A CART extension using Quadratic Decision Borders

Karsten Hartelius

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

    Abstract

    In this article we put forward an extention to the hierarchical CART classification method which uses quadratic decision borders. The original CART applies univariate splits on individual variables as well as splits on combinations of variables to recursively partition the feature-space into subsets which are successively more class-homogeneous. Guided by the fact that class-distributions in feature-space are very often hyper-elliptical shaped, we give an extension to the original CART which also uses quadratic shaped decision borders which can be modelled by a mean-vector and a dispersion matrix. We propose a scheme for finding a good starting guess for a quadratic decision border, and a scheme for subsequently improving the guess, through adjustments of the size and shape of the decision border.
    Original languageEnglish
    Title of host publicationProceedings from The 11th Danish Conference on Image Analysis
    Publication date1999
    Pages777-783
    Publication statusPublished - 1999
    EventThe 11th Danish Conference on Image Analysis - Kangerlussuaq, Greenland
    Duration: 1 Jan 1999 → …

    Conference

    ConferenceThe 11th Danish Conference on Image Analysis
    CityKangerlussuaq, Greenland
    Period01/01/1999 → …

    Cite this