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

Research on inverse analysis and scientific interpretation of property prediction models

Research Project

Project/Area Number 19K15352
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 27020:Chemical reaction and process system engineering-related
Research InstitutionMeiji University

Principal Investigator

Kaneko Hiromasa  明治大学, 理工学部, 専任准教授 (00625171)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2021: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2020: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2019: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Keywords適応的実験計画法 / 能動学習 / 直接的逆解析 / 予測精度 / ベイズ最適化 / 分子設計 / 材料設計 / プロセス設計 / QSPR / QSAR / モデルの逆解析 / モデルの解釈 / ケモインフォマティクス / マテリアルズインフォマティクス / プロセスインフォマティクス / 人工知能
Outline of Research at the Start

本研究の目的は、化学構造および実験条件から材料の物性を予測する人工知能モデルを逆方向に解析(逆解析)することで、目標の物性を満たすための化学構造情報および実験条件情報を獲得し、さらにモデルを科学的に解釈することである。本研究の目的を達成するため、以下の項目 A) B) を実施する。
A) 化学構造・実験条件と物性の間の関係を確率分布で表現することでモデルの逆解析が可能となる、複数物性を対象にした高精度な物性予測モデル (人工知能モデル) を構築する
B) 人工知能モデルを数値的に”実験”することで、モデルを科学的に解釈する

Outline of Final Research Achievements

Conventional inverse analysis in the design of molecules, materials and processes involves constructing mathematical model Y=f(X) between properties/activities Y and features X, then generating a large number of virtual samples of X, inputting them into mathematical model to predict the values of Y and selecting virtual samples with good prediction values. It was only a pseudo-inverse analysis, in which forward analysis was repeated exhaustively. This was nothing more than predicting Y in the search range of X assumed in advance by humans, and was not at all compatible with the search for new functions that would only emerge under conditions that were not initially assumed. In this study, a method for directly predicting the values of X from the values of Y, i.e. a method for truly inverse analysis of mathematical model by converting Y=f(X) to X=g(Y) was proposed, and the proposed method was applied to various molecules, materials and processes.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果により、科学者・開発者の創造力のつまった実験結果の中にある暗黙知を形式知化でき、実験結果および実験データから構築された数理モデルを化学的・工学的に理解できる形にすることが可能になる。提案手法により、どうしてその実験結果になったのか、どうしてその化学構造・実験条件・プロセス条件で物性値・活性値が得られたのか、望ましい物性値・活性値を得るためにはどのような化学構造・実験条件・プロセス条件にすればよいのか、といったことが明らかになり、科学的なメカニズムの解明に貢献する。本研究の成果により実験と統計とが融合することにより新たな科学的知識発見につながる。

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

    (71 results)

All 2023 2022 2021 2020 2019

All Journal Article (36 results) (of which Peer Reviewed: 29 results,  Open Access: 16 results) Presentation (31 results) (of which Int'l Joint Research: 4 results,  Invited: 21 results) Book (4 results)

  • [Journal Article] Direct prediction of the batch time and process variable profiles using batch process data based on different batch times2023

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Computers & Chemical Engineering

      Volume: 169 Pages: 108072-108072

    • DOI

      10.1016/j.compchemeng.2022.108072

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Local interpretation of nonlinear regression model with k-nearest neighbors2023

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Digital Chemical Engineering

      Volume: 6 Pages: 100078-100078

    • DOI

      10.1016/j.dche.2022.100078

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] De Novo Direct Inverse QSPR/QSAR: Chemical Variational Autoencoder and Gaussian Mixture Regression Models2023

    • Author(s)
      Nemoto Kohei、Kaneko Hiromasa
    • Journal Title

      Journal of Chemical Information and Modeling

      Volume: 63 Issue: 3 Pages: 794-805

    • DOI

      10.1021/acs.jcim.2c01298

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Design of batch process with machine learning, feature extraction, and direct inverse analysis2023

    • Author(s)
      Yamakage Shuto、Kaneko Hiromasa
    • Journal Title

      Case Studies in Chemical and Environmental Engineering

      Volume: 7 Pages: 100308-100308

    • DOI

      10.1016/j.cscee.2023.100308

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Retrosynthetic and Synthetic Reaction Prediction Model Based on Sequence‐to‐Sequence with Attention for Polymer Designs2023

    • Author(s)
      Taniwaki Hiroaki、Kaneko Hiromasa
    • Journal Title

      Macromolecular Theory and Simulations

      Volume: - Issue: 4

    • DOI

      10.1002/mats.202300011

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Machine Learning Model for Predicting the Material Properties and Bone Formation Rate and Direct Inverse Analysis of the Model for New Synthesis Conditions of Bioceramics2023

