A wavelet network model for short-term traffic volume forecasting. (English) Zbl 1151.90342

Summary: Wavelet networks (WNs) are recently developed neural network models. WN models combine the strengths of discrete wavelet transform and neural network processing to achieve strong nonlinear approximation ability, and thus have been successfully applied to forecasting and function approximations. In this study, two WN models based on different mother wavelets are used for the first time for short-term traffic volume forecasting. The Levenberg-Marquardt algorithm is used to train the WN models because it has better efficiency than the other algorithms based on gradient descent. Using the traffic volume data collected on Interstate 80 in California, the WN models are compared with the widely used back-propagation neural network (BPNN) and radial basis function neural network (RBFNN) models. The performance evaluation is based on mean absolute percentage error (MAPE) and variance of absolute percentage error (VAPE). The test and comparison results show that the WN models consistently produce lower average MAPE and VAPE values than the BPNN and RBFNN models, suggesting that the WN models are a better predictor of accuracy, stability, and adaptability.


90B15 Stochastic network models in operations research
92B20 Neural networks for/in biological studies, artificial life and related topics
42C40 Nontrigonometric harmonic analysis involving wavelets and other special systems
90B06 Transportation, logistics and supply chain management
Full Text: DOI


[1] Ahmed, M. and Cook, A. (1979) Analysis of freeway traffic time-series data by using Box-Jenkins techniques <i>Transportation Research Board</i>, 722, pp. 1 - 9.
[2] Arem, B. and Kirby, H. and Van Der Vlist, M. and Whittaker, J. (1997) Recent advances and applications in the field of short-term traffic forecasting <i>International Journal of Forecasting</i>, 13, pp. 1 - 12. <a href=”http://dx.doi.org/10.1016
[3] Adeli, H. and Karim, A. (2000) Fuzzy-wavelet RBFNN model for freeway incident detection <i>Journal of Transportation Engineering</i>, 126(6), pp. 464 - 471. <a href=”http://dx.doi.org/10.1061
[4] Ampazis, N. and Perantonis, S. (2002) Two highly efficient second-order algorithms for training feedforward networks <i>IEEE Transactions on Neural Networks</i>, 13, pp. 1064 - 1074. <a href=”http://dx.doi.org/10.1109
[5] Burrus, C. and Gopinath, R. and Guo, H.(1998) <i> Introduction to Wavelets and Wavelet Transforms: A Primer</i>. Upper Saddle River New Jersey: Prentice Hall, Inc.
[6] Chen, H. and Grant-Muller, S. (2001) Use of sequential learning for short-term traffic flow forecasting <i>Transportation Research Part C</i>, 9, pp. 319 - 336. <a href=”http://dx.doi.org/10.1016
[7] Cui, W. and Zhu, C. and Zhao, H. (2005) Prediction of thin film thickness of field emission using wavelet neural networks <i>Thin Solid Films</i>, 473, pp. 224 - 229. <a href=”http://dx.doi.org/10.1016
[8] Chen, Y. and Yang, B. and Dong, J. (2006) Time-series prediction using a local linear wavelet neural network <i>Neurocomputing</i>, 69, pp. 449 - 465. <a href=”http://dx.doi.org/10.1016
[9] Davis, G. and Nihan, N. (1991) Nonparametric regression and short-term freeway traffic forecasting <i>Journal of Transportation Engineering</i>, 117(2), pp. 178 - 188. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0733-947X&vol=117&iss=2&firstpage=178” target=”new”>[CSA]</a>
[10] Hagan, M. and Menhaj, M. (1994) Training feedforward networks with the Marquardt algorithm <i>IEEE Transactions on Neural Networks</i>, 5, pp. 989 - 993. <a href=”http://dx.doi.org/10.1109
[11] Hamed, M. and Al-Masaeid, H. and Bani Said, Z. (1995) Short-term prediction of traffic volume in urban arterials <i>Journal of Transportation Engineering</i>, 121(3), pp. 249 - 254. <a href=”http://dx.doi.org/10.1061
[12] Hung, S. and Huang, C. and Wen, C. and Hsu, Y. (2003) Nonparametric identification of a building structure from experimental data using wavelet neural network <i>Computer-Aided Civil and Infrastructure Engineering</i>, 18(5), pp. 356 - 368. <a href=”http://dx.doi.org/10.1111
[13] Kirby, H. and Watson, S. and Dougherty, M. (1997) Should we use neural network or statistical models for short-term motorway traffic forecasting? <i>International Journal of Forecasting</i>, 13, pp. 43 - 50. <a href=”http://dx.doi.org/10.1016
