Abstract | ||
---|---|---|
Cluster ensemble is one of the hot topics in the machine learning area. Though plenty of cluster ensemble methods and frameworks have been proposed, many cluster ensemble methods are easily faded by noisy datasets and local optimal problems. In this article, we introduced a novel cluster ensemble method, named as Double Partition Around Medoids based Cluster Ensemble (PAM2CE). PAM2CE will effectively weaken or even eliminate the effect of noisy datasets and local optimal problems via clustering attributes and selecting the representative attributes. The experimental results reveal the better robustness and effectiveness of proposed method. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/ICMLC.2012.6359568 | ICMLC |
Keywords | Field | DocType |
noisy datasets,pattern clustering,clustering attribute,learning (artificial intelligence),representative attribute,pam2ce,cluster ensemble,double partition around medoids,machine learning,local optimal problem,learning artificial intelligence | Data mining,Pattern recognition,Computer science,Pattern clustering,Robustness (computer science),Artificial intelligence,Cluster analysis,Partition (number theory),Ensemble learning,Machine learning,Medoid | Conference |
Volume | ISSN | ISBN |
4 | 2160-133X | 978-1-4673-1484-8 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Le Li | 1 | 158 | 10.10 |
Jane You | 2 | 1885 | 136.93 |
Guoqiang Han | 3 | 439 | 43.27 |
Hantao Chen | 4 | 36 | 2.93 |