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 115
- Downloads 0
Selection of the most adequate trip-modelling tool for integrated transport planning system
This paper deals with the problem of selection the most suitable trip-modelling tool (TMT), which is a part of the more complex integrated transport planning system (ITPS) at the regional scale. Since an application of T...
Improving the quality of voltage in the system of traction power supply of direct current
Purpose of the work is improved approaches to ensure the required quality parameters of voltage in the traction network based on modern technologies and equipment in the application of power distribution system. Actualit...
The system of IT support for logistics in the rail transport
The paper presents the requirements, architecture and important features of a modern IT system of logistics for rail transport. The purpose of the system is to provide logistic support of transport issues relating to the...
Analysis of travel behaviour in Petaling Jaya, Malaysia: an application of the theory of planned behaviour
In order to understand travellers’ willingness to use the train in Petaling Jaya, this study adds four predictors - situational factors, trust, novelty seeking and external influence - to the existing model of theory of...
Research of Sorting Process of Unit Loads by Rotary Active Fence
The paper presents results of research of a sorting process applied to a stream of unit loads (cubiform objects, parcels) transported on conveyors. The sorting process is performed by means of an active fence (flexible a...