2003
DOI: 10.1002/int.10118
|View full text |Cite
|
Sign up to set email alerts
|

An interpretation of focal elements as fuzzy sets

Abstract: This article proposes defining focal elements in the Dempster-Shafer theory as fuzzy sets in an application to medical diagnosis support. Membership functions for medical parameters of "fuzzy" nature are constructed. A diagnosis support consists of Bel measure calculation only for these focal elements that have membership function values grater than a "truth" threshold. Coherence between membership function shapes and the truth threshold is shown and a new way of membership function designing is proposed. An e… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2004
2004
2021
2021

Publication Types

Select...
5
2

Relationship

1
6

Authors

Journals

citations
Cited by 17 publications
(4 citation statements)
references
References 13 publications
0
4
0
Order By: Relevance
“…Membership functions for numerical variables can be found as triangular, trapezoidal or Gaussian functions based on some statistical parameters (Civanlar & Trussell, 1986; Rojas et al , 1998; Szczepaniak et al , 2000; Polat et al , 2006). The method of membership function design for the present algorithm is described in detail by Straszecka (2003, 2006a, 2006b). The algorithm of the bpa calculation is given in Figure 1.…”
Section: Methods Of Symptom Representation and Knowledge Combiningmentioning
confidence: 99%
“…Membership functions for numerical variables can be found as triangular, trapezoidal or Gaussian functions based on some statistical parameters (Civanlar & Trussell, 1986; Rojas et al , 1998; Szczepaniak et al , 2000; Polat et al , 2006). The method of membership function design for the present algorithm is described in detail by Straszecka (2003, 2006a, 2006b). The algorithm of the bpa calculation is given in Figure 1.…”
Section: Methods Of Symptom Representation and Knowledge Combiningmentioning
confidence: 99%
“…It is still convenient that the value is identical for all the membership functions, e.g. 0.5 [33]. Hence, (x * , 0.5) and (x ** , 0.5) points resemble (a 0 , 0.5) and (d 0 , 0.5) points of the membership function in Fig.…”
Section: Defining the Membership Functionmentioning
confidence: 96%
“…Some classical methods of clustering (ISODATA [34], FUZZY ISODATA [3]) as well as fuzzy inference [9] in its basic Mamdani-like format have resulted in a classification error ranging from 8% to 50% [33] for a single diagnosis. Also, statistical and classical probabilitybased methods [7] have revealed a complex structure of data sets, although classification has been simplified into two separate processes of distinction between H and D 1 as well as between H and D 2 .…”
Section: Experimental Datamentioning
confidence: 99%
“…In the same way, fuzzy sets were also used as an interpretation of focal elements by Straszecka in [23]. We suggest using the membership function obtained to initialize the mass function.…”
Section: Mass Function Initialization and Distributionmentioning
confidence: 99%