Abstract
Fuzzy rule interpolation (FRI) is well known forreducing the complexity of fuzzy models and making inferencepossible in sparse rule-based systems. However, in practicalfuzzy applications with inter-connected rule bases, situationsmay arise when a crucial antecedent of observation is absent,either due to human error or difficulty in obtaining data,while the associated conclusion may be derived according todifferent rules or even observed directly. To address such issues,a concept termed Backward Fuzzy Rule Interpolation (B-FRI) is proposed, allowing the observations which directly relateto the conclusion be inferred or interpolated from the knownantecedents and conclusion. B-FRI offers a way to broaden thefields of research and application of fuzzy rule interpolationand fuzzy inference. The steps of B-FRI implemented using thescale and move transformation-based fuzzy interpolation aregiven, along with two numerical examples to demonstrate thecorrectness and accuracy of the approach. Finally, a practicalexample is presented to show the applicability and potential of B-FRI.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 11th UK Workshop on Computational Intelligence |
| Publisher | Manchester University Press |
| Pages | 194-200 |
| Publication status | Published - 26 Sept 2011 |