DOI: 10.17587/prin.17.366-375

Analysis of Urban Transport Network Connectivity using a Self-Tuning Gaussian Kernel

N. D. Povaliaev, Postgraduate Student, nikita03565@gmail.com, A. Yu. Krylatov, D. Sc. (Phys. & Math.), Associate Professor, Head of Department, a.krylatov@spbu.ru, Saint Petersburg State University, Saint Petersburg, 199034, Russian Federation

Corresponding author: Nikita D. Povaliaev, Postgraduate Student, Saint Petersburg State University, Saint Petersburg, 199034, Russian Federation, E-mail: nikita03565@gmail.com

This paper considers methods for analyzing urban transportation networks based on their representation as weighted graphs reflecting travel-time characteristics. An approach to assessing the connectivity of street networks is proposed, which relies on constructing a proximity matrix using a Gaussian similarity function followed by graph-based clustering of transport links. The influence of similarity-function parameters and local scaling strategies on the properties of the resulting cluster structures, including their stability and interpretability, is analyzed. In contrast to traditional models employing a fixed smoothing parameter, a self-tuning Gaussian kernel is introduced, in which the scale parameter is defined individually for each vertex based on the characteristics of its local neighborhood. This approach enables adaptive edge weighting and allows the spatial heterogeneity of urban transportation networks to be taken into account. Functional zones of the city are identified using the Leiden algorithm, which optimizes the modularity of the cluster structure. A comparative analysis of clustering results obtained under different levels of traffic congestion is performed, reflecting changes in travel conditions from free-flow to highly congested regimes. The experimental results show that, compared with models using a fixed smoothing parameter, the proposed approach yields more stable cluster partitions of the transport graph and makes it possible to identify consistent patterns in the transformation of network connectivity as traffic conditions vary. Visualization of weight distributions and cluster structures confirms the sensitivity of the model to changes in traffic conditions. The proposed approach can be applied to the analysis of urban transport connectivity and the study of spatio-temporal patterns of urban mobility.

Keywords: self-tuning Gaussian kernel, connectivity analysis, transportation network, graph clustering, spatial data processing, traffic flow management, urban mobility, urban planning

pp. 366—375

For citation:
Povaliaev N. D., Krylatov A. Yu. Analysis of Urban Transport Network Connectivity using a Self-Tuning Gaussian Kernel, Programmnaya Ingeneria, 2026, vol. 17, no. 7, pp. 366—375. DOI: 10.17587/prin.17.366-375. (in Russian).

References:

