Neural-network-based models for short-term traffic flow forecasting using a hybrid exponential smoothing and levenberg-marquardt algorithm

IEEE Transactions on Intelligent Transportation Systems

Volumn 13, Issue 2, 2012, Pages 644-654

  Chan, Kit Yan ^a   Dillon, Tharam S ^a   Singh, Jaipal ^a   Chang, Elizabeth ^a  

^a CURTIN UNIVERSITY   (Australia)

Author keywords

Exponential smoothing method; LevenbergMarquardt (LM) algorithm; neural networks (NNs); short term traffic flow forecasting

Indexed keywords

EXPONENTIAL SMOOTHING; EXPONENTIAL SMOOTHING METHOD; GENERALIZATION CAPABILITY; LEVENBERG-MARQUARDT ALGORITHM; LM ALGORITHM; NOVEL NEURAL NETWORK; PREPROCESS; SHORT-TERM TRAFFIC FLOW; SHORT-TERM TRAFFIC FLOW FORECASTING; TRAFFIC FLOW; TRAINING METHODS; WESTERN AUSTRALIA;

ALGORITHMS; FORECASTING; NEURAL NETWORKS;

TRAFFIC CONTROL;

EID: 84861893114     PISSN: 15249050     EISSN: None     Source Type: Journal    
DOI: 10.1109/TITS.2011.2174051     Document Type: Article

References (59)