    • Author(s)
      Motojima Kohei、Shiratsuchi Rina、Suzuki Kitaru、Aizawa Mamoru、Kaneko Hiromasa
    • Journal Title

      Industrial & Engineering Chemistry Research

      Volume: 62 Issue: 14 Pages: 5898-5906

    • DOI

      10.1021/acs.iecr.3c00332

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Adaptive soft sensor based on transfer learning and ensemble learning for multiple process states2022

    • Author(s)
      Yamada Nobuhito、Kaneko Hiromasa
    • Journal Title

      Analytical Science Advances

      Volume: 3 Issue: 5-6 Pages: 205-211

    • DOI

      10.1002/ansa.202200013

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Molecular design of monomers by considering the dielectric constant and stability of the polymer2022

    • Author(s)
      Taniwaki Hiroaki、Kaneko Hiromasa
    • Journal Title

      Polymer Engineering & Science

      Volume: 62 Issue: 9 Pages: 2750-2756

    • DOI

      10.1002/pen.26058

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Design of adaptive soft sensor based on Bayesian optimization2022

    • Author(s)
      Yamakage Shuto、Kaneko Hiromasa
    • Journal Title

      Case Studies in Chemical and Environmental Engineering

      Volume: 6 Pages: 100237-100237

    • DOI

      10.1016/j.cscee.2022.100237

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Design of Molecules with Low Hole and Electron Reorganization Energy Using DFT Calculations and Bayesian Optimization2022

    • Author(s)
      Ando Tatsuhito、Shimizu Naoto、Yamamoto Norihisa、Matsuzawa Nobuyuki N.、Maeshima Hiroyuki、Kaneko Hiromasa
    • Journal Title

      The Journal of Physical Chemistry A

      Volume: 126 Issue: 36 Pages: 6336-6347

    • DOI

      10.1021/acs.jpca.2c05229

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Cross‐validated permutation feature importance considering correlation between features2022

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Analytical Science Advances

      Volume: 3 Issue: 9-10 Pages: 278-287

    • DOI

      10.1002/ansa.202200018

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Integration of Materials and Process Informatics: Metal Oxide and Process Design for CO<sub>2</sub> Reduction2022

    • Author(s)
      Iwama Ryo、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 7 Issue: 50 Pages: 46922-46934

    • DOI

      10.1021/acsomega.2c06008

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Process-Informatics-Assisted Preparation of Lithium Titanate Crystals with Various Sizes and Morphologies2022

    • Author(s)
      Kaneko Daigo、Kaneko Hiromasa、Hayashi Fumitaka、Fukaishi Kohei、Yamada Tetsuya、Teshima Katsuya
    • Journal Title

      Industrial & Engineering Chemistry Research

      Volume: 62 Issue: 1 Pages: 511-518

    • DOI

      10.1021/acs.iecr.2c02729

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Initial Sample Selection in Bayesian Optimization for Combinatorial Optimization of Chemical Compounds2022

    • Author(s)
      Morishita Toshiharu、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 8 Issue: 2 Pages: 2001-2009

    • DOI

      10.1021/acsomega.2c05145

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Open Access
  • [Journal Article] Development of Prediction Models for the Self-Accelerating Decomposition Temperature of Organic Peroxides2022

    • Author(s)
      Morishita Toshiharu、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 7 Issue: 2 Pages: 2429-2437

    • DOI

      10.1021/acsomega.1c06481

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Deep Convolutional Neural Network with Deconvolution and a Deep Autoencoder for Fault Detection and Diagnosis2022

    • Author(s)
      Kanno Yasuhiro、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 7 Issue: 2 Pages: 2458-2466

    • DOI

      10.1021/acsomega.1c06607

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] True Gaussian mixture regression and genetic algorithm-based optimization with constraints for direct inverse analysis2022

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Science and Technology of Advanced Materials: Methods

      Volume: 2 Issue: 1 Pages: 14-22

    • DOI

      10.1080/27660400.2021.2024101

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Genetic Algorithm-Based Partial Least-Squares with Only the First Component for Model Interpretation2022

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 7 Issue: 10 Pages: 8968-8979

    • DOI

      10.1021/acsomega.1c07379

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Design and Analysis of Metal Oxides for CO<sub>2</sub> Reduction Using Machine Learning, Transfer Learning, and Bayesian Optimization2022

    • Author(s)
      Iwama Ryo、Takizawa Koji、Shinmei Kenichi、Baba Eisuke、Yagihashi Noritoshi、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 7 Issue: 12 Pages: 10709-10717

