Big Data Analytics and Visualization with Spatio-Temporal Correlations for Traffic Accidents

Big data analytics for traffic accidents is a hot topic and has significant values for a smart and safe traffic in the city. Based on the massive traffic accident data from October 2014 to March 2015 in Xiamen, China, we propose a novel accident occurrences analytics method in both spatial and temporal dimensions to predict when and where an accident with a specific crash type will occur consequentially by whom. Firstly, we analyze and visualize accident occurrences in both temporal and spatial view. Second, we illustrate spatio-temporal visualization results through two case studies in multiple road segments, and the impact of weather on crash types. These findings of accident occurrences analysis and visualization would not only help traffic police department implement instant personnel assignments among simultaneous accidents, but also inform individual drivers about accident-prone sections and the time span which requires their most attention.

[1]  Srinivas Reddy Geedipally,et al.  Investigating the effect of modeling single-vehicle and multi-vehicle crashes separately on confidence intervals of Poisson-gamma models. , 2010, Accident; analysis and prevention.

[2]  Xun Zhang,et al.  Analyzing fault and severity in pedestrian-motor vehicle accidents in China. , 2014, Accident; analysis and prevention.

[3]  Harald Piringer,et al.  AlVis: Situation awareness in the surveillance of road tunnels , 2012, 2012 IEEE Conference on Visual Analytics Science and Technology (VAST).

[4]  Ezra Hauer,et al.  Speed and Safety , 2009 .

[5]  John N. Ivan,et al.  Differences in the Performance of Safety Performance Functions Estimated for Total Crash Count and for Crash Count by Crash Type , 2009 .

[6]  Xindong Wu,et al.  Data mining with big data , 2014, IEEE Transactions on Knowledge and Data Engineering.

[7]  Darya Filippova,et al.  ICE--visual analytics for transportation incident datasets , 2009, 2009 IEEE International Conference on Information Reuse & Integration.

[8]  Jignesh M. Patel,et al.  Big data and its technical challenges , 2014, CACM.

[9]  Xiaoru Yuan,et al.  Urban trajectory timeline visualization , 2014, 2014 International Conference on Big Data and Smart Computing (BIGCOMP).

[10]  Nalini Ravishanker,et al.  Bayesian estimation of hourly exposure functions by crash type and time of day. , 2006, Accident; analysis and prevention.

[11]  Margaret M. Peden,et al.  World Report on Road Traffic Injury Prevention , 2004 .

[12]  Guangnan Zhang,et al.  Risk factors associated with traffic violations and accident severity in China. , 2013, Accident; analysis and prevention.

[13]  Paul Damien,et al.  A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods. , 2008, Accident; analysis and prevention.

[14]  Adel W. Sadek,et al.  A Novel Variable Selection Method based on Frequent Pattern Tree for Real-time Traffic Accident Risk Prediction , 2015, ArXiv.

[15]  Xiaoru Yuan,et al.  Visual Traffic Jam Analysis Based on Trajectory Data , 2013, IEEE Transactions on Visualization and Computer Graphics.

[16]  Xuesong Wang,et al.  Utilizing Microscopic Traffic and Weather Data to Analyze Real-Time Crash Patterns in the Context of Active Traffic Management , 2014, IEEE Transactions on Intelligent Transportation Systems.

[17]  Mohamed Abdel-Aty,et al.  Utilizing support vector machine in real-time crash risk evaluation. , 2013, Accident; analysis and prevention.

[18]  Hyoshin Park,et al.  Real-time prediction of secondary incident occurrences using vehicle probe data , 2016 .

[19]  Hwasoo Yeo,et al.  Development of a Deceleration-Based Surrogate Safety Measure for Rear-End Collision Risk , 2015, IEEE Transactions on Intelligent Transportation Systems.