检索结果-内蒙古大学图书馆

Performance analysis of synchronization buffering mechanism in peer-to-peer live streaming systems

ICIC Express Letters, Part B: Applications 2012年第6期3卷 1665-1672页

作者： Jin, Shunfu Liu, Na Ma, Zhanyou College of Information Science and Engineering Yanshan University No. 438 Hebei Avenue Qinhuangdao 066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University No. 438 Hebei Avenue Qinhuangdao 066004 China College of Science Yanshan University No. 438 Hebei Avenue Qinhuangdao 066004 China

In the peer-to-peer (P2P) live streaming systems, a single stream is decomposed into multiple sub-streams. For the participating nodes, data blocks of different sub-streams are stored in different sub-buffers for synchronization, then forwarded and assembled to the original video stream in chronological order. In this paper, regarding the sub-buffers as multiple queues with homogeneous Poisson arrival processes, the data block forwarding procedure as a polling service, the forwarding suspension in an empty sub-buffer as a service delay state, a symmetric polling model is constructed. By using the method of embedded Markov chain, the mean queueing length and the probability for one queue to be empty when it is visited are derived in steady-state. Moreover, the performance measures in terms of average synchronization buffering length and video continuity level are obtained accordingly. Finally, numerical results are given to demonstrate that an appropriate number of sub-streams and a reasonable time limit for forwarding suspension can enhance the system performance.© 2012 ISSN 2185-2766.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

The study of a hierarchical hadoop architecture in multiple data centers environment

引用

Open Cybernetics and Systemics Journal 2015年第1期9卷 131-137页

作者： Shengtao, Sun Aizhi, Wu Xiaoyang, Liu School of Information Science and Engineering Yanshan University QinhuangdaoHebei066004 China College of Vehicles and Energy Yanshan University QinhuangdaoHebei066004 China Data Industry Research Institute Limited Company QinhuangdaoHebei066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei066004 China

Hadoop is a reasonable tool for cloud computing in big data era and MapReduce paradigm may be a highly successful programming model for large-scale data-intensive computing application, but the conventional MapReduce model and Hadoop framework limit themselves to implement jobs within single cluster. Traditional single-cluster Hadoop may not suitable for situations when data and compute resources are widely distributed this paper focuses on the application of Hadoop across multiple data centers and clusters. A hierarchical distributed computing architecture of Hadoop is designed and the virtual Hadoop file system is proposed to provide global data view across multiple data centers. The job submitted by user can be decomposed automatically into several sub-jobs which are then allocated and executed on corresponding clusters by location-aware manner. The prototype based on this architecture shows encouraging results. © Shengtao et al.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Cooperative bi-path metric for few-shot learning

arXiv

引用

arXiv 2020年

作者： Wang, Zeyuan Zhao, Yifan Li, Jia Tian, Yonghong State Key Laboratory of Virtual Reality Technology and Systems SCSE Beihang University Beijing100191 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Peng Cheng Laboratory Shenzhen518066 China

Given base classes with sufficient labeled samples, the target of few-shot classification is to recognize unlabeled samples of novel classes with only a few labeled samples. Most existing methods only pay attention to the relationship between labeled and unlabeled samples of novel classes, which do not make full use of information within base classes. In this paper, we make two contributions to investigate the few-shot classification problem. First, we report a simple and effective baseline trained on base classes in the way of traditional supervised learning, which can achieve comparable results to the state of the art. Second, based on the baseline, we propose a cooperative bi-path metric for classification, which leverages the correlations between base classes and novel classes to further improve the accuracy. Experiments on two widely used benchmarks show that our method is a simple and effective framework, and a new state of the art is established in the few-shot classification field. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

An improved community discovery algorithm in weighted social networks

引用

ICIC Express Letters 2016年第1期10卷 35-41页

作者： Guo, Jingfeng Liu, Miaomiao Liu, Linlin Chen, Xiao College of Information Science and Engineering Yanshan University No. 438 West Hebei Ave Qinhuangdao China College of Information Science and Engineering Northeast Petroleum University No. 199 Fazhan Road Daqing China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 West Hebei Ave Qinhuangdao China

The algorithm AGMA (Automatic Graph Mining Algorithm) is improved and a novel community discovery algorithm, namely CRMA (Clustering Re-clustering Merging Algorithm) is proposed which can realize more reasonable community division for weighted social networks. Firstly, in the re-clustering stage, AGMA neglected the clustering situation of neighbors of current node and it did not take the weights of edges connecting the current node and its unclustered neighbors into account, which led to that some nodes cannot be clustered or their clustering was unreasonable. Aiming to this, the concept of the connection compactness between the node and the community is introduced, and then through clustering and re-clustering each node would be divided into the community that has the largest connection compactness with the node according to the node weight, the edge weight and the friend coecient between the node and the community. Secondly, for community division in some unweighted networks and signed networks, if there are many nodes whose clustered neighbors are less than its unclustered neighbors, the division results of AGMA tend to result in the lower modularity. In view of this problem, the concepts of positive edge weight density, the cluster density and the connection coecient between clusters are proposed. Lastly, communities are merged based on the above three concepts after re-clustering and the modularity is eectively enhanced. The higher correctness and better generality of the improved algorithm are veried through experiments. © 2016 ICIC International.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Network for LiDAR 3D Object Detection

