Abstract | ||
---|---|---|
In cluster analyses, setting the scale parameter which is implicitly related to the complexity of the data distribution is an important issue; different scale values lead to different results and hence cause different interpretation. In this study, we discuss a framework of multi-scale clustering, where clustering is done with multiple scale values and then the obtained results are compiled into a visually appropriate form to observe overall structures of the clusters. For such purpose, a brick view method is proposed in this study. The construction of a brick view diagram consists of a re-indexing procedure of clusters obtained with various scale values and a sorting procedure of samples so as to minimize the distortion defined based on the multiple clustering results. Although some popular clustering methods, such as K-means, spherical K-means, and hierarchical clustering, have been used within the multi-scale framework, we introduce mean-shift clustering based on the kernel density estimation for directional data. We evaluate our approach and existing hierarchical clustering by using an artificial data set and a real data set of gene expression profiles. The results show global structures of distributions can be observed well and in a stable manner, in the brick view diagram. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/BIBE.2005.41 | BIBE |
Keywords | Field | DocType |
popular clustering method,different scale value,gene expression profiling data,multi-scale clustering,artificial data,multiple clustering result,multiple scale value,hierarchical clustering,data distribution,brick view diagram,directional data,k means,mean shift,kernel density estimate,sorting,genetics,molecular biophysics,statistical analysis | Hierarchical clustering,Data mining,Fuzzy clustering,CURE data clustering algorithm,Correlation clustering,Computer science,Determining the number of clusters in a data set,Constrained clustering,Bioinformatics,Cluster analysis,Single-linkage clustering | Conference |
ISBN | Citations | PageRank |
0-7695-2476-1 | 2 | 0.40 |
References | Authors | |
6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shigeyuki Oba | 1 | 290 | 27.68 |
Kikuya Kato | 2 | 40 | 3.49 |
Shin Ishii | 3 | 212 | 24.55 |