There are two main ways to construct Fuzzy Logic rule-based models: using expert knowledge and using data mining methods. One of the most important aspects of Granular Computing (GrC) is to discover and extract knowledge from raw data in the form of information granules. The knowledge gained from the GrC, the information granules, can be used in constructing the linguistic rule-bases of a Fuzzy-Logic based system. Algorithms for iterative data granulation in the literature, so far, do not account for data uncertainty during the granulation process. In this paper, the uncertainty during the data granulation process is captured using the fundamental concept in information theory, entropy. In the proposed GrC algorithm, data granules are defined as information objects, hence the entropy measure being used in this research work is to capture the uncertainty in the data vectors resulting from the merging of the information granules. The entropy-based uncertainty measure is used to guide the iterative granulation process, hence promoting the formation of new granules with less uncertainty. The enhanced information granules are then being translated into a Fuzzy Logic inference system. The effectiveness of the proposed approach is demonstrated using established datasets.
Discovering and extracting knowledge from large databases are key elements in granular computing (GrC). The knowledge extracted, in the form of information granules can be used to build rule-based systems such as Fuzzy Logic inference systems. Algorithms for iterative data granulation in the literature treat all variables equally and neglects the difference in variable importance, as a potential mechanism to influence the data clustering process. In this paper, an iterative data granulation algorithm with feature weighting called W-GrC is proposed. By hypothesising that the variables or features used during the data granulation process can have different importance to how data granulation evolves, the weight of each feature's influence is estimated based on the information granules on a given instance; this is updated in each iteration. The feature weights are estimated based on the sum of within granule variances. The proposed method is validated through various UCI classification problems:-Iris, Wine and Glass datasets. Result shows that for certain range of feature weight parameter, the new algorithm outperforms the conventional iterative granulation in terms of classification accuracy. We also give attention to the interpretability-accuracy trade-off in Fuzzy Logic-based systems and we show that W-GrC produces higher classification performancewithout significant deterioration in terms of its interpretability (Nauck's index).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.