Abstract
The problem of neural network forecasting of processes with changing laws of their behavior and imperfection of time-series samples is considered on the example of analysis of urban traffic flows. The goal is to improve the accuracy of such forecasting. To achieve this goal, we analyze the applicability of self-learning recurrent neural networks with controlled elements and the spiral structure of layers. Based on the development and application of these neural networks, the new methods and the system implementing them are proposed. These methods, in contrast to known solutions, allow continuous training of neural networks and forecasting of processes. There is no need to interrupt training to perform forecasting. For forecasting, it is possible to continuously take into account the properties of the observed processes. In addition, improved controlling of associative recall of information from the memory of recurrent neural networks is provided to improve the accuracy of forecasting. The results of traffic flow forecasting are presented. The results are compared with estimates obtained using other methods. It is shown that the proposed methods have advantages in accuracy compared to the known solutions. The developed methods are recommended for use in advanced robotic and other intelligent systems.
Similar content being viewed by others
References
Naderpour H, Mirrashid M (2020) Bio-inspired predictive models for shear strength of reinforced concrete beams having steel stirrups. Soft Comput. https://doi.org/10.1007/s00500-020-04698-x
Naderpour H, Mirrashid M (2020) Proposed soft computing models for moment capacity prediction of reinforced concrete columns. Soft Comput. https://doi.org/10.1007/s00500-019-04634-8
Lu H, Tang H, Wang Z (eds) (2019) Advances in neural networks—ISNN 2019. LNCS 11554. Springer, Berlin. https://doi.org/10.1007/978-3-030-22796-8
Haykin S (2008) Neural networks and learning machines, 3rd edn. Prentice Hall, New-York
Rezaeianzadeh M, Tabari H, ArabiYazdi A, Isik S, Kalin L (2014) Flood flow forecasting using ANN, ANFIS and regression models. Neural Comput Appl 25:25. https://doi.org/10.1007/s00521-013-1443-6
Saâdaoui F, Saadaoui H, Rabbouch H (2019) Hybrid feedforward ANN with NLS-based regression curve fitting for US air traffic forecasting. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04539-5
Naser M, Abu-Lebden G, Hawileh R (2012) Analysis of RC T-beams strengthened with CFRP plates under fire loading using ANN. Constr Build Mater 37:301–309. https://doi.org/10.1016/j.conbuildmat.2012.07.001
Gairaa Kacem, Khellaf Abdallah, Messlem Youcef, Chellali Farouk (2016) Estimation of the daily global solar radiation based on Box–Jenkins and ANN models: a combined approach. Renew Sustain Energy Rev 57:238–249. https://doi.org/10.1016/j.rser.2015.12.111
Shen Z, Wang W, Shen Q et al (2019) A novel learning method for multi-intersections aware traffic flow forecasting. Neurocomputing. https://doi.org/10.1016/j.neucom.2019.04.094
Hu W, Wang Y, Qiu Z, Yan L, Nie C, Du B (2018) An urban traffic simulation model for traffic congestion predicting and avoiding. Neural Comput Appl 30:1769–1781. https://doi.org/10.1007/s00521-016-2785-7
Goudarzi S, Kama MN, Anisi MH, Soleymani SA, Doctor F (2018) Self-organizing traffic flow prediction with an optimized deep belief network for Internet of vehicles. Sensors 18:3459. https://doi.org/10.3390/s18103459
Wu Y, Tan H, Qin L, Ran B, Jiang Z (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res Part C 90:166–180. https://doi.org/10.1016/j.trc.2018.03.001
Skorobogatchenko DA, Stepanova PYu (2017) Application of artificial neural networks with short-term prediction of the level of loading of urban automobile roads. IZVESTIYa VolgGTU 4(209):24–30
Shumway RH, Stoffer DS (2011) Time series analysis and its applications, 3rd edn. Springer, Berlin
Hyndman RJ, Athanasopoulos G (2018) Forecasting: principles and practice, 2nd edn. OTexts, Melbourne
Polson NG, Sokolov VO (2017) Deep learning for short-term traffic flow prediction. Transp Res Part C 79:1–17. https://doi.org/10.1016/j.trc.2017.02.024
Li H (2016) Research on prediction of traffic flow based on dynamic fuzzy neural networks. Neural Comput Appl 27:1969–1980. https://doi.org/10.1007/s00521-015-1991-z
