Empirical Comparison of Clustering Methods for Long Time-Series Databases

• Published in: Active Mining pp. 268 - 286
• Main Authors: Hirano, Shoji, Tsumoto, Shusaku
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005
• Series: Lecture Notes in Computer Science
• Subjects: Agglomerative Hierarchical Cluster; Cluster Method; Dynamic Time Warping; Empirical Comparison; Planar Curf

In this paper we report some characteristics of time-series comparison methods and clustering methods found empirically using a real-world medical database. First, we examined basic characteristics of two sequence comparison methods, multiscale matching (MSM) and dynamic time warping (DTW), using a...