TY - GEN
T1 - Traceable Business-to-Safety Analysis Framework for Safety-critical Machine Learning Systems
AU - Husen, Jati H.
AU - Washizaki, Hironori
AU - Tun, Hnin Thandar
AU - Yoshioka, Nobukazu
AU - Fukazawa, Yoshiaki
AU - Takeuchi, Hironori
N1 - Funding Information:
This work was supported by JST-Mirai Program Grant Number JPMJMI20B8 and by JST SPRING Grant Number JPMJSP2128, Japan.
Publisher Copyright:
© 2022 ACM.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - machine learning
KW - safety requirements
KW - traceability
UR - http://www.scopus.com/inward/record.url?scp=85133409121&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85133409121&partnerID=8YFLogxK
U2 - 10.1145/3522664.3528619
DO - 10.1145/3522664.3528619
M3 - Conference contribution
AN - SCOPUS:85133409121
T3 - Proceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
SP - 50
EP - 51
BT - Proceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
Y2 - 16 May 2022 through 17 May 2022
ER -