Presents the design of a monitoring software for predictive maintenance in smart-factory systems, grounded in international reliability standards. Machine learning models are used for equipment fault prediction and condition monitoring, with the software architecture organized around reliability and maintainability requirements. Work conducted as part of a Samsung Heavy Industries project at the Embedded & Software Lab, Ajou University.
@inproceedings{hwang2026monitoring,title={Design of Monitoring Software for Predictive Maintenance in Smart Factory},author={Hwang, Se-Hyeon and Kim, J.-S. and Choi, M. and Lee, J.-W.},booktitle={Proceedings of the 28th Korea Conference on Software Engineering (KCSE 2026)},volume={28},number={1},pages={211--218},year={2026},note={In Korean}}
2025
ACK
Requirements Analysis of Data and Model for Reliability of Ultrasound-based Diagnostic Model
Se-Hyeon Hwang, H. Choi, J. Kim, and J.-W. Lee
In Proceedings of the Annual Conference of KIPS (ACK 2025), 2025
Analyzes the data and model requirements needed for a reliable ultrasound-based diagnostic model, with particular attention to improving detection of the malignant class. Conducted within a 3-year ITRC (IITP-funded) project on AI-based diagnosis of gallbladder disease from ultrasound, in collaboration with Ajou University Hospital. This line of work continues as the author’s M.S. thesis research on trustworthy medical AI.
@inproceedings{hwang2025ultrasound,title={Requirements Analysis of Data and Model for Reliability of Ultrasound-based Diagnostic Model},author={Hwang, Se-Hyeon and Choi, H. and Kim, J. and Lee, J.-W.},booktitle={Proceedings of the Annual Conference of KIPS (ACK 2025)},volume={32},number={2},pages={489--490},year={2025},note={In Korean}}