VS-Net: A Voxel Encoding and Sparse Convolution Embedded Net...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Meng Liu Jianwei Niu Yu Liu China North Artificial Intelligence and Innovation Research Institute Beijing China China North Vehicle Research Institute Beijing China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China State Key Laboratory of Software Development Envi-ronment School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9781665481106

Accurate and efficient 3D object detection in LiDAR point cloud is critical for autonomous driving. In this paper, we provide a solution for LiDAR-only detection which employs voxel features and a sparse convolution network. Specifically, we utilized voxel centers to encode point clouds' voxel features. Then, combining the sparse convolution method, we leveraged residual learning to design the backbone network. The detector output predicted results for multi-category and multi-object detection. Our method was evaluated on three popular and challenging datasets (KITTI, nuScence and Waymo). Experimental results demonstrated that the accuracy and speed (27.8 FPS) of our model could effectively support object detection for autonomous driving in various scenarios.

关键词： Point cloud compression Laser radar Three-dimensional displays Convolution Object detection Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Model Ownership Protection for Healthcare Consumer Electronics in Federated Edge Learning

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Wang, Rong Liang, Junchuan Feng, Chaosheng Chakraborty, Chinmay Alqahtani, Fayez Yu, Keping Sichuan Normal University College of Computer Science Chengdu610101 China Sichuan Normal University Visual Computing and Virtual Reality Key Laboratory of Sichuan Chengdu610068 China Birla Institute of Technology Mesra India King Saud University College of Computer and Information Sciences Software Engineering Department Riyadh12372 Saudi Arabia Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan

With the rising demand for intelligent services and privacy protection in consumer artificial intelligence (AI), federated edge learning has emerged as a beacon for privacy-preserving distributed machine learning. This non-centralized approach offers distinct data privacy advantages, making it especially suitable for applications with strict privacy policies, such as consumer-centric healthcare systems. However, consumer electronics/devices in federated edge learning might unlawfully violate model ownership by duplicating or distributing models. Another concern is that a central server, if compromised, can become a conduit for model leakage, whether for profit motives or due to external intrusions, thus exacerbating the model ownership violation. To our knowledge, few works have focused on model ownership protection for federated edge learning in the consumer-centric healthcare domain. In this paper, we introduce a federated model ownership protection (FedMOP) approach. FedMOP is a model ownership safeguard and a formidable fortress built upon two core innovations. First, FedMOP can swiftly embed and replace watermarks during local training, allowing for the accurate identification and subsequent flagging of deceitful consumer devices. Second, FedMOP ensures that the server only accesses encrypted versions of the federated model, keeping the model a secret. Extensive evaluations demonstrate the robustness and effectiveness of FedMOP. We hope that FedMOP can light the way for surmounting similar ethical challenges in the broader realm of consumer-edge AI. © 1975-2011 IEEE.

关键词： ethical AI Federated edge learning healthcare consumer electronicss model ownership protection

来源：评论

学校读者我要写书评

暂无评论

Deep learning based joint resource scheduling algorithms for hybrid MEC networks

arXiv

引用

arXiv 2019年

作者： Jiang, Feibo Wang, Kezhi Dong, Li Pan, Cunhua Xu, Wei Yang, Kun Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Department of Computer and Information Sciences Northumbria University United Kingdom Key Laboratory of Hunan Province for New Retail Virtual Reality Technology Hunan University of Technology and Business Changsha China School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom NCRL Southeast University Nanjing China School of Computer Technology and Engineering Changchun Institute of Technology Changchun China School of Computer Sciences and Electrical Engineering University of Essex ColchesterCO4 3SQ United Kingdom

In this paper, we consider a hybrid mobile edge computing (H-MEC) platform, which includes ground stations (GSs), ground vehicles (GVs) and unmanned aerial vehicle (UAVs), all with mobile edge cloud installed to enable user equipments (UEs) or Internet of thing (IoT) devices with intensive computing tasks to offload. Our objective is to obtain an online offloading algorithm to minimize the energy consumption of all the UEs, by jointly optimizing the positions of GVs and UAVs, user association and resource allocation in real-time, while considering the dynamic environment. To this end, we propose a hybrid deep learning based online offloading (H2O) framework where a large-scale path-loss fuzzy c-means (LSFCM) algorithm is first proposed and used to predict the optimal positions of GVs and UAVs. Secondly, a fuzzy membership matrix U-based particle swarm optimization (U-PSO) algorithm is applied to solve the mixed integer nonlinear programming (MINLP) problems and generate the sample datasets for the deep neural network (DNN) where the fuzzy membership matrix can capture the small-scale fading effects and the information of mutual interference. Thirdly, a DNN with the scheduling layer is introduced to provide user association and computing resource allocation under the practical latency requirement of the tasks and limited available computing resource of H-MEC. In addition, different from traditional DNN predictor, we only input one UEs information to the DNN at one time, which will be suitable for the scenarios where the number of UE is varying and avoid the curse of dimensionality in DNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Distributed Computation Offloading Scheduling Framework based on Deep Reinforcement Learning

A Distributed Computation Offloading Scheduling Framework ba...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Bin Dai Tao Ren Jianwei Niu Zheyuan Hu Shucheng Hu Meikang Qiu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China Texas A&M University-Commerce TX USA

Recent years have witnessed the rapid growth of smart devices and mobile applications. However, mobile applications are typically computation-intensive and delay-sensitive, while User Devices (UDs) are usually resource-limited. Mobile Edge Computing (MEC) has been proposed as a promising paradigm to mitigate the tension, where UDs’ tasks could be executed either locally on itself or remotely on the edge server via computation offloading. Lots of efficient computation offloading scheduling approaches have been proposed, whereas most of them are based on centralized scheduling which could face troubles in large-scale MEC. To address the issue, this paper proposes a distributed scheduling framework by leveraging the idea of ‘centralized training and distributed scheduling’. Furthermore, the Actor-Critic reinforcement learning is adopted to build the framework where the Actor and Critic play the roles of distributed scheduling and centralized training, respectively. Extensive simulations are conducted and the experimental results verify the effectiveness and efficiency of the proposed framework.

关键词： Training Processor scheduling Computational modeling Simulation Reinforcement learning Mobile applications Servers

来源：评论

学校读者我要写书评

暂无评论

computer network defense policy specification language

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2009年第1期46卷 89-99页

作者： Xia, Chunhe Wei, Yudi Li, Xiaojian Wang, Haiquan He, Wei State Key Laboratory of Virtual Reality Technology Beihang University Beijing 100083 China Key Laboratory of Beijing Network Technology Beihang University Beijing 100083 China College of Computer Science and Information Technology Guilin 541000 China College of Software Beihang University Beijing 100083 China

Policy is an essential part of computer network defense, which has important directive to the deployment, implementation, configuration and effects of defense systems. Presently, models and specifications on access control policy work well. However, they can not be directly applied to the whole defense policy area. In this paper, a new computer network defense policy specification language called CNDPSL is proposed to provide a common method of specifying protection, detection and response policies according to a new defined model called CNDPM, which is put forward by extending Or-BAC (organization based access control model). In CNDPM, automatic assignment mechanism is introduced to improve efficiency, and derivative principles are presented to refine abstract policies to concrete rules. Moreover, completeness, validity and consistency of policy are also formally analyzed and demonstrated. CNDPSL is declarative and able to abstract defense control behaviors of network, which makes this language flexible, extensible and adaptable to network defense requirements. Finally, a policy engine is implemented. Detailed experiments in GTNetS platform indicate that CNDSPL can be refined to concrete technical rules automatically, such as ACL (access control list) in firewall, IDS detection rules, response rules, etc, and obtain defense effects it expresses. The above information proves its effectiveness and efficiency.

关键词： Specification languages

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for geoscience:Progress,challenges,and perspectives

引用

The Innovation 2024年第5期5卷 136-160,135页

作者： Tianjie Zhao Sheng Wang Chaojun Ouyang Min Chen Chenying Liu Jin Zhang Long Yu Fei Wang Yong Xie Jun Li Fang Wang Sabine Grunwald Bryan MWong Fan Zhang Zhen Qian Yongjun Xu Chengqing Yu Wei Han Tao Sun Zezhi Shao Tangwen Qian Zhao Chen Jiangyuan Zeng Huai Zhang Husi Letu Bing Zhang Li Wang Lei Luo Chong Shi Hongjun Su Hongsheng Zhang Shuai Yin Ni Huang Wei Zhao Nan Li Chaolei Zheng Yang Zhou Changping Huang Defeng Feng Qingsong Xu Yan Wu Danfeng Hong Zhenyu Wang Yinyi Lin Tangtang Zhang Prashant Kumar Antonio Plaza Jocelyn Chanussot Jiabao Zhang Jiancheng Shi Lizhe Wang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Computer Science China University of GeosciencesWuhan 430078China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China Data Science in Earth Observation Technical University of Munich80333 MunichGermany The National Key Laboratory of Water Disaster Prevention Yangtze Institute for Conservation and DevelopmentHohai UniversityNanjing 210098China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China Soil Water and Ecosystem Sciences DepartmentUniversity of FloridaPO Box 110290GainesvilleFLUSA Materials Science Engineering Program Cooperating Faculty Member in the Department of Chemistry and Department of Physics Astronomy University of CaliforniaCaliforniaRiversideCA 92521USA Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China Key Laboratory of Computational Geodynamics University of Chinese Academy of SciencesBeijing 100049China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China College of Geography and Remote Sensing Hohai UniversityNanjing 211100China Department of Geography The University of Hong KongHong Kong 999077SARChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China School of Environmental Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China Collaborative Inno

This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection *** models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical ***,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world *** contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical *** techniques have shown promise in addressing Earth science-related ***,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into *** integration of physics-based and data-driven methodologies into hybrid models presents an alternative *** models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data *** review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and *** examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in *** paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.

关键词： Earth utilizing landscape

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：