Skip to main content

Speed Transition Matrix Feature Extraction for Traffic State Estimation Using Machine Learning Algorithms

  • Chapter
  • First Online:
The Science and Development of Transport—ZIRP 2021

Abstract

Feature extraction is a crucial part of data preparation when using machine learning algorithms, especially for emerging datasets. The speed transition matrix (STM) emerged only recently as a traffic data modeling technique. In this paper, key features from STMs are extracted and proposed for the purpose of traffic state estimation. This step simplifies the learning process and the interpretability of the results obtained when estimating the traffic state using the STMs. Using the proposed features, traffic state is estimated for the most crucial road segments in the City of Zagreb, Croatia. The method is evaluated on some of the most used machine learning algorithms, with the highest accuracy value obtained with decision tree and random forest algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 119.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 159.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 159.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Cvetek D, Muštra M, Jelušić N, Tišljarić L (2021) A survey of methods and technologies for congestion estimation based on multisource data fusion. Appl Sci (Switzerland) 11:2306. https://doi.org/10.3390/app11052306

  2. Erdelić T, Carić T, Erdelić M et al (2021) Estimating congestion zones and travel time indexes based on the floating car data. Comput Environ Urban Syst 87:101604. https://doi.org/10.1016/j.compenvurbsys.2021.101604

  3. Ermagun A, Levinson DM (2019) Development and application of the network weight matrix to predict traffic flow for congested and uncongested conditions. Environ Plan B Urban Anal City Sci 46:1684–1705. https://doi.org/10.1177/2399808318763368

    Article  Google Scholar 

  4. Harris CR, Millman KJ, van der Walt SJ et al (2020) Array programming with NumPy. Nature 585:357–362. https://doi.org/10.1038/s41586-020-2649-2

    Article  Google Scholar 

  5. HCM (2010) Highway capacity manual, 5th edn. Transportation Research Board, National Research Council, Washington, DC

    Google Scholar 

  6. Ma X, Dai Z, He Z et al (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors (Switzerland) 17:1–16. https://doi.org/10.3390/s17040818

    Article  Google Scholar 

  7. Mandžuka S, Ivanjko E, Vujić M et al (2016) The use of cooperative ITS in urban traffic management. In: Perallos A, Hernandez-Jayo U, Onieva E, García-Zuazola IJ (eds) Intelligent transport systems: technologies and applications. Wiley, New Jersey, SAD, pp 272–288

    Google Scholar 

  8. McKinney W (2010) Data structures for statistical computing in Python. In: van der Walt S, Millman J (eds) Proceedings of the 9th Python in science conference, pp 56–61

    Google Scholar 

  9. Nguyen TT, Krishnakumari P, Calvert SC et al (2019) Feature extraction and clustering analysis of highway congestion. Transp Res Part C Emerg Technol 100:238–258. https://doi.org/10.1016/j.trc.2019.01.017

    Article  Google Scholar 

  10. Pavlyuk D (2019) Feature selection and extraction in spatiotemporal traffic forecasting: a systematic literature review. Eur Transp Res Rev 11. https://doi.org/10.1186/s12544-019-0345-9

  11. Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830

    MathSciNet  MATH  Google Scholar 

  12. Tišljarić L (2021) Speed transition matrix feature extraction. GitHub repository. https://github.com/tisljaricleo/stm-feature-extraction

  13. Tišljarić L, Carić T, Abramović B, Fratrović T (2020a) Traffic state estimation and classification on citywide scale using speed transition matrices. Sustainability 12:7278. https://doi.org/10.3390/su12187278

  14. Tišljarić L, Fernandes S, Carić T, Gama J (2020b) Spatiotemporal traffic anomaly detection on urban road network using tensor decomposition method. In: Appice A, Tsoumakas G, Manolopoulos Y, Matwin S (eds) Discovery science. Lecture notes in computer science. Springer, Cham, pp 674–688

    Google Scholar 

  15. Tišljarić L, Majstorović Ž, Erdelić T, Carić T (2020c) Measure for traffic anomaly detection on the urban roads using speed transition matrices. In: Proceedings of international convention on information and communication technology, electronics and microelectronics, Opatija, pp 268–275

    Google Scholar 

  16. Vrbanić F, Ivanjko E, Kušić K, Čakija D (2021) Variable speed limit and ramp metering for mixed traffic flows: a review and open questions. Appl Sci (Switzerland) 11:1–26. https://doi.org/10.3390/app11062574

    Article  Google Scholar 

  17. Xu L, Wang Y, Yu H, Li H (2015) Feature extraction of urban traffic network data based on locally sensitive discriminant analysis algorithm. In: 15th COTA international conference of transportation, Beijing, pp 2192–2203

    Google Scholar 

  18. Yu H, Wu Z, Wang S et al (2017) Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks. Sensors (Switzerland) 17:1–16. https://doi.org/10.3390/s17071501

    Article  Google Scholar 

Download references

Acknowledgements

This research has been supported by the University of Zagreb, Student Center, as part of the project “Znanstveno-istraživačke aktivnosti studentske istraživačke skupine SIS-DVA,” European Regional Development Fund under the grant KK.01.1.1.01.0009 (DATACROSS), and the University of Zagreb Support Program for scientific and artistic research year 2021 short-term support: “Innovative control strategies for sustainable mobility in smart cities.” Data used for this research are collected during project SORDITO, European Regional Development Fund under contract RC.2.2.08-0022.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Leo Tišljarić .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Tišljarić, L., Ribić, F., Majstorović, Ž., Carić, T. (2022). Speed Transition Matrix Feature Extraction for Traffic State Estimation Using Machine Learning Algorithms. In: Petrović, M., Novačko, L., Božić, D., Rožić, T. (eds) The Science and Development of Transport—ZIRP 2021. Springer, Cham. https://doi.org/10.1007/978-3-030-97528-9_5

Download citation

Publish with us

Policies and ethics