ADAPTIVE SELECTION OF NEURAL NETWORKS FOR A COMMITTEE DECISION

Authors

  • Arunas Lipnickas
  • Jozef Korbicz

DOI:

https://doi.org/10.47839/ijc.3.2.282

Keywords:

Adaptive committees, neural networks, , half & half sampling

Abstract

To improve recognition results, decisions of multiple neural networks can be aggregated into a committee decision. In contrast to the ordinary approach of utilising all neural networks available to make a committee decision, we propose creating adaptive committees, which are specific for each input data point. A prediction network is used to identify classification neural networks to be fused for making a committee decision about a given input data point. The jth output value of the prediction network expresses the expectation level that the jth classification neural network will make a correct decision about the class label of a given input data point. The proposed technique is tested in three aggregation schemes, namely majority vote, averaging, and aggregation by the median rule and compared with the ordinary neural networks fusion approach. The effectiveness of the approach is demonstrated on three well known real data sets and also applied to fault identification of the actuator valve at one sugar factory within the DAMADICS RTN.

References

L. Xu, A. Krzyzak, C.Y. Suen, Methods for combining multiple classifiers and their applications to handwriting recognition. IEEE Trans. Systems, Man, and Cybernetics 22(3), pp. 418-435, 1992.

V. Tresp and M. Taniguchi, Combining estimators using non-constant weighting functions. In G. Tesauro, D. S. Touretzky, and T. K. Leen, editors, Advances in Neural Information Processing Systems 7, MIT Press, 1996.

S. Hashem, Optimal linear combinations of neural networks. Neural Networks 10(4), pp. 599-614, 1997.

A. Verikas, A. Lipnickas, K. Malmqvist, M. Bacauskiene, A. Gelzinis, Soft combination of neural classifiers: A comparative study. Pattern Recognition Letters 20, 429-444, 1999.

M. Grabisch and J.-M. Nicolas, Classification by fuzzy integral: Performance and tests. Fuzzy Sets and Systems 65, 255-271, 1994.

A. Verikas, A. Lipnickas, M. Bacauskiene, K. Malmqvist, Fusing neural networks through fuzzy integration. In H. Bunke, A. Kandel, editors, Hybrid Methods in Pattern Recognition, World Scientific, 2002.

K. Woods, W.P. Kegelmeyer, K. Bowyer, Combination of multiple classifiers using local accuracy estimates. IEEE Trans. Pattern Analysis and Machine Intelligence 19(4), 405-410, 1997.

A. Verikas and A. Lipnickas, Fusing neural networks through space partitioning and fuzzy integration, Neural Processing Letters, Kluwer Academic Publishers, 2002.

A. Lipnickas, Classifiers Fusion With Data Dependent Aggregation Schemes, Proceedings of the 7th International Conference on Information Networks, System and Technologies, ICINASTe'2001, Minsk, Belarus, October 2-4, pp.:147-154, 2001.

B. Efron, R. Tibshirani, An introduction to the bootstrap, London, Chapman and Hall, 1993.

L. Breiman, Half&Half bagging and hard boundary points. Technical report 534, Statistics Departament, University of California, Berkeley, 1998. (www.stat.berkley.edu /users/breiman).

D.J. MacKay, Bayesian interpolation, Neural Computation, 4, 415-447, 1992.

EC FP5 Research Training Network DAMADICS: Development and Application of Methods for Actuator Diagnosis in Industrial Control Systems, (http://www.eng.hull.ac.uk/research/control/damadics1.htm).

R. J. Patton, P. M. Frank, R. N. Clark (ed): Issues of Fault Diagnosis for Dynamic Systems. –London: Springer Verlag, 2000.

J. Chen, R. J. Patton, Robust model-based fault diagnosis for dynamic systems, Kluwer Academic Publisher, 1999.

Downloads

Published

2014-08-01

How to Cite

Lipnickas, A., & Korbicz, J. (2014). ADAPTIVE SELECTION OF NEURAL NETWORKS FOR A COMMITTEE DECISION. International Journal of Computing, 3(2), 23-30. https://doi.org/10.47839/ijc.3.2.282

Issue

Section

Articles