Skip to main content
SpringerLink
Log in

Empirical validation of the performance of a class of transient detector

  • Evolutionary Machine Learning and Classifier Systems
  • Conference paper
  • First Online:
Evolutionary Computing (AISB EC 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1305))

Included in the following conference series:

  • 107 Accesses

Abstract

Transient detection in the presence of noise is a problem which occurs in many areas of engineering. A description is given of a classifier system suitable for the identification of high frequency waveforms. It uses the Wavelet Transform for signal pre-processing to produce a more parsimonious representation of the signal to be identified. A comparison is presented of the use of a Forward Selection algorithm and a Genetic Algorithm to pick appropriate indicator variables as inputs to a classifier. A Radial Basis Function neural network is employed to model the class conditional probability density function. The classifier is applied to the identification of a number of high frequency Acoustic Emission signals, which are difficult to classify,.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bishop, C. Neural Networks for Pattern Recognition, Oxford University Press, 1995.

    Google Scholar 

  2. Broomhead, D.S., Lowe, D., “Multi-variable Functional Interpretation and Adaptive Networks”, Complex Systems, Vol. 2, 1988, pp.321–355.

    Google Scholar 

  3. Chui, Ch., K., An Introduction to Wavelets. Wavelet Analysis and its Applications, Vol. 1, Academic Press, Boston, 1992.

    Google Scholar 

  4. Daubechies, I., “The Wavelet Transform, Time-frequency Localization and Signal Analysis”, I.EEE. Trans. Information Theory, Vol. 36, 1990, pp.961–1005.

    Google Scholar 

  5. Kittler, J., “Feature Selection and Extraction”, Handbook of Pattern Recognition and Image Processing, Eds.Young, T.Y., Fu, K.S., Academic Press, 1986, pp. 60–81.

    Google Scholar 

  6. Newland, D.E., An Introduction to Random Vibrations, Spectral and Wavelet Analysis, 3rd Ed., Longman Scientific and Technical, Essex, 1994.

    Google Scholar 

  7. Pudil, P., Novovicová, J., Ferri, F., “New Tools for Knowledge Guided Approach to Statistical Pattern Recognition”, AISB96 Workshop, 1 April, 1996, Brighton, UK.

    Google Scholar 

  8. Press, W.H., et al., Numerical Recipes in C, Cambridge University Press, 1994, pp. 808–812.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Engineering, University of Manchester, M13 9PL, Manchester, UK

    Philip J. Jacob & Andrew D. Ball

Authors
  1. Philip J. Jacob
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrew D. Ball
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

David Corne Jonathan L. Shapiro

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Jacob, P.J., Ball, A.D. (1997). Empirical validation of the performance of a class of transient detector. In: Corne, D., Shapiro, J.L. (eds) Evolutionary Computing. AISB EC 1997. Lecture Notes in Computer Science, vol 1305. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0027171

Download citation

  • DOI: https://doi.org/10.1007/BFb0027171

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63476-8

  • Online ISBN: 978-3-540-69578-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation