Fig. 9

Impact of two-cluster overlap on clustering results for K-means algorithm and bipartite-graph model. a) Mean angular change of SSR(K) (bipartite-graph model) and within-cluster scatter (K-means) at K = 2. b) Mean misclassification rates of K-means and bipartite-graph model (see text) compared to theoretical prediction. All curves coincide. c) Mean squared-error loss of bipartite-graph model.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.