Support Vector Machine in Novelty Detection for Multi-channel Combustion Data

  • Lei A. Clifton
  • Hujun Yin
  • Yang Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)


Multi-channel combustion data, consisting of gas pressure and two combustion chamber luminosity measurements, are investigated in the prediction of combustion instability. Wavelet analysis is used for feature extraction. A SVM approach is applied for novelty detection and the construction of a model of normal system operation. Novelty scores generated by classifiers from different channels are combined to give a final decision of data novelty. Comparisons between the proposed SVM method and a GMM approach show that earlier identification of combustion instability, and greater distinction between stable and unstable data classes, are achieved with the proposed SVM approach.


Support Vector Machine Gaussian Mixture Model Stable Data Stable Combustion Novelty Detection 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chen, Y., Zhou, X.S., Huang, T.: One-class SVM for Learning in Image Retrieval. In: IEEE ICIP, Thessaloniki, Greece, vol. 1, pp. 34–37 (2001)Google Scholar
  2. 2.
    Daubechies, I.: Orthonormal Bases of Compactly Supported Wavelets. Comm. Pure and Appl. Math. 41, 909–996 (1988)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Gretton, A., Desobry, F.: On-line One-class Support Vector Machines. An Application to Signal Segmentation. In: Gretton, A., Desobry, F. (eds.) IEEE ICASSP, Hong-Kong, China (2003)Google Scholar
  4. 4.
    Hardoon, D.R., Manevitz, L.M.: fMRI Analysis via One-class Machine Learning Techniques. In: 19th IJCAI, Edinburgh, UK, pp. 1604–1605 (2005)Google Scholar
  5. 5.
    Hayton, P., Tarassenko, L., Schölkopf, B., Anuzis, P.: Support Vector Novelty Detection Applied to Jet Engine Vibration Spectra. In: NIPS, London, pp. 946–952 (2000)Google Scholar
  6. 6.
    Kittler, J., Hatef, M., Duin, R., Matas, J.: On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  7. 7.
    Kuncheva, L.I.: A Theoretical Study on Six Classifier Fusion Stragies. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(2), 281–286 (2002)CrossRefGoogle Scholar
  8. 8.
    Mallat, S.: A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. IEEE Pattern Anal. and Machine Intell. 11, 674–693 (1989)MATHCrossRefGoogle Scholar
  9. 9.
    Ng, W.B., Clough, E., Syed, K.J., Zhang, Y.: The Combined Investigation of the Flame Dynamics of an Industrial Gas Turbine Combustor Using High-speed Imaging and an Ooptically Integrated Data Collection Method. Measurement Science and Tachnology 15, 2303–2309 (2004)CrossRefGoogle Scholar
  10. 10.
    Schölkopf, B., Platt, J., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the Support of a High-dimensional Distribution. Neural Computation 13, 1443–1471 (2001)MATHCrossRefGoogle Scholar
  11. 11.
    Tax, D.M.J., Duin, R.P.W.: Data Domain Description Using Support Vectors. In: ESAN 1999, Brussels, pp. 251–256 (1999)Google Scholar
  12. 12.
    Wang, L., Yin, H.: Wavelet Analysis in Novelty Detection for Combustion Image Data. In: 10th CACSC, Liverpool, pp. 79–82 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Lei A. Clifton
    • 1
  • Hujun Yin
    • 1
  • Yang Zhang
    • 2
  1. 1.School of Electrical and Electronic EngineeringThe University of ManchesterManchesterUK
  2. 2.School of Mechanical, Aerospace and Civil EngineeringThe University of ManchesterManchesterUK

Personalised recommendations