1. I. G. Aliand Y. T. Chen, "Designualityand robustness with neural networks," IEEE Trans. Neural Netw., vol. 10, no. 6, pp. 1518-1527, Nov. 1999.
2. S. Amari, N. Murata, K. Muller, M. Finke,and H. H. Yang, "Asymptotic statistical theory of overtrainingand cross validation," IEEE Trans. Neural Netw., vol. 8, no. 5, pp. 985-996, Sep. 1997. (Pubitemid 127763330)
3. V. B. Arem, H. R. Kirby, M. J. M. Van Der Vlist,and J. C. Whittaker, "Recentadvancesandapplications in the field of short-term traffic forecasting," Int. J. Forecasting, vol. 13, no. 1, pp. 1-12, Mar. 1997. (Pubitemid 127165539)
4. R. G. Brownand R. F. Meyer, "The fundamental theorem of exponential smoothing," Oper. Res., vol. 9, no. 5, pp. 673-685, Sep./Oct. 1961.
5. M. Castro-Neto, Y. S. Jeong, M. K. Jeong,and L. D. Han, "Online-SVR for short-term traffic flow prediction under typicalandatypical traffic conditions," Expert Syst. Appl., vol. 36, no. 3, pp. 6164-6173, Apr. 2009.
6. P. C. Chang, Y. W. Wang,and C. H. Liu, "The development ofa weighted evolving fuzzy neural network for PCB sales forecasting," Expert Syst. Appl., vol. 32, no. 1, pp. 86-96, 2007.
7. S. C. Chang, R. S. Kim, S. J. Kim,and M. H. Ahn, "Traffic flow forecasting usinga 3-stage model," in Proc. IEEE Intell. Veh. Symp., 2000, pp. 451-456. (Pubitemid 32135707)
8. H. C. Coand R. Boosarawongse, "Forecasting Thailand's rice export: Statistical techniues vs.artificial neural networks," Comput. Ind. Eng., vol. 53, no. 4, pp. 610-627, Nov. 2007. (Pubitemid 47588647)
9. I. Daubechies, "The wavelet transform, time-freuency localizationand signalanalysis," IEEE Trans. Inf. Theory, vol. 36, no. 5, pp. 961-1005, Sep. 1990. (Pubitemid 20738359)
10. G. A. Davisand N. L. Nihan, "Nonparametric regressionand short-term freeway traffic forecasting," J. Transp. Eng., vol. 177, no. 2, pp. 178-188, Apr. 1991.
11. S. De Lurgio, Forecasting Principlesand Applications.. New York: McGraw-Hill, 1998.
12. H. Dia, "An object-oriented neural networkapproach to short-term traffic forecasting," Eur. J. Oper. Res., vol. 131, no. 2, pp. 253-261, Jun. 2001. (Pubitemid 32271741)
13. T. S. Dillon, S. Sestito,and S. Leung, "Short term load forecasting usinganadaptive neural network," Elect. Power Energy Syst., vol. 13, no. 4, pp. 186-192, 1991.
14. M. Dougherty, "A review of neural networksapplied to transport," Transp. Res. Part C: Emerging Technol., vol. 3, no. 4, pp. 247-260, 1995.
15. M. S. Dougherty, H. R. Kirby,and R. D. Boyle, "Using neural networks to recognize, predictand model traffic," in Artificial Intelligence Applications to Traffic Engineering. Utrecht, The Netherlands: VSP, 1994, pp. 235-250.
16. M. S. Doughertyand M. R. Cobbett, "Short-term inter-urban traffic forecasts using neural networks," Int. J. Forecasting, vol. 13, no. 1, pp. 21-31, Mar. 1997. (Pubitemid 127165541)
17. E. L. Faria, M. P. Albuuerue, J. L. Gonzalez, J. T. P. Cavalcanta,and M. P. Albuuerue, "Predicting the Brazilian stock market through neural networksandadaptive exponential smoothing methods," Expert Syst. Appl., vol. 36, no. 10, pp. 12 506-12 509, Dec. 2009.
18. F. D. Foreseeand M. T. Hagan, "Gauss-Newtonapproximation to Bayesian regularization," in Proc. Int. Joint Conf. Neural Netw., 1997, pp. 1930-1935.
19. L. Fuand L. R. Rilett, "Estimation of time-dependent, stochastic route travel times usingartificial neural networks," Transp. Planning Technol., vol. 24, no. 1, pp. 25-48, 2000. (Pubitemid 32477773)
20. Y. Gaoand M. J. Er, "NARMAX time series model prediction: Feedforwardand recurrent fuzzy neural networkapproaches," Fuzzy Sets Syst., vol. 150, no. 2, pp. 331-350, Mar. 2005. (Pubitemid 40056024)
21. R. S. Gutierrez, O. S. Adriano,and S. Mukhopadhyay, "Lumpy demand forecasting using neural networks," Int. J. Prod. Econ., vol. 111, no. 2, pp. 409-420, Feb. 2008. (Pubitemid 350299143)
22. S. Innamaa, "Effect of monitoring system structure on short-term prediction of highway travel time," Transp. Planning Technol., vol. 29, no. 2, pp. 125-140, Apr. 2006. (Pubitemid 43931956)
23. X. Jiangand H. Adeli, "Dynamic wavelet neural network model for traffic flow forecasting," J. Transp. Eng., vol. 131, no. 10, pp. 771-779, Oct. 2005. (Pubitemid 41419813)
24. C. F. Juang, "Temporal problems solved by dynamic fuzzy network based on geneticalgorithm with variable-length chromosomes," Fuzzy Sets Syst., vol. 142, no. 2, pp. 199-219, Mar. 2004.
25. N. K. Kasabovand Q. Song, "DENFIS: Dynamic evolving neural-fuzzy inference systemand itsapplication for time-series prediction," IEEE Trans. Fuzzy Syst., vol. 10, no. 2, pp. 144-154, Apr. 2002. (Pubitemid 34554860)
26. G. N. Karystinosand D. A. Pados, "On overfitting, generalization,and randomly expanded training sets," IEEE Trans. Neural Netw., vol. 11, no. 5, pp. 1050-1057, Sep. 2000.
27. S. Lawrence, C. L. Giles,and A. C. Tsoi, "What size neural network gives optimal generalization? Convergence properties of backpropagation," Instrum. Adv. Comput. Studies, Univ. Maryland, College Park, MD, Tech. Rep., UMIACS-TR-96-22and CS-TR-3617, Jun. 1996.
28. C. Ledoux, "An urban traffic flow model integrating neural network," Transp. Res. Part C, Emerging Technol., vol. 5, no. 5, pp. 287-300, Oct. 1997.
29. G. L. Lilienand P. Kotler, Marketing Decision Making: A Model Building Approach. New York: Harper & Row, 1983.
30. F. Liang, "Bayesian neural networks for nonlinear time series forecasting," Statist. Comput., vol. 15, no. 1, pp. 13-29, Jan. 2005. (Pubitemid 40389960)
31. Y. Liu, J. A. Starzyk,and Z. Zhu, "Optimizedapproximationalgorithm in neural networks without overfitting," IEEE Trans. Neural Netw., vol. 19, no. 6, pp. 983-995, Jun. 2008.
32. D. MacKay, "A practical Bayesian framework for backpropagation networks," Neural Comput., vol. 4, no. 3, pp. 448-472, May 1992.
33. S. G. Mallat, "A theory for multiresolution signal decomposition: The wavelet representation," IEEE Trans. Pattern Anal. Mach. Intell., vol. 11, no. 7, pp. 674-693, Jul. 1989.
34. P. A. Mastorocostasand J. B. Theocharis, "An orthogonal least-suares method for recurrent fuzzy-neural modeling," Fuzzy Sets Syst., vol. 140, no. 2, pp. 285-300, Dec. 2003.
35. I. Okutaniand Y. J. Stephanedes, "Dynamic prediction of traffic volume through Kalman filtering theory," Transp. Res. Part B: Methodology, vol. 18, no. 1, pp. 1-11, Feb. 1984. (Pubitemid 14528238)
36. S. E. Papadakis, J. B. Theocharis,and A. G. Bakirtzis, "A load curve based fuzzy modeling techniue for short-term load forecasting," Fuzzy Sets Syst., vol. 135, no. 2, pp. 279-303, Apr. 2003.
37. L. Prechelt, "Automatic early stopping using cross validation: Quantifying the criteria," Neural Netw., vol. 11, no. 4, pp. 761-767, Jun. 1998. (Pubitemid 28400276)
38. P. Ross, "Exponential filtering of traffic data," in Proc. Transp. Res. Board, Washington, DC, 1982, vol. 869, pp. 43-49.
39. C. Quek, M. Pasuier,and B. B. S. Lim, "POP-TRAFFIC: A novel fuzzy neuralapproach to road trafficanalysisand prediction," IEEE Trans. Intell. Transp. Syst., vol. 7, no. 2, pp. 133-146, Jun. 2006. (Pubitemid 44144050)
40. R. Setiono, "Feedforward neural network construction using cross validation," Neural Comput., vol. 13, no. 12, pp. 2865-2877, Dec. 2001. (Pubitemid 33598000)
41. D. Srinivasan, C. W. Chan,and P. G. Balaji, "Computational intelligence based congestion prediction fora dynamic urban street network," Neurocomputing, vol. 72, no. 10-12, pp. 2710-2716, 2009.
42. B. L. Smith, B.M.Williams,and R. K. Oswald, "Comparison of parametricand nonparametric models for traffic flow forecasting," Transp. Res. Part C, Emerging Technol., vol. 19, pp. 303-321, 2002.
43. A. Stathopoulos, L. Dimitriou,and T. Tsekeris, "Fuzzy modelingapproach for combined forecasting of urban traffic flow," Comput.-Aided Civil Infrastruct. Eng., vol. 23, no. 7, pp. 521-535, Oct. 2008.
44. M. C. Tan, S. C. Wong, J. M. Xu, Z. R. Guan,and P. Zhang, "Anaggregationapproach to short term traffic flow prediction," IEEE Trans. Intell. Transp. Syst., vol. 10, no. 1, pp. 60-69, Mar. 2009.
45. R.-J. Wai, R.-Y. Duen, J.-D. Lee,and H.-H. Chang, "Wavelet neural network control for induction motor drive using sliding-mode design techniue," IEEE Trans. Ind. Electron., vol. 50, no. 4, pp. 733-748, Aug. 2003.
46. N. Wanas, G. Auda, M. S. Kamel,and F. Karray, "On the optimal number of hidden nodes ina neural network," in Proc. IEEE Can. Conf. Elect. Comput. Eng., 1998, vol. 2, pp. 918-921.
47. R. A. Yaffeeand M. McGee, Introduction to Time Series Analysisand Forecasting. San Diego, CA: Academic, 2000.
48. H. Yin, S. C.Wong, J. Xu,and C. K.Wong, "Urban traffic flow prediction usinga fuzzy-neuralapproach," Transp. Res. Part C, Emerging Technol., vol. 10, no. 2, pp. 85-98, Apr. 2002. (Pubitemid 34039575)
49. S. J. Yoo, J. B. Park,and Y. H. Choi, "Adaptive dynamic surface control of flexible-joint robots using self-recurrent wavelet neural networks," IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 36, no. 6, pp. 1342-1355, Dec. 2006. (Pubitemid 46405765)
50. G. P. Zhangand D. M. Kline, "Quarterly time series forecasting with neural networks," IEEE Trans. Neural Netw., vol. 18, no. 6, pp. 1800-1814, Nov. 2007. (Pubitemid 350148428)
51. G. P. Zhangand M. Qi, "Neural network forecasting for seasonaland trend time series," Eur. J. Oper. Res., vol. 160, no. 2, pp. 501-514, Jan. 2005.
52. Q. Zhangand A. Benveniste, "Wavelet networks," IEEE Trans. Neural Netw., vol. 3, no. 6, pp. 889-898, Nov. 1992. (Pubitemid 23580843)
53. W. Zheng, D. H. Lee,and Q. Shi, "Short-term freeway traffic flow prediction: Bayesian combined neural networkapproach," J. Transp. Eng., vol. 132, no. 2, pp. 114-121, Feb. 2006. (Pubitemid 43119041)
54. K. Y. Chan, J. Singh, T. S. Dillon,and E. Chang, "Traffic flow forecasting neural networks based on exponential smoothing method," in Proc. 6th IEEE Conf. Ind. Electron. Appl., 2011, pp. 376-381.
55. G. E.-P. Box, J. S. Hunter,and W. G. Hunter, Statistics for Experiments: Design, Innovation,and Discovery, 2nd ed. New York: Wiley, 2005.
56. A. Simrothand H. Zähle, "Travel time prediction using floating car dataapplied to logistics planning," IEEE Trans. Intell. Transp. Syst., vol. 12, no. 1, pp. 243-253, Mar. 2011.
57. T. Thomas,W.Weijermars,and E. Berkum, "Predictions of urban volumes in single time series," IEEE Trans. Intell. Transp. Syst., vol. 11, no. 1, pp. 71-80, Mar. 2010.
58. M. Yang, Y. Liu,and Z. You, "The reliability of travel time forecasting," IEEE Trans. Intell. Transp. Syst., vol. 11, no. 1, pp. 162-171, Mar. 2010.
59. M. T. Haganand M. B. Menhaj, "Training feedforward networks with the Maruardtalgorithm," IEEE Trans. Neural Netw., vol. 5, no. 6, pp. 989-993, Nov. 1994.