Structural rule-based modeling with granular computing

Abstract

In order to analyze the dynamic behaviors of complex systems in the era of big data, a new rule-based modeling approach is proposed in this paper. This approach considers structural information mining and granular computing (GrC) in rule-based modeling, it also aims at utilizing granular fuzzy intervals to reflect systems’ behaviors on uncertainty. Major contributions can be summarized as three points. First, using DBSCAN’s advantages in clustering arbitrarily-shaped data, DBSCAN is applied to extract structural information as the basis of rules in complex systems. Second, GrC is leveraged for rule formation and effective rule-based modeling, e.g. granules constructed in input space to refine structural DBSCAN clusters, granular intervals constructed in output space with the principle of justifiable granulating to reflect system dynamic behaviors. Third, experimental analysis based on three different design scenarios was studied on both synthetic data and publicly available datasets. Through comparative discussion, the proposed approach can outperform the conventional rule-based models, specifically having an improvement ratio of 0.18% to 1.48% on the proposed comprehensive indicator. Therefore, it can be concluded that the proposed approach has the feasibility and advantages of reflecting the structural and uncertainty characteristics of system dynamic analysis.