Mixed-integer evolution strategies for parameter optimization and their applications to medical image analysis

Leiden Repository

Mixed-integer evolution strategies for parameter optimization and their applications to medical image analysis

Type: Doctoral Thesis
Title: Mixed-integer evolution strategies for parameter optimization and their applications to medical image analysis
Author: Li, Rui
Publisher: Leiden Institute of Advanced Computer Science (LIACS), Faculty of Science, Leiden University
Issue Date: 2009-10-06
Keywords: Computer Tomographic Angiography Image Analysis
Evolution Strategies
Evolutionary Computation
Intravascular Ultrasound Image Analysis
Medical Image Analysis
Mixed-Integer Evolution Strategies
Abstract: The target of this work is to extend the canonical Evolution Strategies (ES) from traditional real-valued parameter optimization domain to mixed-integer parameter optimization domain. This is necessary because there exist numerous practical optimization problems from industry in which the set of decision variables simultaneously involves continuous, integer and discrete variables. Furthermore, objective functions of this type of problems could be based on large-scale simulation models or the structure of the objective functions may be too complex to be modeled. From this perspective, optimization problems of this kind are classified into the black-box optimization category. For them, classic optimization techniques, which come from Mathematical Programming (MP) research field, cannot be easily applied, since they are based on the assumption that the search space can always be efficiently explored using a divide-and-conquer sche me. While our new proposed algorithm, the so-called Mixed-Integer Evolution Strategies (MIES), by contrast, is capable of yielding good solutions to these challenging black-box optimization problems by using specialized variation operators tailored for mixed-integer parameter classes. In this work not only did we study MIES intensively from a theoretical point of view, but also we develop the framework for applying MIES to the real-world optimization problem in the medical field.
Description: Promotor: T.H.W. Bäck, Co-promotor: M.T.M. Emmerich
With summary in Dutch
Faculty: Faculteit der Wiskunde en Natuurwetenschappen
Citation: Li, R., 2009, Doctoral thesis, Leiden University
ISBN: 9789090246659
Sponsor: This research was financed by the Netherlands Organization for Scientific Research (NWO) under project 612.066.408 "SAVAGE". The work in this thesis has been carried out under the auspices of the research school IPA (Institute for Programming research and Algorithmics).
Handle: http://hdl.handle.net/1887/14049
 

Files in this item

Description Size View
application/pdf Full text 4.388Mb View/Open
application/pdf Propositions 24.24Kb View/Open

This item appears in the following Collection(s)