Received 29.09.2022, Revised 27.10.2022, Accepted 01.12.2022

Intellectualization of traffic management as a means of increasing the efficiency of the city's transport network in emergency situations

Andriy Kashkanov, Oleh Palchevskyi

An assessment of modern trends in the development of intelligent traffic management systems and their role in ensuring the efficiency of the functioning of transport networks was carried out. The processes of introducing technologies for expanding the flow of processed data into existing intelligent transport systems (ITS) that ensure an increase in the speed of information transmission in them have been determined. The classification of information sources that become available when the ITS transitions to the 5G standard and provide a basis for the implementation of technologies for avoiding extraordinary situations in transport networks is given. 
Existing methods of improving the efficiency of the city's transport network are mainly aimed at ensuring the ability of ITS to predict traffic flows. These include statistical and nonlinear methods, simulation-based methods, artificial intelligence methods, and combined methods. The implementation of these methods is achieved by increasing the information flow coming from the system. A comparison of these methods revealed that they can generally make predictions with high accuracy, however, regardless of the chosen standard, some of them are already at the peak of their potential in terms of application in ITS, and the rest still have room for development. 
The suitability of the forecasting method for working in real-time conditions is a significant advantage in ensuring effective management of traffic flows, allows to increase the stability of the transport network and the efficiency of the ITS, and has a positive effect on the level of traffic jams, road safety and ecological impact on the environment. The most promising in terms of a quick and flexible solution to an extraordinary situation are models with the use of artificial intelligence or a combination thereof, based on deep learning algorithms, which have proven their importance in predicting the results, making decisions regarding traffic flow forecasts and ensuring the elimination and avoidance of traffic jams based on the passage of vehicles through the intersection depending on the length and duration of the traffic light signals

 

intelligent transport systems, transport networks, traffic forecasting, traffic management, information flows, extraordinary situations
42-50
Kashkanov, A., & Palchevskyi, O. (2022). Intellectualization of traffic management as a means of increasing the efficiency of the city's transport network in emergency situations . Journal of Mechanical Engineering and Transport, 8(2), 42-50. https://doi.org/10.31649/2413-4503-2022-16-2-42-50

References

[1] European Union. (n.d.). Safe, sustainable and connected transport. Retrieved from https://europa.eu/european-union/topics/transport_en.

[2] Mena-Oreja, J., & Gozalvez, J. (2020). A comprehensive evaluation of deep learning-based techniques for traffic prediction. IEEE Access, 8, 1-25. doi: 10.1109/ACCESS.2020.2994415.

[3] Aulin, V.V., Grinkov, A.V., & Golovaty A.O. (2020). Methodological basis for the design and functioning of intelligent transport and transmission systems. Kropyvnytskyi: V.F. Lisenko

[4] Kashkanov, A.A., & Palchevsky, O.V. (2022). Problems of functioning of transport systems of great cities of Ukraine in current minds. Current Technologies in Mechanical Transport, 1(18), 97-102. doi: 10.36910/automash.v1i18.764.

[5] Semchenko, N.O., & Reshetnikov, E.B. (2018). Investigation of the parameters of the management of groups of transport facilities on the street-road boundary of the city. Communal Government of the City, 7(146), 12-19. doi: 10.33042/2522-1809-2018-7-146-12-19.

[6] Official website of the Ukrainian Patrol Police. (n.d.). Statistics. Retrieved from http://patrol.police.gov.ua/statystyka.

[7] Implementing an intelligent transportation system: A bottom-up approach to value creation.(n.d.). Retrieved from https://intellias.com/implementingintelligent-transportation-system.

[8] Tahir, M.N., Leviäkangas, P., & Katz, M. (2022). Connected vehicles: V2V and V2I road weather and traffic communication using cellular technologies. Sensors, 22(3), article number 1142. doi: 10.3390/s22031142.

[9] Hui, M., Bai, L., Li, Y., & Wu, Q. (2015). Highway traffic flow nonlinear character analysis and prediction. Mathematical Problems in Engineering, 8. doi: 10.1155/2015/902191.

[10] Emami, A., Sarvi, M., & Bagloee, S.A. (2019). Using Kalman filter for short-term traffic flow prediction in a connected vehicle environment. Journal of Modern Transportation, 27, 222-232. doi: 10.1007/s40534-019-0193-2.

[11] Chaudhary, S., & Chaudhary, S. (2017). Video-based road traffic monitoring and prediction using dynamic bayesian networks. IET Intelligent Transport Systems, 12(3). doi: 10.1049/iet-its.2016.0336.

[12] Kaelblinga, L.P., Littman, M.L., & Cassandrac, A.R. (1998). Planning and acting in partially observable stochastic domains. Artificial Intelligence, 101(1-2), 99-134.

[13] Doshi-Velez, F., Wingate, D., & Tenenbaum, J.B. (2011). Infinite dynamic Bayesian networks. In Proceeding of the 28th internet conference machine learning, (ICML 2011) (pp. 913-920). Washington: IMLS.

[14] Nasser, A., & Simon, V. (2022). Wavelet‐attention‐based traffic prediction for smart cities. IET Smart Cities, 4(1), 3-16. doi: 10.1049/smc2.12018.

[15] Yuanqing, W., & Jing, L. (2017). Study of rainfall impacts on freeway traffic flow characteristics. Transportation Reseach Procedia, 25, 1533-1543. doi: 10.1016/j.trpro.2017.05.180.

[16] Wang, C., Pang, X., Xi, Z., & Si, G. (2019). An elastic combination forecasting method for urban road traffic status. Journal of Physics: Conference Series, 1237, article number 022027. doi: 10.1088/1742-6596/1237/2/022027.

[17] Ciont, N., Cadar, R.D., & Cimpean, D.S. (2018). A road traffic prediction study based on weigh-in-motion data. Proceedings of the Romanian Academy Series A, 19, 567-574.

[18] Fareeduddeen, V.M., Sreerambabu, J., & Riyaz, M.M. (2022). Traffic prediction for intelligent transportation system using machine learning. International Journal for Research in Applied Science & Engineering Technology, 10(8), 922-925. doi: 10.22214/ijraset.2022.46306.

[19] Geetha, V., Gomathy, C.K., Thommandru, H., & Varma, P.V.N. (2021). A traffic prediction for intelligent transportation system using machine learning. International Journal of Engineering and Advanced Technology, 10(4), 166-168. doi: 10.35940/ijeat.D2426.0410421.

[20] Yogita, B., & Raghavendra, P. (2022). Traffic prediction for intelligent transportation system using deep learning. International Journal of Research in Engineering, Science and Management, 7(5), 61-62.

[21] Qiu, X., Zhang, L., Ren, Y., Suganthan, P., & Amaratunga, G. (2014). Ensemble deep learning for regression and time series forecasting. In 2014 IEEE Symposium on computational intelligence in ensemble learning (CIEL) (pp. 1-6). Orlando: IEEE. https://doi.org/10.1109/CIEL.2014.7015739.

[22] Zhang, Q., Wang, H., Dong, J., Zhong, G., & Sun, X. (2017). Prediction of sea surface temperature using long short-term memory. IEEE Geoscience and Remote Sensing Letters, 14(10), 1745-1749. doi: 10.1109/LGRS.2017.2733548.

[23] Sagheer, A., & Kotb, M. (2019). Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing, 323, 203-213. doi: 10.1016/j.neucom.2018.09.082.

[24] Luo, X., Li, D., Yang, Y., & Zhang, S. (2019). Spatiotemporal traffic flow prediction with KNN and LSTM. Journal of Advanced Transportation, 5, article number 4145353. doi: 10.1155/2019/4145353.