Application of nonparametric regression in predicting traffic incident duration
Open Access
- 26 January 2015
- journal article
- research article
- Published by Vilnius Gediminas Technical University in Transport
- Vol. 33 (1) , 22-31
Abstract
Predicting the duration time of incidents is important for effective real-time Traffic Incident Management (TIM). In the current study, the k-Nearest Neighbor (kNN) algorithm is employed as a nonparametric regression approach to develop a traffic incident duration prediction model. Incident data from 2008 on the third ring expressway mainline in Beijing are collected from the local Incident Reporting and Dispatching System. The incident sites are randomly distributed along the mainline, which is 48.3 km long and has six two-way lanes with a single-lane daily volume of more than 10000 veh. The main incident type used is sideswipe and the average incident duration time is 32.69 min. The most recent one-fourth of the incident records are selected as testing set. Vivatrat method is employed to filter anomalous data for the training set. Incident duration time is set as the dependent variable in Kruskal–Wallis test, and six attributes are identified as the main factors that affect the length of duration time, which are ‘day first shift’, ‘weekday’, ‘incident type’, ‘congestion’, ‘incident grade’ and ‘distance’. Based on the characteristics of duration time distribution, log transformation of original data is tested and proven to improve model performance. Different distance metrics and prediction algorithms are carefully investigated. Results demonstrate that the kNN model has better prediction accuracy using weighted distance metric based on decision tree and weighted prediction algorithm. The developed prediction model is further compared with other models based on the same dataset. Results show that the developed model can obtain reasonable prediction results, except for samples with extremely short or long duration. Such a prediction model can help TIM teams estimate the incident duration and implement real-time incident management strategies.Keywords
This publication has 24 references indexed in Scilit:
- Estimating freeway incident duration using accelerated failure time modelingSafety Science, 2013
- Incident management integration tool: dynamically predicting incident durations, secondary incident occurrence and incident delaysIET Intelligent Transport Systems, 2012
- Development of an accident duration prediction model on the Korean Freeway SystemsAccident Analysis & Prevention, 2010
- An Information-Based Time Sequential Approach to Online Incident Duration PredictionJournal of Intelligent Transportation Systems, 2008
- Sequential forecast of incident duration using Artificial Neural Network modelsAccident Analysis & Prevention, 2007
- A decision tree-based attribute weighting filter for naive BayesKnowledge-Based Systems, 2006
- Comparison of two non‐parametric models for daily traffic forecasting in Hong KongJournal of Forecasting, 2006
- Components of Congestion: Delay from Incidents, Special Events, Lane Closures, Weather, Potential Ramp Metering Gain, and Excess DemandTransportation Research Record: Journal of the Transportation Research Board, 2006
- Feature selection for the naive bayesian classifier using decision treesApplied Artificial Intelligence, 2003
- Estimating Magnitude and Duration of Incident DelaysJournal of Transportation Engineering, 1997