A Freeway Crash Involvement Analysis Model based on Real-Time and Historical Traffic BigData

Vehicle accidents, including automobile accidents and traffic fatalities threat social and public health. With rapid development of road traffic status monitoring and measuring technologies, it is possible to observe accident patterns for preventing them recently. However as the traffic data collected by human beings have reached an incredible level, it become a big challenge to analysis such a huge amount of data. Inspired by many previous findings, we proposed a section traffic state based crash involvement rate analysis model which considering both real-time and historical traffic data. Our experimental result show that our approach 1) is possible for analyzing traffic data in real-time, 2) is sufficient for distributed computing environment, 3) works efficiently for huge number of traffic events.

[1]  Moshe Livneh,et al.  Relationships between road accidents and hourly traffic flow—I: Analyses and interpretation , 1982 .

[2]  Bob Green,et al.  Use of Event-Based Traffic Data in Generating Time–Space Diagrams for Evaluation of Signal Coordination , 2014 .

[3]  Mohamed Abdel-Aty,et al.  Predicting Freeway Crashes from Loop Detector Data by Matched Case-Control Logistic Regression , 2004 .

[4]  Yadira Espinal.  Viktor Mayer-Schonberger and Kenneth Cukier, Big Data: A Revolution That Will Transform How We Live, Work and Think , 2013 .

[5]  Biswajit Basu,et al.  Real-Time Traffic Flow Forecasting Using Spectral Analysis , 2012, IEEE Transactions on Intelligent Transportation Systems.

[6]  Wilfred W Recker,et al.  Freeway safety as a function of traffic flow. , 2002, Accident; analysis and prevention.

[7]  Alexander Skabardonis,et al.  Impact of Traffic States on Freeway Collision Frequency , 2010 .

[8]  Alexander Skabardonis,et al.  Freeway Performance Measurement System: Operational Analysis Tool , 2002 .

[9]  Chung-Cheng Lu,et al.  Short-Term Highway Traffic State Prediction Using Structural State Space Models , 2014, J. Intell. Transp. Syst..

[10]  Jiancheng Weng,et al.  Freeway Travel Speed Calculation Model Based on ETC Transaction Data , 2014, Comput. Intell. Neurosci..

[11]  Francesc Soriguera,et al.  Freeway Travel-Time Information: Design and Real-Time Performance Using Spot-Speed Methods , 2013, IEEE Transactions on Intelligent Transportation Systems.

[12]  Eric Gossett,et al.  Big Data: A Revolution That Will Transform How We Live, Work, and Think , 2015 .

[13]  Wei Shen,et al.  Real-time road traffic forecasting using regime-switching space-time models and adaptive LASSO , 2012 .

[14]  E. Dahlen,et al.  The Big Five factors, sensation seeking, and driving anger in the prediction of unsafe driving☆ , 2006 .

[15]  M. Livneh,et al.  Relationships between road accidents and hourly traffic flow -- i. analyses and interpretation , 1983 .

[16]  A D May,et al.  ACCIDENT PREDICTION MODEL DEVELOPMENT FOR UNSIGNALIZED INTERSECTIONS: FINAL REPORT , 1988 .

[17]  Fred L. Mannering,et al.  The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives , 2010 .

[18]  Jason J. Jung,et al.  Intelligent Advisory Speed Limit Dedication in Highway Using VANET , 2014, TheScientificWorldJournal.

[19]  J. W. C. van Lint,et al.  Online Learning Solutions for Freeway Travel Time Prediction , 2008, IEEE Transactions on Intelligent Transportation Systems.

[20]  Reza Noroozi,et al.  Real-Time Prediction of Near-Future Traffic States on Freeways Using a Markov Model , 2014 .