De-Ming Liang

ORCID: 0000-0003-4020-1029
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Cardiac Arrhythmias and Treatments
  • Optical Coherence Tomography Applications
  • Face and Expression Recognition
  • Machine Learning and Data Classification
  • Text and Document Classification Technologies
  • Advanced Graph Neural Networks
  • Medical Imaging Techniques and Applications
  • Atrial Fibrillation Management and Outcomes
  • Laser Design and Applications
  • Software Engineering Research
  • Advanced MRI Techniques and Applications
  • Domain Adaptation and Few-Shot Learning
  • MRI in cancer diagnosis
  • Advanced Image and Video Retrieval Techniques
  • Online Learning and Analytics
  • Machine Learning and Algorithms
  • Algorithms and Data Compression
  • Advanced Fiber Laser Technologies

University Hospital of Bern
2018-2020

Nanjing University
2018-2019

University of Bern
2018-2019

Novelis (Canada)
2018

Capital Normal University
2015

10.1007/s11704-019-8452-2 article EN Frontiers of Computer Science 2019-05-02

Label propagation spreads the soft labels from few labeled data to a large amount of unlabeled according intrinsic graph structure. Nonetheless, most label solutions work under relatively small-scale and fail cope with many real applications, such as social network analysis, where graphs usually have millions nodes. In this paper, we propose novel algorithm named \algo deal large-scale data. A lightweight iterative process derived well-known stochastic gradient descent strategy is used...

10.24963/ijcai.2018/475 article EN 2018-07-01

Abstract Background Radiofrequency catheter ablation (RFA) is an effective treatment for atrial fibrillation. However, lesions are usually only assessed functionally. The immediate effect of RFA on the tissue not directly visualized. Optical coherence tomography (OCT) imaging technique that uses light to capture high‐resolution images with histology‐like quality. Therefore, it might be used high‐precision lesions. Methods and results ( n = 25) were produced freshly excised left right...

10.1111/jce.13917 article EN Journal of Cardiovascular Electrophysiology 2019-03-18

Label propagation spreads the soft labels from few labeled data to a large amount of unlabeled according intrinsic graph structure. Nonetheless, most label solutions work under relatively small-scale and fail cope with many real applications, such as social network analysis, where graphs usually have millions nodes. In this paper, we propose novel algorithm named SLP deal large-scale data. A lightweight iterative process derived well-known stochastic gradient descent strategy is used...

10.1109/tkde.2019.2949297 article EN IEEE Transactions on Knowledge and Data Engineering 2019-01-01

The students' ability of self-regulated learning will affect their personal development in the future.Micro-lesson as a new video resource provides more suitable form for learning.At present, existing micro-lesson platform puts too much emphasis on resources, cannot completely provide students with independent support service.Therefore, this paper first analyzes characteristics environment which should be, and then, designs platforms based massive micro-lesson, describe its process design,...

10.2991/ssemse-15.2015.328 article EN cc-by-nc 2015-01-01

Abstract Background The immediate effect of radiofrequency catheter ablation (RFA) on the tissue is not directly visualized. Optical coherence tomography (OCT) an imaging technique that uses light to capture histology-like images with a penetration depth 1-3 mm in cardiac tissue. There are two specific features lesions OCT images: disappearance birefringence artifacts lateral and sudden decrease signal at bottom (Figure panel A D). These can only be used recognize from by eye, but also train...

10.1093/europace/euaa162.064 article EN EP Europace 2020-06-01
Coming Soon ...