Presentation | 2017-03-14 Search Capability of Random Search PSO with Linked Random Update Kouhei Sakayori, Masato Kaneko, Toshiya Iwai, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Particle Swarm Optimization (PSO) is a metaheuristics using the swarm intelligence. Although PSO is usually applied to the function optimization problem, the search capability is influenced by such properties of objective function as unimodal, multimodal and non-separable behaviors. Especially, it is difficult to search a solution for a non-separable objective function. Koguma and Aiyoshi reported that the difficulty was caused by an anisotropy of velocities of PSO particles and proposed Linked Random Model to reduce the anisotropy. They also reported that, instead of reducing the anisotropy, the global search capability decreased by the model. In this study, we propose the random search PSO (RS-PSO) with Linked Random updata by applying linked random model to RS-PSO that is a variant of PSO improved in the global search ability. We perform the numerical simulations of minimization problems of various types of benchmark functions by our proposed model and find that our proposed model shows high search capability for unimodal, multimodal and non-separable functions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Particle Swarm Optimization / Continuous Optimization Problem / random search / Levy distribution / anisotropy |
Paper # | NLP2016-107 |
Date of Issue | 2017-03-07 (NLP) |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2017/3/14(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Nebuta Museum Warasse |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Hisato Fujisaka(Hiroshima City Univ.) |
Vice Chair | Masaharu Adachi(Tokyo Denki Univ.) |
Secretary | Masaharu Adachi(Konan Univ.) |
Assistant | Hiroyuki Asahara(Okayama Univ. of Science) / Toshihiro Tachibana(Shonan Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Nonlinear Problems |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Search Capability of Random Search PSO with Linked Random Update |
Sub Title (in English) | |
Keyword(1) | Particle Swarm Optimization |
Keyword(2) | Continuous Optimization Problem |
Keyword(3) | random search |
Keyword(4) | Levy distribution |
Keyword(5) | anisotropy |
1st Author's Name | Kouhei Sakayori |
1st Author's Affiliation | Nhon University(Nihon Univ.) |
2nd Author's Name | Masato Kaneko |
2nd Author's Affiliation | Nhon University(Nihon Univ.) |
3rd Author's Name | Toshiya Iwai |
3rd Author's Affiliation | Nhon University(Nihon Univ.) |
Date | 2017-03-14 |
Paper # | NLP2016-107 |
Volume (vol) | vol.116 |
Number (no) | NLP-523 |
Page | pp.pp.7-12(NLP), |
#Pages | 6 |
Date of Issue | 2017-03-07 (NLP) |