Robust PCA-based abnormal traffic flow pattern isolation and loop detector fault detection

Abstract One key function of intelligent transportation systems is to automatically detect abnormal traffic phenomena and to help further investigations of the cause of the abnormality. This paper describes a robust principal components analysis (RPCA)-based abnormal traffic flow pattern isolation and loop detector fault detection method. The results show that RPCA is a useful tool to distinguish regular traffic flow from abnormal traffic flow patterns caused by accidents and loop detector faults. This approach gives an effective traffic flow data pre-processing method to reduce the human effort in finding potential loop detector faults. The method can also be used to further investigate the causes of the abnormality.

[1]  M. Shyu,et al.  A Novel Anomaly Detection Scheme Based on Principal Component Classifier , 2003 .

[2]  Billy M. Williams,et al.  Comparison of parametric and nonparametric models for traffic flow forecasting , 2002 .

[3]  Yi Zhang,et al.  Traffic Data Analysis Using Kernel PCA and Self-Organizing Map , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[4]  Sanne Engelen,et al.  A comparison of three procedures for robust PCA in high dimensions , 2016 .

[5]  I. Jolliffe.  Principal Component Analysis , 2002 .

[6]  Nancy L. Nihan,et al.  Aid to determining freeway metering rates and detecting loop errors , 1997 .

[7]  P. Rousseeuw,et al.  A fast algorithm for the minimum covariance determinant estimator , 1999 .

[8]  Mia Hubert,et al.  ROBPCA: A New Approach to Robust Principal Component Analysis , 2005, Technometrics.

[9]  Gene H. Golub,et al.  Matrix computations , 1983 .

[10]  Yi Zhang,et al.  Spatial-temporal traffic data analysis based on global data management using MAS , 2004, IEEE Trans. Intell. Transp. Syst..

[11]  Rod E. Turochy.  Enhancing Short-Term Traffic Forecasting with Traffic Condition Information , 2006 .

[12]  Yi Zhang,et al.  Simultaneously Prediction of Network Traffic Flow Based on PCA-SVR , 2007, ISNN.

[13]  Yu-Long Xie,et al.  Robust principal component analysis by projection pursuit , 1993 .

[14]  Alexander Skabardonis,et al.  Detecting Errors and Imputing Missing Data for Single-Loop Surveillance Systems , 2003 .

[15]  Christophe Croux,et al.  High breakdown estimators for principal components: the projection-pursuit approach revisited , 2005 .

[16]  B. L. Smith,et al.  Applying quality control to traffic condition monitoring , 2000, ITSC2000. 2000 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.00TH8493).

[17]  Bell Telephone,et al.  ROBUST ESTIMATES, RESIDUALS, AND OUTLIER DETECTION WITH MULTIRESPONSE DATA , 1972 .