Relating confidence to information uncertainty in qualitative reasoning
- Los Alamos National Laboratory
Qualitative reasoning makes use of qualitative assessments provided by subject matter experts to model factors such as security risk. Confidence in a result is important and useful when comparing competing security risk results. Quantifying the confidence in an evidential reasoning result must be consistent and based on the available information. A novel method is proposed to determine a qualitative measure of confidence in a qualitative reasoning result from the available information uncertainty in the result using membership values in the fuzzy sets of confidence. In this study information uncertainty is quantified through measures of non-specificity and conflict. Fuzzy values for confidence are established from information uncertainty values that lie between the measured minimum and maximum information uncertainty values. Measured values of information uncertainty in each result is used to obtain the confidence. The determined confidence values are used to compare competing scenarios and understand the influences on the desired result.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 1043536
- Report Number(s):
- LA-UR-10-08016; LA-UR-10-8016; TRN: US201214%%78
- Resource Relation:
- Conference: ERCIM '10 ; December 11, 2010 ; London, UK
- Country of Publication:
- United States
- Language:
- English
Similar Records
Information Uncertainty to Compare Qualitative Reasoning Security Risk Assessment Results
A comparison of approximate reasoning results using information uncertainty