Applying genetics to fuzzy logic
AI Expert
Fundamentals of Artificial Neural Networks
Fundamentals of Artificial Neural Networks
Neural Networks and Genetic Algorithm Approaches to Auto-Design of Fuzzy Systems
FLAI '93 Proceedings of the 8th Austrian Artificial Intelligence Conference on Fuzzy Logic in Artificial Intelligence
| Hi-index | 0.00 |
A system combining genetic algorithms and a fuzzy-rule induction routine has been developed. Two prototype expert systems, one derived analytically, and one derived empirically by the fuzzy-rule induction system, were developed to evaluate the utility of expert system technology relative to waste nondestructive assay (NDA) data review. Technical review of waste NDA measurement data, though warranted with respect to present day waste NDA system capabilities, is labor intensive. Hence it is desirable to have an automated system to perform technical review. It has been shown that both the analytically and empirically derived expert systems produce reasonable results, but that the automatic system can produce fuzzy rules more efficiently and accurately than the analytical method. A visual explanation facility for fuzzy expert systems has also been developed.