TRANSPORT FLOW FORECASTING MODEL BASED ON NEURAL NETWORKS FOR TRAFFIC PREDICTION ON ROADS
Abstract
In connection with the industrialization of modern society, the growth of the transport systems
of our country, an increase in certain necessary for the development of the needs of the citizens
of our country, the number of vehicles of various types continues to increase every year very
fast, causing huge traffic jams on transport roads, especially in large cities and megacities. Thus,
forecasting traffic flows is an important and necessary component of optimal traffic control in
modern conditions of transport network development. As a solution to this problem, this article
aims to analyze and describe the application of artificial intelligence methods, in particular neural
networks, which represent a modern approach to modeling in complex and nonlinear situations
that arise when predicting a traffic flow model. The shown accuracy method is based on the development
of a neural network to predict the daily traffic flow. The expected traffic flow is then compared
with the actual dataset recorded on the road section and provided by the infrastructure
manager. In fact, neural networks are able to learn from past situations and predict future situations
on the transport network. In this study, various neural network structures were examined, and the simulation results showed that the best predictions were obtained using the multilayer
perceptron architecture, which has a good generalization system with a root mean square error of
0.00927 with the current set of vehicles. The first part of the article is devoted to defining various
concepts related to the current research area, including a review of the literature on traffic prediction
and neural networks. The second part is devoted to describing the problem of traffic congestion
using forecasting problems and presenting the proposed solution method with an emphasis on
artificial neural networks as a means of forecasting demand and its various structures. Then, numerical
experiments are illustrated by analyzing the forecast results after the formation and testing
of various neural network architectures.
References
and New Challenges, IEEE Intell. Transp. Syst. Mag., 2018, Vol. 10, No. 2, pp. 93-109.
2. Zargaryan E.V., Akopdzhanyan Zh.Zh. Issledovanie avtomatizatsii kollaborativnykh robotov i
sposoby ikh primeneniya [Research of automation of collaborative robots and methods of their
application], Tekhnologii razrabotki informatsionnykh sistem TRIS-2020: Mater. X
Mezhdunarodnoy nauchno-tekhnicheskoy konferentsii [Technologies for the development of
information systems TRIS-2020. Materials of the X International Scientific and Technical
Conference], 2020, pp. 218-223.
3. Zargaryan Yu.A. Zadacha upravlyaemosti v adaptivnoy avtomatnoy obuchaemoy sisteme
upravleniya [The problem of controllability in an adaptive automaton learning control system],
Tekhnologii razrabotki informatsionnykh sistem TRIS-2020: Mater.X Mezhdunarodnoy
nauchno-tekhnicheskoy konferentsii [Technologies for the development of information systems
TRIS-2020. Materials of the X International Scientific and Technical Conference], 2020.
4. Zargaryan E.V., Zargaryan Y.A., Dmitrieva I.A., Sakharova O.N. and Pushnina I.V. Modeling
design information systems with many criteria. Information Technologies and Engineering –
APITECH – 2020, Journal of Physics: Conference Series, 2020, Vol. 2085 (3), pp. 032057(1-7).
DOI: 10.1088/1742-6596/1679/3/032057.
5. Kamarianakis Y. et Prastacos P. Forecasting Traffic Flow Conditions in an Urban Network:
Comparison of Multivariate and Univariate Approaches, Transp. Res. Rec. J. Transp. Res.
Board, Janv. 2003, Vol. 1857, No. 1, pp. 74-84.
6. Zargaryan E.V., Zargaryan Y.A., Kapc I.V., Sakharova O.N., Kalyakina I.M and Dmitrieva
I.A. Method of estimating the Pareto-optimal solutions based on the usefulness, International
Conference on Advances in Material Science and Technology - CAMSTech-2020: IOP Conf.
Series: Materials Science and Engineering, 2020, Vol. 919 (2), pp. 022027 (1-8). DOI:
10.1088/1757-899X/919/2/022027.
