Abstract
Interactive expert systems seek relevant information from a user in order to answer a query or to solve a problem that the user has posed. A fundamental design issue for such a system is therefore itsinformation-seeking strategy, which determines the order in which it asks questions or performs experiments to gain the information that it needs to respond to the user. This paper examines the problem of “optimal” knowledge acquisition through questioning in contexts where it is expensive or time-consuming to obtain the answers to questions. An abstract model of an expert classification system — considered as a set of logical classification rules supplemented by some statistical knowledge about attribute frequencies — is developed and applied to analyze the complexity and to present constructive algorithms for doing probabilistic question-based classification. New heuristics are presented that generalize previous results for optimal identification keys and questionnaires. For an important class of discrete discriminant analysis problems, these heuristics find optimal or near-optimal questioning strategies in a small fraction of the time required by an exact solution algorithm.
Similar content being viewed by others
References
L. Breiman, J. Friedman, R. Olshen and C. Stone,Classification and Regression Trees (Wadsworth, Belmont, CA, 1984).
K.A. Grajski et al., Classification of EEG spatial patterns with a tree structured methodology: CART, IEEE Trans. Biomed. Eng. EME-33 (1986) 1076–1086.
L. Gordon and R.A. Olshen, Tree-structured survival analysis, Cancer Treatment Reports 69 (1985) 1065–1069.
M.R. Segal, Recursive Partitioning Using Ranks, Tech. Report no. 15, Department of Statistics, Stanford University (August, 1985).
A. Ciampi et al., Recursive partitioning algorithms: A versatile method for exploratory data analysis in biostatistics, in:Biostatistics, eds I.B. MacNeill and G. Umphrey (Reidel, Boston, MA, 1987).
J.R. Quinlan, The effect of noise on concept learning, in:Machine Learning: An Artificial Intelligence Approach, eds. R.S. Michalski et al. (Morgan Kaufmann, Los Altos, CA, 1986) chap. 6.
J.Q. Quinlan, Generating production rules from decision trees,IJCAI '87 (Morgan Kaufmann, Los Altos, CA, 1987).
J.C. Schlimmer and D. Fisher, A case study of incremental concept induction,AAAI-86 Proc., 1 (Morgan Kaufmann, Los Altos, CA, 1986) pp. 496–501.
L.A. Cox, Jr., Pragmatic information-seeking strategies in expert classification systems, in:OR/AI: The Integration of Problem Solving Strategies, eds. D. Brown and C. White (Kluwer, 1990, in press).
D.H. Fisher, Knowledge acquisition via incremental conceptual clustering, Machine Learning 2 (1987) 139–172.
G.T. Duncan, Optimal diagnostic questionnaires, Oper. Res. 23 (1975) 22–32.
Y. Ben-Dov, Optimal testing procedures for special structures of coherent systems, Management Sci. 27 (1981) 1410–1420.
J. Halpern, Fault-testing of a k-out-of-n system, Oper. Res. 22 (1974) 1267–1271.
D. Angluin and P. Laird, Learning from noisy examples, Machine Learning 2 (1988) 343–370.
N. Littlestone, Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm, ibid., 235–318.
L.G. Valiant, A theory of the learnable, Commun. ACM 27 (1984) 1134–1142.
L.A. Cox, Jr., Y. Qiu and W. Kuehner, Heuristic least-cost computation of discrete classification functions with uncertain argument values, Ann. Oper. Res.:Artificial Intelligence and Operations Research (to appear).
R.W. Payne and D.A. Preece, Identification keys and diagnostic tables: A review, J.R. Statist. Soc. A143 (1980) 253–292.
C.J. Colbourn,The Combinatorics of Network Reliability (Oxford University Press, New York, 1987).
K.S. Fu,Sequential Methods in Pattern Recognition and Machine Learning (Academic Press, New York, 1968).
M. James,Classification Algorithms (Wiley, New York, 1985).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Cox, L.A. Incorporating statistical information into expert classification systems to reduce classification costs. Ann Math Artif Intell 2, 93–107 (1990). https://doi.org/10.1007/BF01530999
Issue Date:
DOI: https://doi.org/10.1007/BF01530999