检索结果-内蒙古大学图书馆

2nd International Conference on Signal Image Processing and Communication, ICSIPC 2022

作者： Li, Zhongyu Liu, Yang Kuang, Yin Wang, Huajun Liu, Cheng College of Computer Science Chengdu Normal University Chengdu611130 China College of Geophysics Chengdu University of Technology Chengdu610059 China Key Laboratory of Pattern Recognition and Intelligent Information Processing of Sichuan Chengdu University Chengdu610106 China Artificial Intelligence Key Laboratory of Sichuan Province Zigong643000 China Key Laboratory of interior Layout optimization and Security Institutions of Higher Education of Sichuan Province Chengdu Normal University Sichuan Chengdu611130 China College of Movie and Media Sichuan Normal University Chengdu610066 China

ISBN: (纸本)9781510657694

Aiming at the problem of model instability and overfitting of deep neural networks with the deepening of the number of network layers, the current mainstream method is to use batch normalization (BN) to alleviate them. However, since the BN method is more sensitive to batch size when the batch size is small, the model performance will be poor. For a relatively large model, due to the limitation of video memory, the batch size cannot take a large value, limiting the model's performance. Because of the dependence of BN on batch size, this paper adopts group normalization (GN) instead of batch normalization (BN) in the UNet network to alleviate the impact of the model on batch size. Then experiments are carried out on the WHUBuilding dataset. The experimental results show that the improved model (UNet-GN) improves the mean intersection over union (MIoU) and mean pixel accuracy (MPA) by 10.66% and 1.65% respectively compared with the original model (UNet-BN). © 2022 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Dynamic Analysis Technology of Quantitative Control Oriented to Characteristics of Power Grid Digital Application Scenarios 1

引用

4th International Conference on 3D Imaging Technologies- Multidimensional Signal Processing and Deep Learning, 3D IT-MSP and DL 2022

作者： Wang, Gang Pan, Jianhong Lv, Changhui Zhao, Bo Dong, Aidi State Grid Smart Grid Research Institute CO. LTD Nanjing210003 China State Grid Key Laboratory of Information & Network Security Nanjing210003 China State Grid Jilin Electric Power Company Limited Changchun130021 China Power Economic Research Institute of Jilin Electric Power Co. Ltd Changchun130011 China

ISBN: (数字)9789819911455

ISBN: (纸本)9789819911448

The digitalization construction of power grid companies will gradually be carried out in depth, while the research on the quantitative control dynamic analysis for the characteristics of power grid digitalization application scenarios has not yet been carried out. In this paper, the dynamic analysis technology of quantitative control of power grid is studied, and the expected project costs and benefits are preliminarily calculated using the functional analysis method;Based on expert scoring method, the quantitative influencing factor set of digital application scene target features is constructed;Based on fuzzy analytic hierarchy process, the quantitative impact index set of digital application scenario features is constructed;Based on K2 structure algorithm and Markov Monte Carlo structure algorithm, the application model of Bayesian network computing is constructed, and a dynamic technical and economic evaluation model adapted to different application scenarios is formed;Based on the calculation application model, according to the corresponding background and characteristics of different projects, carry out data analysis, predict the cause level of the factors, match the data statistical results with the initial network data, and finally calculate the possible costs and benefits of the project by calculating the expected value of the nodes, so as to realize the dynamic technical and economic evaluation of the power grid adapted to different application scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Economic analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic resource provision for cloud broker with multiple reserved instance terms 1

引用

15th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2015

作者： Zhang, Jiangtao Chen, Shi Huang, Hejiao Wang, Xuan Du, Dingzhu School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen518055 China Public Service Platform of Mobile Internet Application Security Industry Shenzhen518057 China Shenzhen Key Laboratory of Internet of Information Collaboration Shenzhen518055 China Shenzhen Applied Technology Engineering Laboratory for Internet Multimedia Application Shenzhen518055 China Department of Computer Science University of Texas at Dallas RichardsonTX75080 United States

ISBN: (数字)9783319271194

ISBN: (纸本)9783319271187

Relying on the knowledge of the pricing benefit of long-term reserved resource and multiplexing gains, cloud broker strives to minimize its cost by utilizing infrastructure resources from public cloud service provider. Different reserved instance terms accompanied by different prices are provisioned by the provider. How to choose the appropriate ones from various terms to meet the dynamic user demands at the least cost is a great challenge. This paper addresses the challenge by two algorithms. Extensive real world traces driven evaluations show that the heuristic algorithm runs about twice as fast as the approximation one, while both algorithms can save almost the same resource cost up to 27%. © Springer International Publishing Switzerland 2015.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Video Publish-Subscribe Scheme with Integrity Verification and Copyright Protection for Distributed Edge Storage

SSRN

引用

SSRN 2021年

作者： Ding, Yan Li, Yanping Zhang, Kai Ding, Yong School of Mathematics and Statistics Shaanxi Normal University Shaanxi Xi’an710119 China Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

