Granular models as networks of associations of information granules: A development scheme via augmented principle of justifiable granularity

This study proposes an approach to the construction of granular models directly based on information granules expressed both in input and output spaces. Associating these information granules, the constructed granular models come in the framework of three layers networks: input granules, an inference scheme and output granules. The proposed approach consists of two stages. First, an augmented principle of justifiable granularity is proposed and applied to construct information granules in an input space. This principle constructs information granules not only through establishing a sound balance between two criteria, i.e., coverage and specificity, but also by optimizing those information granules on the basis of their homogeneity assessed with respect to data localized in output space. At the second stage, we propose an inference scheme by analyzing a location of an input datum in relation with the already formed information granules in an input space. The computed relation can be quantified as membership grades, thus yielding aggregation results involving information granules in an output space. The performance of the proposed granular model is supported by the mechanisms of granular computing and the principle of justifiable granularity. Experimental studies concerning synthetic and publicly available data are performed and some comparative analysis involving rule-based models is given.