A Simulation Study of Predicting Real-Time Conflict-Prone Traffic Conditions

Abstract

Current approaches to estimate the probability of a traffic collision occurring in real-time primarily depend on comparing traffic conditions just prior to collisions with normal traffic conditions. Most studies acquire pre-collision traffic conditions by matching the collision time in the national crash database with the time in the traffic database. Since the reported collision time sometimes differs from the actual time, the matching method may result in traffic conditions not representative of pre-collision traffic dynamics. In this paper, this is overcome through the use of highly disaggregated vehicle-based traffic data from a traffic micro-simulation (i.e., VISSIM) and the corresponding traffic conflicts data generated by the surrogate safety assessment model (SSAM). In particular, the idea is to use traffic conflicts as surrogate measures of traffic safety so that traffic collisions data are not needed. Three classifiers (i.e., support vector machines, k-nearest neighbours, and random forests) are then employed to examine the proposed idea. Substantial efforts are devoted to making the traffic simulation as representative of the real-world as possible by employing data from a motorway section in England. Four temporally aggregated traffic datasets (i.e., 30 s, 1 min, 3 min, and 5 min) are examined. The main results demonstrate the viability of using traffic micro-simulation along with the SSAM for real-time conflicts prediction and the superiority of random forests with 5-min temporal aggregation in the classification results. However, attention should be given to the calibration and validation of the simulation software so as to acquire more realistic traffic data, resulting in more effective prediction of conflicts.

Real-time crash prediction models: State-of-the-art, design pathways and ubiquitous requirements

“…Lee et al, 2003a,b,c;, 2006cAbdel-Aty and Abdalla, 2004;Oh et al, 2005a,b;Dias et al, 2009;Muromachi, 2012, 2013b;Xu et al. 2013a,b,c;Yu and Abdel-Aty, 2013a,b;Sun and Sun, 2016;Katrakazas et al, 2016Katrakazas et al, , 2017Yang et al, 2018a,b;Roy et al, 2018b), identifying their types (Golob et al, 2004;Pande and Abdel-Aty, 2006a,b;Christoforou et al, 2011), understanding crash mechanism (Lee et al, 2003a,b,c;Luo and Garber, 2006, Hossain and Muromachi, 2011Xu et al, 2012;Yeo et al, 2013), evaluating countermeasures through variable speed limits (Abdel-Aty et al, 2006a,b, 2008aAbdel-Aty, 2008, Lee et al, 2004), ramp metering (Abdel-Aty and Gayah, 2010; Lee et al, 2006b), and variable message signs (Al-Ghamdi, 2007;Lee and Abdel-Aty, 2008). The recent trend has been focused on addressing the issues of transferability (Shew et al, 2013;Roy et al, 2018a), building them for specific road sections (e.g., weaving areas as shown by Wang et al, 2015), optimizing real-time safety and congestion in tandem (Park and Haghani, 2015), considering severity (Xu et al, 2013a) or simply, using more sophisticated modeling methods to improve accuracy (Xu et al, 2013b;Park and Haghani, 2015;Xu et al, 2016aXu et al, , 2016b.…”

“…Studies dated later 2017 started considering the traffic flow variables related to ramp areas along with the basic freeway segment (5:63,65-68). Some studies included density, queue length, exposure to traffic(Lee et al, 2003a), hazard ratio for average volume (Abdel-Aty and, complex calculation of shockwaves(Yu and Abdel-Aty, 2005), safe stopping distance of individual vehicles(Son et al, 2008), average flow ratio calculated from the peak flow(Pande and Abdel-Aty, 2006b), congestion index(Dias et al, 2009; Muromachi, 2012, 2013a; Shi and Abdel-Aty 2015;, percentage of heavy vehicles(Pham et al, 2010;Wang et al, 2017b;Park et al, 2018), geometric mean of average flow ratios(Qu et al, 2012b), average journey time(Katrakazas et al, 2017) first order autocorrelation of count, speed and occupancy(Xu et al, 2014b), weaving volume ratio, speed difference between the beginning and end of weaving segment(Wang et al, 2015) as variables. Use of coarser data such as peak hour traffic data(Abdel-Aty et al, 2006c;Christoforou et al, 2011), 75th percentile of average, standard deviation and coefficient of variation of speed, 75th percentile of standard deviation and coefficient of variation of volume(Abdel-Aty et al, 2006c), or day of week(Xu et al, 2016b), mainly seen in conventional CPMs, were also practiced.RTCPMs built with microscopic traffic flow data also introduced traffic pressure, kinetic energy, coefficient of variation of time headway, mean velocity gradient and mean reaction time as variables(Hourdakis et al, 2006;Paikari et al, 2014).…”

“…examined the theory and application of a recently developed machine learning technique namely RelevanceVector Machines (RVMs) in the task of traffic conditions classification and found that RVMs could successfully be employed in real-time classification of traffic conditions. They rely on a fewer number of decision vectors, their training time could be reduced to the level of seconds and their classification rates are similar to those of SVMs Katrakazas et al (2017). also used two classifiers namely Support Vector Machines (SVMs) -a sophisticated classifier and k-Nearest Neighbors (k-NN) -a relatively simple classifier.…”

Crash Prediction on Expressway Incorporating Traffic Flow Continuity Parameters Based on Machine Learning Approach

“…rough predicting the time and location of possible crash occurrences in real time, proactive traffic management strategies can be applied to prevent crashes in time and improve traffic safety. Moreover, with the rapid development of autonomous vehicle techniques, it is important to accurately identify unsafe traffic condition to ensure the fast reaction of these new techniques and improve the proactive safety control of traffic systems [3].…”

Method of Predicting Passenger Flow in Scenic Areas Considering Multisource Traffic Data

“…The method for gathering and evaluating the passenger flow in urban tourist attractions should go hand in hand with the changes in passenger flow inside the scenic area. (2)(3)(4)(5) Therefore, in this paper, we consider fusing the prediction of multisource traffic passenger flows around scenic areas and passenger flows in the core area. Buses, subways, taxis, and shared bicycles are the main research objects of scholars of passenger flows because these are the most important modes of transportation in cities.…”