检索结果-内蒙古大学图书馆

2020 International Conference on Virtual Reality and intelligent Systems, ICVRIS 2020

作者： Zhan-Jiang, Ji Wei, Shi Wuzhou University School of Information and Electronic Engineering China Guangxi Colleges Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou University China Guangxi Colleges China Wuzhou Vocational College China

ISBN: (纸本)9781728196367

The accessibility and transitivity have an important significance in terms of theory and application. The concept of the accessibility and transitivity are introduced in this paper. We study their dynamical properties. The following result are obtained: (l)Let (K , G ) be the hyperspace of (X , G ). Then ( X , G ) is accessible if and only if (K , G ) is accessible;(2) Let (K , G) be the hyperspace of (X , G). Then (X , G ) is transitive if and only if (K , G ) is transitive. These results enriched the theory of the accessibility and transitivity of topological group. © 2020 IEEE.

关键词： Accessibility Topological group Transitivity

来源：评论

学校读者我要写书评

暂无评论

Arbitrary shape text detection method based on improved PSE network structure 3

Arbitrary shape text detection method based on improved PSE ...

引用

3rd IEEE International Conference of Safe Production and Informatization, IICSPI 2020

作者： Xie, Chen Chen, guangxi Tang, Min Li, Qiaochu Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781728177380

The problem of low efficiency of text detection in natural scenes due to the Curved text or the multi-directional text, a arbitrary shape text detection method based on PSE network structure is proposed. By changing the backbone network of the original PSE and adopting a new lightweight network as backbone, and the post-processing method of the original network is optimized, which effectively improves the speed without losing the original accuracy. The experimental results show that the speed of the proposed method is 5.81 FPS/s compared with the original PSE on CTW1500 data set. The improved network has good robustness and generalization ability, and has better overall performance. © 2020 IEEE.

关键词： lightweight network PSEnet scene text text detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of NOMA-Based Cooperative Networks with Relay Selection

引用

China Communications 2020年第11期17卷 111-119页

作者： Ronglan Huang Dehuan Wan Fei Ji Hua Qing Jie Li Hua Yu Fangjiong Chen Guangxi Colleges and Universities Key Laboratory of Image Processing and Intelligent Information System Wuzhou UniversityWuzhou 543002China Guangdong University of Finance Guangzhou 510521China School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510641China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourcesGuangzhou510300China

Non-orthogonal multiple access(NOMA)technique is an expert on channel differences *** this paper,a dual-hop NOMA-based cooperative relaying network where a best relay is selected as an active node to accomplish the communication between a source and a destination is *** assume that both decode-and-forward(DF)and amplify-and-forward(AF)protocols are applied to the selected *** metrics that ergodic sum-rate and outage probability are investigated,and the closed-form expressions of the latter for DF and AF protocols are *** and simulation results are conducted to verify the validity of the theoretical analysis,in which we can see that the NOMA based DF relaying is better than the NOMA based AF relaying and other existing NOMA-based cooperative communication schemes.

关键词： non-orthogonal multiple access(NOMA) decode-and-forward(DF) amplify-and-forward(AF) relay selection ergodic sum-rate outage probability

来源：评论

学校读者我要写书评

暂无评论

OGFNet: Original resolution subnetwork and GRU based feature fusion network for image denoising 4

OGFNet: Original resolution subnetwork and GRU based feature...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021

作者： Li, Long Zhao, Feng Wang, Wenhao Lan, Rushi Qin, Binyi Luo, Xiaonan Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China School of Physics and Telecommunication Engineering Yulin Normal University Yulin537000 China National Local Joint Engineering Research Center of Satellite Navigation and Location Service Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9781665413220

