A Proposition for Combining Pattern Structures and Relational Concept Analysis

摘要: In this paper we propose an adaptation of the RCA process enabling relational scaling pattern structures. a nutshell, allows scenario where needs to be applied in context family composed by structures instead formal contexts. To achieve define heterogeneous as model describe objects combination spaces, namely original object description space and set attributes derived from process. We frame our approach problem characterizing latent variables (LV) variable documents terms. LVs are used compact improved dataset representations. LV characterization missing LV-model, through application adapted using Finally, discuss implications proposition.