Title :
A Modified k-means Algorithm for Clustering Problem with Balancing Constraints
Author :
Yuepeng, Sun ; Min, Liu ; Cheng, Wu
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
A clustering problem with balancing constraints is studied in this paper, which means that the sample number in each cluster has to be at least pre-given value. A modified k-means clustering algorithm is proposed, which adopt the proposed heuristic cluster assignment algorithm to deal with the balancing constraints. Numerical computation shows that the proposed algorithm can deal with the balancing constraints and lead to the improvement of the clustering objective.
Keywords :
pattern clustering; unsupervised learning; balancing constraints; clustering problem; modified k-means algorithm; Algorithm design and analysis; Approximation algorithms; Clustering algorithms; Computed tomography; Databases; Heuristic algorithms; Silicon; Balancing Constraints; Clustering Algorithm; k-means;
Conference_Titel :
Measuring Technology and Mechatronics Automation (ICMTMA), 2011 Third International Conference on
Conference_Location :
Shangshai
Print_ISBN :
978-1-4244-9010-3
DOI :
10.1109/ICMTMA.2011.37
