2018/10/12 by Souad Bouasker, Bouasker, Souad
Computer Science · #Databases (cs.DB) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.DB #cs.LG
paper · pdf · doi:10.48550/arxiv.1810.05570
arxiv created 2018/10/12 · arxiv updated 2018/10/15
Correlated pattern mining has increasingly become an important task in data mining since these patterns allow conveying knowledge about meaningful and surprising relations among data. Frequent correlated patterns were thoroughly studied in the literature. In this thesis, we propose to benefit from both frequent correlated as well as rare correlated patterns according to the bond correlation measure. We propose to extract a subset without information loss of the sets of frequent correlated and of rare correlated patterns, this subset is called ``Condensed Representation``. In this regard, we are based on the notions derived from the Formal Concept Analysis FCA, specifically the equivalence classes associated to a closure operator fbond dedicated to the bond measure, to introduce new concise representations of both frequent correlated and rare correlated patterns.