Skip to main content
SpringerLink
Log in

Short-term prediction of traffic flow using a binary neural network

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

This paper introduces a binary neural network-based prediction algorithm incorporating both spatial and temporal characteristics into the prediction process. The algorithm is used to predict short-term traffic flow by combining information from multiple traffic sensors (spatial lag) and time series prediction (temporal lag). It extends previously developed Advanced Uncertain Reasoning Architecture (AURA) k-nearest neighbour (k-NN) techniques. Our task was to produce a fast and accurate traffic flow predictor. The AURA k-NN predictor is comparable to other machine learning techniques with respect to recall accuracy but is able to train and predict rapidly. We incorporated consistency evaluations to determine whether the AURA k-NN has an ideal algorithmic configuration or an ideal data configuration or whether the settings needed to be varied for each data set. The results agree with previous research in that settings must be bespoke for each data set. This configuration process requires rapid and scalable learning to allow the predictor to be set-up for new data. The fast processing abilities of the AURA k-NN ensure this combinatorial optimisation will be computationally feasible for real-world applications. We intend to use the predictor to proactively manage traffic by predicting traffic volumes to anticipate traffic network problems.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Abbreviations

Variable:

One feature of a traffic data vector, for example the flow value from a sensor

Attribute:

One time slice of one variable, for example the flow value from a sensor 5 min ago

References

  1. Gorry G, Scott-Morton M (1971) A framework for management information systems. Sloan Manag Rev 13(1):55–70

    Google Scholar 

  2. Glover P, Rooke A, Graham A (2008) Flow diagram. Think Highw 3(3):20–23

    Google Scholar 

  3. Schelter B, Winterhalder M, Timmer J (2006) Handbook of time series analysis: recent theoretical developments and applications, Wiley-VCH, ISBN: 978-3-527-40623-4

  4. Ding A, Zhao X, Jiao L (2002) Traffic flow time series prediction based on statistics learning theory. In: Proceedings IEEE 5th International conference on intelligent transportation systems, pp 727–730

  5. Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New York. ISBN 0387987800

    Book  MATH  Google Scholar 

  6. Box G, Jenkins G (1976) Time series analysis: forecasting and control. Holden-Day, San Francisco

    MATH  Google Scholar 

  7. Hamed M, Al-Masaeid H (1995) Short-term prediction of traffic volume in urban arterials. J Transp Eng (ASCE) 121(3):249–254

    Article  Google Scholar 

  8. Williams B, Durvasula P, Brown D (1998) Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transp Res Rec: J Transp Res Board 1644:132–141

    Article  Google Scholar 

  9. Ghosh B, Basu B, O’Mahony M (2007) Bayesian time-series model for short-term traffic flow forecasting. J Transp Eng (ASCE) 133(3):180–189

    Article  Google Scholar 

  10. Amin S, Rodin E, Liu A-P, Rink K (1998) Traffic prediction and management via RBF neural nets and semantic control. J Comput Aided Civ Infrastruct Eng 13:315–327

    Article  Google Scholar 

  11. Vlahogianni E, Karlaftis M, Golias J (2005) Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach. Transp Res Part C: Emerg Technol 13(3):211–234

    Article  Google Scholar 

  12. Abdulhai B, Porwal H, Recker W (2002) Short-term traffic flow prediction using neuro-genetic algorithms. J Intell Transp Sys: Technol Plan Oper 7(1):3–41

    Article  MATH  Google Scholar 

  13. Martinetz T, Berkovich S, Schulten K (1993) Neural-gas network for vector quantization and its application to time-series prediction. IEEE Trans Neural Netw 4(4):558–569

    Article  Google Scholar 

  14. Zhang, C, Sun, S, Yu G (2004) Short-term traffic flow forecasting using expanded Bayesian network for incomplete data. In: Proceedings international symposium on neural networks, Dalian, China. Lecture Notes in Computer Science, (LNCS 3174), Springer-Verlag

  15. Kindzerske M, Ni D (2007) A composite nearest neighbor nonparametric regression to improve traffic prediction. Transp Res Rec: J Transp Res Board 1993:30–35

    Article  Google Scholar 

  16. Yakowitz S (1987) Nearest-neighbour methods for time series analysis. J Time Ser Anal 8(2):235–247

    Article  MATH  MathSciNet  Google Scholar 

  17. Krishnan R, Polak J (2008) Short-term travel time prediction: An overview of methods and recurring themes. In: Proceedings transportation planning and implementation methodologies for developing countries conference (TPMDC 2008), Mumbai, India, December 3–6. CD-ROM

  18. Kamarianakis Y, Prastacos P (2003) Forecasting traffic flow conditions in an urban network: comparison of multivariate and univariate approaches. Transp Res Rec: J Transp Res Board 1857:74–84

    Article  Google Scholar 

  19. Hodge V, Jackson T, Austin J (2012) A binary neural network framework for attribute selection and prediction. In: Proceedings 4th international conference on neural computation theory and applications (NCTA 2012), SciTePress, Barcelona, pp 510–515

  20. Hodge V, Austin J (2012) Discretisation of data in a binary neural k-nearest neighbour algorithm. Tech Report YCS-2012-473, Department of Computer Science, University of York, UK

  21. Hodge V, Austin J (2005) A binary neural k-nearest neighbour technique. Knowl Inf Syst 8(3):276–292

    Article  Google Scholar 

  22. Austin J, Kennedy J, Lees K (1998) The advanced uncertain reasoning architecture, AURA. In: RAM-based neural networks, Ser Progress in Neural Processing. World Scientific Publishing, 9: 43–50

