Wei Huo

ORCID: 0000-0002-6562-6018
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Glioma Diagnosis and Treatment
  • Text and Document Classification Technologies
  • Integrated Energy Systems Optimization
  • Meningioma and schwannoma management
  • Stochastic Gradient Optimization Techniques
  • MRI in cancer diagnosis
  • Advanced Image and Video Retrieval Techniques
  • Cerebrovascular and Carotid Artery Diseases
  • Optimal Power Flow Distribution
  • Hand Gesture Recognition Systems
  • Grey System Theory Applications
  • Human Pose and Action Recognition
  • Privacy-Preserving Technologies in Data
  • Spinal Fractures and Fixation Techniques
  • Antibiotic Resistance in Bacteria
  • Pneumocystis jirovecii pneumonia detection and treatment
  • Vascular Malformations Diagnosis and Treatment
  • Power Systems and Renewable Energy
  • Mycobacterium research and diagnosis
  • Moyamoya disease diagnosis and treatment
  • Blind Source Separation Techniques
  • Neurofibromatosis and Schwannoma Cases
  • Radiomics and Machine Learning in Medical Imaging
  • Power Systems and Technologies
  • Face recognition and analysis

Xi'an Jiaotong University
2023-2024

Anhui University
2024

Guangdong Academy of Agricultural Sciences
2019

Peking University First Hospital
2002-2004

Peking University
2002-2004

10.1016/j.cviu.2024.103995 article EN Computer Vision and Image Understanding 2024-03-19

This paper investigates the use of cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in learning: privacy leakage and communication bottleneck. We introduce algorithm called Differentially Private Federated Cubic Regularized (DP-FCRN). By leveraging second-order techniques, our achieves lower iteration complexity compared to first-order methods. also incorporate noise perturbation during local computations ensure...

10.48550/arxiv.2408.04315 preprint EN arXiv (Cornell University) 2024-08-08

Hierarchical load forecasting (HLF) is a type of multi-load problem with cumulative consistency, which usually decomposed into multiple single and hierarchical optimization problems. However, the prediction results this model are often biased. In addition, compared offline learning methods, online methods considered to be more effective adaptive method. paper, we propose an improved reconciliation method on batch that guarantees unbiased results. Case studies power data one province in China...

10.1109/ei259745.2023.10512394 article EN 2021 IEEE 5th Conference on Energy Internet and Energy System Integration (EI2) 2023-12-15

10.1016/s0531-5131(02)01077-4 article EN International Congress Series 2002-12-01

10.1016/s0531-5131(03)01415-8 article EN International Congress Series 2004-01-22

Objective To investigate the clinical and etiological characteristics of Klebsiella pneumoniae (KP) infection in recipients after liver transplantation. Methods Clinical data 54 patients infected with KP transplantation Lingnan Hospital, Third Affiliated Hospital Sun Yat-sen University from January 2015 to December 2018 were retrospectively analyzed. Among them, 48 male 6 female, aged 7 months 75 years a median age years. The incidence, distribution drug resistance expression levels...

10.3877/cma.j.issn.2095-3232.2019.06.009 article EN Chin J Hepat Surg(Electronic Edition) 2019-12-10
Coming Soon ...