Search

Your search keyword '"Ge, YongXing"' showing total 6 results
Start Over Author "Ge, YongXing"
6 results on '"Ge, YongXing"'

1. Local Contrast Learning

Author

Xu, Chuanyun, Zhang, Yang, Feng, Xin, Ge, YongXing, Zhang, Yihao, and Long, Jianwu

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named Local Contrast Learning (LCL) based on the key insight about a human cognitive behavior that human recognizes the objects in a specific context by contrasting the objects in the context or in her/his memory. LCL is used to train a deep model that can contrast the recognizing sample with a couple of contrastive samples randomly drawn and shuffled. On one-shot classification task on Omniglot, the deep model based LCL with 122 layers and 1.94 millions of parameters, which was trained on a tiny dataset with only 60 classes and 20 samples per class, achieved the accuracy 97.99% that outperforms human and state-of-the-art established by Bayesian Program Learning (BPL) trained on 964 classes. LCL is a fundamental idea which can be applied to alleviate parametric model's overfitting resulted by lack of training samples., Comment: 10 pages, 4 figures

Published
2018

4. Impacts of COVID-19 Pandemic on Dermatology Outpatient Department at a Tertiary Hospital in Eastern China: A Pre-Post Study

Author

Yan,Ting, Shao,Chengming, Zhang,Minjie, Ge,Yongxing, Chen,Tingting, Chai,Dayang, Yan,Ting, Shao,Chengming, Zhang,Minjie, Ge,Yongxing, Chen,Tingting, and Chai,Dayang

Abstract

Ting Yan,1,&ast; Chengming Shao,1,&ast; Minjie Zhang,1 Yongxing Ge,1 Tingting Chen,1 Dayang Chai2 1Department of Dermatology, The First People’s Hospital of Taicang, The Affiliated Taicang Hospital of Soochow University, Taicang, People’s Republic of China; 2Department of Cardiology, The First People’s Hospital of Taicang, The Affiliated Taicang Hospital of Soochow University, Taicang, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Dayang Chai, Department of Cardiology, The First People’s Hospital of Taicang, The Affiliated Taicang Hospital of Suzhou University, No. 58 Changsheng Road, Taicang, 215400, People’s Republic of China, Tel/Fax +86-512-53101356, Email dayangchai@outlook.comBackground: The COVID-19 pandemic has considerable impact on health care system in the world directly. Although the pandemic has been effectively controlled, people’s lifestyle, stress of job, economic status and health conditions have all changed. Therefore, it is unclear whether the COVID-19 pandemic has affected the distribution of diseases in dermatology outpatient department, especially in the post-pandemic era and how we should respond to these changes.Objective: We aimed to assess the impact of the COVID-19 pandemic on diagnosis of dermatology outpatient department in eastern China.Methods: A pre-post study design was a retrospective study to assess the changes of diseases diagnoses from the outpatient department of Dermatology, Taicang first people’s hospital, Suzhou University, Suzhou, China in the 2021 (Post-COVID-19 pandemic) compared to the 2019 (Pre-COVID-19 pandemic). Statistical analysis was performed using the SPSS 23.0 and Excel 2010. The data were analysed by methods independent t-test and Pearson’s chi-square test. A two-sided p-value of < 0.05 was considered statistically significant.Results: A total of 67,994 patients in 2019 and 67,288 patients in 2021 were included in the study. During

Published
2022

5. TTL based AQM in large delay network

Author

Ge Yongxing, Lv Jianbin, and Li Bo

Subjects
Network congestion, Router, Queueing theory, Network packet, Computer science, business.industry, ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS, Real-time computing, Algorithm design, Active queue management, Time to live, business, Computer network
Abstract

This paper proposes a novel combination of ECN and BECN based on the value of the TTL, the hops that a packet has been passed since it was sent. Since the ECN and the BECN both have merits and disadvantages, the combination would be expected to enhance the performance and effectiveness of the congestion control. The TTL, a default attribute of a data packet transferring on networks, must be checked on each router to decide whether to drop or forward the packet. Based on the value of the TTL, ECN or BECN would be selected to inform the sender the incipient congestion. We developed a mathematical model to analyze behaviors of the mechanism and test the model under different conditions. The results are accorded to the network behaviors very well.

Published
2011
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results