Name
Abstract | ||
|---|---|---|
Clustering a set of objects into homogeneous classes is a fundamental operation in data mining. Several cluster analysis techniques have been developed to group objects having similar characteristics. Recently, many attentions have been put on categorical data clustering, where data objects are made up of non-numerical attributes. An algorithm termed MMR using classical rough set theory was proposed to deal with problems in clustering categorical data. However, the MMR algorithm fails to handle noisy data as an integral part of databases. In this paper, an alternative technique for clustering noisy categorical data using Variable Precision Rough Set model is proposed. The results show that the technique provides better performance in selecting the clustering attribute. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.3233/IDA-2011-0478 | Intell. Data Anal. |
Keywords | Field | DocType |
noisy categorical data,data mining,data object,categorical data,mmr algorithm,noisy data,cluster analysis technique,classical rough set theory,alternative technique,clustering attribute,variable precision | Fuzzy clustering,Data mining,CURE data clustering algorithm,Computer science,Artificial intelligence,Cluster analysis,Canopy clustering algorithm,Data stream clustering,Pattern recognition,Correlation clustering,Determining the number of clusters in a data set,Constrained clustering,Machine learning | Journal |
Volume | Issue | ISSN |
15 | 4 | 1088-467X |
Citations | PageRank | References |
6 | 0.44 | 0 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Iwan Tri Riyadi Yanto | 1 | 64 | 7.29 |
| Tutut Herawan | 2 | 608 | 75.21 |
| Mustafa Mat Deris | 3 | 510 | 56.25 |