Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Explainable Ensemble Learning for Structural Damage Prediction under Seismic Events

Title: Explainable Ensemble Learning for Structural Damage Prediction under Seismic Events
Authors: Baldassini, Michele; Foglia, Pierfrancesco; Lazzerini, Beatrice; Pistolesi, Francesco; Prete, Cosimo Antonio
Contributors: Collectif; Baldassini, Michele; Foglia, Pierfrancesco; Lazzerini, Beatrice; Pistolesi, Francesco; Prete, Cosimo Antonio
Publisher Information: i6doc.com; BEL; Louvain-la-Neuve
Publication Year: 2025
Collection: ARPI - Archivio della Ricerca dell'Università di Pisa
Subject Terms: explainable AI; ensemble learning; structural damage; masonry buildings; seismic events
Description: This paper presents an explainable ensemble learning framework using Bootstrap Aggregating to predict structural damage in masonry buildings during seismic events. It estimates the peak ground acceleration (PGA) leading to the damage control limit state (significant damage) based on structural parameters. The model achieves high accuracy (R2=0.9536, MAE=0.0057) and interpretability through SHAP, aligning with structural engineering principles. Compared to finite element analyses, it offers faster computations (milliseconds) and scalability, enabling rapid intervention planning after earthquakes. Developed under the MEDEAproject(EUGrantn. 10101236), it supports disaster response and enhances seismic resilience.
Document Type: conference object
File Description: ELETTRONICO
Language: English
Relation: info:eu-repo/semantics/altIdentifier/isbn/9782875870933; ispartofbook:ESANN 2025 - Proceedings - 33rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning; European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning; volume:1; firstpage:609; lastpage:614; numberofpages:6; https://hdl.handle.net/11568/1338491
DOI: 10.14428/esann/2025.ES2025-198
Availability: https://hdl.handle.net/11568/1338491; https://doi.org/10.14428/esann/2025.ES2025-198; https://www.esann.org/sites/default/files/proceedings/2025/ES2025-198.pdf
Accession Number: edsbas.9A1A351A
Database: BASE