Automatic Logical Inconsistency Detection in the National Bridge Inventory

Din, Zia Ud; Tang, Pingbo

doi:10.1016/j.proeng.2016.04.093

Cited by 11 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, out of 3,127 bridges in Wyoming in 2017, there are only 168 bridges that have valid records in this variable, and among these bridges, some decks' conditions remain unchanged or even deteriorated since the previous inspection. This could be caused by entry errors [24] or they only replaced or rebuilt one part of the bridges (e.g. just superstructure or substructure) [17].…”

Section: Dimension Reduction In Nbi Datasetmentioning

confidence: 99%

Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups

Zhang

Marsh

2020

Information Sciences

View full text Add to dashboard Cite

This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

show abstract

Section: Dimension Reduction In Nbi Datasetmentioning

confidence: 99%

Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups

Zhang

Marsh

2020

Information Sciences

View full text Add to dashboard Cite

show abstract

“…Currently, around 42% of those bridges are more than half a century old, and 7.5% of them are in ''poor'' condition (1). These structures require close monitoring and an efficient treatment schedule, both of which are often guided by the NBI data (2). This data, which is a collection of more than 100 fields (explained by the Federal Highway Administration [FHWA]), contains information belonging to the following categories (3): Bridge general information and features (e.g., location, length, deck area, average daily traffic [ADT], number of spans, border bridge, etc.)…”

Section: Introductionmentioning

confidence: 99%

“…The effectiveness of these decisions naturally depends on the quality of the collected NBI data, among other things. Some studies (e.g., Din and Tang, Cook, and Dekelbab et al) have shown that errors and missing values are common in NBI data sets, raising the need for data improvement efforts ( 2 , 5 , 6 ). Moreover, higher quality NBI data is believed to reduce the number of unexpected structural failures in bridges (which, as of 2014, are estimated to occur between 87 to 222 times annually in the U.S.) ( 2 , 5 ).…”

Section: Introductionmentioning

confidence: 99%

“…Some studies (e.g., Din and Tang, Cook, and Dekelbab et al) have shown that errors and missing values are common in NBI data sets, raising the need for data improvement efforts ( 2 , 5 , 6 ). Moreover, higher quality NBI data is believed to reduce the number of unexpected structural failures in bridges (which, as of 2014, are estimated to occur between 87 to 222 times annually in the U.S.) ( 2 , 5 ). This, in turn, decreases the amount of casualties and adverse economic consequences caused by these catastrophic events.…”

Section: Introductionmentioning

confidence: 99%

“…Some state Departments of Transportation (DOTs) added other complementary checks to the FHWA’s error check logics, especially for their own state-developed data fields (e.g., VDOT and Florida Department of Transportation [FDOT]) ( 8 , 9 ). Din and Tang also adapted a statistical method for detecting errors in NBI data based on logical rules ( 2 ). These error checks verify the NBI data against invalid values, nulls, or logical rules that should hold among several interdependent fields.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detecting Anomalies in National Bridge Inventory Databases Using Machine Learning Methods

Fereshtehnejad¹,

Gazzola²,

Parekh³

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

National Bridge Inventory (NBI) data is regularly collected for 617,000+ national bridges in the U.S. These data, which consist of 100+ fields related to bridges and culverts, have been shown to contain errors. These errors could reduce the effectiveness of the decisions made based on this data, and cause safety issues. For this reason, an anomaly detection platform is developed to identify data anomalies in NBI datasets more effectively than existing rule-based error-check tools can. First, the user provides groups of correlated NBI fields as input to the platform. Then, for each group, it utilizes two tools to detect anomalous data and determine errors. The first tool uses three machine learning algorithms to identify anomalous data points and categorizes them based on their degree of anomaly. The second tool visualizes the distributions of the NBI fields in the group with histograms, scatter plots, and so forth. These plots are used to analyze the data points that are identified from the first tool as anomalies. The results of these two tools, together with expert knowledge about the data fields, are then used to distinguish data errors from outliers. The proposed platform is applied to a state’s NBI dataset that was submitted to the Federal Highway Administration (FHWA) in 2020. For this dataset, two groups of correlated fields are considered. The results showed the platform could effectively pinpoint anomalous values of NBI fields that individually, or in conjunction with other fields, do not follow the patterns that characterize most of the data, prompting the identification of potential inconsistencies and errors.

show abstract

Mapping textual descriptions to condition ratings to assist bridge inspection and condition assessment using hierarchical attention

Alipour

Harris

2021

Automation in Construction

View full text Add to dashboard Cite

Automatic Logical Inconsistency Detection in the National Bridge Inventory

Cited by 11 publications

References 11 publications

Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups

Multi-state deterioration prediction for infrastructure asset: Learning from uncertain data, knowledge and similar groups

Detecting Anomalies in National Bridge Inventory Databases Using Machine Learning Methods

Mapping textual descriptions to condition ratings to assist bridge inspection and condition assessment using hierarchical attention

Contact Info

Product

Resources

About