Summary
This chapter addresses issues concerning a problem of constructing an optimal classification algorithm. The notion of a parameterized approximation space is used to model the process of classifier construction. The process can be viewed as hierarchical searching for optimal information granulation to fit a concept described by empirical data. The problem of combining several parameterized information granules (given by classification algorithms) to obtain a global data description is described. Some solutions based on adaptive methods are presented.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Reference
Th. Bäck. An overview of parameter control methods by self-adaptation in evolutionary algorithms. Fundamenta Informaticae, 35(1): 51–66,1998.
S.D. Bay. Combining nearest neighbor classifiers through multiple feature subsets. In Proceedings of the 15th International Conference on Machine Learning (ICML’98), Morgan Kaufmann, San Mateo, CA, 1998.
J.G. Bazan, H.S. Nguyen, S.H. Nguyen, P. Synak, J. Wróblewski. Rough set algorithms in classification problem. In L. Polkowski, S. Tsumoto, and T.Y. Lin, editors, Rough Set Methods and Applications: New Developments in Knowledge Discovery in Information Systems, 49–88, Physica, Heidelberg, 2000.
I. Düntsch, G. Gediga. Uncertainty measures of rough set prediction. Artificial Intelligence, 106: 77–107, 1998.
I. Düntsch, G. Gediga, H.S. Nguyen. Rough set data analysis in the KDD process. In Proceedings of the 8th International Conference on Information Processing and Management under Uncertainty (IPMU 2000), 220–226, Madrid, Spain, 2000.
I.T. Jolliffe. Principal Component Analysis. Springer, Berlin, 1986.
M. Li, P. Vitanyi. An Introduction to Kolmogorov Complexity and its Applications. Springer, New York, 1993.
T.Y. Lin, A.M. Wildberger, editors. Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery. Simulation Councils, San Diego, CA, 1995.
H. Liu, H. Motoda, editors. Feature Extraction, Construction and Selection: A Data Mining Perspective. Kluwer, Dordrecht, 1998.
S.H. Nguyen, L. Polkowski, A. Skowron, P. Synak, J. Wrblewski. Searching for approximate description of decision classes. In Proceedings of the 4th International Workshop on Rough Sets, Fuzzy Sets and Machine Discovery, (RSFD’96), 153–161, Tokyo, 1996.
H.S. Nguyen. Discretization of Real Value Attributes: Boolean Reasoning Approach. Ph.D. Dissertation, Faculty of Mathematics, Informatics and Mechanics, Warsaw University, 2002.
H.S. Nguyen, A.Skowron, J.Stepaniuk. Granular computing: A rough set approach. Computational Intelligence, 17(3): 514–544, 2001.
S.K. Pal, W. Pedrycz, A. Skowron, R. Swiniarski, editors. Rough-neuro computing (special issue). Vol. 36 of Neurocomputing: An International Journal, 2001.
Z. Pawlak. Rough Sets: Theoretical Aspects of Reasoning about Data. Kluwer, Dordrecht, 1991.
L. Polkowski, A. Skowron, J. Zytkow. Tolerance based rough sets. In [18], 55–58, 1994.
L. Polkowski, A. Skowron. Rough mereological foundations for design, analysis, synthesis and control in distributed systems. Information Sciences, 104(1/2): 129–156, 1998.
L. Polkowski, A. Skowron, editors. Rough Sets in Knowledge Discovery Vols. 1, 2. Physica, Heidelberg, 1998.
L. Polkowski, A. Skowron, editors. Rough-Neuro Computing. In Proceedings of the 2nd International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000), LNAI 2005, 25–32, Springer, Heidelberg, 2001.
RSES homepage-rough set based data analysis system. Available at http://loic.mimuw.edu.plrrses/
A. Skowron. Approximation spaces in rough neurocomputing. In S. Hirano, M. Inuiguchi, S. Tsumoto, editors, Rough Set Theory and Granular Computing, Physica, Heidelberg, to appear.
