Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm

Zhan, Chengjun; Gan, Albert; Hadi, Mohammed

doi:10.1109/tits.2011.2161634

Cited by 97 publications

(49 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regard to treatment-4 situations (accidents in congested traffic conditions), accidents needed longer clearance time than was necessary for treatment-2 accidents, which occurred in non-congested traffic. The clearance time for accidents that involve one or two vehicles was 20.23 % shorter than for accidents that involve more than two vehicles, as expected [31]. This study found that the involvement of a taxi was another variable that affected traffic-accident clearance time.…”

Section: Accident Characteristicssupporting

confidence: 82%

Analysis of the Different Duration Stages of Accidents with Hazard-Based Model

Guo²,

2015

Int. J. ITS Res.

View full text Add to dashboard Cite

This study investigates and identifies significant contributing variables that affect the duration of three traffic accident stages, namely, preparation, travel, and clearance as well as the total duration of the accident. Accelerated failure time (AFT) hazard-based models were developed with different underlying probability distributions for the hazard function, including models with gamma heterogeneity and models with time-varying covariates. The results indicate that the gamma distribution model with a time variable is the best model for the four different duration stages, and different parameters and variables were appropriate for modeling the different duration stages of traffic accidents. The findings of this study provide an important demonstration of method and an empirical basis for accident management programs.

show abstract

Section: Accident Characteristicssupporting

confidence: 82%

Analysis of the Different Duration Stages of Accidents with Hazard-Based Model

Guo²,

2015

Int. J. ITS Res.

View full text Add to dashboard Cite

show abstract

“…Various data mining and machine learning approaches have been employed to estimate and predict traffic incident duration time. Some of these approaches are the following: Lee et al [14] proposed a genetic algorithm on traffic incident duration time prediction problems; Kim et al and Zhan et al [32] applied decision trees and classification tree models on the same problem and achieved improvements; Valenti et al [29] proposed a support vector machine related method that utilizes the temporal features of the traffic data; artificial neural networks [30] is another highlighted direction for traffic incident duration prediction. In recent years, the research field of Intelligent Transportation Systems (ITS) have addressed its attention towards the hybrid methods [12] to predict traffic incident durations.…”

Section: Related Workmentioning

confidence: 99%

“…However, strong assumptions on the design matrix are required [39]. Zhan et al [32] propose an M5P tree algorithm to predict the clearance time of traffic incident based on the geometric, and traffic features. Feature learning algorithms for biomarker identification [40] and social event indicators [36] are proved to be effective while finding higher level features.…”

Section: Introductionmentioning

confidence: 99%

Titan

Zhao

et al. 2019

Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

View full text Add to dashboard Cite

Critical incident stages identification and reasonable prediction of traffic incident duration are essential in traffic incident management. In this paper, we propose a traffic incident duration prediction model that simultaneously predicts the impact of the traffic incidents and identifies the critical groups of temporal features via a multi-task learning framework. First, we formulate a sparsity optimization problem that extracts low-level temporal features based on traffic speed readings and then generalizes higher level features as phases of traffic incidents. Second, we propose novel constraints on feature similarity exploiting prior knowledge about the spatial connectivity of the road network to predict the incident duration. The proposed problem is challenging to solve due to the orthogonality constraints, non-convexity objective, and non-smoothness penalties. We develop an algorithm based on the alternating direction method of multipliers (ADMM) framework to solve the proposed formulation. Extensive experiments and comparisons to other models on real-world traffic data and traffic incident records justify the efficacy of our model.

show abstract

“…According to the accidents report of the United States Census Bureau, there were 10.8 million accidents and 35,900 persons killed in 2009 (US census bureau, 2013). To address this, many studies have been conducted to predict accident frequencies and analyze the characteristics of traffic accidents, including studies on hazardous location/hot spot identification (Lin et al, 2014), accident injury-severities analysis (Milton et al, 2008), and accident duration analysis (Zhan et al, 2011). http://dx.doi.org/10.1016/j.trc.2015.03.015 0968-090X/Ó 2015 Elsevier Ltd. All rights reserved.…”

Section: Introductionmentioning

confidence: 99%