Support functions for fuzzy sets

Keyword(s):  
1998 ◽  
Vol 37 (01) ◽  
pp. 16-25 ◽  
Author(s):  
P. Ringleb ◽  
T. Steiner ◽  
P. Knaup ◽  
W. Hacke ◽  
R. Haux ◽  
...  

Abstract:Today, the demand for medical decision support to improve the quality of patient care and to reduce costs in health services is generally recognized. Nevertheless, decision support is not yet established in daily routine within hospital information systems which often show a heterogeneous architecture but offer possibilities of interoperability. Currently, the integration of decision support functions into clinical workstations is the most promising way. Therefore, we first discuss aspects of integrating decision support into clinical workstations including clinical needs, integration of database and knowledge base, knowledge sharing and reuse and the role of standardized terminology. In addition, we draw up functional requirements to support the physician dealing with patient care, medical research and administrative tasks. As a consequence, we propose a general architecture of an integrated knowledge-based clinical workstation. Based on an example application we discuss our experiences concerning clinical applicability and relevance. We show that, although our approach promotes the integration of decision support into hospital information systems, the success of decision support depends above all on an adequate transformation of clinical needs.


2012 ◽  
Vol 2 (12) ◽  
pp. 548-552
Author(s):  
P. Pandian P. Pandian ◽  
◽  
D. Kalpanapriya D. Kalpanapriya

2005 ◽  
Vol 10 (1) ◽  
pp. 65-75 ◽  
Author(s):  
Z. Kala

The load-carrying capacity of the member with imperfections under axial compression is analysed in the present paper. The study is divided into two parts: (i) in the first one, the input parameters are considered to be random numbers (with distribution of probability functions obtained from experimental results and/or tolerance standard), while (ii) in the other one, the input parameters are considered to be fuzzy numbers (with membership functions). The load-carrying capacity was calculated by geometrical nonlinear solution of a beam by means of the finite element method. In the case (ii), the membership function was determined by applying the fuzzy sets, whereas in the case (i), the distribution probability function of load-carrying capacity was determined. For (i) stochastic solution, the numerical simulation Monte Carlo method was applied, whereas for (ii) fuzzy solution, the method of the so-called α cuts was applied. The design load-carrying capacity was determined according to the EC3 and EN1990 standards. The results of the fuzzy, stochastic and deterministic analyses are compared in the concluding part of the paper.


Sign in / Sign up

Export Citation Format

Share Document