Advertisement

A New Metric for Supervised dFasArt Based on Size-Dependent Scatter Matrices That Enhances Maneuver Prediction in Road Vehicles

  • Ana Toledo
  • Rafael Toledo-Moreo
  • José Manuel Cano-Izquierdo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5602)

Abstract

In previous investigations, a supervised version of a dynamic FasArt method (SdFasArt) proved its capability to supply good results to the problem of maneuver prediction in road vehicles. The dynamic character of dFasArt minimized problems caused by noise in the sensors and provided stability on the predicted maneuvers. This paper presents a new SdFasArt architecture enhanced by the inclusion of size-dependent scatter matrices (SDSM) to compute the activation of the neurons. In this novel approach, the receptive fields of the neurons are capable to rotate and scale in order to better respond to data distributions with a preferred orientation in the input space, what leads to a more efficient classification. The results achieved by both methods in a series of experiments in real scenarios with a probe vehicle show that SDSM-SdFasArt supplies better results in terms of maneuver prediction and number of nodes.

Keywords

dFasArt Collision Avoidance Maneuver Detection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Toledo, R., Sotomayor, C., Gomez-Skarmeta, A.F.: Quadrant: An Architecture Design for Intelligent Vehicle Services in Road Scenarios. Monograph on Advances in Transport Systems Telematics, 451–460 (2006)Google Scholar
  2. 2.
    Huang, D., Leung, H.: EM-IMM based land-vehicle navigation with GPS/INS. In: Proceedings of the IEE ITSC Conference, Washington, DC USA, October 2004, pp. 624–629 (2004)Google Scholar
  3. 3.
    Hoffmann, C., Dang, T.: Cheap Joint Probabilistic Data Association Filters in an Interacting Multiple Model Design. In: Proceedings of the 2006 IEEE-MFI 2006, Heidelberg, Germany, September 3-6, 2006, pp. 197–202 (2006)Google Scholar
  4. 4.
    Toledo-Moreo, R., Zamora-Izquierdo, M.A.: IMM-Based Lane-Change Prediction in Highways With Low-Cost GPS/INS. IEEE Transactions on Intelligent Transporation Systems 10(1), 180–185 (2009)CrossRefGoogle Scholar
  5. 5.
    Toledo-Moreo, R., Pinzolas, M., Cano-Izquierdo, J.M.: Supervised dFasArt: a Neuro-Fuzzy Dynamic Architecture for Maneuver Detection in Road Vehicle Collision Avoidance Support Systems. In: Mira, J., Álvarez, J.R. (eds.) IWINAC 2007. LNCS, vol. 4528, pp. 419–428. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Cano-Izquierdo, J.M., Almonacid, M., Pinzolas, M., Ibarrola, J.: dFasArt: Dynamic neural processing in FasArt model. Neural Networks (2008), doi:10.1016/j.neunet.2008.09.018Google Scholar
  7. 7.
    Juyang, W., Wey-Shiuan, H.: Incremental Hierarchical Discriminant Regression. IEEE Transactions on Neural Networks 18(2), 397–415 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ana Toledo
    • 1
  • Rafael Toledo-Moreo
    • 2
  • José Manuel Cano-Izquierdo
    • 3
  1. 1.Dpto. Tecnología ElectrónicaSpain
  2. 2.Dpto. Electrónica, Tecnología de Computadoras y ProyectosSpain
  3. 3.Dpto. Ingeniería de Sistemas y AutomáticaUniversidad Politécnica de CartagenaSpain

Personalised recommendations