Where do we stand on measures of uncertainty, ambiguity, fuzziness, and the like?
Fuzzy Sets and Systems - Special Issue: Measures of Uncertainty
Fuzzy entropy threshold approach to breast cancer detection
Information Sciences—Applications: An International Journal
Fuzzy set theory—and its applications (3rd ed.)
Fuzzy set theory—and its applications (3rd ed.)
Fuzzy Sets and Systems
A novel fuzzy entropy approach to image enhancement and thresholding
Signal Processing
On quantification of different facets of uncertainty
Fuzzy Sets and Systems
Entropy and information energy for fuzzy sets
Fuzzy Sets and Systems
A Mathematical Theory of Communication
A Mathematical Theory of Communication
Are fuzzy sets a reasonable tool for modeling vague phenomena?
Fuzzy Sets and Systems
Hi-index | 0.20 |
Many decision-making settings incorporate both possibilistic and probabilistic uncertainty. In this study, entropy is used as a common measure in quantifying both types of uncertainty. This measure facilitates the direct comparison of the ''amounts'' of the two types of uncertainty in a given situation. The main objective of this study is, however, to illustrate how, in a decision-making setting, incorporating fuzzy membership function to represent possibilistic uncertainty leads to a more realistic assessment of the decision-making problem at hand. A methodology for the evaluation of land condition and for aiding the decision on restoration allocation and a case study is presented. The methodology enables handling both types of uncertainty: probabilistic uncertainty from the spatial simulation data and possibilistic uncertainty due to vagueness in land condition factor. Erosion status is selected as the land condition factor. Restoration allocation decision is based on fuzzy logic to reflect the continuous transition between different land conditions. The analysis is done six times, each time using a membership function with a different degree of fuzziness. Insights gathered from this study would relate to the risks associated with taking a decision in the presence of both types of uncertainty. The comparison of the output of the analysis (i.e. the loss associated with misclassification) from six different trials reveals that the variance in the loss values decreases as more fuzziness is incorporated into the analysis. In other words, there is an inverse relation between the coefficient of variance of the loss values and the fuzziness incorporated into the analysis. A more in-depth analytical investigation is needed to understand if this observation is specific to this case study or a more general phenomenon.