Fuzzy rule interpolation (FRI) enables sparse fuzzy rule-based systems to derive an interpolated conclusion using neighboring rules, when presented with an observation that matches none of the given rules. The efficacy of FRI has been further empowered by the recent development of weighted FRI techniques, particularly the one that introduces attribute weights of rule antecedents from the given rule base, removing the conventional assumption of antecedent attributes having equal weighting or significance. However, such work was carried out within the specific transformation-based FRI mechanism. This short paper reports the results of generalizing it through enhancing two alternative representative FRI methods. The resultant weighted FRI algorithms facilitate the individual attribute weights to be integrated throughout the corresponding procedures of the conventional unweighted methods. With systematical comparative evaluations over benchmark classification problems, it is empirically demonstrated that these algorithms work effectively and efficiently using just two nearest neighboring rules.
|Pages (from-to)||2255 - 2262|
|Number of pages||8|
|Journal||IEEE Transactions on Fuzzy Systems|
|Early online date||15 Jul 2019|
|Publication status||Published - 01 Sept 2020|
- Attribute weights
- fuzzy interpolative reasoning
- nearest neighboring rules
- weighted rule interpolation
FingerprintDive into the research topics of 'Interpolation with Just Two Nearest Neighboring Weighted Fuzzy Rules'. Together they form a unique fingerprint.
- Faculty of Business and Physcial Sciences, Department of Computer Science - Senior Research Fellow
- Faculty of Business and Physcial Sciences, Faculty of Business and Physical Sciences (Dept) - Pro Vice-Chancellor: Faculty of Business and Physical Sciences
Person: Teaching And Research