  23. Hodge V, Krishnan R, Austin J, Polak J (2010) A computationally efficient method for online identification of traffic incidents and network equipment failures. Presented at, 3rd transport science and technology congress: TRANSTEC 2010, New Delhi, April 4–7

  24. Krishnan R, Hodge V, Austin J, Polak J (2010a) A computationally efficient method for online identification of traffic control intervention measures. 42nd annual UTSG conference, centre for sustainable transport, University of Plymouth, UK, 5–7 Jan 2010

  25. Krishnan R, Hodge V, Austin J, Polak J, Lee T-C (2010b) On identifying spatial traffic patterns using advanced pattern matching techniques. In: Transportation Research Board (TRB) 89th annual meeting, Washington, DC, 10–14 Jan 2010. (DVD-ROM: 2010 TRB 89th annual meeting: compendium of papers)

  26. Hebb D (1949) The organization of behavior: a neuropsychological theory. Wiley, New York

    Google Scholar 

  27. Hodge V, Austin J (2001) An evaluation of standard retrieval algorithms and a binary neural approach. Neural Netw 14(3):287–303

    Article  Google Scholar 

  28. Bentz H, Hagstroem M, Palm G (1989) Information storage and effective data retrieval in sparse matrices. Neural Netw 2(4):289–293

    Article  Google Scholar 

  29. Austin J (1995) Distributed associative memories for high speed symbolic reasoning. In: Sun R, Alexandre F (eds) IJCAI’95 working notes of workshop on connectionist-symbolic integration: from unified to hybrid approaches. Montreal, Quebec, pp 87–93

    Google Scholar 

  30. Weeks M, Hodge V, O’Keefe S, Austin J, Lees K (2003) Improved AURA k-nearest neighbour approach. In: Proceedings IWANN-2003, international work-conference on artificial and natural neural networks, Mahon, Spain. 3–6 June 2003. Lecture notes in computer science (LNCS) 2687, Springer Verlag, Berlin

  31. Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I (2009) The WEKA data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18

    Article  Google Scholar 

  32. Witten I, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann Publishers Inc., San Francisco

    Google Scholar 

  33. Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27

    Article  MATH  Google Scholar 

  34. Rumelhart D, Hinton G, Williams R (1988) Learning representations by back-propagating errors. MIT Press, Cambridge, MA, pp 696–699

    Google Scholar 

  35. Platt J (1998) Fast training of support vector machines using sequential minimal optimization. In: Schoelkopf B, Burges C, Smola A (eds) Advances in Kernel methods—support vector learning. MIT Press, Cambridge, MA, pp 185–208

  36. Labeeuw W, Driessens K, Weyns D, Holvoet T, Deconinck G (2009) Prediction of congested traffic on the critical density point using machine learning and decentralised collaborating cameras. In: New trends in artificial intelligence, 14th Portuguese conference on artificial intelligence, EPIA 2009, Aveiro, pp 15–26

  37. Krishnan R (2008) Travel time estimation and forecasting on urban roads, PhD thesis, Centre for Transport Studies, Imperial College London

  38. Zhou P, Austin J, Kennedy J (1999) High performance k-NN classifier using a binary correlation matrix memory. In: Cohn David A (ed) Procs advances in neural information processing systems, vol II. MIT Press, Cambridge, MA, pp 713–719

    Google Scholar 

  39. Mulhern F, Caprara R (1994) A nearest neighbor model for forecasting market response. Int J Forecast 10(2):191–207, ISSN 0169–2070

  40. Oswald R, Scherer W, Smith B (2001) Traffic flow forecasting using approximate nearest neighbour nonparametric regression. Research Report No. UVACTS-15-13-7. Centre for Transportation Studies, University of Virginia

Download references

Acknowledgments

The work reported in this paper forms part of the FREEFLOW project, which is supported by the UK Engineering and Physical Sciences Research Council, the UK Department for Transport and the UK Technology Strategy Board. The project consortium consists of partners including QinetiQ, Mindsheet, ACIS, Kizoom, Trakm8, City of York Council, Kent County Council, Transport for London, Imperial College London and University of York.

Author information

Authors and Affiliations

  1. Department of Computer Science, University of York, Deramore Lane, York, YO10 5GH, UK

    Victoria J. Hodge, Jim Austin & Tom Jackson

  2. Centre for Transport Studies, Imperial College London, London, UK

    Rajesh Krishnan & John Polak

Authors
  1. Victoria J. Hodge
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajesh Krishnan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jim Austin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. John Polak
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Tom Jackson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Victoria J. Hodge.

Appendix

Appendix

1.1 WEKA MLP configuration

Settings in italic were changed from the WEKA defaults but not changed between runs, and settings in bold/italic were varied for each run to tune the MLP.

gui

false

autoBuild

true

debug

false

decay

true

hiddenLayers

t (number of hidden layers = numAttribs + numClasses)

learningRate

0.4

momentum

0.3

nominalToBinaryFilter

true

normaliseAttributes

true

normaliseNumericClass

true

reset

true

seed

0

trainingTime

500

validationSetSize

30

validationThreshold

20

1.2 WEKA SVM configuration

Settings in italic were changed from the WEKA defaults but not changed between runs, and settings in bold/italic were varied for each run to tune the SVM.

complexity

50.0

debug

false

fileType

Normalise training data

kernel

RBFKernel -C 250007 -G 0.01

regOptimizer

RegSMOImproved -L 0.0010 -W 1 -P 1.0E−12 -T 0.0010 -V

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hodge, V.J., Krishnan, R., Austin, J. et al. Short-term prediction of traffic flow using a binary neural network. Neural Comput & Applic 25, 1639–1655 (2014). https://doi.org/10.1007/s00521-014-1646-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-014-1646-5

Keywords

Search

Navigation