Many denoising models have a good performance on images containing spatially invariant noise, especially those based on Convolutional Neural Networks (CNN). Nevertheless, the result of these methods is unreliable in preserving spatial image details. In our paper, we put forward a new design that achieves the goal of image denoising as well as preserve image details. In recent years, attention mechanisms is more and more popular in computer vision. We have done some researches on attention mechanisms in image denoising. Firstly, a combination of residual network and channel attention mechanisms and Gated Recurring Unit (GRU) is proposed to boost the denoising performance. Significantly, the GRU extracts features from different layers and selects more refined image features. Secondly, Original Resolution Subnetwork (ORSNet) is proposed to preserve the structural and textural image details. Few methods use a subnetwork for detail preservation. Extensive experiments on public denoising datasets attest to the validity of our proposed model. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations

arXiv

引用

arXiv 2023年

作者： Wang, Chao Qi, Shuren Huang, Zhiqiu Zhang, Yushu Lan, Rushi Cao, Xiaochun Fan, Feng-Lei The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China The Department of Mathematics The Chinese University of Hong Kong Hong Kong The Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China The School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China

The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective, it poses a critical risk for modern vision systems, e.g., the popular Deep Learning as a Service (DLaaS) frameworks. For protecting deep models while not modifying them, current algorithms typically detect adversarial patterns through discriminative decomposition for natural and adversarial data. However, these decompositions are either biased towards frequency resolution or spatial resolution, thus failing to capture adversarial patterns comprehensively. Also, when the detector relies on few fixed features, it is practical for an adversary to fool the model while evading the detector (i.e., defense-aware attack). Motivated by such facts, we propose a discriminative detector relying on a spatial-frequency Krawtchouk decomposition. It expands the above works from two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability, capturing the differences between natural and adversarial data comprehensively in both spatial and frequency distributions, w.r.t. the common trigonometric or wavelet basis;2) the extensive features formed by the Krawtchouk decomposition allows for adaptive feature selection and secrecy mechanism, significantly increasing the difficulty of the defense-aware attack, w.r.t. the detector with few fixed features. Theoretical and numerical analyses demonstrate the uniqueness and usefulness of our detector, exhibiting competitive scores on several deep models and image sets against a variety of adversarial attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Research on SDN Multi Controller Deployment based on K-means++

Research on SDN Multi Controller Deployment based on K-means...

引用

2020 International Conference on 5G Mobile Communication and Information Science, MCIS-5G 2020

作者： Yue, Li Junyan, Chen Chuxin, Liang Xiaochun, Lei School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Cloud Computing and Big Data Collaborative Innovation Center Guilin541001 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

In large-scale SDN network, a single centralized controller can not meet the demand, and multiple controllers are needed to deal with the problem, which leads to the problem of multi control balanced deployment. In this paper, the topology of SDN switches and links is known. The main research contents are as follows: The mathematical model of SDN multi controller deployment is established, and the appropriate network topology is selected and the multi controller deployment problem is solved. In the research, the number of controllers needed in the network and the switches managed by each controller is determined by the algorithm results, and the mapping relationship between controllers and switches is established. By analyzing the deployment results of the same network topology under different algorithms, the influence of different clustering algorithms on the experimental results is obtained. At the same time, the better deployment experiment results are simulated. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Improved Height Estimation Using Extended Kalman Filter on UWB-Barometer 3D Indoor Positioning System

引用

Wireless Communications and Mobile Computing 2021年第1期2021卷

作者： Li, Ji Wang, Yepeng Chen, Zhuo Ma, Linlin Yan, Suqing Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China University of British Columbia Vancouver Canada Zhengzhou Locaris Technology Co. Ltd. Zhengzhou450000 China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic Technology Guilin541004 China

Indoor 3D positioning system requires precise information from all three dimensions in space, but measurements in the vertical direction are usually interfered by sensors properties, unexpected obstructions, and other factors. Thus, accuracy and robustness are not guaranteed. Aiming at this problem, we propose a novel sensor fusion algorithm to improve the height estimation for a UWB-barometer integrated positioning system by introducing a pseudo reference update mechanism and the extended Kalman filter (EKF). The proposed fusion approach effectively helps with sensing noise reduction and outlier restraint. The results from numerical experiment investigations demonstrate that the accuracy and robustness of the proposed method achieved better improvement in height determination. © 2021 Ji Li et al.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

