We propose a feature selection method that constructs each new feature by analysis of tight error clusters. This is a greedy, time-efficient forward selection algorithm that itera...
We present a slicing-based coherence measure for clusters of DTI integral curves. For a given cluster, we probe samples from the cluster by slicing it with a plane at regularly spa...
It is a key activity in CBD to identify high-quality components which have high cohesion and low coupling. However, component clustering is carried out in manual fashion by develop...
We present a new method for spectral clustering with paired data based on kernel canonical correlation analysis, called correlational spectral clustering. Paired data are common i...
In this paper, we introduce a novel framework for clustering web data which is often heterogeneous in nature. As most existing methods often integrate heterogeneous data into a un...