2008 21st IEEE International Symposium on Computer-Based Medical Systems
Mining Trajectories of Laboratory Data using Multiscale Matching and Clustering
June 17-June 19
ISBN: 978-0-7695-3165-6
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/CBMS.2008.140
This paper shows application of trajectory mining techniquesto laboratory examination data, where dynamics of two laboratoryexaminations are represented as a trajectory in a two dimensionalplane. Each trajectory is segmented and compared with other trajectoriesby multiscale matching, and clustered by using similarities obtainedby matching technique.Experimental results on chronic hepatitis data demonstratedthat the method could find the groups of trajectorieswhich reflects temporal covariance of platelet, albumin and cholineesterase.
Index Terms:
trajectory mining, medical data mining, temporal data mining
Citation:
Shusaku Tsumoto, Shoji Hirano, "Mining Trajectories of Laboratory Data using Multiscale Matching and Clustering," cbms, pp.626-631, 2008 21st IEEE International Symposium on Computer-Based Medical Systems, 2008
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||