www.uhasselt.be
DSpace

Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/26227

Title: Medical Decision Making Based on Fuzzy Cognitive Map and a Generalization Linguistic Weighted Power Mean for Computing with Words
Authors: Najafi, Azam
Amirkhani, Abdollah
Papageorgiou, Elpiniki I.
Mosavi, Mohammad R.
Issue Date: 2017
Publisher: IEEE
Citation: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE,p. 1-6
Series/Report: IEEE International Conference on Fuzzy Systems
Abstract: Given high uncertainty in medicine, it is essential to use some approaches to deal with this uncertainty. Therefore, this article utilizes computing with words (CWW) in fuzzy cognitive maps (FCMs) for the application of a new medical decision support system. In this framework, expressed as CWW FCM, all concepts and the weights of connecting links between them are described based on interval type-2 membership functions (IT2 MFs) expressed as a set of words. This type of FCM structure shows high performance by taking into account uncertainties in experts' opinions and in system parameters in the process of modeling. In this paper, we utilize CWW FCM to classify celiac disease (CD), a chronic disorder. Thus, to illustrate the behavior and performance of the proposed model in classifying CD, we have collected a real dataset from patients with different types of CD. Applying the model on this dataset, acceptable accuracy in classification is achieved.
Notes: Najafi, A (reprint author), Iran Univ Sci & Technol, Dept Elect Engn, Tehran 1684613114, Iran, a_najafi@elec.iust.ac.ir; amirkhani@ieee.org; epapageorgiou@teiste.gr; m_mosavi@iust.ac.ir
URI: http://hdl.handle.net/1942/26227
DOI: 10.1109/FUZZ-IEEE.2017.8015541
ISI #: 000426449100160
ISBN: 9781509060344
ISSN: 1098-7584
Category: C1
Type: Proceedings Paper
Appears in Collections: Research publications

Files in This Item:

Description SizeFormat
Published version855.06 kBAdobe PDF

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.