Murinto, Murinto and Prahara, Adhi and Iman HU, Erik
(2021)
*An Investigation of Logarithm Decreasing Inertia Weight Particle Swarm Optimization in Global Optimization Problem.*
[Artikel Dosen]

Text
HASIL CEK_Murinto_An Investigation of Logarithm Decreasing Inertia Weight Particle Swarm Optimization in Global Optimization Problem.pdf Download (1MB) |

## Abstract

ABSTRACT

This research investigates Logarithm Decreasing Inertia Weight

(LogDIW) to improve the performance of Particle Swarm

Optimization (PSO). The general problem of PSO algorithm is

premature convergence when solving complex optimization

problem. Some researchers try to solve the problem by

modifying the PSO or proposing another PSO variants. Some

PSO variants proved to have a better performance than the

original PSO. The purpose of this research is to obtain some

experimental facts to prove the efficiency of LogDIWPSO if the

parameters are tuned correctly and to show that the

LogDIWPSO performs better compared to the other PSO

variants. In the early step of the experiment, a percentage value

of search space boundary is obtained. This step is important to

compute the velocity threshold of LogDIW based on the

optimization problem. The next experiment is done to measure

the performance of LogDIWPSO using six benchmark functions

in optimization problems and to prove the superiority of

LogDIWPSO compared to the other PSO variants. The

experiment result shows that LogDIW achieves better

performance than the other PSO variants.

Item Type: | Artikel Dosen |
---|---|

Keyword: | inertia weight, particle swarm optimization, logarithm decreasing inertia weight |

Subjects: | Q Science > Q Science (General) |

Divisi / Prodi: | Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Informatics Engineering (S1-Teknik Informatika) |

Depositing User: | murinto murinto |

Date Deposited: | 18 Apr 2023 09:48 |

Last Modified: | 23 Sep 2023 06:22 |

URI: | http://eprints.uad.ac.id/id/eprint/43002 |

## Actions (login required)

View Item |