This work addresses the sensitivity analysis on the settings of fuzzy inference systems where multiple, yet dissimilar inputs are aggregated and resolved into a single output. The JAVA platform-independent development environment DANA (Data Analysis aNd Assessment) includes components for computation of fuzzy-logic based rules guiding the fuzzification-aggregation-defuzzification process by alternative membership functions (of an input to belong to fuzzy sets) and weighing systems, and unlimited aggregation levels. The integration of the library for sensitivity analysis SimLab within DANA is illustrated using the Morris screening method to determine the relative importance ranking of fuzzy settings (lower and upper limits, weights) on the final defuzzified output. The assumptions about the settings of the analysis are also discussed using an illustrative example where sensitivity analysis is applied to the fuzzy inference system designed to evaluate analytical methods in the domain of genetically modified organisms.

Sensitivity analysis in fuzzy systems : integration of SimLab and DANA / F. Foscarini, G. Bellocchi, R. Confalonieri, C. Savini, G. Van den Eede. - In: ENVIRONMENTAL MODELLING & SOFTWARE. - ISSN 1364-8152. - 25:10(2010 Oct 12), pp. 1256-1260. [10.1016/j.envsoft.2010.03.024]

Sensitivity analysis in fuzzy systems : integration of SimLab and DANA

R. Confalonieri;
2010

Abstract

This work addresses the sensitivity analysis on the settings of fuzzy inference systems where multiple, yet dissimilar inputs are aggregated and resolved into a single output. The JAVA platform-independent development environment DANA (Data Analysis aNd Assessment) includes components for computation of fuzzy-logic based rules guiding the fuzzification-aggregation-defuzzification process by alternative membership functions (of an input to belong to fuzzy sets) and weighing systems, and unlimited aggregation levels. The integration of the library for sensitivity analysis SimLab within DANA is illustrated using the Morris screening method to determine the relative importance ranking of fuzzy settings (lower and upper limits, weights) on the final defuzzified output. The assumptions about the settings of the analysis are also discussed using an illustrative example where sensitivity analysis is applied to the fuzzy inference system designed to evaluate analytical methods in the domain of genetically modified organisms.
Settore AGR/02 - Agronomia e Coltivazioni Erbacee
12-ott-2010
Article (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/146916
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 15
social impact