Decision making with probabilitic and possibilistic assessments
Abstract
System models are constructed to provide tools for both situation assessment and decision analysis. Two distinct types of information are used in system modeling: external information provided by mechanical sensors or human observation and internal information that describes relationships between components of the system. The former type of information is frequently represented by probability estimates, fuzzy sets, or other techniques for representing uncertain or ambiguous information while the latter type is represented by logical relations, rules, or other variations of predicate calculus. Modeling complex system requires the ability to combine the internal system relationships with the information that describes the current assessment of the status of the system. Updating an assessment incorporates sensor information and propagates it through the relational constraints of the system. Two strategies have been introduced to attempt to integrate probabilistic and possibilistic information: probability-possibility transformations and consistency measures. Consistency measures have been designed to analyze the degree of agreement of possibilistic and probabilistic interpretations of the same data. In this paper we consider the problem of assessing the consistency of probabilistic and possibilistic information obtained from different sources. Criteria for possibilistic-probabilistic consistency measures are developed using inclusion measures for fuzzy sets.
- Authors:
-
- Wright State Univ., Dayton, OH (United States)
- Publication Date:
- OSTI Identifier:
- 466443
- Report Number(s):
- CONF-9610138-
TRN: 97:001309-0022
- Resource Type:
- Conference
- Resource Relation:
- Conference: International multi-disciplinary conference on intelligent systems: a semiotic perspective, Gaithersburg, MD (United States), 21-23 Oct 1996; Other Information: PBD: 1996; Related Information: Is Part Of Intelligent systems: A semiotic perspective. Volume I: Theoretical semiotics; Albus, J.; Meystel, A.; Quintero, R.; PB: 303 p.
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 MATHEMATICS, COMPUTERS, INFORMATION SCIENCE, MANAGEMENT, LAW, MISCELLANEOUS; DECISION MAKING; PROBABILISTIC ESTIMATION; SYSTEMS ANALYSIS; FUZZY LOGIC; PROBABILITY; ARTIFICIAL INTELLIGENCE
Citation Formats
Sudkamp, T. Decision making with probabilitic and possibilistic assessments. United States: N. p., 1996.
Web.
Sudkamp, T. Decision making with probabilitic and possibilistic assessments. United States.
Sudkamp, T. 1996.
"Decision making with probabilitic and possibilistic assessments". United States.
@article{osti_466443,
title = {Decision making with probabilitic and possibilistic assessments},
author = {Sudkamp, T},
abstractNote = {System models are constructed to provide tools for both situation assessment and decision analysis. Two distinct types of information are used in system modeling: external information provided by mechanical sensors or human observation and internal information that describes relationships between components of the system. The former type of information is frequently represented by probability estimates, fuzzy sets, or other techniques for representing uncertain or ambiguous information while the latter type is represented by logical relations, rules, or other variations of predicate calculus. Modeling complex system requires the ability to combine the internal system relationships with the information that describes the current assessment of the status of the system. Updating an assessment incorporates sensor information and propagates it through the relational constraints of the system. Two strategies have been introduced to attempt to integrate probabilistic and possibilistic information: probability-possibility transformations and consistency measures. Consistency measures have been designed to analyze the degree of agreement of possibilistic and probabilistic interpretations of the same data. In this paper we consider the problem of assessing the consistency of probabilistic and possibilistic information obtained from different sources. Criteria for possibilistic-probabilistic consistency measures are developed using inclusion measures for fuzzy sets.},
doi = {},
url = {https://www.osti.gov/biblio/466443},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Dec 31 00:00:00 EST 1996},
month = {Tue Dec 31 00:00:00 EST 1996}
}