    • DOI

      10.1021/acsomega.2c00461

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Correlation between the Metal and Organic Components, Structure Property, and Gas-Adsorption Capacity of Metal?Organic Frameworks2021

    • Author(s)
      Yuyama Shunsuke、Kaneko Hiromasa
    • Journal Title

      Journal of Chemical Information and Modeling

      Volume: 61 Issue: 12 Pages: 5785-5792

    • DOI

      10.1021/acs.jcim.1c01205

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Adaptive soft sensor ensemble for selecting both process variables and dynamics for multiple process states2021

    • Author(s)
      Yamada Nobuhito、Kaneko Hiromasa
    • Journal Title

      Chemometrics and Intelligent Laboratory Systems

      Volume: 219 Pages: 104443-104443

    • DOI

      10.1016/j.chemolab.2021.104443

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Lifting the limitations of Gaussian mixture regression through coupling with principal component analysis and deep autoencoding2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Chemometrics and Intelligent Laboratory Systems

      Volume: 218 Pages: 104437-104437

    • DOI

      10.1016/j.chemolab.2021.104437

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Design of Experimental Conditions with Machine Learning for Collaborative Organic Synthesis Reactions Using Transition-Metal Catalysts2021

    • Author(s)
      Ebi Tomoya、Sen Abhijit、Dhital Raghu N.、Yamada Yoichi M. A.、Kaneko Hiromasa
    • Journal Title

      ACS Omega

      Volume: 6 Issue: 41 Pages: 27578-27586

    • DOI

      10.1021/acsomega.1c04826

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Examining variable selection methods for the predictive performance of regression models and the proportion of selected variables and selected random variables2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Heliyon

      Volume: 7 Issue: 6 Pages: e07356-e07356

    • DOI

      10.1016/j.heliyon.2021.e07356

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Extended Gaussian mixture regression for forward and inverse analysis2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Chemometrics and Intelligent Laboratory Systems

      Volume: 213 Pages: 104325-104325

    • DOI

      10.1016/j.chemolab.2021.104325

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Design of ethylene oxide production process based on adaptive design of experiments and Bayesian optimization2021

    • Author(s)
      Iwama Ryo、Kaneko Hiromasa
    • Journal Title

      Journal of Advanced Manufacturing and Processing

      Volume: 3 Issue: 3

    • DOI

      10.1002/amp2.10085

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Transfer learning and wavelength selection method in NIR spectroscopy to predict glucose and lactate concentrations in culture media using VIP‐Boruta2021

    • Author(s)
      Kaneko Hiromasa、Kono Shunsuke、Nojima Akihiro、Kambayashi Takuya
    • Journal Title

      Analytical Science Advances

      Volume: 2 Issue: 9-10 Pages: 470-479

    • DOI

      10.1002/ansa.202000177

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Estimating the reliability of predictions in locally weighted partial least‐squares modeling2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Journal of Chemometrics

      Volume: 35 Issue: 9

    • DOI

      10.1002/cem.3364

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Adaptive design of experiments based on Gaussian mixture regression2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Chemometrics and Intelligent Laboratory Systems

      Volume: 208 Pages: 104226-104226

    • DOI

      10.1016/j.chemolab.2020.104226

    • Related Report
      2020 Research-status Report
  • [Journal Article] Estimation and visualization of process states using latent variable models based on Gaussian process2021

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Analytical Science Advances

      Volume: - Issue: 5-6 Pages: 326-333

    • DOI

      10.1002/ansa.202000122

    • Related Report
      2020 Research-status Report
  • [Journal Article] Prediction of spin?spin coupling constants with machine learning in NMR2021

    • Author(s)
      Shibata Kaina、Kaneko Hiromasa
    • Journal Title

      Analytical Science Advances

      Volume: - Issue: 9-10 Pages: 464-469

    • DOI

      10.1002/ansa.202000180

    • Related Report
      2020 Research-status Report
  • [Journal Article] Direct inverse analysis based on Gaussian mixture regression for multiple objective variables in material design2020

    • Author(s)
      Shimizu Naoto、Kaneko Hiromasa
    • Journal Title

      Materials & Design

      Volume: 196 Pages: 109168-109168

    • DOI

      10.1016/j.matdes.2020.109168

    • Related Report
      2020 Research-status Report
  • [Journal Article] Two‐ and Three‐dimensional Quantitative Structure‐activity Relationship Models Based on Conformer Structures2020

