Title | ||
---|---|---|
Improving the efficiency and efficacy of the K-means clustering algorithm through a new convergence condition |
Abstract | ||
---|---|---|
Clustering problems arise in many different applications: machine learning, data mining, knowledge discovery, data compression, vector quantization, pattern recognition and pattern classification. One of the most popular and widely studied clustering methods is K-means. Several improvements to the standard K-means algorithm have been carried out, most of them related to the initial parameter values. In contrast, this article proposes an improvement using a new convergence condition that consists of stopping the execution when a local optimum is found or no more object exchanges among groups can be performed. For assessing the improvement attained, the modified algorithm (Early Stop K-means) was tested on six databases of the UCI repository, and the results were compared against SPSS, Weka and the standard K-means algorithm. Experimentally Early Stop K-means obtained important reductions in the number of iterations and improvements in the solution quality with respect to the other algorithms. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-74484-9_58 | ICCSA (3) |
Field | DocType | Volume |
Canopy clustering algorithm,Fuzzy clustering,Data mining,k-means clustering,CURE data clustering algorithm,Mathematical optimization,Data stream clustering,Correlation clustering,Linde–Buzo–Gray algorithm,Computer science,Algorithm,Cluster analysis | Conference | 4707 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-74482-5 | 3 |
PageRank | References | Authors |
0.52 | 9 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Joaquín Pérez Ortega | 1 | 10 | 6.40 |
R. Rodolfo Pazos | 2 | 24 | 6.92 |
Laura Cruz | 3 | 89 | 28.40 |
Gerardo Reyes Salgado | 4 | 14 | 4.89 |
Rosy Basave T. | 5 | 3 | 0.52 |
Héctor J. Fraire H. | 6 | 46 | 9.52 |