both models beat standard regression approaches and other machine learning rivals. The building's natural frequency proved an especially strong input. The lean model kept most of the accuracy while asking only for features that are easy to obtain. The authors say it could feed near-real-time damage checks after a quake, when response teams need fast answers.
Catalog record
| CREATOR | Dongwang Tao, Shizhe Fang, Haixu Liu, Jianqi Lu, Jiang Wang, Qiang Ma |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |