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

Establishment of Accident Analysis Method for Sociotechnical System by System Theory

Research Project

Project/Area Number 21K21301
Research Category

Grant-in-Aid for Research Activity Start-up

Allocation TypeMulti-year Fund
Review Section 1001:Information science, computer engineering, and related fields
Research InstitutionTohoku University of Community Service and Science (2022)
National Institute of Informatics (2021)

Principal Investigator

KANEKO TOMOKO  東北公益文科大学, 公私立大学の部局等, 研究員 (60906345)

Project Period (FY) 2021-08-30 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥3,120,000 (Direct Cost: ¥2,400,000、Indirect Cost: ¥720,000)
Fiscal Year 2022: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2021: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Keywords事故分析手法 / AIシステム / 社会技術システム / CAST / 自動運転 / セキュリティ・レジリエンス / FRAM / 意思決定インテリジェンス / STAMP S&S / 安全性 / セキュリティ / AI / DNN / リスクマネジメント
Outline of Research at the Start

社会インフラのシステムにおける事故は多大な影響を社会に与え,同じような事故は繰り返し起きている.一方、現状のAIは,その品質,特に安全性や信頼性に対して大きな懸念がある.AIの動作は安全保証しがたく,AIシステムである自動運転は実証段階において,複数の人身事故が発生している.
そこでデジタル社会に与える影響をモデリングし,社会技術システムの新たな事故分析方法の確立を目指す.特に機械学習技術を用いたAIの実用化が促進され、システムに組み込まれることで事故原因となってきているため,自動運転を中心にAIを含んだCPS(Cyber-Physical System)の事故分析手法の研究とする.

Outline of Final Research Achievements

This project aims to tackle the issue that the accuracy of conventional single models alone is not enough to evaluate the entire system in a system that includes AI, and based on system theory, to measure risk from a global perspective, to find points to be improved based on hazard factors, to determine leading indicators based on hazard factors and external conditions, and to develop optimal countermeasures and problemーーーsolving. The project is also aimed at creating a system that can be used in a wide range of fields, such as information science and engineering, and in developing a system that can be used in a wide range of areas, such as information technology and information engineering.

Academic Significance and Societal Importance of the Research Achievements

事故は社会インフラに多大な影響を社会に与え,同じような事故は繰り返し起きている.一方、現状のAIは,特に安全性や信頼性に対して大きな懸念がある.AIの動作は安全保証しがたく,AIシステムである自動運転は実証段階において,複数の人身事故が発生している.この状態の解決のために本研究では,事故分析手法CASTの拡張分析手順の研究やAIシステムの事故分析を行った.

Report

(3 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • Research Products

    (24 results)

All 2023 2022 2021 Other

All Journal Article (8 results) (of which Int'l Joint Research: 2 results,  Peer Reviewed: 6 results) Presentation (11 results) (of which Int'l Joint Research: 5 results,  Invited: 1 results) Book (4 results) Remarks (1 results)

  • [Journal Article] 安全性分析の新潮流と事故分析手法STAMP/CAST2023

    • Author(s)
      金子朋子
    • Journal Title

      日本ソフトウェア科学会

      Volume: -

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Naturally Decision Intelligence - Perfect Algorithm generated by hypothetical and synchronizing model for life system2023

    • Author(s)
      Tomoko Kaneko
    • Journal Title

      Intelligent Decision Technologies- An International, Publication of special issue, OUTSTANDING WOMEN CONTRIBUTIONS IN THEORY AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE

      Volume: 17(1):1-17 Issue: 1 Pages: 195-210

    • DOI

      10.3233/idt-220231

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] コンピュータシステムにおけるセーフティ&セキュリティ技法と統合アプローチ2023

    • Author(s)
      金子朋子
    • Journal Title

      日本信頼性学会誌 (REAJ誌)

      Volume: Vol45. No.2(通巻270号)

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Decision Intelligence ~データ活用による未来の意思決定~2022

    • Author(s)
      金子朋子, 安部浩之
    • Journal Title

      NTTDATA 公開サイト

      Volume: ー

    • Related Report
      2022 Annual Research Report
  • [Journal Article] Safety and Risk Analysis and Evaluation Methods for DNN Systems in Automated Driving2022

    • Author(s)
      Tomoko Kaneko Yuji Takahashi Shinichi Yamaguchi Jyunji Hashimoto Nobukazu Yoshioka
    • Journal Title

      14th International Joint Conference on Knowledge-Based Software Engineering (JCKBSE 2022)

      Volume: ー

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] 自動運転におけるDNNシステムを対象とした安全・リスク分析・評価方法2022

    • Author(s)
      金子朋子,髙橋雄志,山口晋一,橋本順之,吉岡信和
    • Journal Title

      電子情報通信学会 KBSE研究会

      Volume: IEICE-121 Pages: 60-65

    • Related Report
      2021 Research-status Report
  • [Journal Article] リモートメンテナンスを伴いフィードバックを 有するIoTシステムのリスクアセスメント手法2022