7. Nagatani T. The physics of traffic jams, Rep. Prog. Phys., Sept. 2002, Vol. 65, No. 9,
pp. 1331-1386.
8. Jiber M., Lamouik I., Ali Y., et Sabri M.A. Traffic flow prediction using neural network, in
2018 International Conference on Intelligent Systems and Computer Vision (ISCV), Fez, 2018,
pp. 1-4.
9. Zhang Y.et Liu Y. Comparison of Parametric and Nonparametric Techniques for Non-peak
Traffic Forecasting, 2009, Vol. 3, No. 3, pp. 7.
10. Beloglazov D., Shapovalov I., Soloviev V., Zargaryan E. The hybrid method of path planning
in non-determined environments based on potential fields, ARPN Journal of Engineering and
Applied Sciences, 2017, Vol. 12, No. 23, pp. 6762-6772.
11. Zargarjan E.V., Zargarjan Ju.A., Finaev V.I. Information support for the training of fuzzy
production account balance in the conditions of incomplete data. Innovative technologies and
didactics in teaching (ITDT-2016), Collected papers, 2016, pp. 128-138.
12. Ahmed M.S. et. Cook A.R. Analysis of Freeway Traffic Time-Series Data by Using Box-
Jenkins Techniques, pp. 9.
13. Finaev V.I., Zargaryan Yu.A., Zargaryan E.V., Solov'ev V.V. Formalizatsiya grupp
podvizhnykh ob"ektov v usloviyakh neopredelennosti dlya vybora upravlyayushchikh resheniy
[Formalization of groups of mobile objects in conditions of uncertainty for the choice of control
decisions], Informatizatsiya i svyaz' [Informatization and communication], 2016, No. 3,
pp. 56-62.
14. Slimani I., Farissi I.E.l, et Achchab S. Artificial Neural Networks for Demand Forecasting:
Application Using Moroccan Supermarket Data, 2015.
15. Slimani I., Farissi I. El, et Achchab S. Configuration and implementation of a daily artificial
neural network-based forecasting system using real supermarket data, Int. J. Logist. Syst.
Manag., 2017, Vol. 28, No. 2, pp. 144-163.
16. Pushnina I.V. Sistema upravleniya podvizhnym ob"ektom v usloviyakh neopredelennosti [The
control system of a moving object in conditions of uncertainty], Nauka i obrazovanie na
rubezhe tysyacheletiy: Sb. nauchno-issledovatel'skikh rabot [Science and education at the turn
of the millennium: A collection of research papers]. Kislovodsk, 2018, pp. 65-74.
17. Wang X., Wang C. Time series data cleaning: A survey, IEEE Access, 2020, Vol. 8, pp. 1866-1881.
DOI: 10.1109/ACCESS.2019.2962152.
18. Data-driven smart cities: Big Data, analytics, and security, 2018. Available at:
https://skelia.com/ articles/data-driven-smart-cities-big-data-analytics-and-security/ (accessed
14 september2020).
19. Kim J., Tae D., Seok J. A survey of missing data imputation using generative adversarial networks,
Proc. of the 2020 Int. Conf. on Artificial Intelligence in Information and Communication,
ICAIIC 2020, pp. 454-456. DOI: 10.1109/ICAIIC48513.2020.9065044.
20. Dmitrieva I.A., Mileshko L.P., Begun O.V., Berezhnaya A.V. Information Modernization of
The General Theory Of Environmental Safety Ensuring, IOP Conference Series: Materials
Science and Engineering. III International Scientific Conference. Krasnoyarsk, 2021,
pp. 12072.
21. Ivanova N.A., Begun O.V., Dmitrieva I.A., Mileshko L.P., Sklifus R.V. Impact Of Road
Transport on The Environmental Situation In The Urban Environment, European Proceedings
of Social and Behavioural Sciences EpSBS. Krasnoyarsk, Russia, 2021, pp. 2600-2606.
