Rough Set Approach to Domain Knowledge Approximation

• Autorzy: Nguyen T.T.
• Języki publikacji: EN

Abstrakty

EN

Classification systems working on large feature spaces, despite extensive learning, often perform poorly on a group of atypical samples. The problem can be dealt with by incorporating domain knowledge about samples being recognized into the learning process. We present a method that allows to perform this task using a rough approximation framework. We show how human expert's domain knowledge expressed in natural language can be approximately translated by a machine learning recognition system. We present in details how the method performs on a system recognizing handwritten digits from a large digit database. Our approach is an extension of ideas developed in the rough mereology theory.

Słowa kluczowe

EN

rough mereology; concept approximations; domain knowledge; machine learning; handwritten digit recognition

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2004
• Tom: Vol. 59, nr 2,3
• Strony: 261--270
• Opis fizyczny: Bibliogr. 11 poz., tab., wykr.

Twórcy

autor

Nguyen T.T.

• Warsaw University, ul. Banacha 2, 02-097 Warsaw, Poland,

Bibliografia

• [1] P. Doherty, W. Lukasiewicz, and A. Skowron. Knowledge Engineering: Rough Set Approach. Physica Verlag, in preparation.
• [2] J. Geist, R. A. Wilkinson, S. Janet, P. J. Grother, B. Hammond, N. W. Larsen, R. M. Klear, C. J. C. Burges, R. Creecy, J. J. Hull, T. P. Vogl, and C. L. Wilson. The second census optical character recognition systems conference. NIST Technical Report N1STIR 5452, pages 1-261, 1994.
• [3] K. Komori, T. Kawatani, K. Ishii, and Y. Iida. A feature concentrated method for character recognition. In Bruce Gilchrist, editor. Information Processing 77, Proceedings of the International Federation for Information Processing Congress 77, pages 29-34, Toronto, Canada. August 8-12, 1977. North Holland.
• [4] Z.C. Li, C.Y. Suen, and J. Guo. Hierarchical models for analysis and recognition of handwritten characters. Annals of Mathematics and Artificial Intelligence, pages 149-174, 1994.
• [5] Tuan Trung Nguyen and Andrzej Skowron. Rough set approach to domain knowledge approximation. In G. Wang, Q. Liu, Y. Yao, and A. Skowron, editors. Proceedings of the 9th International Conference: Rough Sets. Fuzzy Sets. Data Mining, and Granular Computing. RSFDGRC '03. Lecture Notes in Computer Science Vol. 2639, pages 221-228. Chongqing, China. Oct 19-22, 2003. Springer Verlag.
• [6] L. Polkowski and A. Skowron. Rough mereology: A new paradigm for approximate reasoning. Journal of Approximate Reasoning, 15(4):333-365, 1996.
• [7] L. Polkowski and A. Skowron. Towards adaptive calculus of granules. In L.A. Zadeh and J. Kacprzyk, editors. Computing with Words in Information/Intelligent Systems, pages 201-227, Heidelberg, 1999. Physica-Verlag.
• [8] L. Polkowski and A. Skowron. Rough mereology in information systems, a case study: Qualitative spatial reasoning. In L. Polkowski, T.Y. Lin, and S. Tsumoto, editors. Rough Set Methods and Applications: New Developments in Knowledge Discoverу in Information Systems, volume 56, pages 89-136. Heidelberg, Germany, 2000. Physica-Verlag.
• [9] L. Polkowski and A. Skowron. Constructing rough mereological granules of classifying rules and classifying algorithms. In B. Bouchon-Meunier. J.Rios-Gutierrez, L. Magdalena, and R.R. Yager, editors. Technologies for Constructing Intelligent Systems I, pages 57-70. Heidelberg, 2002. Physica-Verlag.
• [10] Robert J. Schalkoff. Pattern Recognition: Statistical. Structural and Neural Approaches. John Wiley & Sons, Inc., 1992.
• [11] A. Skowron and L. Polkowski. Rough mereological foundations for design, analysis, synthesis, and control in distributed systems. Information Sciences, 104(1-2): 129-156, 1998.