Improving the conversion accuracy between bridge element conditions and NBI ratings using deep convolutional neural networks

Fiorillo, Graziano; Nassif, Hani

doi:10.1080/15732479.2020.1725065

Cited by 13 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training data set is limited (Fiorillo and Nassif, 2020) This study presents a procedure that allows bridge engineers to estimate health index deterioration rates for bridge elements…”

Section: Results Show That the Proposed Id Cnn Was The Most Efficient...mentioning

confidence: 99%

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Elghaish

Matarneh

Talebi

et al. 2021

View full text Add to dashboard Cite

Purpose The massive number of pavements and buildings coupled with the limited inspection resources, both monetary and human, to detect distresses and recommend maintenance actions lead to rapid deterioration, decreased service life, lower level of service and increased community disruption. Therefore, this paper aims at providing a state-of-the-art review of the literature with respect to deep learning techniques for detecting distress in both pavements and buildings; research advancements per asset/structure type; and future recommendations in deep learning applications for distress detection. Design/methodology/approach A critical analysis was conducted on 181 papers of deep learning-based cracks detection. A structured analysis was adopted so that major articles were analyzed according to their focus of study, used methods, findings and limitations. Findings The utilization of deep learning to detect pavement cracks is advanced compared to assess and evaluate the structural health of buildings. There is a need for studies that compare different convolutional neural network models to foster the development of an integrated solution that considers the data collection method. Further research is required to examine the setup, implementation and running costs, frequency of capturing data and deep learning tool. In conclusion, the future of applying deep learning algorithms in lieu of manual inspection for detecting distresses has shown promising results. Practical implications The availability of previous research and the required improvements in the proposed computational tools and models (e.g. artificial intelligence, deep learning, etc.) are triggering researchers and practitioners to enhance the distresses’ inspection process and make better use of their limited resources. Originality/value A critical and structured analysis of deep learning-based crack detection for pavement and buildings is conducted for the first time to enable novice researchers to highlight the knowledge gap in each article, as well as building a knowledge base from the findings of other research to support developing future workable solutions.

show abstract

“…Training data set is limited (Fiorillo and Nassif, 2020) This study presents a procedure that allows bridge engineers to estimate health index deterioration rates for bridge elements…”

Section: Results Show That the Proposed Id Cnn Was The Most Efficient...mentioning

confidence: 99%

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Elghaish

Matarneh

Talebi

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[15] In order to identify personalized recommendations for users on the basis of their preferences and behavior, the Rating Filtering method, Movie Categories Based Filtering-Singular Value Decomposition (MCBF-SVD) algorithm was used and it was established that MCBF-SVD is highly effective in reducing errors of rating prediction models. [16] The prediction accuracy of deep convolutional neural networks was found to be more than 90% accurate, [17] in ref. [18] generative convolutional network was used and it was identified that the model having components: artificial feature generator, artificial label generator, and traditional DCNN model for prediction of movie ratings outperformed other baseline models.…”

Section: Review Of Literaturementioning

confidence: 99%

Modeling Consumer Price Index: A Machine Learning Approach

Sarangi

Sahoo

Sinha

2022

Macromolecular Symposia

View full text Add to dashboard Cite

The change in price of a group of goods and services is reflected in terms of consumer price index (CPI), making it one of the most important economic indicators. This is also the mostly used measure of inflation. Forecasted CPI values help the Government to take corrective measures to control the economic conditions of the country. This paper implements and examines two machine learning models such as artificial neural network (ANN) and ANN model optimized with particle swarm optimization (PSO) known as ANN-PSO to assess the accuracy in predictability of CPI. The data set for four groups such as food and beverages, housing, clothing, and footwear used for the calculation of all India CPI has been taken from the official website of the Government of India. The mean absolute percentage error (MAPE) has been used as the validator for model accuracy. The MAPE calculated for all experiments are less than 10% which indicates that the ANN-PSO models used are highly accurate for prediction of CPI of India.

show abstract

“…The successful assessment of structural conditions depends on the appropriate selection of the main features and the detailed description of its effects. Based on the selection suggestion of previous studies 21,45 and the bridge inspection reports in China, the features are determined based on the comprehensive consideration of the bridge structure, deterioration condition, maintenance history, and so forth. This study extracted the maintenance actions from the bridge inspection reports, which could assist in modeling the deterioration features and maintenance behaviors.…”

Section: Regional Bridge Assessment Frameworkmentioning

confidence: 99%

A data‐driven approach for regional bridge condition assessment using inspection reports

Xia

Lei

Wang

et al. 2021

Structural Contr & Hlth

View full text Add to dashboard Cite

Summary Bridges play an important role in the highway transportation network. There is an increasing concern that highway bridges have been suffering from structural degradation and deficiency due to severe environment, overloading, initial structural defects, and other factors. Ensuring the safety of a large number of regional bridges at the network level becomes a major challenge. This study proposes an entire data‐driven condition assessment framework for network‐level bridges, including data integration, condition assessment, and maintenance management. The periodic bridge inspection reports in China could provide quite a few condition‐related information to reveal the time‐variant bridge condition deterioration and effect of maintenance behaviors. The proposed framework is applied to a real highway bridge network located in Hebei province, China. Inspection data are obtained from thousands of bridges over quite a few years. The established regional deterioration model could effectively predict the bridge future condition based on the extracted hidden features. The regional maintenance strategies are optimized to satisfy the economic and performance constraints, which allows bridge managers to select the most appropriate one for implementation. It is shown that the proposed data‐driven approach can provide a guideline to bridge managers to estimate the future condition and allocate the maintenance resources.

show abstract

Improving the conversion accuracy between bridge element conditions and NBI ratings using deep convolutional neural networks

Cited by 13 publications

References 26 publications

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Modeling Consumer Price Index: A Machine Learning Approach

A data‐driven approach for regional bridge condition assessment using inspection reports

Contact Info

Product

Resources

About