Improved strategies for distance based clustering of objects on subsets of attributes in high-dimensional data

Leiden Repository

Improved strategies for distance based clustering of objects on subsets of attributes in high-dimensional data

Type: Doctoral Thesis
Title: Improved strategies for distance based clustering of objects on subsets of attributes in high-dimensional data
Author: Kampert, M.M.D.
Issue Date: 2019-07-03
Keywords: High-Dimensional Data
Clustering
Distance based Clustering
Dissimilarity
COSA
Multidimensional Scaling
Unsupervised learning
Exploratory Analysis
Abstract: This monograph focuses on clustering of objects in high-dimensional data, given the restriction that the objects do not cluster on all the attributes, not even on a single subset of attributes, but often on different subsets of attributes in the data. With the objective to reveal such a clustering structure, Friedman and Meulman (2004) proposed a framework and a specific algorithm, called COSA. In this monograph we propose various improvements to the original COSA algorithm. The first improvement targets the optimization strategy for the tuning parameters in COSA. Further, a reformulation of the COSA criterion brings down the number of tuning parameters from two to one, enables incorporation of pre-specified initial weights for the attribute distances and allows for a solution that consists of zero-valued attribute weights. The third improvement consists of a new definition of the COSA distances that yields a better separation between objects from different clusters. We compared the `old' and the improved COSA with other state of the art methods. The comparison is based on simulated and real omics data sets.
Promotor: Supervisor: Meulman J.J.
Faculty: Faculty of Science
University: Leiden University
Handle: http://hdl.handle.net/1887/74690
 

Files in this item

Description Size View
application/pdf Full text 3.070Mb View/Open
application/pdf Cover 95.74Kb View/Open
application/pdf Title pages_Contents 206.4Kb View/Open
application/pdf Chapter 1 501.6Kb View/Open
application/pdf Chapter 2 552.1Kb View/Open
application/pdf Chapter 3 1.440Mb View/Open
application/pdf Chapter 4 998.3Kb View/Open
application/pdf Chapter 5 615.7Kb View/Open
application/pdf Chapter 6 636.1Kb View/Open
application/pdf Chapter 7 381.8Kb View/Open
application/pdf References 210.4Kb View/Open
application/pdf Index 156.4Kb View/Open
application/pdf Summary in English 195.4Kb View/Open
application/pdf Summary in Dutch 196.5Kb View/Open
application/pdf Acknowledgements_Curriculum Vitae 100.9Kb View/Open
application/pdf Propositions 112.9Kb View/Open

This item appears in the following Collection(s)