ERUDIT-Workshop
Fuzzy Diagnostic and Therapeutic Decision Support
11–12 May 2000, Vienna, Austria

Abstract

Membership Functions and a Basic Probability Assignment as Certainty Measures for a Medical Diagnosis Support

Ewa Straszecka

Institute of Electronics, Division of Biomedical Engineering
Silesian University of Technology, 16 Akademicka St., 44-101 Gliwice, Poland

e-mail: ewa@biomed.iele.polsl.gliwice.pl

Abstract. The paper aims at presenting difficulties in defining fuzzy membership functions for medical implementations and giving suggestions for solving the problems with the use of the classical definition of a fuzzy set as well as by introducing the Dempster-Shafer theory of evidence. Fuzzy sets are proposed for a similarity interpretation while a basic probability assignment is suggested for an estimation of a diagnosis quality. Tasks for future research are stated.

(In: Adlassnig, K.-P. (ed.) Fuzzy Diagnostic and Therapeutic Decision Support. Proc. of the ERUDIT Workshop, Österreichische Computer Gesellschaft, Vienna, p.138.)