Effectiveness of Feature Extraction in Neural Network Architectures for Novelty Detection

@inproceedings{Addison1999EffectivenessOF,
  title={Effectiveness of Feature Extraction in Neural Network Architectures for Novelty Detection},
  author={Jonathan Francis Dale Addison and Stefan Wermter and John MacIntyre},
  year={1999}
}
This paper examines the performance of seven neural network architectures in classifying and detecting novel events contained within data collected from turbine sensors. Several different multi-layer perceptrons were built and trained using back propagation, conjugate gradient and Quasi-Newton training algorithms. In addition, Linear networks, Radial Basis Function networks, Probabilistic networks and Kohonen self organising feature maps were also built and trained, with the objective of… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS
20 Citations
19 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 20 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 19 references

Choosing an Appropriate Model for Novelty Detection

  • N. T. Alexandre, C. Corbett, R. Ripley, W TownsendN., T. Tarassenko
  • Proceedings of IEEE Fifth International…
  • 1997
1 Excerpt

Neural Networks for Pattern Recognition

  • C. M. Bishop
  • 1997
2 Excerpts

An Integrated Signal Processing and Neural Networks System for Steam Generator Tubing Diagnostics using Eddy Current Inspection

  • W. Yan, R. Upadhaya
  • Annals Nuclear Energy,
  • 1996
1 Excerpt

Fault Classification using Kohonen Feature Mapping, Electrical Engineering Department, University of Wyoming

  • B. H. Chowdhury, K. Wang
  • 1996
1 Excerpt

Similar Papers

Loading similar papers…