    • Author(s)
      佐々木良一,金子朋子,髙橋雄志,福澤寧子
    • Journal Title

      JSSM論文誌

      Volume: 35,3 Pages: 3-17

    • Related Report
      2021 Research-status Report
    • Peer Reviewed
  • [Journal Article] Cyber-Security Incident Analysis by Causal Analysis using System Theory (CAST)2021

    • Author(s)
      Tomoko Kaneko,NobukazuYoshioka,Ryoichi Sasaki
    • Journal Title

      2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C)

      Volume: ー Pages: 806-815

    • DOI

      10.1109/qrs-c55045.2021.00123

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] Proposal of Naturally Decision Intelligence as a Promoter of Safety Activities in Japan2023

    • Author(s)
      Tomoko Kaneko
    • Organizer
      2th International Association for Advanced Space Safety(IAASS) Conference,
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Decision Intelligence into Synchronization2023

    • Author(s)
      Tomoko Kaneko
    • Organizer
      the 15th International Conference on Computer and Automation Engineering (ICCAE2023)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Security Resilience - Considerations from the Application of the Functional Resonance Method(FRAM) to Information Security Incidents2022

    • Author(s)
      Tomoko Kaneko
    • Organizer
      IEEE QRS2022, Workshop on Cyber Forensics, Security, and E-discovery
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Safety and Risk Analysis and Evaluation Methods for DNN Systems in Automated Driving2022

    • Author(s)
      Tomoko Kaneko, Yuji Takahashi, Shinichi Yamaguchi, Jyunji Hashimoto, Nobukazu Yoshioka
    • Organizer
      14th International Joint Conference on Knowledge-Based Software Engineering (JCKBSE 2022)
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] STAMP/STPAを用いた 高齢者見守りシステムのIoT化に対する安全性分析2022

    • Author(s)
      鎌田桂太郎, 髙橋雄志, 金子朋子
    • Organizer
      日本科学技術連盟ソフトウェア品質研究会
    • Related Report
      2022 Annual Research Report
  • [Presentation] Thinking from Incidents - Security Resilience2022

    • Author(s)
      Tomoko Kaneko
    • Organizer
      FRAMily2022
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] ITシステムにおいてセキュリティとセーフティをどう両立・ 実現するか~ITリスク学の知見を活用した対策の方法や今後の課題 ~2021

    • Author(s)
      金子朋子
    • Organizer
      【日本銀行 金融研究所】セミナー 招待講演
    • Related Report
      2021 Research-status Report
    • Invited
  • [Presentation] 「セーフティ&セキュリティ入門」~2大セーフティ理論から考えるセキュリティ・バイ・デザイン2021

    • Author(s)
      金子朋子
    • Organizer
      日本セキュリティマネジメント学会ITリスク学研究会
    • Related Report
      2021 Research-status Report
  • [Presentation] 自動運転におけるDNN安全性評価方法~eAIプロジェクト 交通PoCの活動を通じて2021

    • Author(s)
      金子朋子
    • Organizer
      第3回AI/IoTシステム安全性シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] 日本語訳完成記念 ~CASTチュートリアル~2021

    • Author(s)
      金子朋子
    • Organizer
      第3回AI/IoTシステム安全性シンポジウム
    • Related Report
      2021 Research-status Report
  • [Presentation] <基調講演> セーフティ&セキュリティ入門 SQiP分科会活動から本がうまれた!2021

    • Author(s)
      金子朋子
    • Organizer
      ソフトウェア品質管理研究会
    • Related Report
      2021 Research-status Report
  • [Book] Handbook on Artificial Intelligence-empowered Applied Software Engineering: VOL.1: Novel Methodologies to Engineering Smart Software Systems P225-250) Methods for Ensuring the Overall Safety of Machine Learning Systems2022

    • Author(s)
      Kaneko, Nobukazu Yoshioka
    • Total Pages
      26
    • Publisher
      Springer
    • ISBN
      9783031082023
    • Related Report
      2022 Annual Research Report
  • [Book] 機械学習システムセキュリティガイドライン2022

    • Author(s)
      機械学習システムセキュリティ・セーフティワーキンググループ
    • Total Pages
      135
    • Publisher
      機械学習システムセキュリティガイドライン策定委員会
    • Related Report
      2022 Annual Research Report
  • [Book] Ensuring the safety of entire machine learning systems with STAMP S&S2022

    • Author(s)
      Tomoko Kaneko,Nobukazu Yoshioka
    • Total Pages
      27
    • Publisher
      Springer, LEARNING AND ANALYTICS IN INTELLIGENT SYSTEMS (LAIS) book series
    • Related Report
      2021 Research-status Report
  • [Book] セーフティ・セキュリティ入門2021

    • Author(s)
      金子朋子
    • Total Pages
      217
    • Publisher
      日本科学技術連盟出版社
    • ISBN
      9784817197375
    • Related Report
      2021 Research-status Report
  • [Remarks] 教員一覧 創価大学理工学部情報システム工学科

    • URL

      https://www.soka.ac.jp/faculty-profiles/tomoko-kaneko/

    • Related Report
      2022 Annual Research Report

URL: 

Published: 2021-10-22   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi