Discovery of Semantic Traffic Flow Patterns Generated by the Trajectories of Moving Objects over Road Networks

Abstract

Several diverse works were proposed for the discovery of traffic flow patterns from trajectory data collected from moving objects over urban road networks using different approaches. More recently, a few works have focused on the discovery of movement patterns considering additional sources of data to spatiotemporal trajectories, referred to as semantic data. The semantic data considered in these works is associated with each spatiotemporal position from the trajectories. Modern technologies enable the collection of additional data related to each moving object or the performed trip, which could enhance available traffic flow patterns from a different context. In this work, we present a model for the discovery of high traffic flow patterns from moving objects’ trajectory data over a road network, semantically described by the moving objects or trip data associated with the trajectories. We focus on a model based on traffic flow in order to incorporate the identification of semantic description as part of the discovery of the patterns. Discovered patterns from experimentation show different advantages, for instance, allowing identification of particular semantic descriptions between close patterns in the road network. Results show the potential for improved applications of the discovered patterns based on the available semantic data, including campaigns for promoting better use of the road network and reorganization of areas considering different semantic descriptions.

Keywords

Traffic flow / moving object trajectory / semantic data / road network / data mining

References

[1] Achtert E, Kriegel H-P, Schubert E, Zimek A. Interactive data mining with 3D-parallel-coordinate-trees. Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD 2013), 2013June 22–27, 2013

[2] Benkert M, Gudmundsson J, Hübner F, Wolle T. Reporting flock patterns. Computational Geometry, 2008, 41(3): 111-125

[3] Chatziioannou I, Nikitas A, Tzouras P G, Bakogiannis E, Alvarez-Icaza L, Chias-Becerril L, Karolemeas C, Tsigdinos S, Wallgren P, Rexfelt O. Ranking sustainable urban mobility indicators and their matching transport policies to support liveable city Futures: A MICMAC approach. Transportation Research Interdisciplinary Perspectives, 2023, 18: 100788

[4] Chen B Y, Luo Y-B, Zhang Y, Jia T, Chen H-P, Gong J, Li Q. Efficient and scalable DBSCAN framework for clustering continuous trajectories in road networks. International Journal of Geographical Information Science, 2023, 37(8): 1693-1727

[5] Cormen T H, Leiserson C E, Rivest R L, Stein C. Introduction to Algorithms (3ed), 2009, USA, MIT Press

[6] Ding L, Zhang N. A travel mode choice model using individual grouping based on cluster analysis. Procedia Engineering, 2016, 137: 786-795

[7] Feng Z, Zhu Y. A survey on Trajectory Data Mining: Techniques and applications. IEEE Access, 2016, 4: 2056-2067

[8] Ferrero C A, Petry L M, Alvares L O, da Silva C L, Zalewski W, Bogorny V. MasterMovelets: Discovering heterogeneous movelets for multiple aspect trajectory classification. Data Mining and Knowledge Discovery, 2020, 34(3): 652-680

[9] Geržinič N, Cats O, van Oort N, Hoogendoorn-Lanser S, Hoogendoorn S. What is the market potential for on-demand services as a train station access mode?. Transportmetrica A: Transport Science, 2023, 20(3): 2179345

[10] Han J, Kamber M, Pei J. Data Mining: Concepts and Techniques (3ed), 2011, USA, Morgan Kaufmann

[11] Hassanvand, M (2020). Long-distance person travel: A cluster-based approach. Findings. https://doi.org/10.32866/001c.17291.

[12] Kalnis P, Mamoulis N, Bakiras S. On discovering moving clusters in spatio-temporal data. Advances in spatial and temporal databases. Lecture Notes in Computer Science, 2005, 3633: 364-381

[13] Kharrat A, Zeitouni K, Sandu-Popa I, Faiz S. Characterizing traffic density and its evolution through moving object trajectories. Proceedings of the Fifth International IEEE Conference on Signal-Image Technologies and Internet-Based Systems, 2009November 29–December 4, 2009

[14] Kohan M, Ale J M. Discovering traffic congestion through traffic flow patterns generated by moving object trajectories. Computers, Environment and Urban Systems, 2020, 80: 101426

[15] Li X, Han J, Lee J-G, Gonzalez H. Traffic density-based discovery of Hot Routes in road networks. Advances in spatial and temporal databases. Lecture Notes in Computer Science, 2007, 4605: 441-459

[16] Li Z, Ding B, Han J, Kays R. Swarm: Mining relaxed temporal moving object clusters. Proceedings of the VLDB Endowment, 2010, 3(1–2): 723-734 Singapore

[17] Liu S, Wang S, Jayarajah K, Misra A, Krishnan R. TODMIS: Mining communities from trajectories. Proceedings of the 22nd ACM International Conference on Information & Knowledge Management (CIKM’ 13), 2013October 27–November 1, 2013

