Title :
On the robustness of fuzzy inference mechanism
Author :
Emami, M. Reza ; Melek, William W. ; Goldenberg, Andrew A.
Author_Institution :
Robotics & Autom. Lab., Toronto Univ., Ont., Canada
Abstract :
The robustness performance of the fuzzy inference mechanism is investigated in terms of maximum deviation of the fuzzy and crisp output as a result of deviation in the input membership grades. A parameterized formulation of fuzzy reasoning helps us adjust the robustness by varying the inference parameters. This feature will improve the generalization capability of the fuzzy logic models as illustrated in an example
Keywords :
fuzzy logic; fuzzy set theory; inference mechanisms; uncertainty handling; crisp output; fuzzy inference mechanism robustness; fuzzy logic models; fuzzy reasoning; generalization capability; inference parameters; input membership grades; maximum deviation; parameterized formulation; robustness performance; Context modeling; Fuzzy reasoning; Fuzzy systems; Inference mechanisms; Input variables; Laboratories; Predictive models; Robotics and automation; Robustness; Training data;
Conference_Titel :
Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American
Conference_Location :
New York, NY
Print_ISBN :
0-7803-5211-4
DOI :
10.1109/NAFIPS.1999.781729
