This study presents a data segmentation method, which was intended to improve the performance of the k-nearest neighbours algorithm for making short-term traffic volume predictions. According to the introduced method, selected segments of vehicle detector data are searched for records similar to the current traffic conditions, instead of the entire database. The data segments are determined on the basis of a segmentation procedure, which aims to select input data that are useful for the prediction algorithm. Advantages of the proposed method were demonstrated in experiments on real-world traffic data. Experimental results show that the proposed method not only improves the accuracy of the traffic volume prediction, but also significantly reduces its computational cost.

References

1. 1)
  - 10. Turochy, R.E.: ‘Enhancing short-term traffic forecasting with traffic condition information’, J. Transp. Eng., 2006, 132, (6), pp. 469–474 (doi: 10.1061/(ASCE)0733-947X(2006)132:6(469)).
2. 2)
  - 12. Smith, B.L., Demetsky, M.J.: ‘Traffic flow forecasting: comparison of modeling approaches’, J. Transp. Eng., 1997, 123, (4), pp. 261–266 (doi: 10.1061/(ASCE)0733-947X(1997)123:4(261)).
3. 3)
  - 14. Huang, Z., Ouyang, H., Tian, Y.: ‘Short-term traffic flow combined forecasting based on nonparametric regression’. Int. Conf. on Information Technology, Computer Engineering and Management Sciences, ICM 2011, 2011, vol. 1, pp. 316–319.
4. 4)
  - 21. Ying, H.: ‘Fuzzy control and modeling: analytical foundations and applications’ (IEEE Press, 2000, 1st edn.).
5. 5)
  - 24. Li, S., Shen, Z., Wang, F.-Y.: ‘A weighted pattern recognition algorithm for short-term traffic flow forecasting’. Nineth IEEE Int. Conf. on Networking, Sensing and Control, ICNSC 2012, pp. 1–6.
6. 6)
  - 25. Berthold, M.R., Cebron, N., Dill, F., et al: ‘KNIME – the Konstanz information miner: version 2.0 and beyond’, ACM SIGKDD Explorations Newsl., 2009, 11, (1), pp. 26–31 (doi: 10.1145/1656274.1656280).
7. 7)
  - 7. Vlahogianni, E.L., Karlaftis, M.G., Golias, J.C.: ‘Optimized and meta-optimized neural networks for short-term traffic flow prediction: a genetic approach’, Transp. Res. C, Emerg. Technol., 2005, 13, (3), pp. 211–234 (doi: 10.1016/j.trc.2005.04.007).
8. 8)
  - 19. Li, S., Shen, Z., Xiong, G.: ‘A k-nearest neighbor locally weighted regression method for short-term traffic flow forecasting’. 15th Int. IEEE Conf. on Intelligent Transportation Systems, ITSC 2012, pp. 1596–1601.
9. 9)
  - 3. Guo, F., Krishnan, R., Polak, J.W.: ‘Short-term traffic prediction under normal and abnormal traffic conditions on urban roads’. Transportation Research Board 91st Annual Meeting, 2012, Paper #12–1627, pp. 1–17.
10. 10)
  - 11. Zhang, T., Hu, L., Liu, Z., Zhang, Y.: ‘Nonparametric regression for the short-term traffic flow forecasting’. Int. Conf. on Mechanic Automation and Control Engineering, MACE, 2010, pp. 2850–2853.
11. 11)
  - 16. Kindzerske, M.D., Ni, D.: ‘Composite nearest neighbor nonparametric regression to improve traffic prediction’, Transp. Res. Record, J. Transp. Res. Board, 2007, 1993, (1), pp. 30–35 (doi: 10.3141/1993-05).
12. 12)
  - 11. Chang, H., Lee, Y., Yoon, B., Baek, S.: ‘Dynamic near-term traffic flow prediction: system-oriented approach based on past experiences’, IET Intell. Transp. Syst., 2012, 6, (3), pp. 292–305 (doi: 10.1049/iet-its.2011.0123).
