Unsupervised Anomaly Detection and Localization for Multivariate Time Series and Their Applications in Structural Health Monitoring
dc.contributor.author | Liu, Jie | |
dc.contributor.supervisor | Ling Li | en_US |
dc.contributor.supervisor | Senjian An | en_US |
dc.contributor.supervisor | Qilin Li | en_US |
dc.date.accessioned | 2024-12-17T00:20:24Z | |
dc.date.available | 2024-12-17T00:20:24Z | |
dc.date.issued | 2024 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/96603 | |
dc.description.abstract |
This thesis advances the field of anomaly detection in multivariate time series by addressing key challenges in anomaly detection, localization, and severity assessment. Through the development of EdgeConvFormer and U-GraphFormer, this research offers robust, interpretable, and efficient solutions applicable across various domains, with a particular focus on SHM. Extensive evaluations across diverse multivariate time series datasets and real-world scenarios demonstrate the potential of these models to enhance the monitoring and maintenance of critical systems, ensuring their safety and longevity. | en_US |
dc.publisher | Curtin University | en_US |
dc.title | Unsupervised Anomaly Detection and Localization for Multivariate Time Series and Their Applications in Structural Health Monitoring | en_US |
dc.type | Thesis | en_US |
dcterms.educationLevel | PhD | en_US |
curtin.department | School of Electrical Engineering, Computing and Mathematical Sciences | en_US |
curtin.accessStatus | Fulltext not available | en_US |
curtin.faculty | Science and Engineering | en_US |
curtin.contributor.orcid | Liu, Jie [0000-0003-3884-5714] | en_US |
dc.date.embargoEnd | 2026-11-27 |