• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

A Study on Improving Search Ability of Evolutionary Multi-objective Optimization Incorporating Topological Clustering

Research Project

Project/Area Number 19K20358
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 61040:Soft computing-related
Research InstitutionOsaka Metropolitan University (2022)
Osaka Prefecture University (2019-2021)

Principal Investigator

Masuyama Naoki  大阪公立大学, 大学院情報学研究科, 准教授 (00815607)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2020: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2019: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Keywords進化型多目的最適化 / 最適化 / クラスタリング / 適応共鳴理論 / 可視化 / 多目的進化計算
Outline of Research at the Start

進化型多目的最適化手法は,最適化すべき目的が複数存在する問題に対して手法の1回の実行で複数の解を生成できるという利点がある.しかし,既存の進化型多目的最適化手法は単純なテスト問題を手法の評価に利用しているため,実問題のような複雑な問題への対応が困難である.そこで本研究では,進化型多目的最適化手法が保持する解集合の代表点を成長型トポロジカルクラスタリングにより抽出し,代表点となるノードを探索方向とした分割に基づく効率的な進化型多目的最適化手法の提案を行う.本提案手法は,トポロジー構造を利用した最適解分布の推測,および効率的な遺伝的操作を実現する.

Outline of Final Research Achievements

In this research, we proposed an algorithm to summarize the distribution information of the solutions obtained during the search by using a clustering approach, and to adjust the position of the reference vector set according to clustering results. The results of this research have been accepted in IEEE Transactions on Evolutionary Computation, one of the top academic journals in the field of evolutionary computation. In addition, we proposed an analytical method that quantitatively measures each with two evaluation metrics by dividing the search performance of EMOAs into convergence and diversity.

Academic Significance and Societal Importance of the Research Achievements

進化型多目的最適化手法において,探索に重みベクトルを利用する手法の理論的研究は,(a)適応的に重みベクトルの生成や方向調整を行う機構の研究,および重みベクトルに設定する最適な距離関数の選択方法に関する研究に大別される.本研究は,成長型トポロジカルクラスタリング手法をもとに,上記(a),(b)を同時に考慮する独自性の高い発展的研究である.また,探索過程の定量的・定性的評価が可能な指標の提案を基に,進化型多目的最適化手法や,代表的なテスト問題が内包する特性や類似性を明らかにし,新たな最適化手法の設計方針や,現在のテスト問題における問題点を議論することが可能となる.

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (11 results)

All 2022 2021 2020 Other

All Int'l Joint Research (1 results) Journal Article (2 results) (of which Int'l Joint Research: 1 results,  Peer Reviewed: 2 results) Presentation (8 results) (of which Int'l Joint Research: 3 results)

  • [Int'l Joint Research] 南方科技大学(中国)

    • Related Report
      2019 Research-status Report
  • [Journal Article] Fuzzy Genetics-Based Machine Learning to Handle Continually Increasing Unknown Classes2020

    • Author(s)
      入江勇斗,増山直輝,能島裕介,石渕久生
    • Journal Title

      Journal of Japan Society for Fuzzy Theory and Intelligent Informatics

      Volume: 32 Issue: 1 Pages: 512-517

    • DOI

      10.3156/jsoft.32.1_512

    • NAID

      130007798550

    • ISSN
      1347-7986, 1881-7203
    • Year and Date
      2020-02-15
    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] Adapting Reference Vectors and Scalarizing Functions by Growing Neural Gas to Handle Irregular Pareto Fronts2020

    • Author(s)
      Liu Yiping、Ishibuchi Hisao、Masuyama Naoki、Nojima Yusuke
    • Journal Title

      IEEE Transactions on Evolutionary Computation

      Volume: 24 Pages: 439-453

    • DOI

      10.1109/tevc.2019.2926151

    • Related Report
      2020 Research-status Report 2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Search process analysis of multiobjective evolutionary algorithms using convergence-diversity diagram2022

    • Author(s)
      T. Kinoshita, N. Masuyama, and Y. Nojima
    • Organizer
      2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Analytical methods to separately evaluate convergence and diversity for multi-objective optimization2022

    • Author(s)
      T. Kinoshita, N. Masuyama, Y. Nojima, and H. Ishibuchi
    • Organizer
      14th International Conference of Metaheuristics (MIC 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Convergence-Diversity Diagramの探索過程分析への拡張2022

    • Author(s)
      木下貴登,増山直輝,能島裕介
    • Organizer
      第22回進化計算学会研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] 進化型多目的最適化アルゴリズムの分割的性能評価2022

    • Author(s)
      木下貴登,増山直輝,能島裕介,石渕久生
    • Organizer
      第16回進化計算シンポジウム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 適応共鳴理論に基づくクラスタリングを用いた進化型多目的最適化アルゴリズム2021

    • Author(s)
      木下貴登,増山直輝,能島裕介,石渕久生
    • Organizer
      第20回進化計算学会研究会
    • Related Report
      2021 Research-status Report
  • [Presentation] 進化型多目的最適化アルゴリズムの分割的性能評価2021

    • Author(s)
      木下貴登,増山直輝,能島裕介,石渕久生
    • Organizer
      第15回進化計算シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] クラスタリング手法を用いた適応的分割に基づく進化型多目的最適化アルゴリズムの性能評価2020

    • Author(s)
      木下貴登,増山直輝,能島裕介,石渕久生
    • Organizer
      第14回進化計算シンポジウム
    • Related Report
      2020 Research-status Report
  • [Presentation] On the Normalization in Evolutionary Multi-Modal Multi-Objective Optimization2020

    • Author(s)
      Liu Yiping、Ishibuchi Hisao、Yen Gary G.、Nojima Yusuke、Masuyama Naoki、Han Yuyan
    • Organizer
      2020 IEEE Congress on Evolutionary Computation (CEC 2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi