- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Fault Detection and Control Systems
- Advanced Image and Video Retrieval Techniques
- Automated Road and Building Extraction
- Magnetism in coordination complexes
- Advanced Data Processing Techniques
- Adversarial Robustness in Machine Learning
- Satellite Image Processing and Photogrammetry
- Metal complexes synthesis and properties
- Advanced Malware Detection Techniques
- Time Series Analysis and Forecasting
- Metal-Organic Frameworks: Synthesis and Applications
Huazhong University of Science and Technology
2023-2024
Wuhan University
2016
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Multivariate Time Series (MTS) anomaly detection focuses on pinpointing samples that diverge from standard operational patterns, which is crucial for ensuring the safety and security of industrial applications. The primary challenge in this domain to develop representations capable discerning anomalies effectively. prevalent methods literature are predominantly reconstruction-based predictive nature. However, they typically concentrate a single-dimensional instance level, thereby not fully...
Accurate detection and diagnosis of abnormal behaviors such as network attacks from multivariate time series (MTS) are crucial for ensuring the stable effective operation industrial cyber-physical systems (CPS). However, existing researches pay little attention to logical dependencies among system working states, have difficulties in explaining evolution mechanisms signals. To reveal spatio-temporal association relationships states CPS, this paper proposes a fine-grained adaptive anomaly...
Aerial Image records the large-range earth objects with ever-improving spatial and radiometric resolution. It becomes a powerful tool for observation, land-coverage survey, geographical census, etc., helps delineating boundary of different kinds on both manually automatically. In light geo-spatial correspondence between pixel locations aerial image coordinates ground objects, there is an increasing need super-pixel segmentation high-accuracy positioning in image. Besides commercial software...