TY - GEN
T1 - Enterprise Architecture based Representation of Architecture and Design Patterns for Machine Learning Systems
AU - Takeuchi, Hironori
AU - Doi, Takuo
AU - Washizaki, Hironori
AU - Okuda, Satoshi
AU - Yoshioka, Nobukazu
N1 - Funding Information:
This work was supported by a JSPS Grant-in-Aid for Scientific Research (KAKENHI), Grant No. JP19K20416; JST-Mirai Project (Engineerable AI Techniques for Practical Applications of High-Quality Machine Learning-based Systems), Grant No. JPMJMI20B8; and ROIS NII Open Collaborative Research 2021-21S0801.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this study, we consider projects for the development of machine learning (ML) service systems that apply ML techniques to enterprise functions, and propose a method of representing the architecture and design patterns for ML service systems. Based on the proposed method, we represent the items described in the pattern documents as elements in the enterprise architecture modeling and derived a generic model for ML architecture and designed patterns. By applying the proposed method and the generic pattern model, we analyze an existing ML design pattern and represent it as a model. Through modeling practice, we confirm that an effective use scenario occurs when using the represented model during the project activities, and we can revise or enhance the pattern documents consistently by applying the model.
AB - In this study, we consider projects for the development of machine learning (ML) service systems that apply ML techniques to enterprise functions, and propose a method of representing the architecture and design patterns for ML service systems. Based on the proposed method, we represent the items described in the pattern documents as elements in the enterprise architecture modeling and derived a generic model for ML architecture and designed patterns. By applying the proposed method and the generic pattern model, we analyze an existing ML design pattern and represent it as a model. Through modeling practice, we confirm that an effective use scenario occurs when using the represented model during the project activities, and we can revise or enhance the pattern documents consistently by applying the model.
KW - Architecture and design pattern
KW - Enterprise architecture
KW - Machine learning service system
UR - http://www.scopus.com/inward/record.url?scp=85122978925&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122978925&partnerID=8YFLogxK
U2 - 10.1109/EDOCW52865.2021.00055
DO - 10.1109/EDOCW52865.2021.00055
M3 - Conference contribution
AN - SCOPUS:85122978925
T3 - Proceedings - IEEE International Enterprise Distributed Object Computing Workshop, EDOCW
SP - 245
EP - 250
BT - Proceedings - 2021 IEEE 25th International Enterprise Distributed Object Computing Conference Workshops, EDOCW 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th IEEE International Enterprise Distributed Object Computing Conference Workshops, EDOCW 2021
Y2 - 25 October 2021 through 29 October 2021
ER -