Abstract
The paper considers a classification scheme made up by pooling together multiple classifiers and aggregating their decisions. The individual decisions are treated as degrees of membership assigned by the classifier to the object to be classified. We are interested in how the OWA operators compare to simple voting, linear and logarithmic techniques. In general, all the aggregation schemes appear to be of the same quality, superior to the single classifiers. It was found that OWA operators tend to generalize better than their competitors when the individual classifiers are overtrained. The idea is illustrated on a real and on an artificial data set.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ng, K.-C, Abramson, B.: Consensus diagnosis: a simulation study, IEEE Transactions on Systems, Man, and Cybernetics 22 (1992) 916–928.
Xu, L., Krzyżak, A., Suen, C.Y.: Methods of combining multiple classifiers and their applications to handwriting recognition, IEEE Transactions on Systems, Man, and Cybernetics 22 (1992) 418–435.
Battiti, R., Colla, A.M.: Democracy in neural nets: voting schemes for classification, Neural Networls 7 (1994) 691–707.
Lam, L., Suen, C.Y.: A theoretical analysis of the application of majority voting to pattern recognition, Proc. 12th International Conference on Pattern Recognition, Jerusalem, Israel (1994) 418–420.
Ho, T.K., Hull, J.J., Srihari, S.N.: Decision combination in multiple classifier systems, IEEE Transactions on Systems, Man, and Cybernetics 16 66–75.
Tubbs, J.D., Alltop, W.O. Measures of confidence associated with combining classification results, IEEE Transactions on Systems, Man, and Cybernetics 21 (1991) 690–692.
Jacobs, R.A.: Methods for combining experts’ probability assessments, Neural Computation 7 (1995) 867–888.
Benediktsson, J.A., Swain, P.H.: Consensus theoretic classification methods, IEEE Transactions on Systems, Man, and Cybernetics 22 (1992) 688–704.
Hashem, S., Schmeiser, B., Yih, Y.: Optimal linear combinations of neural networks: An overview, Proc. of the IEEE International Conference on Neural Net-worls, Orlando, Florida (1994) 1507–1512.
Trsep, V., Tanaguchi, M.: Combining estimators using nonconstant weighting functions, in; Tesauro G., Touretzly, D.S., Leen, T.K., eds.: ”Advances in Neural Information Processing Systems 7” MIT Press, Cambridge MA (1995).
Dubois, D., H. Prade. A review of fuzzy aggregation connectives, Information Sciences, 36, 1985, 85–121.
Bloch, I. Information combination operators for data fusion: A comparative review with classification, IEEE Transactions on Systems, Man, and Cybernetics, 26, 1996, 52–67.
Grabisch, M. On equivalence classes of fuzzy connectives — the case of fuzzy integral, IEEE Transactions on Fuzzy Systems, 3, 1995, 96–109.
Yager, R.R. On ordered weighted averaging aggregation operators in multicriteria decisionmaking, IEEE Transactions on Systems, Man, and Cybernetics, 18, 1988, 183–190.
Fodor, J. J.-L. Marichal, M. Roubens. Characterization of the ordered weighted averaging operators, IEEE Transactions on Fuzzy Systems, 3, 1995, 236–240.
Bishop, C. Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
Jacobs, R.A., Jordan, M.I. Adaptive mixture of local experts, Neural Computation 3 (1991) 79–87.
Śmieja, F. The pandemonium system of reflective agents, IEEE Transactions on Neural Networls, 7, 1996, 97–106.
Chiang C.-C, Pu, H.-C: A divide-and-conquer methodology for modular supervised neural network, Proc. IEEE International Conference on Neural Networls, Orlando, Florida (1994) 119–124.
Kuncheva L.I., Change-glasses approach in pattern recognition, Pattern Recognition Letters, 14, 1993, 619–623.
Alpaydin, E. Combining global vs local perceptrons for classification, Proc. International Conference on Soft Computing, SOCO’96, Reading, UK, 1996, B291–297.
Rastrigin, L.A., Erenshtein, R.H.: Method of Gourd Recognition, Moscow, ”En-ergoizdat” (1981).(In Russian)
Dasarathy, B.V., Sheela, B.V.: A composite classifier system designxoncepts and methodology, Proceedings of the IEEE 67 (1979) 708–713.
Filev, D., R.R. Yager. Learning OWA operator weights from data, Proc. IIId IEEE Conference on Fuzzy Systems, Orlando, FL, 1994, 468–473.
L. Prechelt, PROBEN1 — A set of neural network benchmark problems and benchmarking rules, Technical Report # 21/94 (1994).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Kuncheva, L.I. (1997). An Application of OWA Operators to the Aggregation of Multiple Classification Decisions. In: Yager, R.R., Kacprzyk, J. (eds) The Ordered Weighted Averaging Operators. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-6123-1_25
Download citation
DOI: https://doi.org/10.1007/978-1-4615-6123-1_25
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7806-8
Online ISBN: 978-1-4615-6123-1
eBook Packages: Springer Book Archive