Xueyan Bi

ORCID: 0009-0001-8184-965X
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Phytochemicals and Antioxidant Activities
  • Cell Image Analysis Techniques
  • Metabolomics and Mass Spectrometry Studies
  • Natural product bioactivities and synthesis
  • AI in cancer detection
  • Gear and Bearing Dynamics Analysis
  • Advanced Image Fusion Techniques
  • Digital Imaging for Blood Diseases
  • Hydraulic and Pneumatic Systems
  • Computational Drug Discovery Methods
  • Cloud Data Security Solutions
  • Remote Sensing and Land Use
  • Flavonoids in Medical Research
  • Adversarial Robustness in Machine Learning
  • Security and Verification in Computing
  • Iterative Learning Control Systems
  • Remote-Sensing Image Classification
  • Machine Learning in Materials Science

City University of Hong Kong
2004

Pharyngiyan tablet is a traditional Chinese medicine (TCM) renowned for its efficacy in moisturizing the lungs, clearing throat. However, it exhibits quality variations due to discrepancies regulatory standards and challenges comprehensive evaluation. In this study, ultra-performance liquid chromatography-quadrupole time-of-flight tandem mass spectrometry (UPLC-Q-TOF-MS/MS) was used qualitatively analyze chemical composition of pharyngiyan tablets. Full analysis detected 131 constituents....

10.1155/jamc/6691730 article EN cc-by Journal of Analytical Methods in Chemistry 2025-01-01

Federated learning (FL) enables decentralized model training while preserving privacy. Recently, integrating Foundation Models (FMs) into FL has boosted performance but also introduced a novel backdoor attack mechanism. Attackers can exploit the FM's capabilities to embed backdoors synthetic data generated by FMs used for fusion, subsequently infecting all client models through knowledge sharing without involvement in long-lasting process. These attacks render existing defenses ineffective,...

10.48550/arxiv.2410.17573 preprint EN arXiv (Cornell University) 2024-10-23

This paper presents a novel model-free parameterization approach of friction modeling for servo-motion systems, where support vector machine networks parameterize the static behavior. In training such network via SVM regression, effort accounting complexity variation mapping is made in terms varying smoothness and error-tolerance constraints. It experimentally demonstrated that proposed can achieve satisfactory predictions.

10.1109/acc.2003.1243752 article EN 2004-01-23
Coming Soon ...