Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge

The usage of anomaly detection is of critical importance to numerous domains, including structural health monitoring (SHM). In this study, we examine an online setting for damage detection in the Z24 bridge. We evaluate and compare the performance of the elliptic envelope, incremental one-class supp...

Full description

Saved in:
Bibliographic Details
Main Author: Amro Abdrabo
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7866
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261150608916480
author Amro Abdrabo
author_facet Amro Abdrabo
author_sort Amro Abdrabo
collection DOAJ
description The usage of anomaly detection is of critical importance to numerous domains, including structural health monitoring (SHM). In this study, we examine an online setting for damage detection in the Z24 bridge. We evaluate and compare the performance of the elliptic envelope, incremental one-class support vector classification, local outlier factor, half-space trees, and entropy-guided envelopes. Our findings demonstrate that XGBoost exhibits enhanced performance in identifying a limited set of significant features. Additionally, we present a novel approach to manage drift through the application of entropy measures to structural state instances. The study is the first to assess the applicability of one-class classification for anomaly detection on the short-term structural health data of the Z24 bridge.
format Article
id doaj-art-88d7ab1684cc495cac890169e4ba2d8d
institution OA Journals
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-88d7ab1684cc495cac890169e4ba2d8d2025-08-20T01:55:30ZengMDPI AGSensors1424-82202024-12-012423786610.3390/s24237866Application of Online Anomaly Detection Using One-Class Classification to the Z24 BridgeAmro Abdrabo0Department of Computer Science, ETH Zürich, 8092 Zurich, SwitzerlandThe usage of anomaly detection is of critical importance to numerous domains, including structural health monitoring (SHM). In this study, we examine an online setting for damage detection in the Z24 bridge. We evaluate and compare the performance of the elliptic envelope, incremental one-class support vector classification, local outlier factor, half-space trees, and entropy-guided envelopes. Our findings demonstrate that XGBoost exhibits enhanced performance in identifying a limited set of significant features. Additionally, we present a novel approach to manage drift through the application of entropy measures to structural state instances. The study is the first to assess the applicability of one-class classification for anomaly detection on the short-term structural health data of the Z24 bridge.https://www.mdpi.com/1424-8220/24/23/7866structural health monitoringonline anomaly detectionsupervised feature extractionconcept drift
spellingShingle Amro Abdrabo
Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
Sensors
structural health monitoring
online anomaly detection
supervised feature extraction
concept drift
title Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
title_full Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
title_fullStr Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
title_full_unstemmed Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
title_short Application of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge
title_sort application of online anomaly detection using one class classification to the z24 bridge
topic structural health monitoring
online anomaly detection
supervised feature extraction
concept drift
url https://www.mdpi.com/1424-8220/24/23/7866
work_keys_str_mv AT amroabdrabo applicationofonlineanomalydetectionusingoneclassclassificationtothez24bridge