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

2022 Fiscal Year Final Research Report

A scenario generation and its simulation for safety and sustainable operation of social systems

Research Project

  • PDF
Project/Area Number 18KT0061
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section特設分野
Research Field Intensification of Artifact Systems
Research InstitutionThe University of Fukuchiyama (2020-2022)
Osaka University (2018-2019)

Principal Investigator

Hatanaka Toshiharu  福知山公立大学, 情報学部, 教授 (10252884)

Co-Investigator(Kenkyū-buntansha) 内種 岳詞  愛知工業大学, 情報科学部, 准教授 (70710143)
Project Period (FY) 2018-07-18 – 2023-03-31
Keywords多因子最適化 / 群知能 / 社会シミュレーション
Outline of Final Research Achievements

Multi-agent type evacuation simulations where assume possible disasters are considered in its environment is useful, for example evaluating evacuation routes. Although conditions corresponding to various damage situations are set there, it may be not able to prepare all combinations of damage situations and to execute simulations under the all conditions. Therefore, in this research project, we investigated a condition setting method from the framework of evolutionary computation with the aim of generating a condition with a greater degree of influence from the output for multiple condition settings, and presented the framework of the method.
In addition, in such evolutionary computation, an algorithm with multiple different factors as the objective function is assumed. Therefore, we verified the evolutionary computation from the framework of multi-factor evolution and proposed an algorithm using hybrid swarm intelligence.

Free Research Field

進化計算

Academic Significance and Societal Importance of the Research Achievements

災害時の行動計画に代表される不測の事態に備えることへ,不測の事態を含む環境下でエージェントモデルが行動し,その結果から計画の評価を行う計算機シミュレーションが利用されている.しかし,不測の事態を網羅的に設定し,評価を行うことには困難さがある.
この問題に対して,複数の用意した事態(状況)を評価し,その評価値に従い,新しい事態(状況)を生成し,評価する手法の枠組みを提案したこと,およびこの枠組みは進化計算の考え方に立脚しており,進化計算における多因子最適化との関連を考察し,ハイブリッド型の多因子最適化法を提案したことが本課題の成果の意義といえる.

URL: 

Published: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi