Modeling bridge deck deterioration by using decision tree algorithms

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Existing bridge management systems have adopted Markov chain models to predict the condition of different bridge components for network-level analysis. These models assume that the future condition depends only on the present condition and not on the past condition (i.e., state independence). Moreover, these models do not explicitly account for the effect of governing deterioration parameters, such as average daily traffic, percentage of trucks, and environmental impacts, on the predicted condition. Machine learning approaches have been proposed by many researchers as successful tools for modeling infrastructure deterioration. A work in progress evaluates the prediction accuracy of decision tree algorithms - one of the most common techniques of machine learning - against the prediction accuracy of Markov chain models. Field data of concrete bridge decks were obtained from the Ministère des Transports du Québec, Canada, database to develop and evaluate the performance of decision tree algorithms in modeling bridge deck deterioration. Evaluation results have indicated a slight increase in the performance of decision trees over existing Markov chain models when the past condition is considered or governing deterioration parameters are incorporated.

Original languageEnglish (US)
Title of host publicationTransportation Research Board - 6th International Bridge Engineering Conference
Subtitle of host publicationReliability, Security, and Sustainability in Bridge Engineering
Pages509-516
Number of pages8
StatePublished - Dec 1 2005
EventTransportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering - Boston, MA, United States
Duration: Jul 17 2005Jul 20 2005

Publication series

NameTransportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering

Conference

ConferenceTransportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering
CountryUnited States
CityBoston, MA
Period7/17/057/20/05

Fingerprint

Bridge decks
Decision trees
Deterioration
Markov processes
Learning systems
Bridge components
Concrete bridges
Trucks
Environmental impact

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Morcous, G. (2005). Modeling bridge deck deterioration by using decision tree algorithms. In Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering (pp. 509-516). (Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering).

Modeling bridge deck deterioration by using decision tree algorithms. / Morcous, George.

Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering. 2005. p. 509-516 (Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Morcous, G 2005, Modeling bridge deck deterioration by using decision tree algorithms. in Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering. Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering, pp. 509-516, Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering, Boston, MA, United States, 7/17/05.
Morcous G. Modeling bridge deck deterioration by using decision tree algorithms. In Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering. 2005. p. 509-516. (Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering).
Morcous, George. / Modeling bridge deck deterioration by using decision tree algorithms. Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering. 2005. pp. 509-516 (Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering).
@inproceedings{905e3fa9e7714b2bad74a7f5caa40219,
title = "Modeling bridge deck deterioration by using decision tree algorithms",
abstract = "Existing bridge management systems have adopted Markov chain models to predict the condition of different bridge components for network-level analysis. These models assume that the future condition depends only on the present condition and not on the past condition (i.e., state independence). Moreover, these models do not explicitly account for the effect of governing deterioration parameters, such as average daily traffic, percentage of trucks, and environmental impacts, on the predicted condition. Machine learning approaches have been proposed by many researchers as successful tools for modeling infrastructure deterioration. A work in progress evaluates the prediction accuracy of decision tree algorithms - one of the most common techniques of machine learning - against the prediction accuracy of Markov chain models. Field data of concrete bridge decks were obtained from the Minist{\`e}re des Transports du Qu{\'e}bec, Canada, database to develop and evaluate the performance of decision tree algorithms in modeling bridge deck deterioration. Evaluation results have indicated a slight increase in the performance of decision trees over existing Markov chain models when the past condition is considered or governing deterioration parameters are incorporated.",
author = "George Morcous",
year = "2005",
month = "12",
day = "1",
language = "English (US)",
isbn = "0309093813",
series = "Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering",
pages = "509--516",
booktitle = "Transportation Research Board - 6th International Bridge Engineering Conference",

}

TY - GEN

T1 - Modeling bridge deck deterioration by using decision tree algorithms

AU - Morcous, George

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Existing bridge management systems have adopted Markov chain models to predict the condition of different bridge components for network-level analysis. These models assume that the future condition depends only on the present condition and not on the past condition (i.e., state independence). Moreover, these models do not explicitly account for the effect of governing deterioration parameters, such as average daily traffic, percentage of trucks, and environmental impacts, on the predicted condition. Machine learning approaches have been proposed by many researchers as successful tools for modeling infrastructure deterioration. A work in progress evaluates the prediction accuracy of decision tree algorithms - one of the most common techniques of machine learning - against the prediction accuracy of Markov chain models. Field data of concrete bridge decks were obtained from the Ministère des Transports du Québec, Canada, database to develop and evaluate the performance of decision tree algorithms in modeling bridge deck deterioration. Evaluation results have indicated a slight increase in the performance of decision trees over existing Markov chain models when the past condition is considered or governing deterioration parameters are incorporated.

AB - Existing bridge management systems have adopted Markov chain models to predict the condition of different bridge components for network-level analysis. These models assume that the future condition depends only on the present condition and not on the past condition (i.e., state independence). Moreover, these models do not explicitly account for the effect of governing deterioration parameters, such as average daily traffic, percentage of trucks, and environmental impacts, on the predicted condition. Machine learning approaches have been proposed by many researchers as successful tools for modeling infrastructure deterioration. A work in progress evaluates the prediction accuracy of decision tree algorithms - one of the most common techniques of machine learning - against the prediction accuracy of Markov chain models. Field data of concrete bridge decks were obtained from the Ministère des Transports du Québec, Canada, database to develop and evaluate the performance of decision tree algorithms in modeling bridge deck deterioration. Evaluation results have indicated a slight increase in the performance of decision trees over existing Markov chain models when the past condition is considered or governing deterioration parameters are incorporated.

UR - http://www.scopus.com/inward/record.url?scp=33644992846&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644992846&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0309093813

SN - 9780309093811

T3 - Transportation Research Board - 6th International Bridge Engineering Conference: Reliability, Security, and Sustainability in Bridge Engineering

SP - 509

EP - 516

BT - Transportation Research Board - 6th International Bridge Engineering Conference

ER -