Qualitative test-cost sensitive classification

This paper reports a new framework for test-cost sensitive classification. It introduces a new loss function definition, in which misclassification cost and cost of feature extraction are combined qualitatively and the loss is conditioned with current and estimated decisions as well as their consistency. This loss function definition is motivated with the following issues. First, for many applications, the relation between different types of costs can be expressed roughly and usually only in terms of ordinal relations, but not as a precise quantitative number. Second, the redundancy between features can be used to decrease the cost; it is possible not to consider a new feature if it is consistent with the existing ones. In this paper, we show the feasibility of the proposed framework for medical diagnosis problems. Our experiments demonstrate that this framework is efficient to significantly decrease feature extraction cost without decreasing accuracy.

[1]  J. Doyle,et al.  Background to qualitative decision theory : Special articles on Bayesian techniques , 1999 .

[2]  Jon Doyle,et al.  Background to Qualitative Decision Theory , 1999, AI Mag..

[3]  Lawrence Carin,et al.  Cost-sensitive feature acquisition and classification , 2007, Pattern Recognit..

[4]  Judea Pearl,et al.  Specification and Evaluation of Preferences Under Uncertainty , 1994, KR.

[5]  Qiang Yang,et al.  Test-cost sensitive classification on data with missing values , 2006, IEEE Transactions on Knowledge and Data Engineering.

[6]  Cigdem Demir,et al.  Test-Cost Sensitive Classification Based on Conditioned Loss Functions , 2007, ECML.

[7]  Ronen I. Brafman,et al.  Qualitative decision making in adaptive presentation of structured information , 2004, TOIS.

[8]  Charles Elkan,et al.  The Foundations of Cost-Sensitive Learning , 2001, IJCAI.

[9]  Daniel Lehmann,et al.  Expected Qualitative Utility Maximization , 2001, Games Econ. Behav..

[10]  Craig Boutilier,et al.  Toward a Logic for Qualitative Decision Theory , 1994, KR.

[11]  Steven W. Norton.  Generating Better Decision Trees , 1989, IJCAI.

[12]  Didier Dubois,et al.  Qualitative decision theory: from savage's axioms to nonmonotonic reasoning , 2002, JACM.

[13]  Peter D. Turney.  Types of Cost in Inductive Concept Learning , 2002, ArXiv.

[14]  Robert P. W. Duin,et al.  On the Choice of Smoothing Parameters for Parzen Estimators of Probability Density Functions , 1976, IEEE Transactions on Computers.

[15]  Jason V. Davis,et al.  Cost-Sensitive Decision Tree Learning for Forensic Classification , 2006, ECML.

[16]  Ming Tan,et al.  Cost-Sensitive Learning of Classification Knowledge and Its Applications in Robotics , 1993, Machine Learning.

[17]  Peter D. Turney.  Low Size-Complexity Inductive Logic Programming: The East-West Challenge Considered as a Problem in Cost-Sensitive Classification , 2002, ArXiv.

[18]  Marlon Núñez,et al.  The Use of Background Knowledge in Decision Tree Induction , 1991, Machine Learning.

[19]  Cigdem Demir,et al.  Cost-conscious classifier ensembles , 2005, Pattern Recognit. Lett..

[20]  Ronen I. Brafman,et al.  On the Foundations of Qualitative Decision Theory , 1996, AAAI/IAAI, Vol. 2.

[21]  Peter D. Turney.  Cost-Sensitive Classification: Empirical Evaluation of a Hybrid Genetic Decision Tree Induction Algorithm , 1994, J. Artif. Intell. Res..

[22]  Silja Renooij,et al.  From Qualitative to Quantitative Probabilistic Networks , 2002, UAI.

[23]  Thomas G. Dietterich,et al.  Pruning Improves Heuristic Search for Cost-Sensitive Learning , 2002, ICML.

[24]  Michael P. Wellman.  Fundamental Concepts of Qualitative Probabilistic Networks , 1990, Artif. Intell..

[25]  Benjamin Kuipers,et al.  Qualitative reasoning: Modeling and simulation with incomplete knowledge , 1994, Autom..

[26]  Y. Zhang,et al.  Active and dynamic information fusion for multisensor systems with dynamic bayesian networks , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[27]  Hélène Fargier,et al.  Qualitative Decision under Uncertainty: Back to Expected Utility , 2003, IJCAI.

[28]  Michael P. Wellman.  Graphical inference in qualitative probabilistic networks , 1990, Networks.

[29]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[30]  Didier Dubois,et al.  Possibility Theory as a Basis for Qualitative Decision Theory , 1995, IJCAI.

[31]  Janneke H. Bolt,et al.  Upgrading Ambiguous Signs in QPNs , 2003, UAI.

[32]  Richmond H. Thomason,et al.  Desires and Defaults: A Framework for Planning with Inferred Goals , 2000, KR.

[33]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[34]  Marek J. Druzdzel,et al.  Belief Propagation in Qualitative Probabilistic Networks , 1993 .

[35]  David G. Stork,et al.  Pattern Classification , 1973 .

[36]  D. Dubois,et al.  Decision-making under ordinal preferences and uncertainty , 1997 .

[37]  Silja Renooij,et al.  Decision Making in Qualitative Influence Diagrams , 1998, FLAIRS.

[38]  J. Neumann,et al.  Theory of Games and Economic Behavior. , 1945 .

[39]  Qiang Yang,et al.  Test-cost sensitive naive Bayes classification , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[40]  Christopher J. Merz,et al.  UCI Repository of Machine Learning Databases , 1996 .

[41]  Niall M. Adams,et al.  Comparing classifiers when the misallocation costs are uncertain , 1999, Pattern Recognit..

[42]  Phan Hong Giang,et al.  A Comparison of Axiomatic Approaches to Qualitative Decision Making Using Possibility Theory , 2001, UAI.

[43]  Victor S. Sheng,et al.  Feature value acquisition in testing: a sequential batch test algorithm , 2006, ICML.

[44]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.