A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Predicting Highway–Rail Grade Crossing Collision Risk by Neural Network Systems
In this paper, train-vehicle crash risk at highway–rail grade crossings (HRGCs) is analyzed with a neural network (NN) model to return meaningful rankings of crash-contributory-variable importance based on different criteria, but also to produce dependent nonlinear contributor-crash curves with all other contributors considered for a specific contributor variable. Historical crash data for North Dakota public HRGCs from 1996 to 2014 were used for the study. Several principal findings were observed: (1) 22 input variables describing traffic characteristics and crossing characteristics are related to crashes at public HRGCs; (2) a mean-square error–based NN model and a connection weights–based NN model represent two relative contributory-variable importance lists for different application purposes; (3) the effect of different variables on crash likelihood is different when all other contributors are set at different levels, and the relationship between contributors and crash likelihood is dynamic nonlinear; and (4) in predictive and explanatory power, the neural network model outperforms the decision tree approach for the considered case study.
Predicting Highway–Rail Grade Crossing Collision Risk by Neural Network Systems
In this paper, train-vehicle crash risk at highway–rail grade crossings (HRGCs) is analyzed with a neural network (NN) model to return meaningful rankings of crash-contributory-variable importance based on different criteria, but also to produce dependent nonlinear contributor-crash curves with all other contributors considered for a specific contributor variable. Historical crash data for North Dakota public HRGCs from 1996 to 2014 were used for the study. Several principal findings were observed: (1) 22 input variables describing traffic characteristics and crossing characteristics are related to crashes at public HRGCs; (2) a mean-square error–based NN model and a connection weights–based NN model represent two relative contributory-variable importance lists for different application purposes; (3) the effect of different variables on crash likelihood is different when all other contributors are set at different levels, and the relationship between contributors and crash likelihood is dynamic nonlinear; and (4) in predictive and explanatory power, the neural network model outperforms the decision tree approach for the considered case study.
Predicting Highway–Rail Grade Crossing Collision Risk by Neural Network Systems
Zheng, Zijian (author) / Lu, Pan (author) / Pan, Danguang (author)
2019-05-31
Article (Journal)
Electronic Resource
Unknown
Rail-Highway Grade Crossing Consolidation in Kansas
| British Library Online Contents | 1998
Risk-Based Model for Identifying Highway-Rail Grade Crossing Blackspots
| British Library Online Contents | 2004
Application of Geographic Information Systems Rail-Highway Grade Crossing Safety
| British Library Online Contents | 1995
Low-volume roads and the rail-highway grade crossing problem
| British Library Conference Proceedings | 1998
Low-volume roads and the rail-highway grade crossing problem
| British Library Conference Proceedings | 1998