1. Rahman Md. M., Nower N. Attention Based Deep Hybrid Networks for Traffic Flow Prediction Using Google Maps Data, Proceedings of the 2023 8th International Conference on Machine Learning Technologies, Stockholm, Sweden, ACM, 2023, pp. 74—81. DOI: 10.1145/3589883.3589894.
2. Argota Sanchez-Vaquerizo J. Getting Real: The Challenge of Building and Validating a Large-Scale Digital Twin of Barcelona's Traffic with Empirical Data, ISPRS International Journal of Geo-Information, 2021, vol. 11, no. 1, article 24. DOI: 10.3390/ijgi11010024.
3. Mostafi S., Elgazzar K. An Open Source Tool to Extract Traffic Data from Google Maps: Limitations and Challenges, 2021 International Symposium on Networks, Computers and Communications (ISNCC), Dubai, UAE, IEEE, 2021, pp. 1—8. DOI: 10.1109/ISNCC52172.2021.9615680.
4. Boeing G. OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networks, Computers, Environment and Urban Systems, 2017, vol. 65, pp. 126—139. DOI: 10.1016/j.compenvurbsys.2017.05.004.
5. Blondel V. D., Guillaume J.-L., Lambiotte R., Lefebvre E. Fast Unfolding of Communities in Large Networks, J. Stat. Mech., 2008, vol. 2008, no. 10, article P10008. DOI: 10.1088/1742-5468/2008/10/P10008.
6. Traag V. A., Waltman L., Van Eck N. J. From Louvain to Leiden: Guaranteeing Well-Connected Communities, Sci. Rep., 2019, vol. 9, no. 1, р. 5233. DOI: 10.1038/s41598-019-41695-z.
7. Povaliaev N. D., Krylatov A. Yu. Automation of Traffic Data Extraction and Processing Using Map Services, Programmnaya Ingeneria, 2025, vol. 16, no. 7, pp. 347—357. DOI: 10.17587/prin.16.347-357 (in Russian).
8. Povaliaev N. D., Krylatov A. Yu., Shatalova N. V. Methods of Cluster Analysis of Road Networks for Bottleneck Detection and Traffic Optimization, T-Comm, 2025, vol. 19, no. 7, pp. 34—40. DOI: 10.36724/2072-8735-2025-19-7-34-40 (in Russian).
9. Zelnik-Manor L., Perona P. Self-Tuning Spectral Clustering, Proceedings of the 18th International Conference on Neural Infor­mation Processing Systems (NIPS'04), Cambridge, MA, USA, MIT Press, 2004, pp. 1601—1608.
10. Boeing G., Higgs C., Liu S. et al. Using Open Data and Open-Source Software to Develop Spatial Indicators of Urban De­sign and Transport Features for Achieving Healthy and Sustainable Cities, The Lancet Global Health, 2022, vol. 10, no. 6, pp. e907— e918. DOI: 10.1016/S2214-109X(22)00072-9.
11. Boeing G. Urban Spatial Order: Street Network Orientation, Configuration, and Entropy, Applied Network Science, 2019, vol. 4, no. 1, article 67. DOI: 10.1007/s41109-019-0189-1.
12. Newman M. E. J. Modularity and Community Structure in Networks, Proc. Natl. Acad. Sci. U.S.A., 2006, vol. 103, no. 23, pp. 8577—8582. DOI: 10.1073/pnas.0601602103.
13. Lancichinetti A., Fortunato S. Community Detection Algorithms: A Comparative Analysis, Phys. Rev. E, 2009, vol. 80, no. 5, article 056117. DOI: 10.1103/PhysRevE.80.056117.
14. von Luxburg U. A Tutorial on Spectral Clustering, arXiv, 2007. DOI: 10.48550/arXiv.0711.0189.
15. Zheng H., Yang R., Xu J. Adaptive Local Clustering Over Attributed Graphs, 2025 IEEE 41st International Conference on Data Engineering (ICDE), Hong Kong, IEEE, 2025, pp. 2052—2065. DOI: 10.1109/ICDE65448.2025.00156.
16. Zeng Y., Chen J., Li Y. et al. Clustering via Adaptive and Locality-Constrained Graph Learning and Unsupervised ELM, Neurocomputing, 2020, vol. 401, pp. 224—235. DOI: 10.1016/j.neu-com.2020.03.045.
17. Hasan S., Schneider C. M., Ukkusuri S. V., Gonzalez M. C. Spatiotemporal Patterns of Urban Human Mobility, J. Stat. Phys., 2013, vol. 151, no. 1—2, pp. 304—318. DOI: 10.1007/s10955-012-0645-0.
18. Louail T., Lenormand M., Cantu Ros Oliva G. et al. From Mobile Phone Data to the Spatial Structure of Cities, Sci. Rep., 2014, vol. 4, article 5276. DOI: 10.1038/srep05276.
19. Morea F., De Stefano D. Enhancing Stability and Assessing Uncertainty in Community Detection through a Consensus-Based Approach, arXiv, 2024. DOI: 10.48550/arXiv.2408.02959.
20. Maier M., Hein M., von Luxburg U. Optimal Construction of k-Nearest-Neighbor Graphs for Identifying Noisy Clusters, Theoretical Computer Science, 2009, vol. 410, no. 19, pp. 1749—1764. DOI: 10.1016/j.tcs.2009.01.009.