Measure of independence in soft design

Abstract In this paper is analysed the problem, using soft models, of soft dependence of parameters in design systems. A new form of computing, called Soft Computing , is recently used in many emerging disciplines because it is tolerant to imprecision, uncertainty and partial truth. The Soft Computing uses many disciplines as Bayesian inference and maximum entropy method . The logic relationship that ties the different elements can be defined more easily using the axioms of soft design emanating from MinEnt principle . The fundamental axiom of design is: valid design has minimum values of information and depends on a finite and limited number of independent, or soft dependent , parameters.

[1]  D. Dubois,et al.  Possibility theory as a basis for preference propagation in automated reasoning , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[2]  Marvin H. J. Guber Bayesian Spectrum Analysis and Parameter Estimation , 1988 .

[3]  Designing in many-valued logic , 1999, Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM'99 (Cat. No.99EX296).

[4]  Nam P. Suh,et al.  principles in design , 1990 .