access icon free Leveraging longitudinal driving behaviour data with data mining techniques for driving style analysis

© The Institution of Engineering and Technology
Received 03/07/2014, Accepted 09/02/2015, Revised 17/12/2014, Published 22/04/2015

Accurately understanding driving behaviour is of crucial importance for advanced driving assistant systems such as adaptive cruise control system and intelligent forward collision warning system. To understand different driving styles, this study employs the clustering method and topic model to extract latent driving states, which can elaborate and analyse the commonness and individuality of driving behaviour characteristics with the longitudinal driving behaviour data collected by the instrumented vehicle. To handle the large set of data and discover the valuable knowledge, the data mining techniques including ensemble clustering method based on the kernel fuzzy C-means algorithm and the modified latent Dirichlet allocation model are employed in this study. The ‘aggressive’, ‘cautious’ and ‘moderate’ driving states are discovered and the underlying quantified structure is built for the driving style analysis.

Inspec keywords: learning (artificial intelligence); pattern clustering; driver information systems; data mining; behavioural sciences computing

Other keywords: driving style analysis; ensemble clustering method; longitudinal driving behaviour data; aggressive driving state; data mining techniques; clustering method; modified latent Dirichlet allocation model; advanced driving assistant systems; moderate driving state; intelligent forward collision warning system; driving behaviour characteristics; topic model; kernel fuzzy C-means algorithm; cautious driving state; adaptive cruise control system

Subjects: Social and behavioural sciences computing; Traffic engineering computing; Knowledge engineering techniques; Data handling techniques

References

    1. 1)
    2. 2)
    3. 3)
      • 25. Yang, A.M., Jiang, L.M., Zhou, Y.M.: ‘A KFCM-based fuzzy classifier’. Fourth Int. Conf. on Fuzzy Systems and Knowledge Discovery, Haikou, China, August 2007, pp. 80–84.
    4. 4)
      • 26. Dietterich, T.G.: ‘Ensemble methods in machine learning’. First Int. Workshop on Multiple Classifier Systems, Berlin, Germany, June 2000, pp. 1–15.
    5. 5)
      • 30. Liu, Z., Li, M., Liu, Y., et al: ‘Performance evaluation of latent dirichlet allocation in text mining’. 2011 Eighth Int. Conf. on Fuzzy Systems and Knowledge Discovery (FSKD 2011) Jointly with the 2011 Seventh Int. Conf. on Natural Computation (ICNC'11), Shanghai, China, July 2011, pp. 2695–2698.
    6. 6)
      • 12. Gabard, J.F., Henry, J.J., Tuffal, J., et al: ‘Traffic responsive or adaptive fixed-time policies? A critical analysis with sitra-b’. Int. Conf. on Road Traffic Signalling, London, UK, March 1982, pp. 89–92.
    7. 7)
      • 17. Ishibashi, M., Okuwa, M., Doi, S., et al: ‘Indices for characterizing driving style and their relevance to car following behavior’. SICE'07, 46th SICE Annual Conf., Kagawa University, Japan, September 2007, pp. 1132–1137.
    8. 8)
    9. 9)
    10. 10)
    11. 11)
      • 22. Aljaafreh, A., Alshabatat, N., Najim Al-Din, M.S.: ‘Driving style recognition using fuzzy logic’. 2012 IEEE Int. Conf. on Vehicular Electronics and Safety (ICVES 2012), Istanbul, Turkey, July 2012, pp. 460–463.
    12. 12)
      • 37. Smith, A., Roberts, G.O.: ‘Bayesian computation via the Gibbs sampler and related Markov-chain Monte-Carlo methods’, J. R. Stat. Soc. Ser. B, Methodol., 1993, 55, (1), pp. 3–23.
    13. 13)
      • 8. Leutzbach, W., Wiedemann, R.: ‘Development and applications of traffic simulation models at the karlsruhe institut fuer verkehrswesen’, Traffic Eng. Control, 1986, 27, (5), pp. 270–273.
    14. 14)
      • 18. Rygula, A.: ‘Driving style identification method based on speed graph analysis’. 2009 Int. Conf. on Biometrics and Kansei Engineering, ICBAKE, Cieszyn, Poland, June 2009, pp. 76–79.
    15. 15)
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
      • 23. Bezdek, J.C.: ‘Pattern recognition with fuzzy objective function algorithms’ (Plenum Press, 1981, 1st edn.).
    22. 22)
      • 29. Blei, D.M., Ng, A.Y., Jordan, M.I.: ‘Latent dirichlet allocation’, J. Mach. Learn. Res., 2003, 3, (4–5), pp. 993–1022.
    23. 23)
    24. 24)
      • 21. Baer, T., Nienhueser, D., Kohlhaas, R., et al: ‘Probabilistic driving style determination by means of a situation based analysis of the vehicle data’. IEEE Int. Conf. on Intelligent Transportation Systems, ITSC, Washington DC, USA, October 2011, pp. 1698–1703.
    25. 25)
      • 11. Helly, W.: ‘Simulation of bottlenecks in single-lane traffic flow’, in Herman, R. (Ed.): ‘Proceedings of the symposium on the theory of traffic flow’ (Elsevier Publishing Company, 1961, 1st edn.), pp. 207–238.
    26. 26)
      • 32. Yang, J., Wang, Y., Li, M., et al: ‘Place recognition based on latent dirichlet allocation’. 2011 IEEE Int. Conf. on Mechatronics and Automation (ICMA 2011), Beijing, China, August 2011, pp. 495–500.
    27. 27)
      • 27. Breiman, L.: ‘Bagging predictors’, Mach. Learn., 1996, 24, (2), pp. 123–140.
    28. 28)
      • 20. Constantinescu, Z., Marinoiu, C., Vladoiu, M.: ‘Driving style analysis using data mining techniques’, Int. J. Comput. Commun. Control, 2010, 5, (5), pp. 654–663.
    29. 29)
    30. 30)
    31. 31)
      • 19. Di Lecce, V., Calabrese, M.: ‘Nn-based measurements for driving pattern classification’. 2009 IEEE Instrumentation and Measurement Technology Conf. (I2MTC), Singapore, May 2009, pp. 259–264.
    32. 32)
    33. 33)
    34. 34)
    35. 35)
    36. 36)
    37. 37)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2014.0139
Loading

Related content

content/journals/10.1049/iet-its.2014.0139
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading