This Article 
 Bibliographic References 
 Add to: 
A Method for Attribute Selection in Inductive Learning Systems
November 1988 (vol. 10 no. 6)
pp. 888-896

A computable measure was developed that can be used to discriminate between attributes on the basis of their potential value in the formation of decision rules by the inductive learning process. This relevance measure is the product of extensions to an information-theoretic foundation that address the particular characteristics of a class of inductive learning algorithms. The measure is also conceptually compatible with approaches from pattern recognition. It is described in the context of a generalized model of the expertise development process, and an experiment is presented in which a significant reduction in the number of attributes to be considered was achieved for a complex medical domain.

[1] H. C. Andrews,Introduction to Mathematical Techniques In Pattern Recognition. New York: Wiley, 1972.
[2] D. Angluin and C. H. Smith, "A survey of inductive inference: Theory and Methods," Yale Univ., New Haven, CT, Tech. Rep. 250, 1982.
[3] P. W. Baim, "Automated acquisition of decision rules: The problems of attribute construction and selection," M.S. thesis, Dep. Univ. Comput. Sci., Univ. Illinois at Urbana-Champaign, 1984.
[4] A. D. Bethke, "Genetic algorithms as function optimizers," Ph.D. dissertation, Univ. Michigan, 1980.
[5] J. H. Booze, "Rapid acquisition and combination of knowledge from multiple experts in the same domain," inProc. Second Conf. AI Applications, Miami Beach, FL, Dec. 11-13, 1985.
[6] B. G. Buchanan, "Steps toward mechanizing discovery," Stanford Heuristic Programming Project, Stanford Univ., Memo HPP-79-28, 1979.
[7] C. H. Chin, "On a class of computationally efficient feature selection criteria,"Pattern. Recognition, vol. 7, pp. 87-94, 1975.
[8] W. J. Clancey, "The epistemology of a rule-based expert system: A framework for explanation," Dep. Comput. Sci., Stanford Univ., Rep. STAN-CS-81-896, 1981.
[9] P. R. Cohen and E. A. Feigenbaum,The Handbook of Artificial Intelligence, vol. 3, Los Altos, CA: William Kaufman, 1982.
[10] J. H. Davis, "CONVART: A program for constructive induction on time dependent data," M.S. thesis, Dep. Comput. Sci., Univ. Illinois at Urbana-Champaign, 1981.
[11] T. G. Dietterich and B. G. Buchanan, "The role of the critic in learning systems," Dep. Comput. Sci., Stanford Univ., Rep. STAN-CS- 81-891, 1981.
[12] R. O. Duda and P. E. Hart,Pattern Classification and Scene Analysis. New York: Wiley, 1973.
[13] H. H. Harmon,Modern Factor Analysis. Chicago, IL: University of Chicago Press, 1960.
[14] F. Hayes-Roth, P. Klahr, and D. J. Mostow, "Knowledge acquisition, knowledge programming, and knowledge refinement," Rand, Santa Monica, CA, Rand Publication Series Rep. R-2540-NSF, 1980.
[15] F. Hayes-Roth, "The knowledge-based expert system: A tutorial,"Computer, vol. 17, no. 9, pp. 11-28, 1984.
[16] L. N. Kanal, "Some current concepts and problems in pattern classification and feature extraction," Univ. Maryland, College Park, Comput. Sci. Tech. Rep. TR-640, 1978.
[17] Y. Kodratoff and R. Lemerle-Loisel, "Learning complex structural descriptions from examples," inProc. European Conf. AI, Orsay, France, 1982.
[18] D. N. Lawley and A. E. Maxwell,Factor Analysis as a Statistical Method. London: Butterworth, 1963.
[19] G. S. Lbov, "Selection of an effective system of dependent features," Inst. Math., Acad. Sci., Novosibirsk, USSR, Rep. 19, 1965.
[20] R. S. Michalski, "A variable-valued logic system as applied to picture description and recognition,"Graphic Languages, F. Nake and A. Rosenfeld, Eds. Amsterdam,The Netherlands, North-Holland, 1972.
[21] R. S. Michalski and J. B. Larson, "Selection of most representative training examples and incremental generation of VL1hypotheses," Dep. Comput. Sci., Univ. Illinois, Rep. 867, 1978.
[22] R. S. Michalski, "Inductive inference as rule-guided transformation of symbolic descriptions (Invited Paper)," inProc. Int. Workshop Program Construction, Chatau de Bonas, France, Sept. 8-12, 1980.
[23] R. S. Michalski, J. H. Davis, V. S. Bisht, and J. B. Sinclair, "'PLANT/ds: An expert consulting system for the diagnosis of soybean diseases," inProc. European Conf. AI, Orsay, France, 1982.
[24] R. S. Michalski, "Studies in inductive and plausible inference," research proposal submitted to the National Science Foundation, Dep. Comput. Sci., Univ. of Illinois, Urbana, 1982.
[25] H. Pople, "The formation of composite hypotheses in diagnostic problem solving--An exercise in synthetic reasoning," inProc. IJCAI 5.
[26] J. R. Quinlan, "Fundamentals of the knowledge engineering problem," inIntroductory Readings in Expert Systems, D. Michie, Ed. New York: Gordon and Breach, 1982.
[27] J. R. Quinlan, "Inductive inference as a tool for the construction of high-performance programs," inMachine Learning, R. S. Michalski, T. M. Mitchell, and J. Carbonell, Eds. Palo Alto, CA: Tioga, 1983.
[28] M. O. Rabin, "Theoretical impediments to artificial intelligence," inInformation Processing 74. Amsterdam, The Netherlands: North-Holland, 1974.
[29] E. Y. Shapiro, "Inductive inference of theories from facts," Dep. Comput. Sci., Yale Univ., Res. Rep. 192, 1981.
[30] S. F. Smith, "A learning system based on genetic adaptive algorithms," Ph.D. dissertation, Univ. Pittsburgh, 1980.
[31] K. Spackman, MD, personal communications, 1983.
[32] S. D. Stearns, "On selecting features for pattern classifiers," GTE Sylvania Security Systems Dep. Mountain View, CA, 1976.
[33] R. E. Steppet al., "GEM user's guide," Dep. Comput. Sci., Univ. Illinois, Internal Rep. 1983.
[34] J. T. Tou and R. C. Gonzalez,Pattern Recognition Principles, Reading, MA: Addison, 1974.
[35] K. W. Tunstall, "Recognizing patterns: Are there processes that precede feature analysis?"Pattern Recognition, vol. 7, pp. 95-106, 1975.
[36] H. L. Van Trees,Detection, Estimation, and Modulation Theory, Vol. I. New York: Wiley, 1968.
[37] L. A. Zadeh, "Possibility theory and soft data analysis," inMathematical Frontiers of the Social and Policy Sciences, L. Cobb and R. Thrall, Eds. Boulder, CO: Westview Press, 1981.

Index Terms:
machine learning; rule based systems; knowledge acquisition; attribute selection; inductive learning systems; decision rules; pattern recognition; artificial intelligence; knowledge acquisition; learning systems; pattern recognition
P.W. Baim, "A Method for Attribute Selection in Inductive Learning Systems," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 6, pp. 888-896, Nov. 1988, doi:10.1109/34.9110
Usage of this product signifies your acceptance of the Terms of Use.