Forecast of Traffic Accidents Based on Components Extraction and an Autoregressive Neural Network with Levenberg-Marquardt

In this paper is proposed an improved one-step-ahead strategy for traffic accidents and injured forecast in Concepcion, Chile, from year 2000 to 2012 with a weekly sample period. This strategy is based on the extraction and estimation of components of a time series, the Hankel matrix is used to map the time series, the Singular Value Decomposition(SVD) extracts the singular values and the orthogonal matrix, and the components are forecasted with an Autoregressive Neural Network (ANN) based on Levenberg-Marquardt (LM) algorithm. The forecast accuracy of this proposed strategy are compared with the conventional process, SVD-ANN-LM achieved a MAPE of 1.9% for the time series Accidents, and a MAPE of 2.8% for the time series Injured, in front of 14.3% and 21.1% that were obtained with the conventional process.

[1]  George Yannis,et al.  State-space based analysis and forecasting of macroscopic road safety trends in Greece. , 2013, Accident; analysis and prevention.

[2]  Pilar Poncela,et al.  Forecasting traffic accidents using disaggregated data , 2006 .

[3]  José Perrin,et al.  Singular value decomposition as a denoising tool for airborne time domain electromagnetic data , 2011 .

[4]  George Yannis,et al.  On statistical inference in time series analysis of the evolution of road safety. , 2013, Accident; analysis and prevention.

[5]  Martin T. Hagan,et al.  Neural network design , 1995 .

[6]  Griselda López,et al.  Analysis of traffic accidents on rural highways using Latent Class Clustering and Bayesian Networks. , 2013, Accident; analysis and prevention.

[7]  Albert Sesé,et al.  Designing an artificial neural network for forecasting tourism time series , 2006 .

[8]  A Al-Zaben,et al.  Extraction of foetal ECG by combination of singular value decomposition and neuro-fuzzy inference system , 2006, Physics in medicine and biology.

[9]  Cheng Hua Li,et al.  An efficient document classification model using an improved back propagation neural network and singular value decomposition , 2009, Expert Syst. Appl..

[10]  Kadir Kavaklioglu.  Robust electricity consumption modeling of Turkey using Singular Value Decomposition , 2014 .

[11]  Wendy Weijermars,et al.  Road safety forecasting and ex-ante evaluation of policy in the Netherlands , 2013 .

[12]  Mohammed A Quddus,et al.  Time series count data models: an empirical application to traffic accidents. , 2008, Accident; analysis and prevention.

[13]  Li-Yen Chang,et al.  Analysis of driver injury severity in truck-involved accidents using a non-parametric classification tree model , 2013 .

[14]  Feng Ding,et al.  Model order determination using the Hankel matrix of impulse responses , 2011, Appl. Math. Lett..

[15]  Peter W. Tse,et al.  Development of an advanced noise reduction method for vibration analysis based on singular value decomposition , 2003 .

[16]  Héctor Pomares,et al.  Time series analysis using normalized PG-RBF network with regression weights , 2002, Neurocomputing.

[17]  Juan de Oña,et al.  Analysis of traffic accident severity using Decision Rules via Decision Trees , 2013, Expert Syst. Appl..

[18]  Seok-Beom Roh,et al.  Design of fuzzy radial basis function-based polynomial neural networks , 2011, Fuzzy Sets Syst..

[19]  T. Shores.  Applied Linear Algebra And Matrix Analysis , 1999 .

[20]  Leslie S. Smith,et al.  A novel neural network ensemble architecture for time series forecasting , 2011, Neurocomputing.

[21]  C.-S. Chien,et al.  An adaptive parameterized block-based singular value decomposition for image de-noising and compression , 2012, Appl. Math. Comput..

[22]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[23]  Hiok Chai Quek,et al.  RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction , 2007, Neurocomputing.

[24]  Jin Chen,et al.  Short-time matrix series based singular value decomposition for rolling bearing fault diagnosis , 2013 .

[25]  Juan-Carlos Cano,et al.  A novel approach for traffic accidents sanitary resource allocation based on multi-objective genetic algorithms , 2013, Expert Syst. Appl..