Data publishing and subscribing is an effective method for data users to share and receive data selectively. If the traditional data publish-subscribe schemes based on centralized cloud server are directly applied to video publish-subscribe, it may cause time delay since video is generally large, which will result in a poor user experience. Moreover, the existing data publish-subscribe schemes do not support copyright protection and subscription dynamics. In order to solve the above problems, we propose a video publish-subscribe scheme with integrity verification and copyright protection in the edge computing environment. Firstly, this scheme suggests that video originator adopts distributed edge storage model to store video replicas to reduce latency and improve user experience. Secondly, our proposed scheme adopts digital watermarking technology to achieve the copyright protection and rebroadcast accountability of video data. Thirdly, this scheme also realizes privacy protection and integrity verification of video data based on proxy re-encryption. Fourthly, in order to be more practical and flexible, our scheme also supports subscription dynamics, including adding, unsubscribing and modifying subscription. Performance evaluation and security analysis demonstrate the practicability and effectiveness of our scheme. © 2021, The Authors. All rights reserved.

关键词： Copyrights

来源：评论

学校读者我要写书评

暂无评论

Test-Time Training with Invariant Graph Learning for Out-of-Distribution Generalization

SSRN

引用

SSRN 2024年

作者： Pi, Li Li, Jiaxing Song, Lei Yang, Guanyu Chen, Yang Kong, Youyong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Jiangsu Province Nanjing China

Graph Neural networks (GNNs) frequently do not perform optimally on out-of-distribution (OOD) data. Previous research on graph OOD generalization suggests extracting invariant subgraphs, which provide crucial categorical information even under test distributions. However, this strategy is not optimal due to two issues. Firstly, there is a significant distribution shift between the test and training sets, which may result in incorrect invariant subgraphs being extracted during the test phase. Secondly, the extraction of subgraphs can lead to the loss of important structural information. To address these issues, we propose a novel two-stage training paradigm named \textbf{I}nvariant \textbf{G}raph \textbf{T}est-\textbf{T}ime \textbf{T}raining (\textbf{IGT3}), which uses the training paradigm called Test-Time Training (TTT). We also propose invariant graph recognition to learn key parts of the graph without destroying the original graph structure. In addition, we introduce a multi-level graph contrastive learning method as an auxiliary self-supervised task. To prevent TTT failure, we use the feature constraint to enhance the robustness of the training process. We conduct experiments on seven common graph classification OOD benchmark datasets. The results demonstrate that IGT3 outperforms state-of-the-art (SOTA) methods by an average of 4.2\%, confirming the effectiveness of each module. The paper code is available at https://***/r/IGT3-3281/ © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

DPG-DT: Differentially Private Generative Digital Twin for Imbalanced Learning in Industrial IoT

DPG-DT: Differentially Private Generative Digital Twin for I...

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Siyuan Li Xi Lin Gaolei Li Lixing Chen Siyi Liao Jing Wang Jianhua Li Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Integrated Administration Technologies for Information Security Shanghai China China United Network Communication Co. Ltd

ISBN: (数字)9798350358261

ISBN: (纸本)9798350358278

The existing Artificial Intelligence (AI)-based industrial defect detection methods have received extensive attention in the industrial Internet of Things (IoT). However, due to the limited defect samples, it is difficult for discriminative models to achieve better performance in imbalanced learning. In addition, the privacy concerns surrounding sensitive information hinder the sharing of synthetic industrial data. In this paper, we propose a novel framework called the Differentially Private Generative AI-empowered Digital Twin (DPG-DT) framework, aiming to synthesize realistic samples while satisfying differential privacy and empowering the construction of digital space and its connection with physical space. Specifically, the core of the DPG-DT framework is the proposed Private Synthetic Industry Energy-guided model (PSIE), in which we privatize the energybased model-empowered Langevin Markov Chain Monte Carlo (MCMC) sampling method with Gaussian noise and random response. Our method could replace the conventional generator while guaranteeing privacy. Extensive experiments on real-world industrial datasets NEU-CLS and DeepPCB demonstrate that the proposed framework is capable of generating synthetic industrial images with both high fidelity and differential privacy. Moreover, the achieved downstream accuracy outperforms baselines by 23.9 % in industrial scenarios.

关键词： Industries Differential privacy Privacy Monte Carlo methods Sampling methods Generators Data models

来源：评论

学校读者我要写书评

暂无评论

RFID indoor localization based on relational aggregation

RFID indoor localization based on relational aggregation

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Jiali Zheng Tuanfa Qin Jieming Wu Li Wan Guangxi Key Laboratory of Multimedia Communications and Network Technology (Cultivating Base) Guangxi Colleges and Universities Key Laboratory of Multimedia Communications and Information Processing School of Computer Electronics and Information Guangxi University Nanning China School of Information and Electronic Engineering WuZhou University Wuzhou China

This paper proposes a relational aggregation algorithm based on Radio Frequency Identification (RFID) to achieve accurate indoor localization. The proposed algorithm is composed of three steps: (1) exploring the relationship between reader received power and distance information then estimating Euclid distance of signal strength; (2) employing k-Nearest Neighbour algorithm to aggregate the relationship between nearest reference tag and target tag; (3) optimizing relational aggregation operator to obtain the coordinate of target tag. Simulated experiments show that the proposed algorithm can reduce mean localization error effectively and improve the accuracy of indoor localization.

