Advertisement

Multi-neural network approach for classification of brainstem evoked response auditory

  • Anne-Sophie Dujardin
  • Véronique Amarger
  • Kurosh Madani
  • Olivier Adam
  • Jean-François Motsch
Bio-inspired Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1607)

Abstract

Since about twenty years, the otoneurology functional exploration possesses experimental techniques to analyze objectively the state of the nervous conduction of auditive pathway. It conerns brainstem evoked response auditory. In this paper we present a new classification approach based on a hybrid neural network technique focusing this biomedical application for developing a diagnostic tool. We have used two models of artificial neural networks: Learning Vector Quantization and Radial Basis Function ones. In our approach, these two neural networks are used to achieve the classification in a serial multi-neural network configuration. Case study and experimental results have been reported and discussed.

Keywords

Multi-Neural Network Brainstem Evoked Response Auditory Classification Learning Vector Quantization Radial Basis Function 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    WIDROW B., LEHR M.A., “30 years of adaptative Neural Networks: Perceptron, Madaline, and Backpropagation”, Proceeding of the IEEE, Vol. 78, pp. 1415–1441, 1990.CrossRefGoogle Scholar
  2. [2]
    BENGHARBI A., “Contribution au test et diagnostic des circuits analogiques par des approches basées sur des techniques neuronales”, PhD thesis report, University of Creteil-Paris XII, 1997Google Scholar
  3. [3]
    AMARGER V., BENGHARBI A., MADANI K., “A New Approach to fault diagnosis of Analog Circuit using Neural Networks Based Techniques”, IEEE European Test Workshop 96 Montpellier, June 12–14, 1996.Google Scholar
  4. [4]
    BENGHARBI A., AMARGER, V., MADANI K., “Multi-Fault Diagnosis of Analog non Linear Circuits by Smart Classification Technique”, IEEE European Test Workshop 97, Torino, Mai, 1997.Google Scholar
  5. [5]
    MADANI K., BENGHARBI A., AMARGER V., “Neural Fault Diagnosis Techniques for Non Linear Analogue Circuits”, SPIE'97, Orlando, 1997.Google Scholar
  6. [6]
    BAZOON M., A. STACEY D., CUI C., “A Hierarchical Artificial Neural Network System for the Classification of Cervical Cells”, IEEE International Conference on Neural Networks, Orlando, July, 1994.Google Scholar
  7. [7]
    ALPSAN D. “Auditory Evoked Potential Classification by Unsupervised Art 2-A and Supervised Fuzzy Artmap Networks”, IEEE International Conference on Neural Networks (ICNN), Orlando, July, 1994.Google Scholar
  8. [8]
    KOHONEN T., “Learning Vector Quantization”, Neural Networks, vol. 1, suppl. 1, p. 303, 1988.Google Scholar
  9. [9]
    KOHONEN T., “Self Organizing and Associative Memory”, 3rd ed., Springer-Verlag, Germany, 1989.Google Scholar
  10. [10]
    NIRINJAN M., FALLSIDE F., “Neural Networks and Radial Basis Functions in classifying-static speech pattern”, Report CUED/FINFENG/TR22, Cambridge University, England, 1988.Google Scholar
  11. [11]
    MOTSCH J-F, “La dynamique temporelle du tronc cérébral: Recueil, extraction et analyse optimale des potentiels évoqués auditifs du tronc cérébral”, PhD thesis report (thèse d'état), University of Créteil-Paris XII, 1987.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Anne-Sophie Dujardin
    • 1
  • Véronique Amarger
    • 1
  • Kurosh Madani
    • 1
  • Olivier Adam
    • 2
  • Jean-François Motsch
    • 2
  1. 1.Laboratoire d'Etude et de Recherche en Instrumentation Signaux et Systèmes Division de Recherche Réseaux NeuronauxUniversité Paris XII-Val de Marne. I.U.T. de Sénart-FontainebleauLieusaintFrance
  2. 2.Laboratoire d'Etude et de Recherche en Instrumentation Signaux et Systèmes Division Traitement du Signal et Instrumentation MédicaleUniversité PARIS XII-Val de MarneCreteil CedexFrance

Personalised recommendations