Cover Image

Performance comparison of different swarm intelligence methods towards benchmark functions

Optimization problems are associated with different kinds of complicated and constraints which make optimization still being so important until today. This is because optimization is able to help researchers and organisations reached an optimal solution on different research works or applications us...

Full description

Saved in:
Bibliographic Details
Main Author: Song, Wen Huan
Format: Final Year Project / Dissertation / Thesis
Published: 2020
Subjects:
Q Science (General)
Online Access:http://eprints.utar.edu.my/3912/1/16ACB02672_FYP.pdf
http://eprints.utar.edu.my/3912/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-utar-eprints.3912
record_format eprints
spelling my-utar-eprints.39122021-01-07T07:00:08Z Performance comparison of different swarm intelligence methods towards benchmark functions Song, Wen Huan Q Science (General) Optimization problems are associated with different kinds of complicated and constraints which make optimization still being so important until today. This is because optimization is able to help researchers and organisations reached an optimal solution on different research works or applications using limited resources. In the past 20 years, Swarm Intelligence (SI) methods have been trendy in solving different kinds of complex problems. However, researchers or organisations still did not consider on the performance of the SI methods as there are various SI methods and not everyone contains the knowledge on the methods. Hence, the objective of this research is to analyse different Particle Swarm Optimization (PSO) models and to identify the best method in SI. The original version of PSO, Inertia Weight PSO (IWPSO), Linearly Decrease Inertia Weight PSO (LDIW-PSO), Random Inertia Weight PSO (RIW-PSO), Constriction Factor PSO (CF-PSO) along with and without velocity clamping (VC) are analyzed and compared with Grey Wolf Optimizer (GWO) and Bat Algorithm (BA). The performance of SI method is tested using ten benchmark functions. The results in Experiment 1 show that CF-PSO with VC is performed more significant compared to the other PSO models. Hence, it is considered as the best PSO model in Experiment 1. Therefore, Experiment 2 is conducted and compared with GWO and BA using CF-PSO with VC. The results in Experiment 2 also reveal that CF-PSO with VC is the best SI method when it is compared towards the other SI methods. The result produced can help researchers to acknowledge and have better understanding on the SI methods so that better performance SI method with good accuracy can be applied on their research. 2020-05-14 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/3912/1/16ACB02672_FYP.pdf Song, Wen Huan (2020) Performance comparison of different swarm intelligence methods towards benchmark functions. Final Year Project, UTAR. http://eprints.utar.edu.my/3912/
institution Universiti Tunku Abdul Rahman
building UTAR Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tunku Abdul Rahman
content_source UTAR Institutional Repository
url_provider http://eprints.utar.edu.my
topic Q Science (General)
spellingShingle Q Science (General)
Song, Wen Huan
Performance comparison of different swarm intelligence methods towards benchmark functions
description Optimization problems are associated with different kinds of complicated and constraints which make optimization still being so important until today. This is because optimization is able to help researchers and organisations reached an optimal solution on different research works or applications using limited resources. In the past 20 years, Swarm Intelligence (SI) methods have been trendy in solving different kinds of complex problems. However, researchers or organisations still did not consider on the performance of the SI methods as there are various SI methods and not everyone contains the knowledge on the methods. Hence, the objective of this research is to analyse different Particle Swarm Optimization (PSO) models and to identify the best method in SI. The original version of PSO, Inertia Weight PSO (IWPSO), Linearly Decrease Inertia Weight PSO (LDIW-PSO), Random Inertia Weight PSO (RIW-PSO), Constriction Factor PSO (CF-PSO) along with and without velocity clamping (VC) are analyzed and compared with Grey Wolf Optimizer (GWO) and Bat Algorithm (BA). The performance of SI method is tested using ten benchmark functions. The results in Experiment 1 show that CF-PSO with VC is performed more significant compared to the other PSO models. Hence, it is considered as the best PSO model in Experiment 1. Therefore, Experiment 2 is conducted and compared with GWO and BA using CF-PSO with VC. The results in Experiment 2 also reveal that CF-PSO with VC is the best SI method when it is compared towards the other SI methods. The result produced can help researchers to acknowledge and have better understanding on the SI methods so that better performance SI method with good accuracy can be applied on their research.
format Final Year Project / Dissertation / Thesis
author Song, Wen Huan
author_facet Song, Wen Huan
author_sort Song, Wen Huan
title Performance comparison of different swarm intelligence methods towards benchmark functions
title_short Performance comparison of different swarm intelligence methods towards benchmark functions
title_full Performance comparison of different swarm intelligence methods towards benchmark functions
title_fullStr Performance comparison of different swarm intelligence methods towards benchmark functions
title_full_unstemmed Performance comparison of different swarm intelligence methods towards benchmark functions
title_sort performance comparison of different swarm intelligence methods towards benchmark functions
publishDate 2020
url http://eprints.utar.edu.my/3912/1/16ACB02672_FYP.pdf
http://eprints.utar.edu.my/3912/
_version_ 1688551791875063808
score 13.211869

Similar Items