GIS AS A FOUNDATION FOR INTELLIGENT TRANSPORTATION SYSTEMS
DOI:
https://doi.org/10.18372/2310-5461.69.20953Keywords:
GIS, Intelligent Transportation Systems, traffic flows, road network, map-matching, travel time, congestion indexAbstract
The effective implementation of Intelligent Transportation Systems (ITS) requires high-fidelity spatio-temporal data regarding road network states and traffic flow parameters. In practice, data is sourced from heterogeneous systems (GPS/FCD, stationary detectors, video analytics, traffic signal controllers, and digital road inventories), which vary in precision, sampling frequency, and spatial coverage, complicating their integration for real-time monitoring and control. This study demonstrates that Geographic Information Systems (GIS) provide a robust environment for unified network representation, allowing for the alignment of multi-source observations with specific road segments and time intervals. The primary objective of this research is to develop a reproducible GIS-based framework for traffic flow analysis at the segment level and to establish a standardized set of metrics suitable for ITS applications, including operational monitoring, bottleneck identification, incident impact assessment, and decision support. The methodology utilizes an oriented graph-based network model, topological verification procedures, and road segmentation into homogeneous links. The proposed pipeline incorporates map-matching algorithms for trajectory data, metric aggregation within fixed time windows (△t = 5–15 min), outlier filtering, and data sufficiency control.
The study defines a structured data format and a comprehensive set of network state metrics: speed Ve(t), intensity Qe(t), travel time te(t) = le / Ve(t), and the Congestion Index CIe(t) = te(t) / t0,e (where t0,e represents free-flow conditions). A systematic workflow is proposed, covering network preparation, temporal synchronization, quality control, and validation against ground-truth measurements, ensuring the comparability of estimates across space and time. The results are applicable for real-time congestion mapping, bottleneck ranking, analysis of anomalous/incident regimes (accidents, road closures, maintenance, weather events), and evaluating the efficiency of control measures within the ITS loop.
References
Map-matching algorithms for low-sampling-rate GPS trajectories: A review / X. Chao, S. Wang, J. Li. ISPRS International Journal of Geo-Information. 2020. Vol. 9, no. 3. Art. 186. DOI: https://doi.org/10.3390/ijgi9030186
Yu B., Yin H., Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI). 2018. P. 3634–3640.
Diffusion convolutional recurrent neural network: Data-driven traffic forecasting / Y. Li et al. Proceedings of the 6th International Conference on Learning Representations (ICLR). 2018.
Attention-based spatial–temporal graph convolutional networks for traffic flow forecasting / S. Guo et al. Proceedings of the AAAI Conference on Artificial Intelligence. 2019. Vol. 33. P. 922–929.
Graph WaveNet for deep spatial–temporal graph modeling / Z. Wu et al. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI). 2019. P. 1907–1913.
Trajectory data mining: An overview / K. Zheng et al. ACM Transactions on Intelligent Systems and Technology. 2020. Vol. 11, no. 1. Art. 1. DOI: https://doi.org/10.1145/3361746
Adaptive graph convolutional recurrent network for traffic forecasting / L. Bai et al. Advances in Neural Information Processing Systems. 2020. Vol. 33. P. 17804–17815.
Connecting the dots: Multivariate time series forecasting with graph neural networks / Z. Wu et al. Advances in Neural Information Processing Systems. 2020. Vol. 33. P. 11211–11222.
STG2Seq: Spatial-temporal graph to sequence model for multistep traffic forecasting / X. Zhou et al. Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI). 2020.
Jiang W., Luo J., Zeng W. A survey on spatio-temporal graph neural networks for traffic forecasting. arXiv. 2021. URL: https://arxiv.org/abs/2101.00000 (дата звернення: 12.03.2026).
You S., Wu J., Xiao J. Traffic prediction with spatial–temporal transformer networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2021. Vol. 35. P. 6132–6140.
A spatio-temporal graph-based deep learning framework for traffic forecasting / C. Chen et al. Transportation Research Part C: Emerging Technologies. 2021. Vol. 130. Art. 103234. DOI: https://doi.org/10.1016/j.trc.2021.103234
Li Y., Chen S., Shahabi C. Dynamic graph convolutional recurrent network for traffic forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2021. Vol. 35. P. 613–621.
Zhang J., Zheng Y., Qi D. Deep spatio-temporal graph convolutional networks for traffic forecasting: A unified perspective. IEEE Transactions on Intelligent Transportation Systems. 2022. Vol. 23, no. 6. P. 5400–5413. DOI: https://doi.org/10.1109/TITS.2021.3055906
Yuan N. J., Zheng Y., Xie X. Trajectory data mining: A survey of methods and applications. ACM Computing Surveys. 2022. Vol. 54, no. 2. Art. 29. DOI: https://doi.org/10.1145/3447970
Yang Z., Liu Y., Wang X. Travel time estimation and prediction with deep learning: A review. Transportation Research Part C: Emerging Technologies. 2023. Vol. 146. Art. 103988. DOI: https://doi.org/10.1016/j.trc.2023.103988
Chen Z., Li S., Wang Y. Recent advances in traffic forecasting with graph neural networks: A survey. IEEE Transactions on Intelligent Transportation Systems. 2024. Vol. 25, no. 4. P. 3221–3236. DOI: https://doi.org/10.1109/TITS.2023.3240893.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 К Доля
This work is licensed under a Creative Commons Attribution 4.0 International License.
The scientific journal adheres to the principles of Open Access and provides free, immediate, and permanent access to all published materials without financial, technical, or legal barriers for readers.
All articles are published in Open Access under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.
Copyright
Authors who publish their works in the journal:
-
retain the copyright to their publications;
-
grant the journal the right of first publication of the article;
-
agree to the distribution of their materials under the CC BY 4.0 license;
-
have the right to reuse, archive, and distribute their works (including in institutional and subject repositories), provided that proper reference is made to the original publication in the journal.
