Proximity-Based Outlier Detection Method for Roadway Infrastructure Condition Data

AbstractThe quality of roadway condition data is critical for the accuracy of infrastructure management decision support systems and, ultimately, for the confidence in these systems. This paper presents a novel outlier detection method for roadway infrastructure condition data. By taking the spatial and temporal attributes of condition data into account, this method is able to detect outliers and differentiate them into gross and pseudo outliers. The method consists of two major steps. In the first step, homogenous clusters of neighboring roadway sections are identified so that sections within each cluster have the most homogeneous condition-versus-time deterioration patterns. In the second step, outliers within each cluster are detected and delineated into gross outliers (i.e., likely errors) and pseudo outliers (i.e., roadway sections affected by isolated local factors, causing their condition data to be dissimilar to their neighboring sections). The developed method was applied to roadway pavement in T...

[1]  Daniel A. Ashlock,et al.  Evolutionary computation for modeling and optimization , 2005 .

[2]  Giovanni C. Migliaccio,et al.  Continuous Quality Improvement Techniques for Data Collection in Asset Management Systems , 2014 .

[3]  Dennis A Morian,et al.  Quality management of pavement performance data , 2002 .

[4]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[5]  Samuel H Carpenter,et al.  NEW TECHNIQUES FOR MODELING PAVEMENT DETERIORATION , 1987 .

[6]  Gonzalo R. Rada,et al.  Update of Long-Term Pavement Performance Manual Distress Data Variability: Bias and Precision , 1998 .

[7]  Neeraj Buch,et al.  Statistical analysis of in-service pavement performance data for LTPP SPS-1 and SPS-2 experiments , 2007 .

[8]  Moshe Livneh.  REPEATABILITY AND REPRODUCIBILITY OF MANUAL PAVEMENT DISTRESS SURVEY METHODS , 1994 .

[9]  Kevin K McGhee,et al.  Quality Management of Pavement Condition Data Collection , 2009 .

[10]  Laurence R. Rilett,et al.  Transportation Statistics and Microsimulation , 2016 .

[11]  Mostafa Analoui,et al.  Genetic algorithm and expectation maximization for parameter estimation of mixture Gaussian model phantom , 2002, SPIE Medical Imaging.

[12]  Martti Juhola,et al.  Informal identification of outliers in medical data , 2000 .

[13]  James H. Garrett,et al.  Automated Procedure to Assess Civil Infrastructure Data Quality: Method and Validation , 2005 .

[14]  David R Luhr,et al.  Structured Approach to Managing Quality of Pavement Distress Data: Virginia Department of Transportation Experience , 2000 .

[15]  Sue McNeil,et al.  EVALUATION OF ERRORS IN AUTOMATED PAVEMENT-DISTRESS DATA ACQUISITION , 1991 .

[16]  Dennis A Morian,et al.  Effects of Comprehensive Quality Assurance/Quality Control Plan on Pavement Management , 2007 .

[17]  Nasir G. Gharaibeh,et al.  A Spatial‐Bayesian Technique for Imputing Pavement Network Repair Data , 2012, Comput. Aided Civ. Infrastructure Eng..

[18]  Douglas M. Hawkins.  Identification of Outliers , 1980, Monographs on Applied Probability and Statistics.

[19]  Ying-Haur Lee,et al.  Development of Pavement Prediction Models , 1993 .

[20]  Giovanni C. Migliaccio,et al.  Assessment of Data Quality for Evaluations of Manual Pavement Distress , 2010 .

[21]  Mohamed Y Shahin,et al.  PAVEMENT CONDITION DATA ANALYSIS AND MODELING , 1986 .

[22]  Kumares C. Sinha,et al.  Methodology to Evaluate Quality of Pavement Surface Distress Data Collected by Automated Techniques , 2009 .