关键词： Radiofrequency identification Mathematical model Antenna arrays Mobile computing Wireless communication Multimedia communication Mobile communication

来源：评论

学校读者我要写书评

暂无评论

Space-Air-Ground Integrated network (SAGIN) for 6G: Requirements, Architecture and Challenges

引用

China Communications 2022年第2期19卷 90-108页

作者： Huanxi Cui Jun Zhang Yuhui Geng Zhenyu Xiao Tao Sun Ning Zhang Jiajia Liu Qihui Wu Xianbin Cao School of Electronic and Information Engineering Beijing Key Laboratory for Network-Based Cooperative Air application ManagementBeihang UniversityBeijing 100191China Advanced Research Institute of Multidisciplinary Science Beijing Institute of TechnologyBeijing 100081China China Mobile Research Institute Beijing 100053China Department of Electrical and Computer Engineering University of WindsorONCanadaN9B 3P4 National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology the School of CybersecurityNorthwestern Polytechnical UniversityXi’anShaanxi710072China College of Electronics and Information Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210007China

As the fifth-generation(5G)mobile communication network may not meet the requirements of emerging technologies and applications,including ubiquitous coverage,industrial internet of things(IIoT),ubiquitous artificial intelligence(AI),digital twins(DT),etc.,this paper aims to explore a novel space-air-ground integrated network(SAGIN)architecture to support these new requirements for the sixth-generation(6G)mobile communication network in a flexible,low-latency and efficient ***,we first review the evolution of the mobile communication network,followed by the application and technology requirements of *** the current 5G non-terrestrial network(NTN)architecture in supporting the new requirements is deeply *** that,we proposes a new flexible,low-latency and flat SAGIN architecture,and presents corresponding use ***,the future research directions are discussed.

关键词： 6G AI DT SAGIN NTN network architecture

来源：评论

学校读者我要写书评

暂无评论

Steganography for Neural Radiance Fields by Backdooring

arXiv

引用

arXiv 2023年

作者： Dong, Weina Liu, Jia Ke, Yan Chen, Lifeng Sun, Wenquan Pan, Xiaozhong The College of Cryptography Engineering Engineering University of PAP Shaanxi Xi’an710086 China Key Laboratory of Network and Information Security of PAP Engineering University of PAP Shaanxi Xi’an710086 China

The utilization of implicit representation for visual data (such as images, videos, and 3D models) has recently gained significant attention in computer vision research. In this letter, we propose a novel model steganography scheme with implicit neural representation. The message sender leverages Neural Radiance Fields (NeRF) and its viewpoint synthesis capabilities by introducing a viewpoint as a key. The NeRF model generates a secret viewpoint image, which serves as a backdoor. Subsequently, we train a message extractor using overfitting to establish a one-to-one mapping between the secret message and the secret viewpoint image. The sender delivers the trained NeRF model and the message extractor to the receiver over the open channel, and the receiver utilizes the key shared by both parties to obtain the rendered image in the secret view from the NeRF model, and then obtains the secret message through the message extractor. The inherent complexity of the viewpoint information prevents attackers from stealing the secret message accurately. Experimental results demonstrate that the message extractor trained in this letter achieves high-capacity steganography with fast performance, achieving a 100% accuracy in message extraction. Furthermore, the extensive viewpoint key space of NeRF ensures the security of the steganography scheme. Copyright © 2023, The Authors. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

A Design of Direct Memory Access Controller for Wireless Communication SoC in Power Grid

A Design of Direct Memory Access Controller for Wireless Com...

引用

International Conference on Circuits, System and Simulation (ICCSS)

作者： Yingying Chi Zhe Zheng Research Department of Smart Chip Global Energy Interconnection Research Institute Co. Ltd. Beijing China State Grid Key Laboratory of Information & Network Security State Grid Laboratory of Electric Power Communication Network Technology Beijing China

ISBN: (纸本)9781538678206

This paper presents a complete Register Transfer Level (RTL) design of Direct Memory Access (DMA) controller which is compliable with the Advanced Highperformance Bus (AHB). The DMA is integrated in Cortex-M3-based system-on-chip (SoC) designed for power-grid-dedicated wireless communication system based on IEEE 802.11ah protocol. The hardware implementation and prototype verification indicate that by allowing hardware devices working at different frequencies to communicate with each other without relying on the heavy outage load of CPU, the proposed DMA controller realizes the good convergence with the whole system and improves the overall performance with low power consumption.

关键词： Registers Hardware Writing Wireless communication Data transfer System-on-chip

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：