12 April 2004 Cluster analysis of long time-series medical datasets
Author Affiliations +
Abstract
This paper presents a comparative study about the characteristics of clustering methods for inhomogeneous time-series medical datasets. Using various combinations of comparison methods and grouping methods, we performed clustering experiments of the hepatitis data set and evaluated validity of the results. The results suggested that (1) complete-linkage (CL) criterion in agglomerative hierarchical clustering (AHC) outperformed average-linkage (AL) criterion in terms of the interpretability of a dendrogram and clustering results, (2) combination of dynamic time warping (DTW) and CL-AHC constantly produced interpretable results, (3) combination of DTW and rough clustering (RC) would be used to find the core sequences of the clusters, (4) multiscale matching may suffer from the treatment of 'no-match' pairs, however, the problem may be eluded by using RC as a subsequent grouping method.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shoji Hirano, Shoji Hirano, Shusaku Tsumoto, Shusaku Tsumoto, } "Cluster analysis of long time-series medical datasets", Proc. SPIE 5433, Data Mining and Knowledge Discovery: Theory, Tools, and Technology VI, (12 April 2004); doi: 10.1117/12.542931; https://doi.org/10.1117/12.542931
PROCEEDINGS
8 PAGES


SHARE
Back to Top