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

Bayesian Optimization for Estimation of Unknown Multidimensional Psychophysical Functions

Research Project

Project/Area Number 19K03375
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 10040:Experimental psychology-related
Research InstitutionOsaka Electro-Communication University

Principal Investigator

Komori Masashi  大阪電気通信大学, 情報通信工学部, 教授 (60352019)

Co-Investigator(Kenkyū-buntansha) 遠里 由佳子  立命館大学, 情報理工学部, 教授 (80346171)
Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Keywordsガウス過程選好学習 / ガウス過程回帰 / 効用関数 / 顔知覚 / ベイズ最適化 / 心理物理学 / 顔認知 / 心理物理関数 / 実験計画法
Outline of Research at the Start

例えば「2色の配色」は6次元の物理量により記述され,その組み合わせは膨大な数になる.したがって「配色の良さ」を考えた時膨大な組み合わせの中から良い配色を見つけなければならない.本研究ではこのような複雑な多次元の心理物理関数の全体像を,ベイズ最適化という手法に基づいて解明する手法の構築を目指す.また,この手法を心理学的・実験美学的研究のみならず,人の感性に適合したものづくりへ積極的に応用することを目指す.

Outline of Final Research Achievements

In this project, we developed methodologies for estimating a multidimensional psychophysical function (referred to as a utility function) using Gaussian process regression. We employed Gaussian process preference learning (GPPL), an extension of Gaussian process regression, to estimate human utility functions based on responses to alternative two-choice tasks. Furthermore, we developed various methodologies to apply Gaussian process preference learning to various psychological problems such as facial impression researches and design researches, and demonstrated the effectiveness of the proposed method through experimental investigations. We also developed applications for conducting these experiments and explored the field of application of the methodologies.

Academic Significance and Societal Importance of the Research Achievements

研究成果の学術的意義は(1)ガウス過程選好学習(GPPL)が多様な心理学的な問題に適用可能であり.また多次元の心的な効用関数の推定において従来の手法より高い予測精度を持つことを示したこと,(2)また効用関数の特徴や信頼性を記述するための様々な手法を確立したことである.社会的意義は,GPPLにもとづくベイズ最適化を簡便に行うことができるアプリケーション・実験システムを構築し,この手法が,言語化が容易ではない感性の可視化(他者に対する偏見の可視化,商品コンセプトの可視化)に有効であることを示したことである.

Report

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

    (14 results)

All 2022 2021 2020 2019

All Journal Article (5 results) (of which Peer Reviewed: 4 results) Presentation (9 results) (of which Int'l Joint Research: 2 results)

  • [Journal Article] Generating Shampoo Bottle Contour Shapes Conforming to Product Concepts Based on Pairwise Preferences2022

    • Author(s)
      城下 慧人、小森 政嗣、横山 卓未
    • Journal Title

      The Transactions of Human Interface Society

      Volume: 24 Issue: 1 Pages: 53-62

    • DOI

      10.11184/his.24.1_53

    • NAID

      130008163756

    • ISSN
      1344-7262, 2186-8271
    • Year and Date
      2022-02-25
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Investigation of Facial Preference Using Gaussian Process Preference Learning and Generative Image Model2021

    • Author(s)
      Komori Masashi、Shiroshita Keito、Nakagami Masataka、Nakamura Koyo、Kobayashi Maiko、Watanabe Katsumi
    • Journal Title

      Lecture Notes in Computer Science

      Volume: 12883 Pages: 193-202

    • DOI

      10.1007/978-3-030-84340-3_15

    • ISBN
      9783030843397, 9783030843403
    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Application of Gaussian Process Preference Learning for Visualizing Facial Features Related to Personality Traits2021

    • Author(s)
      Shiroshita Keito、Komori Masashi、Nakamura Koyo、Kobayashi Maiko、Watanabe Katsumi
    • Journal Title

      Proc. the 8th IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE 2021)

      Volume: 1 Pages: 1-6

    • DOI

      10.1109/csde53843.2021.9718431

    • Related Report
      2021 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 二肢選択ベイズ最適化による「かわいい」形の探索2019

    • Author(s)
      小森 政嗣
    • Journal Title

      電子情報通信学会技術研究報告(HCS2019-15)

      Volume: 119(38) Pages: 109-112

    • Related Report
      2019 Research-status Report
  • [Journal Article] 二肢選択ベイズ最適化によるリップ・チークの色のよい組み合わせ の検討2019

    • Author(s)
      小森 政嗣
    • Journal Title

      日本認知科学会第36回大会論文集

      Volume: 2A-045 Pages: 350-353

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] 順位づけ評価に基づくベイズ最適化による塩ラーメンの調味料配合比の決定2021

    • Author(s)
      城下慧人, 木村光栄, 小森政嗣
    • Organizer
      ヒューマンインタフェースシンポジウム2021
    • Related Report
      2021 Annual Research Report
  • [Presentation] ガウス過程選好学習と敵対的生成ネットワークを用いた外集団の顔特徴の可視化―阪神ファンが考える巨人ファンの顔―2021

    • Author(s)
      小森政嗣, 城下慧人, 中村航洋, 小林麻衣子, 渡邊克巳
    • Organizer
      日本心理学会第85回大会
    • Related Report
      2021 Annual Research Report
  • [Presentation] 二肢選択課題にもとづくガウス過程選好学習による外集団の顔のステレオタイプの推定2021

    • Author(s)
      小森政嗣, 城下慧人, 中村航洋, 小林麻衣子, 渡邊克巳
    • Organizer
      HCGシンポジウム2021
    • Related Report
      2021 Annual Research Report
  • [Presentation] Synthesis of contour shapes perceived as kawaii by using Bayesian optimization2021

    • Author(s)
      Komori Masashi、Shiroshita Keito
    • Organizer
      The 32nd International Congress of Psychology (ICP 2020+)
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 生物の気持ち悪い配色の特徴2020

    • Author(s)
      城下 慧人・小森 政嗣
    • Organizer
      人工知能学会(JSAI2020)
    • Related Report
      2020 Research-status Report
  • [Presentation] Synthesis of contour shapes perceived as kawaii by using Bayesian optimization2020

    • Author(s)
      Masashi Komori, Keito Shiroshita
    • Organizer
      ICP2020
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] ガウス過程順序回帰による生物の気持ち悪い配色の探索2020

    • Author(s)
      城下慧人・小森 政嗣
    • Organizer
      人工知能学会全国大会(第34回)
    • Related Report
      2019 Research-status Report
  • [Presentation] ガウス過程回帰によるブーバ/キキ形状の生成2019

    • Author(s)
      小森 政嗣
    • Organizer
      日本心理学会第83回大会
    • Related Report
      2019 Research-status Report
  • [Presentation] ガウス過程順序回帰による輪郭形状の「かわいさ」の検討2019

    • Author(s)
      城下慧人・小森 政嗣
    • Organizer
      HCGシンポジウム2019
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi