Accelerated incident detection across transportation networks using vehicle kinetics and support vector machine in cooperation with infrastructure agents

Access Full Text

Accelerated incident detection across transportation networks using vehicle kinetics and support vector machine in cooperation with infrastructure agents

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Intelligent Transport Systems — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Published

This study presents a framework for highway incident detection using vehicle kinetics, such as speed profile and lane changing behaviour, as envisioned in the vehicle-infrastructure integration (VII, also known as IntelliDrive) in which vehicles and infrastructure communicate to improve mobility and safety. This framework uses an in-vehicle intelligent module, based on a support vector machine (SVM), to determine the vehicle's travel experiences with autonomously generated kinetics data. Roadside infrastructure agents (also known as RSUs: roadside units) detect the incident by compiling travel experiences from several vehicles and comparing the aggregated results with the pre-selected threshold values. The authors developed this VII-SVM incident detection system on a previously calibrated and validated simulation network in rural Spartanburg, South Carolina and deployed it on an urban freeway network in Baltimore, Maryland to evaluate its transportability. The study found no significant differences in the detection performance between the original network and a new network that the VII-SVM system has not seen before. This demonstrated the feasibility of developing a generic VII-SVM system, applicable across transportation networks.

Inspec keywords: multi-agent systems; support vector machines; vehicle dynamics; road accidents; traffic engineering computing; automated highways

Other keywords: vehicle-infrastructure integration; transportation networks; in-vehicle intelligent module; vehicle kinetics; accelerated incident detection; roadside infrastructure agents; VII-SVM incident detection system; support vector machine

Subjects: Knowledge engineering techniques; Health and safety aspects; Traffic engineering computing; Vehicle mechanics; Other engineering applications of IT

