Traffic Accidents Forecasting using Singular Value Decomposition and an Autoregressive Neural Network Based on PSO

 

Lida Barba¹ and Nibaldo Rodriguez²

 

¹ Pontificia Universidad Católica de Valparaíso, Chile and Universidad Nacional de Chimborazo, Ecuador. (e-mail: lbarba@unach.edu.ec).

² Pontificia Universidad Católica de Valparaíso, Chile. (e-mail: nibaldo.rodriguez@ucv.cl).

 

Manuscript received on December 24, 2014,
Accepted for publication on April 20, 2015,
Published on June 15, 2015.

 

Abstract

In this paper, we propose a strategy to improve the forecasting of traffic accidents in Concepción, Chile. The forecasting strategy consists of four stages: embedding, decomposition, estimation and recomposition. At the irst stage, the Hankel matrix is used to embed the original time series. At the second stage, the Singular Value Decomposition (SVD) technique is applied. SVD extracts the singular values and the singular vectors, which are used to obtain the components of low and high frequency. At the third stage, the estimation is implemented with an Autoregressive Neural Network (ANN) based on Particle Swarm Optimization (PSO). The final stage is recomposition, where the forecasted value is obtained. The results are compared with the values given by the conventional forecasting process. Our strategy shows high accuracy and is superior to the conventional process.

Key words: Autoregressive neural network, particle swarm optimization, singular value decomposition.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

ACKNOWLEDGEMENTS

This research was partially supported by the Chilean National Science Fund through the project Fondecyt-Regular 1131105 and by the VRIEA of the Pontificia Universidad Católica de Valparaiso.

 

REFERENCES

[1] Hornik K., Stinchcombe X., White H.: Multilayer feedforward networks are universal approximators. Neural Networks. 2(5), 359-366 (1989).         [ Links ]

[2] Svozil D., Kvasnicka V., Pospichal J.: Introduction to multi-layer feed-forward neural networks. Chemometrics and Intelligent Laboratory Systems. 39(1), 43-62 (1997).         [ Links ]

[3] Chattopadhyay G., Chattopadhyay S.:Autoregressive forecast of monthly total ozone concentration: A neurocomputing approach. Computers & Geosciences. 35(9), 1925-1932 (2009).         [ Links ]

[4] Maali Y., Al-Jumaily A.: Multi Neural Networks Investigation based Sleep Apnea Prediction. Procedia Computer Science. 24, 97-102 (2013).         [ Links ]

[5] Rojas I., Pomares H., Bernier J.L., Ortega J., Pino B., Pelayo F.J., Prieto A.: Time series analysis using normalized PG-RBF network with regression weights. Neurocomputing. 42(1-4), 267-285 (2002).         [ Links ]

[6] Roh S.B., Oh S.K., Pedrycz W.: Design of fuzzy radial basis function-based polynomial neural networks. Fuzzy Sets and Systems. 185(1), 15-37 (2011).         [ Links ]

[7] Liu F., Ng G.S., Quek C.: RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction. Neurocomputing. 70(7-9), 1331-1341 (2007).         [ Links ]

[8] Scarselli F., Chung A.: Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results. Neural Networks. 11(1), 15-37 (1998).         [ Links ]

[9] Gheyas I.A., Smith L.S.: A novel neural network ensemble architecture for time series forecasting. Neurocomputing. 74(18), 3855-3864 (2011).         [ Links ]

[10] Gao D., Kinouchi Y., Ito K., Zhao X.: Neural networks for event extraction from time series: a back propagation algorithm approach. Future Generation Computer Systems. 21(7), 1096-1105 (2005).         [ Links ]

[11] Khashei M., Bijari M., Ali G.: Hybridization of autoregressive integrated moving average (ARIMA) with probabilistic neural networks (PNNS). Computers & Industrial Engineering. 63(1), 37-45 (2012).         [ Links ]

[12] Jeong K., Koo C., Hong T.: An estimation model for determining the annual energy cost budget in educational facilities using SARIMA (seasonal autoregressive integrated moving average) and ANN (artificial neural network). Energy. 71, 71-79 (2014).         [ Links ]

[13] Wei Y., Chen M.C.: Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C: Emerging Technologies. 21(1), 148-162 (2012).         [ Links ]

[14] Shoaib M., Shamseldin A.Y., Melville B.W.: Comparative study of different wavelet based neural network models for rainfall-runoff modeling. Journal of Hydrology. 515, 47-58 (2014).         [ Links ]

[15] Zhou J., Duan Z., Li Y., Deng J., Yu D.: PSO-based neural network optimization and its utilization in a boring machine. Journal of Materials Processing Technology. 178(13), 19-23 (2006).         [ Links ]

[16] Mohandes M.A.: Modeling global solar radiation using particle swarm optimization PSO. Solar Energy. 86(11), 3137-3145 (2012).         [ Links ]

[17] de Mingo Lopez L.F., Blas N.G., Arteta A. The optimal combination: Grammatical swarm, particle swarm optimization and neural networks. Journal of Computational Science. 3(12), 46-55, (2012).         [ Links ]

[18] Shores, T.S.: Applied Linear Algebra and Matrix Analysis. Springer, 291-293, (2007).         [ Links ]

[19] Freeman J.A., Skapura D.M.: Neural Networks, Algorithms, Applications, and Programming Techniques. Addison-Wesley, California (1991).         [ Links ]

[20] Eberhart R.C., Shi Y., Kennedy J.: Swarm Intelligence. Morgan Kaufmann, San Francisco CA (2001).         [ Links ]

[21] Yang X.S.: Chapter 7. Particle Swarm Optimization: Nature-Inspired Optimization Algorithms. Elsevier. 99-110 (2014).         [ Links ]

[22] National Commission of Transit Security, http://www.conaset.cl