13. 13)
  - 20. Stathopoulos, A., Karlaftis, M.G.: ‘A multivariate state space approach for urban traffic flow modeling and prediction’, Transp. Res. C, 2003, 11, pp. 121–135 (doi: 10.1016/S0968-090X(03)00004-4).
14. 14)
  - 26. Weber, R., Schek, H.J., Blott, S.: ‘A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces’. VLDB, 1998, vol. 98, pp. 194–205.
15. 15)
  - 5. May, M., Hecker, D., Korner, C., Scheider, S., Schulz, D.: ‘A vector-geometry based spatial kNN-algorithm for traffic frequency predictions’. IEEE Int. Conf. on Data Mining Workshops (ICDMW'08), 2008, pp. 442–447.
16. 16)
  - 8. Smith, B.L., Oswald, R.K.: ‘Effects of parameter selection on forecast accuracy and execution time in nonparametric regression’. Proc. Intelligent Transportation Systems, 2000, pp. 252–257.
17. 17)
  - 7. Yoon, B., Chang, H.: ‘Potentialities of data-driven nonparametric regression in urban signalized traffic flow forecasting’, J. Transp. Eng., 2014, 10.1061/(ASCE)TE.1943–5436.0000662, 04014027.
18. 18)
  - 23. Pamuła, T.: ‘Classification and prediction of traffic flow based on real data using neural networks’, Arch. Transp., 2012, 24, (4), pp. 519–529 (doi: 10.2478/v10174-012-0032-2).
19. 19)
  - 6. Shi, X., Ren, Q.: ‘The advanced nonparametric model for short-term traffic volume forecasting’. ICCTP 2011 Towards Sustainable Transportation System, pp. 1442–1453.
20. 20)
  - B.L. Smith , B.M. Williams , R. Keith Oswald . Comparison of parametric and nonparametric models for traffic flow forecasting. Transp. Res. C: Emerg. Technol. , 4 , 303 - 321
21. 21)
  - 20. Chang, H., Park, D., Lee, Y., Yoon, B.: ‘Multiple time period imputation technique for multiple missing traffic variables: nonparametric regression approach’, Can. J. Civ. Eng., 2012, 39, (4), pp. 448–459 (doi: 10.1139/l2012-018).
22. 22)
  - 15. Gong, X., Wang, F.: ‘Three improvements on KNN-NPR for traffic flow forecasting’. IEEE Fifth Int. Conf. on Intelligent Transportation Systems, 2002, pp. 736–740.
23. 23)
  - 22. Weijermars, W.A.M., van Berkum, E.C.: ‘Daily flow profiles of urban traffic’. ‘Urban Transport X’ Publication of WIT Press, 2004.
24. 24)
  - 27. Płaczek, B.: ‘A self-organizing system for urban traffic control based on predictive interval microscopic model’, Eng. Appl. Artif. Intell., 2014, 34, pp. 75–84 (doi: 10.1016/j.engappai.2014.05.004).
25. 25)
  - 4. Kim, T., Kim, H., Lovell, D.J.: ‘Traffic flow forecasting: overcoming memoryless property in nearest neighbor non-parametric regression’. Proc. Intelligent Transportation Systems 2005, pp. 965–969.
26. 26)
  - 9. Smith, B.L., Oswald, R.K.: ‘Meeting real-time traffic flow forecasting requirements with imprecise computations’, Comput.-Aided Civ. Infrastruct. Eng., 2003, 18, (3), pp. 201–213 (doi: 10.1111/1467-8667.00310).
27. 27)
  - 18. Oswald, R.K., Scherer, W.T., Smith, B.L.: ‘Traffic flow forecasting using approximate nearest neighbor nonparametric regression’. A research report, ITS center project: traffic forecasting: non-parametric regressions, 2001.

Segmentation of vehicle detector data for improved k-nearest neighbours-based traffic flow prediction

References

Related content