Abstract
Short-term traffic flow forecasting is a vibrant research topic that has been growing in interest since the late 70’s. In the last decade this vibrant field has shifted its focus towards machine learning methods. These techniques often require fine-grained parameter tuning to obtain satisfactory performance scores, a process that usually relies on manual trial-and-error adjustment. This paper explores the use of Harmony Search optimization for tuning the parameters of neural network jointly with the selection of the input features from the dataset at hand. Results are discussed and compared to other tuning methods, from which it is concluded that neural predictors optimized via the proposed heuristic wrapper outperform those tuned by means of naïve parametrized algorithms, thus allowing for longer-term predictions. These promising results unfold potential applications of this technique in multi-location neighbor-aware traffic prediction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Van Hinsbergen, C.P., Van Lint, J.W., Sanders, F.M.: Short term traffic prediction models. In: Proceedings of the 14th World Congress on Intelligent Transport Systems (ITS), Beijing, pp. 22–41 (2007)
Vlahogianni, E.I., Karlaftis, M.G., Golias, J.C.: Short-term traffic forecasting: where we are and where we’re going. Transp. Res. Part C: Emerg. Technol. 43, 3–19 (2014)
Dunne, S., Ghosh, B.: Regime-based short-term multivariate traffic condition forecasting algorithm. J. Transp. Eng. 138(4), 455–466 (2011)
Yang, H., Dillon, T.S., Chen, Y.-P.P.: Evaluation of recent computational approaches in short-term traffic forecasting. In: Dillon, T. (ed.) IFIP AI 2015. IAICT, vol. 465, pp. 108–116. Springer, Heidelberg (2015). doi:10.1007/978-3-319-25261-2_10
Zhang, W., Xiao, R., Deng, J.: Research of traffic flow forecasting based on the information fusion of BP network sequence. In: He, X., Gao, X., Zhang, Y., Zhou, Z.-H., Liu, Z.-Y., Fu, B., Hu, F., Zhang, Z. (eds.) IScIDE 2015. LNCS, vol. 9243, pp. 548–558. Springer, Heidelberg (2015). doi:10.1007/978-3-319-23862-3_54
Meng, M., Shao, C.F., Wong, Y.D., Wang, B.B., Li, H.X.: A two-stage short-term traffic flow prediction method based on AVL and AKNN techniques. J. Cent. South Univ. 22, 779–786 (2015)
Tang, J., Zou, Y., Ash, J., Zhang, S., Liu, F., Wang, Y.: Travel time estimation using freeway point detector data based on evolving fuzzy neural inference system. PloS one 11(2), e0147263 (2016)
Smith, B.L., Demetsky, M.J.: Short-term traffic flow prediction: neural network approach. Transp. Res. Record 1453, 98–101 (1994)
Abdulhai, B., Porwal, H., Recker, W.: Short term freeway traffic flow prediction using genetically-optimized time-delay-based neural networks. California Partners for Advanced Transit and Highways (PATH) (1999)
Vlahogianni, E.I., Karlaftis, M.G., Golias, J.C.: Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach. Transp. Res. Part C: Emerg. Technol. 13(3), 211–234 (2005)
Ishak, S., Kotha, P., Alecsandru, C.: Optimization of dynamic neural network performance for short-term traffic prediction. Transp. Res. Record J. Transp. Res. Board 1836, 45–56 (2003)
Zhong, M., Sharma, S., Lingras, P.: Refining genetically designed models for improved traffic prediction on rural roads. Transp. Plan. Technol. 28(3), 213–236 (2005)
Nagare, A., Bhatia, S.: Traffic flow control using neural network. Traffic 1(2), 50–52 (2012)
Liu, S.Y., Li, D.W., Xi, Y.G., Tang, Q.F.: A short-term traffic flow forecasting method and its applications. J. Shanghai Jiaotong Univ. 20, 156–163 (2015)
Geem, Z.W., Kim, J.H., Loganathan, G.V.: A new heuristic optimization algorithm: harmony search. Simulation 76(2), 60–68 (2001)
Laña, I., Del Ser, J., Olabarrieta, I.: Understanding daily mobility patterns in urban road networks using traffic flow analytics. Network Operations and Management (NOMS), pp. 1157–1162. IEEE, Istanbul (2016)
Madrid Open Data portal. http://datos.madrid.es. Accessed 18 Nov 2016
Bäck, T., Schwefel, H.: An overview of evolutionary algorithms for parameter optimization. Evol. Comput. 1(1), 1–23 (1993)
Hu, W., Liu, Y., Li, L., Xin, S.: The short-term traffic flow prediction based on neural network. International Conference on Future Computer and Communication, pp. 293–296. IEEE, Wuhan (2010)
Vlahogianni, E.I., Karlaftis, M.G., Golias, J.C.: Spatio-temporal short-term urban traffic volume forecasting using genetically optimized modular networks. Comput. Aided Civil Infrastruct. Eng. 22, 317–325 (2007)
Jain, A.K., Mao, J., Mohiuddin, K.M.: Artificial neural networks - a tutorial. Computer 29, 31–44 (1996)
Acknowledgments
This work has been supported by the Basque Government through the ELKARTEK program (ref. KK-2015/0000080 and the BID3ABI project).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Laña, I., Del Ser, J., Vélez, M., Oregi, I. (2017). Joint Feature Selection and Parameter Tuning for Short-Term Traffic Flow Forecasting Based on Heuristically Optimized Multi-layer Neural Networks. In: Del Ser, J. (eds) Harmony Search Algorithm. ICHSA 2017. Advances in Intelligent Systems and Computing, vol 514. Springer, Singapore. https://doi.org/10.1007/978-981-10-3728-3_10
Download citation
DOI: https://doi.org/10.1007/978-981-10-3728-3_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3727-6
Online ISBN: 978-981-10-3728-3
eBook Packages: EngineeringEngineering (R0)