Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation

<p dir="ltr">This study explores the limitations of image-based structural health monitoring (SHM) techniques in detecting structural damage. Leveraging machine learning and computer vision, image-based SHM offers a scalable and efficient alternative to manual inspections. However, i...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Vagelis Plevris (14158863) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513538601517056
author Vagelis Plevris (14158863)
author_facet Vagelis Plevris (14158863)
author_role author
dc.creator.none.fl_str_mv Vagelis Plevris (14158863)
dc.date.none.fl_str_mv 2025-01-26T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s00477-024-02898-7
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Assessing_uncertainty_in_image-based_monitoring_addressing_false_positives_false_negatives_and_base_rate_bias_in_structural_health_evaluation/30197968
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Civil engineering
Information and computing sciences
Artificial intelligence
Machine learning
Image-based damage detection
Structural health monitoring (SHM)
Risk-based decision making
Structural safety
Base rate fallacy
dc.title.none.fl_str_mv Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">This study explores the limitations of image-based structural health monitoring (SHM) techniques in detecting structural damage. Leveraging machine learning and computer vision, image-based SHM offers a scalable and efficient alternative to manual inspections. However, its reliability is impacted by challenges such as false positives, false negatives, and environmental variability, particularly in low base rate damage scenarios. The Base Rate Bias plays a significant role, as low probabilities of actual damage often lead to misinterpretation of positive results. This study uses both Bayesian analysis and a frequentist approach to evaluate the precision of damage detection systems, revealing that even highly accurate models can yield misleading results when the occurrence of damage is rare. Strategies for mitigating these limitations are discussed, including hybrid systems that combine multiple data sources, human-in-the-loop approaches for critical assessments, and improving the quality of training data. These findings provide essential insights into the practical applicability of image-based SHM techniques, highlighting both their potential and their limitations for real-world infrastructure monitoring.</p><h2>Other Information</h2><p dir="ltr">Published in: Stochastic Environmental Research and Risk Assessment<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00477-024-02898-7" target="_blank">https://dx.doi.org/10.1007/s00477-024-02898-7</a></p>
eu_rights_str_mv openAccess
id Manara2_8f75a2fd585174f07594d83a98bb98bb
identifier_str_mv 10.1007/s00477-024-02898-7
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30197968
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluationVagelis Plevris (14158863)EngineeringCivil engineeringInformation and computing sciencesArtificial intelligenceMachine learningImage-based damage detectionStructural health monitoring (SHM)Risk-based decision makingStructural safetyBase rate fallacy<p dir="ltr">This study explores the limitations of image-based structural health monitoring (SHM) techniques in detecting structural damage. Leveraging machine learning and computer vision, image-based SHM offers a scalable and efficient alternative to manual inspections. However, its reliability is impacted by challenges such as false positives, false negatives, and environmental variability, particularly in low base rate damage scenarios. The Base Rate Bias plays a significant role, as low probabilities of actual damage often lead to misinterpretation of positive results. This study uses both Bayesian analysis and a frequentist approach to evaluate the precision of damage detection systems, revealing that even highly accurate models can yield misleading results when the occurrence of damage is rare. Strategies for mitigating these limitations are discussed, including hybrid systems that combine multiple data sources, human-in-the-loop approaches for critical assessments, and improving the quality of training data. These findings provide essential insights into the practical applicability of image-based SHM techniques, highlighting both their potential and their limitations for real-world infrastructure monitoring.</p><h2>Other Information</h2><p dir="ltr">Published in: Stochastic Environmental Research and Risk Assessment<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s00477-024-02898-7" target="_blank">https://dx.doi.org/10.1007/s00477-024-02898-7</a></p>2025-01-26T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s00477-024-02898-7https://figshare.com/articles/journal_contribution/Assessing_uncertainty_in_image-based_monitoring_addressing_false_positives_false_negatives_and_base_rate_bias_in_structural_health_evaluation/30197968CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301979682025-01-26T09:00:00Z
spellingShingle Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
Vagelis Plevris (14158863)
Engineering
Civil engineering
Information and computing sciences
Artificial intelligence
Machine learning
Image-based damage detection
Structural health monitoring (SHM)
Risk-based decision making
Structural safety
Base rate fallacy
status_str publishedVersion
title Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
title_full Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
title_fullStr Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
title_full_unstemmed Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
title_short Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
title_sort Assessing uncertainty in image-based monitoring: addressing false positives, false negatives, and base rate bias in structural health evaluation
topic Engineering
Civil engineering
Information and computing sciences
Artificial intelligence
Machine learning
Image-based damage detection
Structural health monitoring (SHM)
Risk-based decision making
Structural safety
Base rate fallacy