[14] Kardanpour, Z. and Hemmateenejad, B. and Khayamian, T. (2005) Wavelet neural network-based QSPR for prediction of critical micelle concentration of Gemini surfactants <i>Analytica Chimica Acta</i>, 531, pp. 285 - 291. <a href=”http://dx.doi.org/10.1016
[15] Lu, J. (1990) Prediction of traffic flow by an adaptive prediction system <i>Transportation Research Record</i>, 1287, pp. 13 - 20. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1287&iss=&firstpage=13” target=”new”>[CSA]</a>
[16] Lin, W.(2001). A Gaussian maximum likelihood formulation for short-term forecasting of traffic flow. <i> <i>IEEE Intelligent Transportation Systems Conference Proceedings</i> OaklandCA. </i> In [ pp. 150 - 155] . .
[17] Lee, D. and Zheng, W. and Shi, Q.(2004). Short-term freeway traffic flow prediction using a combined neural network model. <i> <i>CD-ROM of the 83rd TRB Annual Meeting</i> WashingtonD.C.January11–15. </i> In [ pp. ] . .
[18] Nicholson, H. and Swann, C. (1974) The prediction of traffic flow volumes based on spectral analysis <i>Transportation Research</i>, 8, pp. 533 - 538. <a href=”http://dx.doi.org/10.1016
[19] Nihan, N. and Holmesland, K. (1980) Use of the Box and Jenkins time series technique in traffic forecasting <i>Transportation</i>, 9, pp. 125 - 143. <a href=”http://dx.doi.org/10.1007
[20] Okutani, I. and Stephanedes, Y. (1984) Dynamic prediction of traffic volume through Kalman filtering theory <i>Transportation Research Part B</i>, 18, pp. 1 - 11. <a href=”http://dx.doi.org/10.1016
[21] Oussar, Y. and Rivals, I. and Personnaz, L. and Dreyfus, G. (1998) Training wavelet networks for nonlinear dynamic input-output modeling <i>Neurocomputing</i>, 20, pp. 173 - 188. <a href=”http://dx.doi.org/10.1016 · Zbl 0910.68186
[22] Park, B. and Messer, C. and Urbanik, T., II. (1998) Short-term freeway traffic volume forecasting using radial basis function neural network <i>Transportation Research Record</i>, 1651, pp. 39 - 47. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1651&iss=&firstpage=39” target=”new”>[CSA]</a>
[23] Park, B. (2002) Hybrid neuro-fuzzy application in short-term freeway traffic volume forecasting <i>Transportation Research Record</i>, 1802, pp. 190 - 196. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1802&iss=&firstpage=190” target=”new”>[CSA]</a>
[24] Rumelhart, D. and Hinton, G. and Williams, R. (1986) Learning representations by back-propagating errors <i>Nature</i>, 323, pp. 533 - 536. <a href=”http://dx.doi.org/10.1038 · Zbl 1369.68284
[25] Smith, B. and Demetsky, M. (1994) Short-term traffic flow prediction: Neural network approach <i>Transportation Research Record</i>, 1453, pp. 98 - 104. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1453&iss=&firstpage=98” target=”new”>[CSA]</a>
[26] Smith, B. and Demetsky, M. (1997) Traffic flow forecasting: comparison of modeling approaches <i>Journal of Transportation Engineering</i>, 123(4), pp. 261 - 266. <a href=”http://dx.doi.org/10.1061
[27] Smith, B. and Williams, B. and Oswald, R. (2002) Comparison of parametric and nonparametric models for traffic flow forecasting <i>Transportation Research Part C</i>, 10, pp. 303 - 321. <a href=”http://dx.doi.org/10.1016
[28] Stathopoulos, A. and Karlaftis, M. (2003) A multivariate state space approach for urban traffic flow modeling and prediction <i>Transportation Research Part C</i>, 11, pp. 121 - 135. <a href=”http://dx.doi.org/10.1016
[29] Wild, D. (1997) Short-term forecasting based on a transformation and classification of traffic volume time series <i>International Journal of Forecasting</i>, 13, pp. 63 - 72. <a href=”http://dx.doi.org/10.1016
[30] Willams, B. and Durvasula, P. and Brown, D. (1998) Urban freeway traffic flow prediction: Application of seasonal autoregressive integrated moving average and exponential smoothing models <i>Transportation Research Record</i>, 1644, pp. 132 - 141. <a href=”http://www.csa.com/htbin/linkabst.cgi?issn=0361-1981&vol=1644&iss=&firstpage=132” target=”new”>[CSA]</a>
[31] Yin, H. and Wong, S. and Xu, J. and Wong, C. (2002) Urban traffic flow prediction using a fuzzy-neural approach <i>Transportation Research Part C</i>, 10, pp. 85 - 98. <a href=”http://dx.doi.org/10.1016
[32] Zhang, Q. and Benveniste, A. (1992) Wavelet networks <i>IEEE Transactions on Neural Networks</i>, 3, pp. 889 - 898. <a href=”http://dx.doi.org/10.1109
[33] Zhang, J. and Walter, G. and Miao, Y. and Lee, W. (1995) Wavelet neural networks for function learning <i>IEEE Transactions on Signal Processing</i>, 43, pp. 1485 - 1497. <a href=”http://dx.doi.org/10.1109
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.