PARTIAL TRAINING METHOD FOR HEURISTIC ALGORITHM OF POSSIBLE CLUSTERIZATION UNDER UNKNOWN NUMBER OF CLASSES
Abstract
A method for constructing a subset of labeled objects which is used in a heuristic algorithm of possible clusterization with partial training is proposed in the paper. The method is based on data preprocessing by the heuristic algorithm of possible clusterization using a transitive closure of a fuzzy tolerance. Method efficiency is demonstrated by way of an illustrative example.
References
1. Bezdek, J. C. Pattern recognition with fuzzy objective function algorithms / J. C. Bezdek. – New York : Plenum Press, 1981. – 230 p.
2. Krishnapuram, R. A possibilistic approach to clustering / R. Krishnapuram, J. M. Keller // IEEE Transactions on Fuzzy Systems. – 1993. – Vol. 1. – P. 98–110.
3. Pedrycz, W. Algorithms of fuzzy clustering with partial supervision / W. Pedrycz // Pattern Recognition Letters. – 1985. – Vol. 3. – P. 13–20.
4. Abonyi, J. Supervised fuzzy clustering for the identification of fuzzy classifiers / J. Abonyi, F. Szeifert // Pattern Recognition Letters. – 2003. – Vol. 24. – P. 2195–2207.
5. Liu, H. Evolutionary semi-supervised fuzzy clustering / H. Liu, S.T. Huang // Pattern Recognition Letters. – 2003. – Vol. 24. – P. 3105–3113.
6. Viattchenin, D. A. A new heuristic algorithm of fuzzy clustering / D. A. Viattchenin // Control & Cybernetics. – 2004. – Vol. 33. – P. 323–340.
7. Viattchenin, D. A. A direct algorithm of possibilistic clustering with partial supervision / D. A. Viattchenin // Journal of Automation, Mobile Robotics and Intelligent Systems. – 2007. – Vol. 1. – P. 29–38.
8. Viattchenin, D. A. A methodology of fuzzy clustering with partial supervision / D. A. Viattchenin // Systems Science. – 2007. – Vol. 33. – P. 61–71.
9. Viattchenin, D. A. Fuzzy objective function-based technique of partial supervision for a heuristic method of possibilistic clustering / D. A. Viattchenin // Neural Networks and Artificial Intelligence: Proceedings of the Fifth International Conference ICNNAI'2008. – Minsk, 2008. – P. 51–55.
10. Вятченин, Д. А. Прямые алгоритмы нечеткой кластеризации, основанные на операции транзитивного замыкания и их применение к обнаружению аномальных наблюдений / Д. А. Вятченин // Искусственный интеллект. – 2007. – № 3. – С. 205–216.
11. Looney, C. G. Interactive clustering and merging with a new fuzzy expected value / C. G. Looney // Pattern Recognition. – 2002. – Vol. 35. – P. 2413–2423.
12. Walesiak, M. Ugólniona miara odległości w statys-
13. tycznej analizie wielowymiarowej / M. Walesiak. – Wrocław : Wydawnictwo Akademii Ekonomicznej im. Oskara Langego, 2002. – 107 s.
Review
For citations:
Viattchenin D.A. PARTIAL TRAINING METHOD FOR HEURISTIC ALGORITHM OF POSSIBLE CLUSTERIZATION UNDER UNKNOWN NUMBER OF CLASSES. Science & Technique. 2009;(5):67-74. (In Russ.)