A new semi-supervised inductive transfer learning framework: Co-transfer

arXiv

引用

arXiv 2021年

作者： Yuan, Zhe Wen, Yimin Guangxi Key Laboratory of Image and Graphic intelligent processing Guilin University of Electronic Technology Guilin541004 China School of Computer Science and Information Safety Guilin University of Electronic Technology Guilin541004 China

In many practical data mining scenarios, such as network intrusion detection, Twitter spam detection, and computer-aided diagnosis, a source domain that is different from but related to a target domain is very common. In addition, a large amount of unlabeled data is available in both source and target domains, but labeling each of them is difficult, expensive, time-consuming, and sometime unnecessary. Therefore, it is very important and worthwhile to fully explore the labeled and unlabeled data in source and target domains to settle the task in target domain. In this paper, a new semi-supervised inductive transfer learning framework, named Co-Transfer is proposed. Co-Transfer first generates three TrAdaBoost classifiers for transfer learning from the source domain to the target domain, and meanwhile another three TrAdaBoost classifiers are generated for transfer learning from the target domain to the source domain, using bootstraped samples from the original labeled data. In each round of co-transfer, each group of TrAdaBoost classifiers are refined using the carefully labeled data. Finally, the group of TrAdaBoost classifiers learned to transfer from the source domain to the target domain produce the final hypothesis. Experiments results illustrate Co-Transfer can effectively exploit and reuse the labeled and unlabeled data in source and target domains. Copyright © 2021, The Authors. All rights reserved.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Performance of Grover's search algorithm with diagonalizable collective noises

arXiv

引用

arXiv 2021年

作者： Pan, Minghua Xiong, Taiping Zheng, Shenggen Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Physics Tsinghua University Beijing100084 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China Peng Cheng Laboratory Shenzhen518055 China

Grover’s search algorithm (GSA) is known to experience a loss of its quadratic speedup when exposed to quantum noise. In this study, we partially agree with this result and present our findings. First, we examine different typical diagonalizable noises acting on the oracles in GSA and find that the success probability decreases and oscillates around 1/2 as the number of iterations increases. Secondly, our results show that the performance of GSA can be improved by certain types of noise, such as bit flip and bit-phase flip noise. Finally, we determine the noise threshold for bit-phase flip noise to achieve a desired success probability and demonstrate that GSA with bit-phase flip noise still outperforms its classical counterpart. These results suggest new avenues for research in noisy intermediate-scale quantum (NISQ) computing, such as evaluating the feasibility of quantum algorithms with noise and exploring their applications in machine learning. Copyright © 2021, The Authors. All rights reserved.

关键词： Quantum noise

来源：评论

学校读者我要写书评

暂无评论

The research of the expansion property and chain mixing property of topological group 12

The research of the expansion property and chain mixing prop...

引用

12th International Conference on Measuring Technology and Mechatronics Automation, ICMTMA 2020

作者： Zhan-Jiang, Ji Wei, Shi School of Information and Electronic Engineering Wuzhou University China Guangxi Colleges and Universities Key Lab. of Image Processing and Intelligent Information System Wuzhou University China Guangxi Colleges and Universities Key Laboratory of Professional Software Technology Wuzhou University China Party Committee Office Wuzhou Vocational College China

ISBN: (纸本)9781728170817

The expansion property and chain mixing property have an important significance in terms of theory and application. The concept of the expansion property and chain mixing property are introduced in this paper. We study their dynamical properties. The following result are obtained: (1)Letbe the hyperspace of. Ifis expansive, thenis expansive;(2)Letbe the hyperspace of. Ifis chain mixing, thenis chain mixing;(3)Letbe the hyperspace of. Ifis chain transitive, thenis chain transitive;These results enriched the theory of the expansion property and chain mixing property of topological group. © 2020 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：