A. Skowron, J. Stepaniuk. Approximation of relations. In [38], 161–166, 1993.
A. Skowron, J. Stepaniuk. Generalized approximation spaces. In T.Y. Lin, A.M. Wild-berger, editors, Soft Computing: Rough Sets, Fuzzy Logic, Neural Networks, Uncertainty Management, Knowledge Discovery 18–21, Simulation Councils, San Diego, CA, 1995.
A. Skowron, J. Stepaniuk. Tolerance approximation spaces. Fundamenta Informaticae, 27: 245–253, 1996.
A. Skowron, J. Stepaniuk. Information granule decomposition. Fundamenta Informaticae, 47: 337–350, 2001.
R. Slowiñski, D. Vanderpooten. Similarity Relation as a Basis for Rough Approximations. Report number 53/95 of the Institute of Computer Science, Warsaw University of Technology, 1995; see also P.P. Wang, editor, Advances in Machine Intelligence & Soft Computing, 17–33,Bookwrights,Raleigh,NC, 1997.
J. Stepaniuk. Approximation spaces, reducts and representatives. In L. Polkowski, A. Skowron, editors, Rough Sets in Knowledge Discovery, Vol. 2, 109–126, Physica, Heidelberg, 1998.
J. Stepaniuk. Knowledge discovery by application of rough set methods. In L. Polkowski, T.Y. Lin, S. Tsumoto, editors, Rough Sets: New Developments in Knowledge Discovery in Information Systems, Physica, Heidelberg, 2000.
D. Ślęzak. Approximate reducts in decision tables. In Proceedings of the 7th International Conference on Information Processing and Management under Uncertainty (IPMU’96), 1159–1164, Universidad da Granada, Granada, 1996.
D. Ślęzak, J.Wróblewski. Classification algorithms based on linear combinations of features. In Proceedings of the 3rd European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD’99), LNAI 1704, 548–553, Springer, Berlin, 1999.
D. Ślęzak, J. Wróblewski. Application of normalized decision measures to the new case classification. In Proceedings of the 2nd International Conference on Rough Sets and Current Trends in Computing (RSCTC 2000), LNAI 2005, 515–522, Springer, Berlin, 2000.
D. Ślęzak. Approximate Decision Reducts. Ph.D. Dissertation, Faculty of Mathematics, Informatics and Mechanics, Warsaw University, 2002 (in Polish).
P. Stone. Layered Learning in Multi-Agent Systems: A Winning Approach to Robotic Soccer. MIT Press, Cambridge, MA, 2000.
J. Wróblewski. Analyzing relational databases using rough set based methods. In Proceedings of the 8th Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2000), 256–262, Madrid, Spain, 2000.
J.Wróblewski. Ensembles of classifiers based on approximate reducts. In Proceedings of the Workshop on Concurrency, Specification and Programming (CS&P 2000), volume 140(2) of Informatik-Bericht, 355–362, Humboldt-Universität, Berlin, 2000; also in Fundamenta Informaticae, 47(3/4): 351–360, 2001.
J. Wróblewski. Adaptive Methods of Object Classification. Ph.D. Dissertation, Faculty of Mathematics, Informatics and Mechanics, Warsaw University, 2002 (in Polish).
L.A. Zadeh, J.Kacprzyk, editors. Computing with Words in Information/Intelligent Systems, Vols. 1, 2. Physica, Heidelberg, 1999.
W. Ziarko. Variable precision rough set model. Journal of Computer and System Sciences, 46: 39–59, 1993.
W. Ziarko, editor.Proceedings of the International Workshop on Rough Sets, Fuzzy Sets and Knowledge Discovery (RSKD’93),Workshops in Computing,Springer & British Computer Society, London, Berlin,1994.
W. Ziarko. Approximation region-based decision tables. In Proceedings of the 1st International Conference on Rough Sets and Current Trends in Computing (RSCTC’98), LNAI 1424, 178–185, Springer, Berlin, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Wróblewski, J. (2004). Adaptive Aspects of Combining Approximation Spaces. In: Pal, S.K., Polkowski, L., Skowron, A. (eds) Rough-Neural Computing. Cognitive Technologies. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18859-6_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-18859-6_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-62328-8
Online ISBN: 978-3-642-18859-6
eBook Packages: Springer Book Archive