Traceable Business-to-Safety Analysis Framework for Safety-critical Machine Learning Systems

Jati H. Husen, Hironori Washizaki, Hnin Thandar Tun, Nobukazu Yoshioka, Yoshiaki Fukazawa, Hironori Takeuchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine learning-based system requires specific attention towards their safety characteristics while considering the higher-level requirements. This study describes our approach for analyzing machine learning safety requirements top-down from higher-level business requirements, functional requirements, and risks to be mitigated. Our approach utilizes six different modeling techniques: AI Project Canvas, Machine Learning Canvas, KAOS Goal Modeling, UML Components Diagram, STAMP/STPA, and Safety Case Analysis. As a case study, we also demonstrated our approach for lane and other vehicle detection functions of self-driving cars.

Original languageEnglish
Title of host publicationProceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages50-51
Number of pages2
ISBN (Electronic)9781450392754
DOIs
Publication statusPublished - 2022
Event1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022 - Pittsburgh, United States
Duration: 2022 May 162022 May 17

Publication series

NameProceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022

Conference

Conference1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
Country/TerritoryUnited States
CityPittsburgh
Period22/5/1622/5/17

Keywords

  • machine learning
  • safety requirements
  • traceability

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint

Dive into the research topics of 'Traceable Business-to-Safety Analysis Framework for Safety-critical Machine Learning Systems'. Together they form a unique fingerprint.

Cite this