%0 Journal Article %J Neurocomputing %D 2009 %T Fuzzy lattice reasoning (FLR) type neural computation for weighted graph partitioning %A Kaburlasos, Vassilis G. %A Moussiades, Lefteris %A Athena Vakali %K Clustering %K Fuzzy lattices %K Graph partitioning %K Metric Measurable path %K Similarity measure %X

The fuzzy lattice reasoning (FLR) neural network was introduced lately based on an inclusion measurefunction. This work presents a novel FLR extension, namely agglomerative similarity measure FLR, orasmFLR for short, for clustering based on a similarity measure function, the latter (function) may also bebased on a metric. We demonstrate application in a metric space emerging from a weighted graphtowards partitioning it. The asmFLR compares favorably with four alternative graph-clusteringalgorithms from the literature in a series of computational experiments on artificial data. In addition,our work introduces a novel index for the quality of clustering, which (index) compares favorably withtwo popular indices from the literature.

%B Neurocomputing %V 72 %P 2121-2133 %G eng