Search

Your search keyword '"Zhang, Yongshun"' showing total 387 results
Start Over Author "Zhang, Yongshun"
387 results on '"Zhang, Yongshun"'

3. Deep Learning-Based Power Control for Uplink Cell-Free Massive MIMO Systems

Author

Zhang, Yongshun, Zhang, Jiayi, Jin, Yu, Buzzi, Stefano, and Ai, Bo

Subjects
Computer Science - Information Theory, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

In this paper, a general framework for deep learning-based power control methods for max-min, max-product and max-sum-rate optimization in uplink cell-free massive multiple-input multiple-output (CF mMIMO) systems is proposed. Instead of using supervised learning, the proposed method relies on unsupervised learning, in which optimal power allocations are not required to be known, and thus has low training complexity. More specifically, a deep neural network (DNN) is trained to learn the map between fading coefficients and power coefficients within short time and with low computational complexity. It is interesting to note that the spectral efficiency of CF mMIMO systems with the proposed method outperforms previous optimization methods for max-min optimization and fits well for both max-sum-rate and max-product optimizations., Comment: 6 pages, 6 figures, accepted by IEEE Globecom 2021

Published
2021

5. Webly Supervised Fine-Grained Recognition: Benchmark Datasets and An Approach

Author

Sun, Zeren, Yao, Yazhou, Wei, Xiu-Shen, Zhang, Yongshun, Shen, Fumin, Wu, Jianxin, Zhang, Jian, and Shen, Heng-Tao

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Learning from the web can ease the extreme dependence of deep learning on large-scale manually labeled datasets. Especially for fine-grained recognition, which targets at distinguishing subordinate categories, it will significantly reduce the labeling costs by leveraging free web data. Despite its significant practical and research value, the webly supervised fine-grained recognition problem is not extensively studied in the computer vision community, largely due to the lack of high-quality datasets. To fill this gap, in this paper we construct two new benchmark webly supervised fine-grained datasets, termed WebFG-496 and WebiNat-5089, respectively. In concretely, WebFG-496 consists of three sub-datasets containing a total of 53,339 web training images with 200 species of birds (Web-bird), 100 types of aircrafts (Web-aircraft), and 196 models of cars (Web-car). For WebiNat-5089, it contains 5089 sub-categories and more than 1.1 million web training images, which is the largest webly supervised fine-grained dataset ever. As a minor contribution, we also propose a novel webly supervised method (termed "{Peer-learning}") for benchmarking these datasets.~Comprehensive experimental results and analyses on two new benchmark datasets demonstrate that the proposed method achieves superior performance over the competing baseline models and states-of-the-art. Our benchmark datasets and the source codes of Peer-learning have been made available at {\url{https://github.com/NUST-Machine-Intelligence-Laboratory/weblyFG-dataset}}., Comment: accepted by ICCV 2021

Published
2021

13. ACE2 Receptor‐Targeted Inhaled Nanoemulsions Inhibit SARS‐CoV‐2 and Attenuate Inflammatory Responses

Author

Wang, Hairui, primary, Luo, Shuang, additional, Xie, Mingxin, additional, Chen, Zhao, additional, Zhang, Yunming, additional, Xie, Zhiqiang, additional, Zhang, Yongshun, additional, Zhang, Yu, additional, Yang, Lan, additional, Wu, Fuhua, additional, Chen, Xiaoyan, additional, Du, Guangsheng, additional, Zhao, Jincun, additional, and Sun, Xun, additional

Published
2024
Full Text
View/download PDF

15. Influence mechanism of flow parameters on temperature field in the regenerative reheating furnace

Author

Yang Lipo, Liu Yunpeng, Hou Yingwu, and Zhang Yongshun

Subjects
Regenerative pusher reheating furnace, Flow field, Coupling temperature field, Injection angle, Burner layout, Heat, QC251-338.5
Abstract

Aimed to the complex characteristics of regenerative pusher reheating furnace, the time-domain coupling relationship of burner layout, injection angle, air-gas ratio was simulated to analyze the influence of flow field on the transient temperature field and the smoke emission. Firstly, according to actual flow rules under different section conditions, the equivalent heat transfer of convection and radiation was the key for establishing the combustion model. Secondly, more details of complex flow fields were provided by the finite element method, which explained the dynamic heat transfer effect on at different atmospheres of furnace by the burner angle, the preheating temperature and the air-gas ratio. Industrial cases testified that new method obviously improved the stability of furnace temperature and pressure. When the average gas flow was reduced by 5.4% and the average furnace pressure was reduced by 12.5%, the average temperature difference was able to control within ±1 °C. Remarkably, the better flow field improved the prediction accuracy of temperature field, which could avoid some problems such as the insufficient burning, the over burning, the overheating and so on. Moreover, it also significantly reduced the gas consumption, the pollutant emission and the oxidative loss. Thus, new method aimed to meet strict index requirements of energy conservation and environmental protection to a large extent.

Published
2022
Full Text
View/download PDF

47. Design and Evaluation of a Novel Person Transfer Assist System

Author

Yongfei Feng, Zhang Yongshun, Hongbo Wang, Lingfeng Sang, Tian Yu, Wang Xusheng, Su Bowen, Wang Lipeng, and Jianye Niu

Subjects
General Computer Science, Computer science, media_common.quotation_subject, General Engineering, Analytic hierarchy process, Control engineering, Mobile robot, Person transfer, performance evaluation, Industrialisation, Originality, mechanical design, Synchronization (computer science), synchronous control system, Robot, General Materials Science, lcsh:Electrical engineering. Electronics. Nuclear engineering, lcsh:TK1-9971, media_common
Abstract

Person transfer is a major problem for nursing in home and clinical, and this problem is becoming more prominent with the development of aging society and the change of population structure. In this article, a novel person transfer assist system named E-Pat (Easy-Patient Transfer), which can meet the transfer needs of the patient between beds, has been designed and analyzed. The importance and originality of this study are that it explores a theoretical design method for device to enhance patient comfortably when transferred, and put it into practice. The main tasks completed in this article include: (1) a prototype of the device is designed based on the principle of relative static contact point theory. In addition, the corresponding relationship between the human body pressure and the insertion angle is proposed, which provides a theoretical basis for the optimization of the mechanism; (2) based on STM32 (STMicroelectronics 32-bits Microcontroller) chip, the hardware circuit part of the device is designed. According to the transfer environment requirements of the device, the synchronization control algorithm of the device is designed and the experiment is carried out; (3) the performance evaluation of the device is carried out by means of Analytic Hierarchy Process (AHP), through the research of a group of 30 volunteers, the performance of the system has been evaluated accurately, which provides a reference for the industrialization of the prototype. The whole research of this article proves that this kind of person transfer assist system has good performance, it can also reduce the burden of caregivers.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results