Sarıca B, Egrioglu E, Asıkgil B (2018) A new hybrid method for time series forecasting: AR–ANFIS. Neural Comput Appl 29:749–760. https://doi.org/10.1007/s00521-016-2475-5
Zhou T, Han G, Xu X, Lin Z, Han C, Huang Y, Qin J (2017) δ-agree AdaBoost stacked autoencoder for short-term traffic flow forecasting. Neurocomputing 247:31–38. https://doi.org/10.1016/j.neucom.2017.03.049
Egrioglu E, Yolcu U, Bas E, Dalar AZ (2019) Median-Pi artificial neural network for forecasting. Neural Comput Appl 31:307–316. https://doi.org/10.1007/s00521-017-3002-z
Moretti F, Pizzuti S, Panzieri S, Annunziato M (2015) Urban traffic flow forecasting through statistical and neural network bagging ensemble hybrid modeling. Neurocomputing 167:3–7. https://doi.org/10.1016/j.neucom.2014.08.100
Krichene E, Masmoudi Y, Alimi AM, Abraham A, Chabchoub H (2017) Forecasting using Elman recurrent neural network. In: Madureira A, Abraham A, Gamboa D, Novais P (eds) Intelligent systems design and applications. ISDA 2016. Advances in intelligent systems and computing, vol 557. Springer, Berlin. https://doi.org/10.1007/978-3-319-53480-0_48
Prokoptsev NG, Alekseenko AE, Kholodov Ya A (2018) Traffic flow speed prediction on transportation graph with convolutional neural networks. Comput Res Model 10(3):359–367. https://doi.org/10.20537/2076-7633-2018-10-3-359-367
Yang B, Sun S, Li J, Lin X, Tian Y (2019) Traffic flow prediction using LSTM with feature enhancement. Neurocomputing 332:320–327. https://doi.org/10.1016/j.neucom.2018.12.016
Tian Y, Zhang K, Li J, Lin X, Yang B (2018) LSTM-based traffic flow prediction with missing data. Neurocomputing 318:297–305. https://doi.org/10.1016/j.neucom.2018.08.067
Ghaderi A, Sanandaji BM, Ghaderi F (2017) Deep forecast: deep learning-based spatio-temporal forecasting. In: Proceedings of the ICML, pp 264–271
Lv Y, Duan Y, Kang W, Li Z, Wang F-Y (2015) Traffic flow prediction with Big Data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873
Dai X, Fu R, Lin Y, Wang F-Y, Li L (2017) DeepTrend: a deep hierarchical neural network for traffic flow prediction. In: 2017 IEEE 20th international conference on intelligent transportation systems (ITSC). IEEE, pp 394–399
Mori U, Mendiburu A, Álvarez M, Lozan JA (2015) A review of travel time estimation and forecasting for advanced traveller information systems. Transp A Transp Sci. https://doi.org/10.1080/23249935.2014.932469
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117. https://doi.org/10.1016/j.neunet.2014.09.003
Fernandez-Navarro M, de la Cruz MA, Gutierrez PA, Castano A, Hervas-Martınez C (2018) Time series forecasting by recurrent product unit neural networks. Neural Comput Appl 29:779–791. https://doi.org/10.1007/s00521-016-2494-2
Osipov V, Osipova M (2018) Space–time signal binding in recurrent neural networks with controlled elements. Neurocomputing 308:194–204. https://doi.org/10.1016/j.neucom.2018.05.009
Osipov V (2016) Space–time structures of recurrent neural networks with controlled synapses. In: Cheng L et al (eds) Advances in neural networks, LNCS 9719. Springer, Cham, pp 177–184. https://doi.org/10.1007/978-3-319-40663-3_21
Osipov V, Nikiforov V (2018) Formal aspects of streaming recurrent neural networks. In: Huang T et al (eds) Advances in neural networks, LNCS 10878. Springer, Cham, pp 29–36. https://doi.org/10.1007/978-3-319-92537-0_4
V. Osipov, Method and apparatus for intelligent information processing in neural network. Patent RU2446463 (2012), Patent RU2502133 (2013), Patent RU2514931 (2014), Patent RU 2553074 (2015). https://worldwide.espacenet.com
Osipov VYu (2015) Neural network prediction of events for intelligent robots. Mekhatronika Avtomatizatsiya Upravlenie 16(12):836–840. https://doi.org/10.17587/mau.16.836-840
http://www.d.umn.edu/~tkwon/TMCdata/TMCarchive.html. Accessed 17 Dec 2019
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Osipov, V., Nikiforov, V., Zhukova, N. et al. Urban traffic flows forecasting by recurrent neural networks with spiral structures of layers. Neural Comput & Applic 32, 14885–14897 (2020). https://doi.org/10.1007/s00521-020-04843-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-04843-5