Rough modeling - a bottom-up approach to model construction

Loken, Terje ; Komorowski, Jan

International Journal of Applied Mathematics and Computer Science, Tome 11 (2001), p. 675-690 / Harvested from The Polish Digital Mathematics Library

Résumé

Traditional data mining methods based on rough set theory focus on extracting models which are good at classifying unseen obj-ects. If one wants to uncover new knowledge from the data, the model must have a high descriptive quality-it must describe the data set in a clear and concise manner, without sacrificing classification performance. Rough modeling, introduced by Kowalczyk (1998), is an approach which aims at providing models with good predictive emphand descriptive qualities, in addition to being computationally simple enough to handle large data sets. As rough models are flexible in nature and simple to generate, it is possible to generate a large number of models and search through them for the best model. Initial experiments confirm that the drop in performance of rough models compared to models induced using traditional rough set methods is slight at worst, and the gain in descriptive quality is very large.

Détail

Publié le : 2001-01-01

Zbl 1010.93009

EUDML-ID : urn:eudml:doc:207526

Bibliographie

[000] Ågotnes T., Komorowski J. and Rhrn A. (1999a): Finding small high performance subsets of induced rule sets. - Proc. 7-th Europ. Congress Intelligent Techniques and Soft Computing, EUFIT'99, Aachen, Germany, p.174.

[001] Ågotnes T., Komorowski J. and Lrken T. (1999b): Taming large rule models in rough set approaches, In: Principles of Data Mining and Knowledge Discovery (J.M. Zytkow and J. Rauch, Eds.). - Berlin: Springer-Verlag.

[002] Bazan J.G., Skowron A. and Synak P. (1994): Dynamic reducts as a tool for extracting laws from decision tables, In: Methodologies for Intelligent Systems (Z.W. Ras and M. Zemankova, Eds.). - New York: Springer, pp.346-355.

[003] Blake C., Keogh E. and Merz C.J. (1998): UCI repository of machine learning databases. - Available at: http://www.ics.uci.edu/~mlearn/MLRepository.html

[004] Carlin U., Komorowski J. and Rhrn A. (1998): Rough set analysis of patients with suspected acute appendicitis. - Proc. 7-th Conf. Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU'98, Paris, France,pp.1528-1533.

[005] Goldberg D.E. (1989): Genetic Algorithms in Search, Optimization, and Machine Learning. - New York: Addison-Wesley. | Zbl 0721.68056

[006] Greco S., Matarazzo B. and Słowinski R. (1998): New developments in the rough set approach to multi-attribute decision analysis. - Bull. Int. Rough Set Soc., Vol.2, No.23, pp.57-87.

[007] Hallan S., Lsberg A. and Edna T.-H. (1997a): Additional value of biochemical tests in suspected acute appendicitis. - Europ.J. Surgery, Vol.163, No.7, pp.533-538.

[008] Hallan S., Lsberg A. and Edna T.-H. (1997b): Estimating the probability of acute appendicitis using clinical criteria of a structured record sheet: The physician against the computer.- Europ. J. Surgery, Vol. 163, No.6, pp.427-432.

[009] Hanley J.A. and McNeil B.J. (1982): The meaning and use of the area under a receiver operating characteristic (roc) curve.- Radiology, Vol. 143, pp.29-36.

[010] Holte R.C. (1993): Very simple classification rules perform well on most commonly used datasets. - Mach. Learn., Vol.11,pp.63-91. | Zbl 0850.68278

[011] hrn A. (2001): The ROSETTA home page, 2001. - http://rosetta.sourceforge.net and http://www.idi.ntnu.no/~aleksrosetta.

[012] hrn A., Komorowski J., Skowron A. and Synak P. (1998): The design and implementation of a knowledge discovery toolkit based on rough sets- the ROSETTA system, In: Rough Sets in Knowledge Discovery 1: Methodology and Applications. - Heidelberg: Physica-Verlag, Ch.19, pp.376-399. | Zbl 0927.68093

[013] Imam I.F. (1996): An empirical study on the incompetence of attribute selection criteria, In: Foundations of Intelligent Systems (Z.W. Raś and M. Michalewicz, Eds.). - Berlin: Springer, pp.458-467.

[014] Klösgen W. (1996): Knowledge discovery in databases and data mining, In: Foundations of Intelligent Systems (Z.W. Raś and M. Michalewicz, Eds.). - Berlin: Springer, pp.623-632.

[015] Kohavi R. and Frasca B. (1994): Useful feature subsets and rough set reducts. - Proc. 3-rd Int. Workshop Rough Sets and Soft Computing (RSSC '94), San Jose, USA.

[016] Kohavi R. and John G.H. (1997): Wrappers for feature subset selection. - Artif. Intell. J., Vol.97, No.1-2, pp.273-324. | Zbl 0904.68143

[017] Kohavi R. and Sommerfield D. (1995): Feature subset selection using the wrapper method: Overfitting and dynamic search space topology. - Proc. 1-st Int. Conf. Knowledge Discovery and Data Mining, KDD'95.

[018] Kowalczyk W. (1998): Rough data modelling: A new technique for analyzing data, In: Rough Sets and Knowledge Discovery 1: Methodology and Applications. - Heidelberg: Physica-Verlag, Ch.20, pp.400-421. | Zbl 0940.68036

[019] Mienko R., Stefanowski J. and Vanderpooten D. (1996): Discovery-oriented induction of decision rules. - Tech. Rep., Cahier du Lamsade No. 141, Universite de Paris Dauphine. | Zbl 0969.68135

[020] Mollestad T. and Komorowski J. (1998): A rough set framework for propositional default rules data mining, In: Rough-Fuzzy Hybridization: A New Trend in Decision Making. - Berlin: Springer-Verlag.

[021] Pawlak Z. (1991): Rough Sets-Theoretical Aspects of Reasoning about Data. - Dordrecht: Kluwer. | Zbl 0758.68054

[022] Provost F., Fawcett T. and Kohavi R. (1998): The case against accuracy estimation for comparing induction algorithms. - Proc. 15-th Int. Conf. Machine Learning (ICML'98).

[023] Russell S. and Norvig P. (1995): Artificial Intelligence-A Modern Approach. - Prentice-Hall. | Zbl 0835.68093

[024] Skowron A. and Rauszer C. (1991): The discernibility matrices and functions in information systems, In: Intelligent Decision Support Systems-Handbook of Applications and Advances in Rough Set Theory (R. Słowinski, Ed.). - Dordrecht: Kluwer, pp.331-362.