C × K-Nearest Neighbor Classification with Ordered Weighted Averaging Distance
In this study, OWA (Ordered Weighted Averaging) distance based C × K-nearest neighbor algorithm (C × K-NN) is considered. In this approach, from each class, where the number of classes is C, K-nearest neighbors are taken. The distance between the new sample and its K-nearest set is determined based on the OWA operator. It is shown that by adjusting the weights of the OWA operator, it is possible to obtain the results of various clustering strategies like single-linkage, complete-linkage, average-linkage, etc.
KeywordsMembership Degree Order Weight Average Order Weight Average Operator Order Weight Average Order Weight Average Weight
The authors would like to thank the anonymous reviewers for the constructive discussions and suggestions to improve the quality of this paper. This work is supported by TUBITAK (Scientific and Technological Research Council of Turkey) Grant No. 111T273.
- 3.B.V. Dasarathy, Visiting nearest neighbor—a survey of nearest neighbor classification techniques, in Proceeding International Conference on Cybernetics Society (1977), pp. 630–636Google Scholar
- 5.J. Friedman, Flexible metric nearest neighbor classification, Technical Report 113, Stanford University, Statistics Department (1994)Google Scholar
- 13.T.D. Pham, An optimally weighted fuzzy k-NN algorithm, in ICAPR’05 Proceedings of the Third international conference on Advances in Pattern Recognition, vol. Part I, (Springer, Berlin, 2005), pp. 239–247Google Scholar
- 15.G. Ulutagay, E. Nasibov, A New C×K-nearest neighbor linkage approach to the classification problem, in Proceedings of the 10th International FLINS Conference, vol. 1, eds. by C. Kahraman, E.K. Kerre, F.K. Bozbura (World Scientific Proceedings on Computer Engineering and Information Science, Istanbul, Turkey, 2012a) , pp. 471–476, ISBN 978-981-4417-73-0Google Scholar
- 16.G. Ulutagay, E. Nasibov, OWA aggregation based C×K-nearest neighbor classification algorithm, in Proceedings of IEEE 6th International Conference Intelligent Systems, vol. 1, ed. by R.R. Yager, V. Sgurev, M. Hadjiski (IEEE Catalog Number CFP12802-PRT, 2012b), pp. 219–224. ISBN 978-1-4673-2782-4Google Scholar