An Evolving Feature Weighting Framework for Granular Fuzzy Logic Models

Discovering and extracting knowledge from large databases are key elements in granular computing (GrC). The extracted, the form of information granules can be used to build rule-based systems such as Fuzzy Logic inference systems. Algorithms for iterative data granulation literature treat all variables equally neglects difference variable importance, a potential mechanism influence clustering process. In this paper, an algorithm with feature weighting called W-GrC is proposed. By hypothesising that or features during process have different importance how evolves, weight each feature’s estimated based on given instance; updated iteration. weights sum within granule variances. proposed method validated through various UCI classification problems:- Iris, Wine Glass datasets. Result shows certain range parameter, new outperforms conventional terms accuracy. We also give attention interpretability-accuracy trade-off Logic-based we show produces higher performance - without significant deterioration its interpretability (Nauck’s index).