Abstract
In the age of smart cities and self-driving cars, ensuring the safety and reliability of integrated computer systems is crucial. My research has found a way to make these systems, known as Cyber-Physical Systems (CPS), more dependable without disturbing their regular operations. I used a concept called Digital Twins (DT) which are like virtual replicas of these systems. They allow us to test and improve the real systems by working on their virtual copies. This is especially useful when there's limited data from new systems. My studies used various data types, from highly specific to more generic, to train these virtual models. We observed improved dependability for real-world applications like elevators, autonomous driving, and even health registry systems. This research not only enhances the safety of everyday technologies but also hints at a future where systems learn and adapt without causing disruptions. In essence, it's a step towards smarter, safer, and more efficient future cities and technologies.
List of papers
Paper I: Digital Twin-based Anomaly Detection in Cyber-physical Systems. Qinghua Xu, Shaukat Ali and Tao Yue. ‘Digital Twin-based Anomaly Detection in Cyber-physical Systems’. In: 2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST). 2021 14th IEEE Conference on Software Testing, Verification and Validation (ICST). Porto de Galinhas, Brazil: IEEE, Apr. 2021, pp. 205–216. doi: 10.1109/ICST49551.2021.00031. The article is included in the thesis. Also available at: https://doi.org/10.1109/ICST49551.2021.00031 |
Paper II: Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems. Qinghua Xu, Shaukat Ali and Tao Yue. ‘Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems’. In: ACM Transactions on Software Engineering and Methodology (Feb. 2023), p. 3582571. doi: 10.1145/3582571. The article is not available in DUO due to publisher restrictions. The published version is available at: https://doi.org/10.1145/3582571 |
Paper III: Uncertainty-aware transfer learning to evolve digital twins for industrial elevators. Qinghua Xu et al. ESEC/FSE 2022: Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering November 2022, pages 1257–1268. doi: 10.1145/3540250.3558957. The article is not available in DUO due to publisher restrictions. The published version is available at: https://doi.org/10.1145/3540250.3558957 |
Paper IV: Pretrain, Prompt, and Transfer: Evolving Digital Twins for Time-to-Event Analysis in Cyber-physical Systems. Qinghua Xu, Tao Yue, Shaukat Ali, Maite Arratibel. Submitted to IEEE Transaction of Software Engineering, received major revision response. To be published. The paper is not available in DUO awaiting publishing. Preprint at: https://arxiv.org/abs/2310.00032 |
Paper V: EvoCLINICAL: Evolving Cyber-cyber Digital Twin with Active Transfer Learning for Automated Cancer Registry System. Chengjie Lu, Qinghua Xu, Tao Yue, Shaukat Ali, Thomas Schwitalla, Jan F. Nygård. Accepted in The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2023. To be published. The paper is not available in DUO awaiting publishing. Preprint at: https://arxiv.org/abs/2309.03246 |
Paper VI: KDDT: Knowledge Distillation-empowered Digital Twin for Anomaly Detection. Qinghua Xu, Shaukat Ali, Tao Yue, Zaimovic Nedim, Inderjeet Singh. Accepted in The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2023. To be published. The paper is not available in DUO awaiting publishing. Preprint at: https://arxiv.org/abs/2309.04616 |