Papers
1
Total Citations
35
H-Index
1
About
Yue Shu is a researcher at the forefront of intelligent fault diagnosis and data quality assurance, with a focus on ensuring the reliability of machine learning models in industrial applications. Her major contribution lies in pioneering graph neural network (GNN)-based data cleaning methods to combat data contamination—a critical issue where noisy or corrupted sensor data undermines diagnostic accuracy. Her most-cited work, "A graph neural network-based data cleaning method to prevent intelligent fault diagnosis from data contamination" (2023), has already garnered 35 citations, reflecting its timely impact on the field. By leveraging GNNs to model complex relationships in sensor data, Shu’s approach enhances the robustness of fault detection systems, reducing false alarms and missed failures in real-world settings like manufacturing and energy systems. This work bridges the gap between data science and industrial engineering, offering a scalable solution to a pervasive problem. Her research is particularly notable for its practical orientation, addressing the "garbage in, garbage out" dilemma that plagues AI-driven diagnostics. For students and researchers exploring trustworthy AI in engineering, Shu’s contributions underscore the importance of data integrity in building resilient, real-world intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1