Cascade Granular Networks for Human-Centric Systems

This paper is concerned with the design of Cascade Granular Networks (CGN) for human-centric systems. In contrast to typical rule-based systems encountered in fuzzy modeling, the proposed method consists of two-phase development for CGN. First, we construct a granular network which could be treated as a preliminary design. Next, all modeling discrepancies are compensated by second granular network with a collection of rules that become attached to the regions of the input space where the error is localized. These granular networks are constructed by building a collection of information granules through Context-based Fuzzy c-Means (CFCM) clustering. Finally, we reveal that the proposed CGN shows a good performance in comparison with the previous works.