    • Author(s)
      Nitta Fumika、Kaneko Hiromasa
    • Journal Title

      Molecular Informatics

      Volume: 40 Issue: 3 Pages: 2000123-2000123

    • DOI

      10.1002/minf.202000123

    • Related Report
      2020 Research-status Report
  • [Journal Article] Design of thermoelectric materials with high electrical conductivity, high Seebeck coefficient, and low thermal conductivity2020

    • Author(s)
      Yoshihama Hiroki、Kaneko Hiromasa
    • Journal Title

      Analytical Science Advances

      Volume: - Issue: 5-6 Pages: 289-294

    • DOI

      10.1002/ansa.202000114

    • Related Report
      2020 Research-status Report
  • [Journal Article] Support vector regression that takes into consideration the importance of explanatory variables2020

    • Author(s)
      Kaneko Hiromasa
    • Journal Title

      Journal of Chemometrics

      Volume: 35 Issue: 4

    • DOI

      10.1002/cem.3327

    • Related Report
      2020 Research-status Report
  • [Journal Article] Development of Ensemble Learning Method Considering Applicability Domains2019

    • Author(s)
      Keigo Sato, Hiromasa Kaneko
    • Journal Title

      Journal of Computer Chemistry, Japan

      Volume: 18 Issue: 4 Pages: 187-193

    • DOI

      10.2477/jccj.2019-0010

    • NAID

      130007790939

    • ISSN
      1347-1767, 1347-3824
    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Presentation] ケモインフォマティクス・マテリアルズインフォマティクス・プロセスインフォマティクスの進展と実現2023

    • Author(s)
      金子弘昌
    • Organizer
      日本結晶成長学会 新技術・新材料分科会 第 2 回研究会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] データサイエンス・機械学習を活用した分子・材料・プロセスの設計2022

    • Author(s)
      金子弘昌
    • Organizer
      日本プロセス化学会2022ウインターシンポジウム
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] データサイエンスに基づく高機能性材料の研究・開発・評価・製造2022

    • Author(s)
      金子弘昌
    • Organizer
      第41回電子材料シンポジウム
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] Molecular, Material, and Process Designs with Direct Inverse Analysis2022

    • Author(s)
      金子弘昌
    • Organizer
      錯体化学会 第72回討論会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 分子設計・材料設計・プロセス設計のための直接的逆解析法2022

    • Author(s)
      金子弘昌
    • Organizer
      高分子学会関東支部神奈川地区講演会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] 最新情報科学を活用したプロセス設計・実験計画のスマート化2022

    • Author(s)
      金子弘昌
    • Organizer
      第37回さんわかセミナー
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] プロセスインフォマティクスの進展2022

    • Author(s)
      金子弘昌
    • Organizer
      化学工学会 反応工学部会 CVD 反応分科会 第35回シンポジウム
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 化学プラントにおけるデータベースを利用したプロセス設計・装置設計・プロセス制御2022

    • Author(s)
      金子弘昌
    • Organizer
      第27回 関西地区分離技術講演会
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] ケモ・マテリアルズ・プロセスインフォマティクスの直接的逆解析法による分子・材料・プロセス設計2022

    • Author(s)
      金子弘昌
    • Organizer
      令和3年度 第5回 食・触コンソーシアム シンポジウム
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 化学工学におけるデータサイエンスの研究例・活用例2022

    • Author(s)
      金子弘昌
    • Organizer
      令和 3 年度化学工学会関東支部若手の会(ChEC-East)講演会
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] プロセスインフォマティクスに基づくプロセスの設計および管理2022

    • Author(s)
      金子弘昌
    • Organizer
      日本化学会第102春季年会
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] データサイエンスに基づく高機能性材料の研究・開発・評価・製造の支援2022

    • Author(s)
      金子弘昌
    • Organizer
      2022年第1回半導体3D実装材料プロセス・インフォマティクス研究会
    • Related Report
      2021 Research-status Report
  • [Presentation] データサイエンスによる高機能材料の設計2021

    • Author(s)
      金子弘昌
    • Organizer
      第4回ファインケミカルジャパン2021
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 機械学習に基づく分子・材料設計および金属有機構造体への応用2021

    • Author(s)
      金子弘昌
    • Organizer
      日本セラミックス協会 第34回秋季シンポジウム
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 機械学習を活用した分子・材料の物性予測2021

    • Author(s)
      金子弘昌
    • Organizer
      超臨界流体部会 第20回サマースクール
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] Pythonで気軽に化学・化学工学2021

    • Author(s)
      金子弘昌
    • Organizer
      第11回CSJ化学フェスタ2021
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] データ駆動型化学工学の進展2021

    • Author(s)
      金子弘昌
    • Organizer
      第50回結晶成長国内会議(JCCG-50)
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 分子・材料・プロセスを設計する直接的逆解析法の開発2021

    • Author(s)
      金子弘昌
    • Organizer
      令和3年度(2021 年度)日本材料科学会若手研究者講演会
    • Related Report
      2021 Research-status Report
  • [Presentation] 化学業界におけるデータサイエンス2021

    • Author(s)
      金子弘昌
    • Organizer
      INCHEM TOKYO 2021
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] ベイズ最適化に基づくエチレンオキシド製造プロセスの設計2020

    • Author(s)
      岩間稜, 金子弘昌
    • Organizer
      化学工学会第85年会
    • Related Report
      2019 Research-status Report
  • [Presentation] プロセス変数と時間遅れを同時に最適化した適応型ソフトセンサーの開発2020

    • Author(s)
      山田信仁, 金子弘昌
    • Organizer
      化学工学会第85年会
    • Related Report
      2019 Research-status Report
  • [Presentation] ベイズ最適化に基づく適応型ソフトセンサー選択手法の開発2020

    • Author(s)
      山影柊斗, 金子弘昌
    • Organizer
      化学工学会第85年会
    • Related Report
      2019 Research-status Report
  • [Presentation] 安全性が高い高熱伝導率を有する冷媒の設計2020

    • Author(s)
      山本統久, 金子弘昌
    • Organizer
      化学工学会第85年会
    • Related Report
      2019 Research-status Report
  • [Presentation] 誘電率と安定性を考慮した高分子材料のモノマー設計2020

    • Author(s)
      谷脇寛明, 金子弘昌
    • Organizer
      化学工学会第85年会
    • Related Report
      2019 Research-status Report
  • [Presentation] データサイエンスによる高機能材料の研究・開発・評価・製造の支援2020

    • Author(s)
      金子弘昌
    • Organizer
      先端化学・材料技術部会 CC分科会 講演会
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] Nonlinear Dynamic Feature Extraction Based on Gaussian Process Dynamical Models for Jit-Based Adaptive Soft Sensors2019

    • Author(s)
      Yasuhiro Kanno, Hiromasa Kaneko
    • Organizer
      2019 AIChE Annual Meeting
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Constructing Interpretable and Accurate Model Combining Decision Tree and Random Forest2019

    • Author(s)
      Naoto Shimizu, Hiromasa Kaneko
    • Organizer
      2019 AIChE Annual Meeting
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] New Evaluation Method of Soft Sensors Considering Characteristics of Time Series Data2019

    • Author(s)
      Takumi Kojima, Hiromasa Kaneko
    • Organizer
      2019 AIChE Annual Meeting
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] Molecular, Material, Product and Process Design and Process Control Based on Materials Informatics, Chemoinformatics and Process Informatics2019

    • Author(s)
      Hiromasa Kaneko
    • Organizer
      Materials Research Meeting 2019
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research / Invited
  • [Presentation] データ解析および機械学習による高機能材料の研究・開発・製造の支援2019

    • Author(s)
      金子弘昌
    • Organizer
      日本化学会 産学交流委員会 R&D懇話会
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] 生成モデルによるデータの可視化・回帰分析・クラス分類・モデルの適用範囲の設定・モデルの逆解析・分子設計・材料設計2019

    • Author(s)
      金子弘昌
    • Organizer
      第63回日本薬学会関東支部大会
    • Related Report
      2019 Research-status Report
    • Invited
  • [Book] 化学・化学工学のための実践データサイエンス2022

    • Author(s)
      金子 弘昌
    • Total Pages
      192
    • Publisher
      朝倉書店
    • ISBN
      4254250479
    • Related Report
      2022 Annual Research Report
  • [Book] Pythonで学ぶ実験計画法入門 ベイズ最適化によるデータ解析2021

    • Author(s)
      金子 弘昌
    • Total Pages
      188
    • Publisher
      講談社
    • ISBN
      9784065235300
    • Related Report
      2021 Research-status Report
  • [Book] Pythonで気軽に化学・化学工学2021

    • Author(s)
      化学工学会、金子 弘昌
    • Total Pages
      196
    • Publisher
      丸善出版
    • ISBN
      9784621306154
    • Related Report
      2021 Research-status Report
  • [Book] 化学のためのPythonによるデータ解析・機械学習入門2019

    • Author(s)
      金子 弘昌
    • Total Pages
      240
    • Publisher
      オーム社
    • ISBN
      9784274224416
    • Related Report
      2019 Research-status Report

URL: 

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

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi