O-Theory: a hybrid uncertainty theory
A hybrid uncertainty theory is developed to bridge the gap between fuzzy set theory and Bayesian inference theory. Its basis is the Dempster-Shafer formalism (a probability-like, set-theoretic approach), which is extended and expanded upon so as to include a complete set of basic operations for manipulating uncertainties in approximate reasoning. The new theory, operator-belief theory (OT), retains the probabilistic flavor of Bayesian inference but includes the potential for defining a wider range of operators like those found in fuzzy set theory. The basic operations defined for OT in this paper include those for: dominance and order, union, intersection, complement and general mappings. A formal relationship between the membership function in fuzzy set theory and the upper probability function in the Dempster-Shafer formalism is also developed. Several sample problems in logical inference are worked out to illustrate the results derived from this new approach as well as to compare them with the other theories currently being used. A general method of extending the theory using the historical development of fuzzy set theory as an example is suggested.
- Research Organization:
- Oak Ridge National Lab., TN (USA)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 5004845
- Report Number(s):
- ORNL/TM-9759; ON: DE86002610
- Country of Publication:
- United States
- Language:
- English
Similar Records
Foundations of O-theory I: the intersection rule
Hybrid uncertainty theory
Information integration using belief functions.
Technical Report
·
Fri Feb 28 23:00:00 EST 1986
·
OSTI ID:6138946
Hybrid uncertainty theory
Conference
·
Mon May 13 00:00:00 EDT 1985
·
OSTI ID:5920350
Information integration using belief functions.
Conference
·
Mon Dec 31 23:00:00 EST 2001
·
OSTI ID:976104