Wyniki wyszukiwania - BazTech

1

Membership Functions for Fuzzy Focal Elements

Porębski S., Straszecka E.

Archives of Control Sciences

|

2016

|

Vol. 26, no. 3

395--427

EN

The paper presents a study on data-driven diagnostic rules, which are easy to interpret by human experts. To this end, the Dempster-Shafer theory extended for fuzzy focal elements is used. Premises of the rules (fuzzy focal elements) are provided by membership functions which shapes are changing according to input symptoms. The main aim of the present study is to evaluate common membership function shapes and to introduce a rule elimination algorithm. Proposed methods are first illustrated with the popular Iris data set. Next experiments with five medical benchmark databases are performed. Results of the experiments show that various membership function shapes provide different inference efficiency but the extracted rule sets are close to each other. Thus indications for determining rules with possible heuristic interpretation can be formulated.

2

Uncertainty and imprecision in medical diagnosis support

Straszecka E.

Journal of Medical Informatics & Technologies

|

2012

|

Vol. 19

11--22

EN

The paper concerns methods of representation of uncertainty and imprecision in successful medical support applications. Advantages of the methods are pointed out and some of their drawbacks are explained. A method of simultaneous representation of imprecision of symptoms and uncertainty of diagnostic rules is proposed. The method suggests an extension of the Dempster-Sahfer theory for fuzzy focal elements. An example of the method is given and their links as well differences from previous approaches are discussed. Conclusions about uncertainty and imprecision representation in medical diagnosis support are provided.

3

Jednoczesna ocena informacji ilościowej i jakościowej podczas wspomagania diagnostyki medycznej

Straszecka E.

Pomiary Automatyka Kontrola

|

2007

|

R. 53, nr 9 bis

372--375

PL

Diagnoza medyczna bazuje na niepełnej i nieprecyzyjnej informacji, dlatego algorytmy wspomagania wnioskowania medycznego muszą spełniać specyficzne wymagania. Praca koncentruje się na jednoczesnej i równoważnej ocenie parametrów medycznych rozmaitej natury: mierzalnych (np. testy laboratoryjne), formułowanych ściśle (ciąża), określanych nieprecyzyjnie (przyrost wagi), a czasem definiowanych w umownej skali (ból). Proponuje się modelowanie wnioskowania medycznego z zastosowaniem teorii Dempstera-Shafera rozszerzonej poprzez zdefiniowanie rozmytych elementów ogniskowych. Pozwala to na reprezentację wiedzy w postaci reguł. W przesłankach tych reguł mogą występować zarówno zmienne ilościowe, jak i jakościowe. Każdej regule jest przypisana wartość bazowego prawdopodobiestwa zdefiniowanego zgodnie z teorią Dempstera-Shafera. Funkcje przynależności charakteryzujące zmienne w przesłankach reguł oraz rozkładu bazowego prawdopodobieństwa można wyznaczyć na podstawie danych uczących. Wniosek diagnostyczny jest wynikiem porównania wartości miar przekonania (Bel) dla kilku hipotez. Przedstawiony model wnioskowania został zweryfikowany się dla 3 niezależnych baz danych dotyczących chorób tarczycy.

EN

Medical diagnosis is based on uncertain and imprecise information. Therefore, algorithms that support medical inference comply with specific requirements. This paper is focused on simultaneous and equal estimation of medical parameters of different nature: measurable (like laboratory tests), precisely formulated (pregnancy), described in an imprecise way (putting on weight), or defined on an assumed scale (pain). It is suggested to model a medical inference in the framework of the Dempster-Shafer theory extended for fuzzy focal elements. By means of the proposed algorithm, diagnostic rules can be formulated. Premises of the rules may include both quantity and quality variables. Each rule is assigned with a value of the basic probability assignment that is defined according to the Dempster-Shafer theory. Membership functions of rule predicates as well as the basic probability assignment are found from training data. The diagnostic conclusion is formulated after a comparison of belief values for several hypotheses. The model of inference is verified for 3 independent data bases of thyroid gland diseases.

4

Building membership functions for medical knowledge representation

Straszecka E.

Journal of Applied Computer Science

|

2003

|

Vol. 11, nr 2

55-66

EN

The paper proposes defining membership functions of fuzzy sets for medical applications. Membership junctions with different kinds of information are constructed. Methods of designing them with a deficient database are suggested A comparison of the membership function resulting form different methods is presented. A representation of an influence of considered population on medical patterns trough fuzzy sets is proposed. Indications for score test transforming into IF- THEN rules of a knowledge base are given. Advantages of the approach are shown.

5

Distance based classifiers and their use to analysis of data concerned acute coronary syndromes

Straszecka E., Straszecka J.

Image Processing & Communications

|

2003

|

Vol. 9, no 3-4

53-69

EN

The paper deals with calculating basic probability assignment (BPA) in the Dempster-Shafer theory of evidence when focal elements are fuzzy sets. A method of membership functions designing for focal elements representation is given. A combination of two BPAs using an extension of Dempster's principle is proposed. A simulation of evidences combining and an example in medical diagnosis support is given.

6

A modern technologies in medical expert systems

Kącki E., Małolepszy A., Stempczyńska J.

Journal of Applied Computer Science

|

2001

|

Vol. 9, nr 1

23-32

EN

The paper presents organization and performance of the module structure expert system for medicine and discussion on certain information technology problems connected with building and exploitation of the system. The considered problems mainly deal with knowledge acquisition automation and hypermedia applications for well communication. After discussion some remarks on conception of knowledge acquisition and dialog organization as well as some conclutions relative to their implementability and utilizability are also given.