This paper addresses the ambitious goal of merging two different approaches to group detec-tion in complex domains: one based on fuzzy clustering and the other on community detectiontheory. To achieve this, two clustering algorithms are proposed: fuzzy C-medoids clusteringwith modularity spatial correction and fuzzy C-modes clustering with modularity spatial cor-rection. The former is designed for quantitative data, while the latter is intended for qualitativedata. The concept of fuzzy modularity is introduced into the standard objective function offuzzy clustering algorithms as a spatial regularization term, whose contribution to the clus-tering criterion based on attributes is controlled by an exogenous parameter. An extensivesimulation study is conducted to support the theoretical framework, complemented by twoapplications to real-world data related to the theme of sustainability. The first applicationinvolves data from the 2030 Agenda for Sustainable Development, while the second focuseson urban green spaces in Italian provincial capitals and metropolitan cities. Both the simu-lation results and the applications demonstrate the advantages of this new methodologicalproposal.

Read the full paper here

by Domenico Cangemi· Pierpaolo D’Urso · Livia De Giovanni · Lorenzo Federico · Vincenzina Vitale