Real-time prediction and avoidance of secondary crashes under unexpected traffic congestion

被引:55
作者
Park, Hyoshin [1 ]
Haghani, Ali [2 ]
Samuel, Siby [3 ]
Knodler, Michael A. [4 ]
机构
[1] North Carolina Agr & Tech State Univ, Dept Computat Sci & Engn, Greensboro, NC 27411 USA
[2] Univ Maryland, Dept Civil & Environm Engn, College Pk, MD 20742 USA
[3] Univ Massachusetts, Dept Mech & Ind Engn, Amherst, MA 01003 USA
[4] Univ Massachusetts, Dept Civil & Environm Engn, Amherst, MA 01003 USA
关键词
Gradient boosting tree; Neural network; Variable importance; Rule extraction; Secondary incidents; INCIDENT;
D O I
10.1016/j.aap.2017.11.025
中图分类号
TB18 [人体工程学];
学科分类号
1201 ;
摘要
According to the Federal Highway Administration, nonrecurring congestion contributes to nearly half of the overall congestion. Temporal disruptions impact the effective use of the complete roadway, due to speed reduction and rubbernecking resulting from primary incidents that in turn provoke secondary incidents. There is an additional reduction of discharge flow caused by secondary incident that significantly increases total delay. Therefore, it is important to sequentially predict the probability of secondary incidents and develop appropriate countermeasures to reduce the associated risk. Advanced computing techniques were used to easily understand and reliably predict secondary incident occurrences that have low sample mean and a small sample size. The likelihood of a secondary incident was sequentially predicted from the point of incident response to the eventual road clearance. The quality of predictions improved with the availability of additional information. The prediction performance of the principled Bayesian learning approach to neural networks (arm) was compared to the Stochastic Gradient Boosted Decision Trees (GBDT). A pedagogical rule extraction approach, TREPAN, which extracts comprehensible rules from the neural networks, improved the ability to understand secondary incidents in a simplified manner. With an acceptable accuracy, GBDT is a useful tool that presents the relative importance of the predictor variables. Unexpected traffic congestion incurred by an incident is a dominant causative factor for the occurrence of secondary incidents at different stages of incident clearance. This symbolic description represents a series of decisions that may assist emergency operators by improving their decision-making capabilities. Analyzing causes and effects of traffic incidents helps traffic operators develop incident-specific strategic plans for prompt emergency response and clearance. Application of the model in connected vehicle environments will help drivers receive proactive corrective feedback before a crash. The proposed methodology can be used to alert drivers about potential highway conditions and may increase the drivers' awareness of potential events when no rerouting is possible, optimal or otherwise.
引用
收藏
页码:39 / 49
页数:11
相关论文
共 26 条
[1]  
[Anonymous], J TRANSP ENG
[2]   Understanding time series networks: A case study in rule extraction [J].
Craven, MW ;
Shavlik, JW .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 1997, 8 (04) :373-384
[3]   Nonparametric Modeling of Vehicle-Type-Specific Headway Distribution in Freeway Work Zones [J].
Dong, Shangjia ;
Wang, Haizhong ;
Hurwitz, David ;
Zhang, Guohui ;
Shi, Jianjun .
JOURNAL OF TRANSPORTATION ENGINEERING, 2015, 141 (11)
[4]   Stochastic gradient boosting [J].
Friedman, JH .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2002, 38 (04) :367-378
[5]  
Haghi AK, 2013, CHEMISTRY AND PHYSICS OF MODERN MATERIALS: PROCESSING, PRODUCTION AND APPLICATIONS, P1
[6]   Incident management integration tool: dynamically predicting incident durations, secondary incident occurrence and incident delays [J].
Khattak, A. ;
Wang, X. ;
Zhang, H. .
IET INTELLIGENT TRANSPORT SYSTEMS, 2012, 6 (02) :204-214
[7]   Development of a variable speed limit strategy to reduce secondary collision risks during inclement weathers [J].
Li, Zhibin ;
Li, Ye ;
Liu, Pan ;
Wang, Wei ;
Xu, Chengcheng .
ACCIDENT ANALYSIS AND PREVENTION, 2014, 72 :134-145
[8]  
Miaou S.-P., 1996, TRANSPORT RES REC, V1542, P6, DOI 10.3141/1542-02
[9]  
Neal RM, 2011, CH CRC HANDB MOD STA, P113
[10]   Modeling the time to the next primary and secondary incident: A semi-Markov stochastic process approach [J].
Ng, ManWo ;
Khattak, Asad ;
Talley, Wayne K. .
TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 2013, 58 :44-57