[18] Liu W, Wang Z, Feng J. Continuous clustering of moving objects in spatial networks. International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (KES 2008), 2008September 3–5, 2008

[19] Liu W, Zheng Y, Chawla S, Yuan J, Xing X. Discovering spatio-temporal causal interactions in traffic data streams. Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2011August 21–24, 2011

[20] MapZen. Metro Extracts, 2017

[21] Mello R d S, Bogorny V, Alvares L O, Santana L H Z, Ferrero C A, Frozza A A, Schreiner G A, Renso C. MASTER: A multiple aspect view on trajectories. Transactions in GIS, 2019, 23(4): 805-822

[22] Ntoutsi I, Mitsou N, Marketos G. Traffic mining in a road-network: How does the traffic flow?. International Conference on Human Factors in Computing and Informatics (SouthCHI 2013), 2008July 1–3, 2008

[23] Oh G, Leblanc D J, Peng H. Vehicle Energy Dataset (VED), a large-scale dataset for vehicle energy consumption research. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(4): 3302-3312

[24] Open Source Geospatial Foundation. GeoTools the open source Java GIS toolkit, 2023

[25] Pendleton S D, Andersen H, Du X, Shen X, Meghjani M, Eng Y H, Rus D, Ang M H. Perception, planning, control, and coordination for autonomous vehicles. Machines, 2017, 5(1): 6

[26] Piorkowski M, Sarafijanovic-Djukic N, Grossglauser M (2022). CRAWDAD epfl/mobility (v.2009-02-24) (Dataset). IEEE Dataport. https://doi.org/10.15783/C7J010.

[27] Rodriguez Cote J D, Diana M. Exploring the benefits of a traveller clustering approach based on multimodality attitudes and behaviours. Transportation Research Procedia, 2017, 25: 2552-2565

[28] Sacharidis D, Patroumpas K, Terrovitis M, Kantere V, Potamias M, Mouratidis K, Sellis T. On-line discovery of hot motion paths. Proceedings of the 11th International Conference on Extending Database Technology: Advances in Database Technology (EDBT’ 08), 2008March 25–29, 2008

[29] SAE International. SAE J3016 levels of driving automation, 2019

[30] Scott M. The San Francisco Bay Area: A Metropolis in Perspective (2ed), 1985, USA, University of California Press

[31] Tan P-N, Steinbach M, Karpatne A, Kumar V. Introduction to Data Mining (2ed), 2019, USA, Pearson

[32] Tritsarolis A, Theodoropoulos G-S, Theodoridis Y. Online discovery of co-movement patterns in mobility data. International Journal of Geographical Information Science, 2021, 35(4): 819-845

[33] US Department of Energy. Electric vehicle basics, 2021

[34] Vij A, Gorripaty S, Walker J L. From trend spotting to trend’ splaining: Understanding modal preference shifts in the San Francisco Bay Area. Transportation Research Part A: Policy and Practice, 2017, 95: 238-258

[35] Wan Z, Dodge S, Bohrer G. Leveraging similarity analysis to understand variability in movement behavior. Transactions in GIS, 2023, 27(5): 1441-1466

[36] Wang S, Bao Z, Culpepper J S, Cong G. A survey on trajectory data management, analytics, and learning. ACM Computing Surveys, 2021, 54(2): 1-36

[37] Wang S, Bao Z, Culpepper J S, Sellis T, Qin X. Fast large-scale trajectory clustering. Proceedings of the VLDB Endowment, 2019, 13(1): 29-42 USA

[38] Wikimedia Foundation. Types of road. Wikipedia, 2022

[39] Yan X, Han J, Afshar R. CloSpan: Mining closed sequential patterns in large datasets. Proceedings of the 2003 SIAM International Conference on Data Mining (SDM), 2003May 1–3, 2003

[40] Yuan Q, Zhang C, Han J. A survey on spatiotemporal and semantic data mining. Trends in spatial analysis and modelling: Decision-support and planning strategies. Geotechnologies and the Environment, 2018, Switzerland, Springer435719

[41] Zhang Z, Zhao X, Zhang Y, Zhang J, Nie H, Lou Y. Efficient mining of hotspot regional patterns with multisemantic trajectories. Big Data Research, 2020, 22: 100157

[42] Zhao P, Bucher D, Martin H, Raubal M. A clustering-based framework for understanding individuals’ travel mode choice behavior. Geospatial technologies for local and regional development. International Conference on Geographic Information Science (AGILE 2019), 2020June 17–20, 2019

[43] Zheng Y. Trajectory data mining: An overview. ACM Transactions on Intelligent Systems and Technology, 2015, 6(3): 1-41

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany