Possibility of applying geoinformation multiagent optimisation for planning the development of road networks

• Autorzy: Hutsul Taras , Karpinskyi Yurii

Identyfikatory

DOI

10.2478/rgg-2021-0002

• Języki publikacji: EN

Abstrakty

EN

In recent years, computational intelligence has been used to solve optimisation problems. An innovative direction in the development of artificial intelligence methods is multiagent methods of intellectual optimisation, which simulate the collective behaviour of insects, animals and other living beings. It indicates the effectiveness of their behaviour, and hence the effectiveness of these methods, and the ability to be involved in solving applied problems. This article is devoted to the study of the development of road transport networks using the metaheuristic ant method of optimisation based on a number of data. The initial data were geospatial layers of information on slope steepness, engineering structures, forests, perennials, land development and hydrographic objects. The parameters of the behaviour of the studied method under different conditions and volumes of input geospatial data are experimentally established. The Max–Min method of multiagent optimisation is modified. The proposed modification takes into account the functional distance – the coefficient of the complexity of the route, which affects its length. This modification had an effective influence on the behaviour of ants and the choice of optimal routes, taking into account the terrain as one of the factors. The result of the advancement is an informational system, which is capable of formulating flexible options for passing optimal alternative routes between specified settlements.

Słowa kluczowe

EN

geographic information system; road design route; ant method optimisation; transport network

PL

system informacji geograficznej; projektowanie dróg; optymalizacja; sieć transportowa

• Wydawca: Wydział Geodezji i Kartografii Politechniki Warszawskiej
• Czasopismo: Reports on Geodesy and Geoinformatics
• Rocznik: 2021
• Tom: Vol. 112
• Strony: 1--8
• Opis fizyczny: Bibliogr. 24 poz., rys., tab., wykr.

Twórcy

autor

Hutsul Taras

• Educational and Scientific Institute of Biology, Chemistry and Bioresources, Chernivtsi National University, Department of LandManagement and Cadastre, St. Lesya Ukrainka, 25, Chernivtsi, Ukraine

• https://orcid.org/0000-0002-7192-3289

autor

Karpinskyi Yurii

• Kyiv National University of Construction and Architecture, Faculty of Geoinformation Systems and Territorial Management, Department of Geoinformatics and Photogrammetry, St. Osvity, 5, Kyiv, Ukraine

• https://orcid.org/0000-0002-0701-1277

Bibliografia

• [1] Burshtynska, H. (2001). Comparative analysis of the construction of digital terrain models using approximation functions. Geodesy, cartography and ariel photography, 61:137-148.
• [2] Chulin, H. and Geng, K. K. (2016). Route planning based on cloud-points maps and improved ant-colony algorithm. Technical Sciences, Izvestiya Tula State University, pages 80-88.
• [3] Dorigo, M. and Stützle, T. (2010). Ant Colony Optimization: Overview and Recent Advances, pages 227-263. Springer US, Boston, MA, doi: 10.1007/978-1-4419-1665-5_8.
• [4] Huang, G., Cai, Y., and Cai, H. (2018). Multi-agent ant colony optimization for vehicle routing problem with soft time windows and road condition. In MATEC web of conferences, volume 173, page 02020. EDP Sciences, doi: 10.1051/matecconf/201817302020.
• [5] Hulianytskyi, L. (2017). Search diversification in ant colony optimization algorithms. Theory of optimal solutions, 1:47-57.
• [6] Hutsul, T. (2018). Productivity analysis and special conditions of the functioning of the method of geoinformation multiagent optimization of the planning of transport flows of the road network. Urban Planning and Spatial Planning, 68:689-705.
• [7] Hutsul, T. and Smirnov, Y. (2017). Comparative accuracy assessment of global dtm and dtm generated from soviet topographic maps for the purposes of road planning. Geodesy and Cartography, 43(4):173-181, doi: doi.org/10.3846/20296991.2017.1412638.
• [8] Kalamdhad, A. S., Singh, J., and Dhamodharan, K. (2016). Advances in waste management. Select Proceedings of Recycle, Springer.
• [9] Karadimas, N. V., Kolokathi, M., Defteraiou, G., and Loumos, V. (2007). Ant colony system vs arcgis network analyst: the case of municipal solid waste collection. In 5th WSEAS international conference on environment, ecosystems and development, pages 128-34. Citeseer, doi: doi.org/10.13140/2.1.3676.9600.
• [10] Khazin, V. (2012). Principles of tracing bypass roads around settlements. Urban Planning and Spatial Planning, 45(3):159-164.
• [11] Kochegurova, E., Martynov, Y., Martynova, Y., and Tsapko, S. (2014). Ant colony algorithm for rational route network design of urban public transport. VestnikSibGUTI, 27(3):89-100.
• [12] Kuzmin, I. and Lotysh, V. (2012). Ant algorithms. Computer-integrated technologies: education, science, production, 9:61-66.
• [13] Lyashchenko, A. (2002). Conceptual modeling of geographic information systems. Bulletin of Geodesy and Cartography, 4:44-50.
• [14] Masoumi, Z., Van Genderen, J., and Sadeghi Niaraki, A. (2021). An improved ant colony optimization-based algorithm for user-centric multi-objective path planning for ubiquitous environments. Geocarto International, 36(2):137-154, doi: 10.1080/10106049.2019.1595176.
• [15] Muliarevych, O. (2016). Solving dynamic travelling salesman problem using and colony behavior model in multiagent systems. PhD thesis, Lviv Polytechnic National University.
• [16] Qiu, Y. and Xu, X. (2018). Rpsbpt: A route planning scheme with best profit for taxi. In 2018 14th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN), pages 121-126. IEEE, doi: 10.1109/MSN.2018.00027.
• [17] Shtovba, S. (2004). Ant optimization algorithms. Visnyk VNTU, 4:62-69.
• [18] Shuts, V. (2014). Multiagent motion control vehicles in the road network of the city. Iskusstvennyi Intellekt, (4):123-128.
• [19] Subbotin, S., Oleynik, A., and Oleynik, O. (2009). Non-iterative, evolutionary and multiagent methods for the synthesis of fuzzy and neural network models. ZNTU, Zaporozhye.
• [20] Vardomatskaja, A., Sharstniou, U., and Alekseeva, Y. (2016). Route optimization using graph theory in the application package. Vestnik of Vitebsk State Technological University, 30(1):130-139.
• [21] Vodák, R., Bíl, M., and Křivánková, Z. (2018). A modified ant colony optimization algorithm to increase the speed of the road network recovery process after disasters. International journal of disaster risk reduction, 31:1092-1106, doi: doi.org/10.1016/j.ijdrr.2018.04.004.
• [22] Yamamoto, K. and Li, X. (2018). A safety evaluation method of evacuation routes in urban areas in case of earthquake disasters using ant colony optimization and geographic information systems (short paper). In 10th International Conference on Geographic Information Science (GIScience 2018). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, doi: 10.4230/LIPIcs.GISCIENCE.2018.68.
• [23] Yu, K.-M., Lee, M.-G., and Chi, S.-S. (2017). Dynamic path planning based on adaptable ant colony optimization algorithm. In 2017 Sixth International Conference on Future Generation Communication Technologies (FGCT), pages 1-7. IEEE, doi: 10.1109/FGCT.2017.8103732.
• [24] Zhang, M., Jiang, Z., Wang, L., and Yao, Y. (2017). Research on parallel ant colony algorithm for 3d terrain path planning. In Asian Simulation Conference, pages 74-82. Springer, doi: 10.1007/978-981-10-6463-0_7.