Home Kontakt Lehre Research Software


Publications of year 1988

Books and proceedings

  • Simon French. Decision Theory - An Introduction to the Mathematics of Rationality, Mathematics and Its Applications. 1988.
    Keywords: Decision Trees.
    Abstract: Decision Problems, Decisions under Strict Uncertainty, Preference Orders and Value Functions, Multi-Attribute Value Theory, Utility Theory, Objective and Subjective Probability, Decision Trees and Multi-Stage Problems, Group Decisions and Social Choice, Measurement, Modelling and Interpretation, Some Non-Bayesian Approaches,
  • Anil K. Jain and Richard C. Dubes. Algorithms for Clustering Data. 1988.
    Keywords: Clustering, Cluster Validity Measures, Image Data.
    Abstract: Chapter headings: Introduction, Data Representation (Data Types and Data Scales, Proximity Indices, Normalization, Linear Projections, Nonlinear Projections, Intrinsic Dimensionality, Multidimensional Scaling), Clustering Methods and Algorithms (Hierarchical Clustering, Partitional Clustering, Clustering Software, Clustering Methodology), Cluster Validity (Background, Indices of Cluster Validity, Validity of Hierarchical Structures/Partitional Structures/Individual Clusters, Clustering Tendency), Applications (Image Processing, Image Segmentation by Clustering, Segmentation of Textured Images/Range Images/Multispectral Images, Image Registration), Appendix (Pattern Recognition, Distributions, Linear Algebra, Scatter Matrices, Factor Analysis, Multivariate Analysis of Variance, Graph Theory, Algorithm for Generating Clustered Data)

Articles in journal or book's chapters

  • Rodney M. Goodman and Padhraic Smyth. Decision Tree Design from a Communication Theory Standpoint. TIT, 34(5):979--994, 1988.
    Keywords: Noise Handling, Classification, Decision Trees, Nearest Neighbour Methods.
    Abstract: The design of efficient decision trees from labeled sample data is currently an important topic in several fields, such as pattern recognition and expert system design. A communication theory approach to decision tree design based on a {\sl top-down} mutual information algorithm is presented. We state and prove that this algorithm is equivalent to a form of Shannon-Fano prefix coding and derive several fundamental bounds relating decision tree parameters. We then use these bounds, in conjunction with a rate-distortion interpretation of tree design, to explain several phenomena previously observed in practical descion tree design. We also propose a new termination rule for the algorithm, called the delta-entropy rule, which improves the robustness of the algorithm in the presence of noise, compared with existing methods. Simulation results are presented from which we show that the tree classifiers derived by our algorithm compare favorably to the single nearest neighbour classifier.

Conference's articles

  • J. J. de Gruyter and A. B. McBratney. A Modified Fuzzy k-Means Method for Predictive Classification. In H. H. Bock, editor, Classification and Related Methods of Data Analysis, pages 97--104, 1988.
    Keywords: Classification, Clustering, Fuzzy c-Means.
    Abstract: It is shown here that classifications resulting from the method of fuzzy k-means are not necessarily suitable for prediction of properties from class memberships. We have modified this method in order to enhance its predictive power. Illustrations using some artificial data sets are given.

Disclaimer

This list of publications is neither official nor complete, but a personal compilation.

Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.

This document was translated from BibTEX by bibtex2html

Home © F. Höppner last update: Tue Dec 7 08:49:56 CET 2004