Advertisement

AUDyC Neural Network using a new Gaussian Densities Merge Mechanism

  • Habiboulaye Amadou Boubacar
  • Stéphane Lecoeuche
  • Salah Maouche

Abstract

In the context of evolutionary data classification, dynamical modeling techniques are useful to continuously learn clusters models. Dedicated to on-line clustering, the AUDyC (Auto-adaptive and Dynamical Clustering) algorithm is an unsupervised neural network with auto-adaptive abilities in nonstationary environment. These particular abilities are based on specific learning rules that are developed into three stages: “Classification”, “Evaluation” and “Fusion”. In this paper, we propose a new densities merge mechanism to improve the “Fusion” stage in order to avoid some local optima drawbacks of Gaussian fitting. The novelty of our approach is to use an ambiguity rule of fuzzy modelling with new merge acceptance criteria. Our approach can be generalized to any type of fuzzy classification method using Gaussian models. Some experiments are presented to show the efficiency of our approach to circumvent to AUDyC NN local optima problems.

Keywords

Gaussian Density Finite Mixture Model Fuzzy Classification Local Optimum Problem Dynamical Classification 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Deng, D., Kasabov, N. (2003) On-line pattern analysis by evolving self organizing maps. Neurocomputing 51: 87–103.CrossRefGoogle Scholar
  2. [2]
    .Simpson, P.K. (1993) “Fuzzy min-max neural networks-Part2: Classification” IEEE Trans. Fuzzy systems, 11): 32–45CrossRefGoogle Scholar
  3. [3]
    Eltoft T. (1998) A new Neural Network for Cluster-Detection-and-Labeling. IEEE Trans. NN, 9(5): 1021–1035.Google Scholar
  4. [4]
    Lecoeuche, S., Lurette C. (2003) Auto-adaptive and Dynamical Clustering Neural Network. ICANN03: 350–358.Google Scholar
  5. [5]
    McLachlan G. J., Peel D. (2000) Finite Mixture Models. Eds Wiley, ISBN 0-471-00626-2Google Scholar
  6. [6]
    Ueda, N., Nakano, R.. (2000) SMEM algorithm for mixture models, Neural Computing 12: 2109–2128.CrossRefGoogle Scholar
  7. [7]
    Zhang, B. Xing, Y. (2003) Competitive EM algorithm for finite mixture models, Pattern recognition 37: 131–144CrossRefGoogle Scholar
  8. [8]
    Lecoeuche, S., Lurette C. (2004) New supervision architecture based on on line modelization of non stationary data, Neural Computing and Applications, To be published.Google Scholar
  9. [9]
    Mouchaweh S. (2003) Conception d’un système de diagnostic adaptatif et prédictif basè sur la méthode Fuzzy Pattern Matching pour la surveillance en ligne des systèmes évolutifs, PhD Univ RCA FranceGoogle Scholar
  10. [10]
    Shaohua, K., Shellappa, R. (2004) Kullback-Leibler Distance between Two Gaussian Densities in Reproducing Kernel Hilbert Space. Chicago DC, ISIT Google Scholar
  11. [11]
    P. M. Kelly (1994). An Algorithm for Merge Hyper-ellipsoidal Clusters. Los Alamos National Laboratory.Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Habiboulaye Amadou Boubacar
    • 1
    • 2
  • Stéphane Lecoeuche
    • 1
    • 2
  • Salah Maouche
    • 1
  1. 1.Laboratoire Automatique, & Génie Informatique et SignalUniversité des Sciences et Technologies de LilleVilleneuve d’AscqFrance
  2. 2.Département Génie Informatique et ProductiqueEcole des Mines de DouaiDouaiFrance

Personalised recommendations