Zhaoyang Song

ORCID: 0000-0003-0754-0846
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Image Processing Techniques and Applications
  • Advanced Image Processing Techniques
  • Advanced Vision and Imaging
  • Advanced Fiber Optic Sensors
  • Cardiac Imaging and Diagnostics
  • Optical Network Technologies
  • Advanced X-ray and CT Imaging
  • Image and Signal Denoising Methods
  • PAPR reduction in OFDM
  • Advanced MRI Techniques and Applications

Lanzhou University of Technology
2024

First Affiliated Hospital of Gannan Medical University
2024

Xi’an University of Posts and Telecommunications
2023

Cardiac magnetic resonance imaging (CMRI) super-resolution (SR) reconstruction technology can enhance the resolution and quality of CMRI, providing experts with clearer more accurate information about cardiac structure function. This aids in rapid diagnosis abnormalities development personalized treatment plans. In processing existing bicubic degradation-based SR methods often suffer from performance degradation, resulting blurred images. To address aforementioned problem, we present a...

10.1109/jbhi.2024.3357988 article EN IEEE Journal of Biomedical and Health Informatics 2024-01-24

The orthogonal time frequency space (OTFS) technique proposed in recent years has excellent anti-Doppler shift and delay performance, enabling its application high speed communication scenarios. In this article, a particle swarm optimization (PSO) signal detection algorithm for OTFS system is proposed, an adaptive mechanism the individual learning factor global formula of designed, position update method particles improved, so as to increase convergence accuracy avoid fall into local...

10.1587/transcom.2022ebp3140 article EN IEICE Transactions on Communications 2023-02-15

Aiming at the problem that super-resolution reconstruction algorithms based on deep learning increase complexity of network model and cause a large number parameters by increasing depth neural to improve performance, an inverted N-type lightweight back projection for image is proposed. First, initial convolutional block used extract shallow features low-resolution images. Secondly, images are extracted through two rounds gradual compression restoration network. Then, combined global residual...

10.3724/sp.j.1089.2022.19037 article EN Journal of Computer-Aided Design & Computer Graphics 2022-06-01
Coming Soon ...