References

    1. 1)
      • M. Levin , G.M. Krause . (1979) Incident-detection algorithms, part 1: off-line evaluation.
    2. 2)
      • USDOT ITS Joint Program Office, Available at http://www.its.dot.gov/intellidrive/index.htm, accessed 21 January 2009.
    3. 3)
      • ITS America: ‘Primer on VII’, http://www.itsa.org/itsa/files/pdf/VIIPrimer.pdf, accessed 11 July 2007.
    4. 4)
      • Y. Ma , M. Chowdhury , A. Sadek , M. Jeihani . Real-time highway traffic condition assessment framework using vehicle-infrastructure integration (VII) with artificial intelligence (AI). IEEE Trans. Intell. Transp. Syst. , 4 , 615 - 627
    5. 5)
      • H.J. Payne , S.C. Tignor . Freeway incident detection algorithms based on decision trees with states. Transp. Res. Rec. , 682 , 30 - 37
    6. 6)
      • K. Petty , W. Mahoney . (2007) Weather applications and products enabled through vehicle infrastructure integration (VII) feasibility and concept development study.
    7. 7)
      • M. Chowdhury , A. Sadek , Y. Ma , P. Bhavsar . (2006) Applications of artificial intelligence paradigms to decision support to real-time traffic management.
    8. 8)
      • (2005) VII architecture and functional requirements version 1.1.
    9. 9)
      • Stitson, M.O., Weston, J.O.E., Gammerman, A., Vovk, V., Vapnik, V.: `Theory of support vector machines', Technical Report CSD-TR-96-17, 1996.
    10. 10)
      • (2005) VII Michigan test bed program concept of operations.
    11. 11)
      • F. Yuan , R. Cheu . Incident detection using support vector machines. Transp. Res. C , 309 - 328
    12. 12)
      • P. Bhagwant , F. Hall . Catastrophe theory and patterns in 30-second freeway traffic data. Implications for incident detection. Transp. Res. A , 103 - 113
    13. 13)
      • Vanajakshi, L., Rilett, L.: `A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed', IEEE Intelligent Vehicles Symp., 2004, p. 194–199.
    14. 14)
      • Qi, H., Cheu, R.L., Lee, D.-H.: `Freeway incident detection using kinematics data from probe vehicles', Ninth World Congress on Intelligent Transport Systems (CD-ROM), 2002.
    15. 15)
      • PATH: ‘VII California bay area test bed development plan’, 4 April 2006.
    16. 16)
      • Ren, J., Ou, X., Zhang, Y., Song, J., Hu, D.: `SVM-based detection of traffic incident', Proc. Ninth World Congress on Intelligent Transportation Systems (ITS), CD-ROM, 2002, Chicago, IL.
    17. 17)
      • S. Knerr , L. Personnaz , G. Dreyfus . (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network.
    18. 18)
      • B. Vanschoenwinkel , F. Liu , B. Manderick . (2006) Context-sensitive kernel functions: a distance function viewpoint.
    19. 19)
      • H.J. Payne , S.C. Tignor . Freeway incident detection algorithms based on decision trees with states. Transp. Res. Rec. , 682 , 30 - 37
    20. 20)
      • C.C. Chang , C.J. Lin . LIBSVM: a library for support vector machines.
    21. 21)
      • U. Kreβel . (1999) Pairwise classification and support vector machines, Advances in Kernel methods – support vector learning.
    22. 22)
      • Ma, Y., Chowdhury, M., Fries, R., Zhou, Y.: `Accelerated incident detection using vehicle kinetics and support vector machines in cooperation with infrastructure agents', Proc. 15th World Congress on Intelligent Transport Systems (ITS) (CD-ROM), 2008, New York, NY.
    23. 23)
      • W. Sarle . (1997) Neural network FAQ.
    24. 24)
      • Bhavsar, P., Chowdhury, M.: `Decision support system for predicting traffic diversion impacts across transportation networks using support vector regression', Proc. Transportation Research Board Annual Meeting, 2007, Washington, DC.
    25. 25)
      • C.W. Hsu , C.C. Chang , C.J. Lin . (2003) A practical guide to support vector classification.
    26. 26)
      • Friedman, J.: `Another approach to polychotomous classification', Technical Report, Department of Statistics, 1996, available at http://www-stat.stanford.edu/reports/friedman/poly.ps.Z.
    27. 27)
      • W. Sermons , F. Koppelman . Use of vehicle positioning data for arterial incident detection. Transp. Res. C , 2 , 87 - 96
    28. 28)
      • VII California demonstrates success: finalist in ITSA ‘Best of” research and innovation. Intellimotion , 1
    29. 29)
      • P.T. Martin , J. Perrin , B. Hansen . Incident detection algorithm evaluation. Prepared for Utah Department of Transportation
    30. 30)
      • R.L. Cheu , H. Qi , D.-H. Lee . (2002) Mobile sensor and sample-based algorithm for freeway incident detection.
    31. 31)
      • Antoniades, C.N., Yorgos, J.S.: `Single-station incident detection algorithm (SSID) for sparsely instrumented freeway sites', Proc. Applications of Advanced Technologies in Transportation Engineering, Fourth Int. Conf., 27–30 June 1995, Capri, Italy, p. 218–221.
    32. 32)
      • Ding, A., Zhao, X., Jiao, L.: `Traffic flow time series prediction based on statistics learning theory', Proc. IEEE Fifth Int. Conf. on Intelligent Transportation System, 2002, p. 727–730.
    33. 33)
      • Crabtree, J.D., Stamatiadis, N.: `Using dedicated short-range communication (DSRC) technology for freeway incident detection: a performance assessment based on traffic simulation data', Transportation Research Board Annual Meeting (CD-ROM), 2007, Washington, DC.
    34. 34)
      • Quadstone Limited: ‘Paramics traffic simulation model’, http://www.paramics-online.com/, accessed 15 July 2007.
    35. 35)
      • W.-C. Lin . (2004) A case study on support vector machine versus artificial neural networks.
    36. 36)
    37. 37)
      • Tanikella, H., Smith, B.L., Zhang, G., Park, B., Scherer, W.T.: `Simulating vehicle-infrastructure-integration-enabled operations applications: traffic monitoring case study', Proc. Transportation Research Board Annual Meeting (CD-ROM), 2007, Washington, DC.
    38. 38)
    39. 39)
      • JHK and Associates: Bay Area Traffic Operations System Incident Detection Algorithms Report, January 1993.
    40. 40)
      • T. Wayne , P. Gary . Vehicle infrastructure integration: more than a very intriguing idea. ITE J. , 4 , 29 - 32
    41. 41)
      • R.L. Chen , D. Srinivasan , E. Tian . Support vector machine models for freeway incident detection. IEEE Proc. Intell. Transp. Syst. , 238 - 243
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-its.2010.0035
Loading

Related content

content/journals/10.1049/iet-its.2010.0035
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading