Experimental analysis on the operation of Particle Swarm Optimization

Simple item page
dc.contributor.advisorChen, Stephen
dc.contributor.authorYadollahpour, Naeemeh
dc.date.accessioned2021-07-06T12:50:52Z
dc.date.available2021-07-06T12:50:52Z
dc.date.copyright2021-04
dc.date.issued2021-07-06
dc.date.updated2021-07-06T12:50:52Z
dc.degree.disciplineInformation Systems and Technology
dc.degree.levelMaster's
dc.degree.nameMA - Master of Arts
dc.description.abstractIn Particle Swarm Optimization, it has been observed that swarms often stall as opposed to converge. A stall occurs when all of the forward progress that could occur is instead rejected as Failed Exploration. Since the swarms particles are in good regions of the search space with the potential to make more progress, the introduction of perturbations to the pbest positions can lead to significant improvements in the performance of standard Particle Swarm Optimization. The pbest perturbation has been supported by a line search technique that can identify unimodal, globally convex, and non-globally convex search spaces, as well as the approximate size of attraction basin. A deeper analysis of the stall condition reveals that it involves clusters of particles that are performing exploitation, and these clusters are separated by individual particles that are performing exploration. This stall pattern can be identified by a newly developed method that is efficient, accurate, real-time, and search space independent. A more targeted (heterogenous) modification for stall is presented for globally convex search spaces.
dc.identifier.urihttp://hdl.handle.net/10315/38481
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsparticle swarm optimization
dc.subject.keywordsconvergence
dc.subject.keywordsstall
dc.subject.keywordsattraction basin
dc.titleExperimental analysis on the operation of Particle Swarm Optimization
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Yadollahpour_Naeemeh_2021_Masters.pdf
Size:
2.46 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Information Systems and Technology

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.