Deep neural network-based predictive modeling of road accidents

This work proposes to use deep neural networks (DNN) model for prediction of road accidents. DNN consists of two or more hidden layers with large number of nodes. Accident data of non-urban sections of eight highways were collected from official records, and dataset consists of a total of 2680 accidents. The data of 16 explanatory variables related to road geometry, traffic and road environment were collected from official records as well as through field studies. Out of a total of 222 data points of accident frequency, 148 were used for training and remaining 74 to test the models. To compare the performance of DNN-based modeling approach, gene expression programming (GEP) and random effect negative binomial (RENB) models were used. A correlation coefficient value of 0.945 (root mean square error = 5.908) was achieved by DNN in comparison with 0.914 (RMSE = 7.474) by GEP, and 0.891 (RMSE = 8.862) by RENB with the test dataset, indicating an improved performance by DNN in prediction of road accidents. In comparison with DNN, though lower value of correlation coefficient was achieved by GEP model, it quantified the effects of various variables on accident frequency and provided a ranked list of variables based upon their importance.

[1]  Tuan Nguyen,et al.  Deep neural network with high‐order neuron for the prediction of foamed concrete strength , 2018, Comput. Aided Civ. Infrastructure Eng..

[2]  Ezra Hauer.  On Prediction in Road Safety , 2010 .

[3]  Dominique Lord,et al.  The statistical analysis of highway crash-injury severities: a review and assessment of methodological alternatives. , 2011, Accident; analysis and prevention.

[4]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[5]  Bahram Gharabaghi,et al.  Reliable method of determining stable threshold channel shape using experimental and gene expression programming techniques , 2019, Neural Computing and Applications.

[6]  Salvatore Cafiso,et al.  Development of comprehensive accident models for two-lane rural highways using exposure, geometry, consistency and context variables. , 2010, Accident; analysis and prevention.

[7]  Yuanchang Xie,et al.  Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis. , 2007, Accident; analysis and prevention.

[8]  Dinesh Mohan,et al.  Road Accidents in India , 2009 .

[9]  Fred L. Mannering,et al.  The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives , 2010 .

[10]  J. Booth,et al.  2. Random-Effects Modeling of Categorical Response Data , 2000 .

[11]  Li-Yen Chang,et al.  Analysis of traffic injury severity: an application of non-parametric classification tree techniques. , 2006, Accident; analysis and prevention.

[12]  A Quimby,et al.  THE FACTORS THAT INFLUENCE A DRIVER'S CHOICE OF SPEED - A QUESTIONNAIRE STUDY , 1999 .

[13]  Fangming Deng,et al.  Compressive strength prediction of recycled concrete based on deep learning , 2018, Construction and Building Materials.

[14]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[15]  Xiqun Chen,et al.  Short-Term Forecasting of Traffic Flow and Speed: A Deep Learning Approach , 2018, CICTP 2018.

[16]  Elnaz Siami-Irdemoosa,et al.  Off-road truck-related accidents in U.S. mines. , 2016, Journal of safety research.

[17]  Maurizio Guida,et al.  Comparison and analysis of road tunnel traffic accident frequencies and rates using random-parameter models , 2016 .

[18]  Mehdi Hosseinpour,et al.  Exploring the effects of roadway characteristics on the frequency and severity of head-on crashes: case studies from Malaysian federal roads. , 2014, Accident; analysis and prevention.

[19]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[20]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[21]  Michael Sivak,et al.  Road Safety in India: Challenges and Opportunities , 2009 .

[22]  Paolo Fadda,et al.  An accident prediction model for urban road networks , 2018 .

[23]  Rune Elvik,et al.  Assessing causality in multivariate accident models. , 2011, Accident; analysis and prevention.

[24]  Fred Wegman,et al.  Analyzing truck accident data on the interurban road Ankara–Aksaray–Eregli in Turkey: Comparing the performances of negative binomial regression and the artificial neural networks models , 2019 .

[25]  Ezra Hauer,et al.  PREDICTION OF THE EXPECTED SAFETY PERFORMANCE OF RURAL TWO-LANE HIGHWAYS , 2000 .

[26]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[27]  A. Kılıçman,et al.  Modelling motorcycle accident on the road section by using general linear model: Case studies in Batu City , 2017 .

[28]  A Veeraragavan,et al.  Random parameter models for accident prediction on two-lane undivided highways in India. , 2011, Journal of safety research.

[29]  Mahesh Pal,et al.  M5 model tree based predictive modeling of road accidents on non-urban sections of highways in India. , 2016, Accident; analysis and prevention.

[30]  M.V.L.R. Anjaneyulu,et al.  Development of crash prediction models for two-lane rural highways using regression analysis , 2013 .

[31]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[32]  Mohammed Salifu,et al.  Crash prediction model for two-lane rural highways in the Ashanti region of Ghana , 2011 .

[33]  M. Driss,et al.  Traffic safety prediction model for identifying spatial degrees of exposure to the risk of road accidents based on fuzzy logic approach , 2015 .

[34]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[35]  D. Lord,et al.  Horizontal Curve Accident Modification Factor with Consideration of Driveway Density on Rural Four-Lane Highways in Texas , 2010 .

[36]  Hasmat Malik,et al.  Application of Gene Expression Programming (GEP) in Power Transformers Fault Diagnosis Using DGA , 2016 .

[37]  Bin Ran,et al.  Large-Scale Full-Coverage Traffic Speed Estimation under Extreme Traffic Conditions Using a Big Data and Deep Learning Approach: Case Study in China , 2019, Journal of Transportation Engineering, Part A: Systems.

[38]  A Baruya,et al.  THE RELATIONSHIP BETWEEN SPEED AND ACCIDENTS OF RURAL SINGLE-CARRIAGEWAY ROADS , 2002 .

[39]  Zhang Yi,et al.  Predicting movie box-office revenues using deep neural networks , 2019, Neural Computing and Applications.

[40]  Ali Nazari,et al.  Predicting the total specific pore volume of geopolymers produced from waste ashes by gene expression programming , 2012, Neural Computing and Applications.

[41]  John Fletcher,et al.  Road Accident Modelling for Highway Development and Management in Developing Countries. Final Report: Trials in India and Tanzania. , 2006 .

[42]  Y. B. Wah,et al.  Evaluating spatial and temporal effects of accidents likelihood using random effects panel count model , 2010, 2010 International Conference on Science and Social Research (CSSR 2010).

[43]  Guizhen Yu,et al.  Application of Long Short-Term Memory Neural Network for Multi-Step Travel Time Forecasting on Urban Expressways , 2018 .

[44]  Felix Kwamena,et al.  Deep Learning for Critical Infrastructure Resilience , 2019, Journal of Infrastructure Systems.

[45]  Rune Elvik,et al.  The Handbook of Road Safety Measures , 2009 .

[46]  Xuesong Yan,et al.  Stock price prediction based on deep neural networks , 2019, Neural Computing and Applications.