A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Mapping textual descriptions to condition ratings to assist bridge inspection and condition assessment using hierarchical attention
Abstract Current bridge management strategies rely on experience-driven manually assigned condition ratings that are vulnerable to human subjectivity and experience variance. To improve the consistency of the condition rating practices, this study identifies narrative descriptions from bridge inspection reports as an untapped data source and proposes a data-driven framework as a supportive tool for two applications: automated condition recommendation and real-time quality control. A hierarchical architecture employing recurrent neural network encoders with an attention mechanism was developed using a collection of reports from the Virginia Department of Transportation. The condition recommendation application performed a classification task and demonstrated improved performance over a variety of baseline systems. The quality control application learns a data-driven decision threshold to decide whether to accept or reject an inspector-provided rating, which provides a cyber-human collaboration route for condition assessment. Visualization of the resulting attention patterns was shown to provide interpretable insights which highlight potentially-overlooked indicators.
Highlights A data-driven approach that maps narrative inspection descriptions to condition ratings. Deep-Learning-based hierarchical attention network for heterogeneous textual data. Visualization of attention patterns showed interpretable insights of condition ratings. Two application proposed: automatic condition rating and quality control tool. Proactively increase the consistency of infrastructure condition rating.
Mapping textual descriptions to condition ratings to assist bridge inspection and condition assessment using hierarchical attention
Abstract Current bridge management strategies rely on experience-driven manually assigned condition ratings that are vulnerable to human subjectivity and experience variance. To improve the consistency of the condition rating practices, this study identifies narrative descriptions from bridge inspection reports as an untapped data source and proposes a data-driven framework as a supportive tool for two applications: automated condition recommendation and real-time quality control. A hierarchical architecture employing recurrent neural network encoders with an attention mechanism was developed using a collection of reports from the Virginia Department of Transportation. The condition recommendation application performed a classification task and demonstrated improved performance over a variety of baseline systems. The quality control application learns a data-driven decision threshold to decide whether to accept or reject an inspector-provided rating, which provides a cyber-human collaboration route for condition assessment. Visualization of the resulting attention patterns was shown to provide interpretable insights which highlight potentially-overlooked indicators.
Highlights A data-driven approach that maps narrative inspection descriptions to condition ratings. Deep-Learning-based hierarchical attention network for heterogeneous textual data. Visualization of attention patterns showed interpretable insights of condition ratings. Two application proposed: automatic condition rating and quality control tool. Proactively increase the consistency of infrastructure condition rating.
Mapping textual descriptions to condition ratings to assist bridge inspection and condition assessment using hierarchical attention
Li, Tianshu (author) / Alipour, Mohamad (author) / Harris, Devin K. (author)
2021-06-10
Article (Journal)
Electronic Resource
English
Assessment of Risk Using Bridge Element Condition Ratings
| Online Contents | 2013
Bridge Inspection and Condition Assessment in Europe
| British Library Online Contents | 2008
Using Classification Trees for Predicting National Bridge Inventory Condition Ratings
| Online Contents | 2013