Non-parametric machine learning methods for evaluating the effects of traffic accident duration on freeways
Journal Title: Archives of Transport - Year 2017, Vol 43, Issue 3
Abstract
Traffic accidents usually cause congestion and increase travel-times. The cost of extra travel time and fuel consumption due to congestion is huge. Traffic operators and drivers expect an accurately forecasted accident duration to reduce uncertainty and to enable the implementation of appropriate strategies. This study demonstrates two non-parametric machine learning methods, namely the k-nearest neighbour method and artificial neural network method, to construct accident duration prediction models. The factors influencing the occurrence of accidents are numerous and complex. To capture this phenomenon and improve the performance of accident duration prediction, the models incorporated various data including accident characteristics, traffic data, illumination, weather conditions, and road geometry characteristics. All raw data are collected from two public agencies and were integrated and cross-checked. Before model development, a correlation analysis was performed to reduce the scale of interrelated features or variables. Based on the performance comparison results, an artificial neural network model can provide good and reasonable prediction for accident duration with mean absolute percentage error values less than 30%, which are better than the prediction results of a k-nearest neighbour model. Based on comparison results for circumstances, the Model which incorporated significant variables and employed the ANN method can provide a more accurate prediction of accident duration when the circumstances involved the day time or drunk driving than those that involved night time and did not involve drunk driving. Empirical evaluation results reveal that significant variables possess a major influence on accident duration prediction.<br/><br/>
Authors and Affiliations
Ying Lee, Chien-Hung Wei, Kai-Chon Chao
Keywords
Related Articles
- EP ID EP220395
- DOI 10.5604/01.3001.0010.4228
- Views 103
- Downloads 0
PASSENGER CARS AND HEAVY DUTY VEHICLES EXHAUST EMISSIONS UNDER REAL DRIVING CONDITIONS
In the assumptions regarding to the transport policy both at the level of country and Europe there is the concept of sustainable development of transport. Warsaw University of Technology in cooperation with Poznan Univer...
Evaluation of the effects of fires and explosions in the transport of hazardous materials
Transportation of liquid and gaseous fuels and chemicals, albeit not frequent, can lead to serious dangers for humans, the environment and property due to fires and explosions. The two most common transportation modes o...
LOGISTICS WASTE UTILIZATION SYSTEM IN THE STEEL PLANT
An important problem associated with the production of steel products is the need to ensure adequate protection of the environment. Throughout the technological foundry formed about 90 types of waste, while a significant...
Risk measures of load loss during service of refrigerated containers in seaports
The presented paper is concerned with the problems of assessing the risk level for service chain of refrigerated containers in seaports. This issue has been examined with regard to the losses related to the loss of cargo...
Object-oriented programming as a method for developing software in rail-traffic-control computer systems
The paper focuses on a new method for specifying safe software for rail traffic control systems. The presented method is particularly convenient to define typical devices and subsystems used in traffic control, defined a...