检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Chen, Mingzhe Yang, Zhaohui Saad, Walid Yin, Changchuan Vincent Poor, H. Cui, Shuguang Chinese University of Hong Kong Shenzhen518172 China Department of Electrical Engineering Princeton University PrincetonNJ08544 United States Centre for Telecommunications Research Department of Informatics King's College London WC2B 4BG United Kingdom Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24060 United States Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China Department of Electrical Engineering Princeton University PrincetonNJ08544 United States Shenzhen Research Institute of Big Data School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China

In this paper, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. In particular, in the considered model, wireless users execute an FL algorithm while training their local FL models using their own data and transmitting the trained local FL models to a base station (BS) that will generate a global FL model and send it back to the users. Since all training parameters are transmitted over wireless links, the quality of the training will be affected by wireless factors such as packet errors and the availability of wireless resources. Meanwhile, due to the limited wireless bandwidth, the BS must select an appropriate subset of users to execute the FL algorithm so as to build a global FL model accurately. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize an FL loss function that captures the performance of the FL algorithm. To address this problem, a closed-form expression for the expected convergence rate of the FL algorithm is first derived to quantify the impact of wireless factors on FL. Then, based on the expected convergence rate of the FL algorithm, the optimal transmit power for each user is derived, under a given user selection and uplink resource block (RB) allocation scheme. Finally, the user selection and uplink RB allocation is optimized so as to minimize the FL loss function. Simulation results show that the proposed joint federated learning and communication framework can reduce the FL loss function value by up to 10% and 16%, respectively, compared to: 1) An optimal user selection algorithm with random resource allocation and 2) a standard FL algorithm with random user selection and resource allocation. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A Pattern Division Multiple Access Scheme with Low Complexity Iterative Receiver for 5G Wireless Communication systems

A Pattern Division Multiple Access Scheme with Low Complexit...

引用

IEEE Vehicular Technology Conference

作者： Kai Zhang Jin Xu Changchuan Yin Chunyu Pan Weiqiang Tan Guixian Xu Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing 100876 P. R. China Zhengzhou University of Light Industry School of Computer and Communication Engineering Zhengzhou 450001 P. R. China Guangzhou University School of Computer Science and Educational Software Guangzhou 510006 P. R. China Aalborg University Department of Electronic Systems Aalborg 9400 Denmark

ISBN: (纸本)9781538663592;9781538663585

Non-orthogonal multiple access schemes with higher spectral efficiency and the capability of accessing more users than orthogonal multiple access (OMA) scheme is preferred for the fifth generation (5G) wireless networks. In this work, a non-orthogonal transmission scheme called pattern division multiple access (PDMA) is proposed for the 5G wireless communication systems. Two pattern matrices are proposed for 150% and 200% overloaded PDMA systems. Then, a low complexity symbol-wise belief propagation iterative detection and decoding (BPIDD) algorithm for multiple user detection is proposed. Numerical results and analysis provided by utilizing extrinsic information transfer chart show that the proposed scheme outperforms the traditional OMA systems significantly, and the performance of the proposed scheme is better than that of the existing schemes up to 1 dB. Finally, simulation results show that the proposed scheme is superior to the existing schemes and the proposed BPIDD algorithm is better than that of the BP algorithm over 0.5 dB.

关键词： 5G mobile communication iterative decoding matrix algebra multi-access systems multiuser detection Multi access systems matrix algebra Multiuser detection Iterative decoding multiple access Wireless communication systems Scheme iterative receiver spectral efficiency Information Transfer

来源：评论

学校读者我要写书评

暂无评论

Federated Echo State Learning for Minimizing Breaks in Presence in Wireless Virtual Reality Networks

arXiv

引用

arXiv 2018年

作者： Chen, Mingzhe Semiari, Omid Saad, Walid Liu, Xuanlin Yin, Changchuan Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China Chinese University of Hong Kong Shenzhen518172 China Department of Electrical Engineering Princeton University PrincetonNJ08544 United States Department of Electrical and Computer Engineering University of Colorado Colorado Springs Colorado SpringsCO80918 United States Wireless@VT Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA24060 United States

In this paper, the problem of enhancing the virtual reality (VR) experience for wireless users is investigated by minimizing the occurrence of breaks in presence (BIP) that can detach the users from their virtual world. To measure the BIP for wireless VR users, a novel model that jointly considers the VR application type, transmission delay, VR video quality, and users’ awareness of the virtual environment is proposed. In the developed model, the base stations (BSs) transmit VR videos to the wireless VR users using directional transmission links so as to provide high data rates for the VR users, thus, reducing the number of BIP for each user. Since the body movements of a VR user may result in a blockage of its wireless link, the location and orientation of VR users must also be considered when minimizing BIP. The BIP minimization problem is formulated as an optimization problem which jointly considers the predictions of users’ locations, orientations, and their BS association. To predict the orientation and locations of VR users, a distributed learning algorithm based on the machine learning framework of deep (ESNs) is proposed. The proposed algorithm uses concept from federated learning to enable multiple BSs to locally train their deep ESNs using their collected data and cooperatively build a learning model to predict the entire users’ locations and orientations. Using these predictions, the user association policy that minimizes BIP is derived. Simulation results demonstrate that the developed algorithm reduces the users’ BIP by up to 16% and 26%, respectively, compared to centralized ESN and deep learning algorithms. Copyright © 2018, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Signal Recognition Based on Signal Power Spectrum Fitting Feature Extraction

引用

Beijing Youdian Daxue Xuebao/Journal of Beijing University of Posts and Telecommunications 2018年第2期41卷 114-118页

作者： Tian, Hao-Min Yin, Liang Ma, Yue Li, Shu-Fang Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China Computer Network Research Center Beijing University of Posts and Telecommunications Beijing100876 China School of Computer Science and Technology Beijing University of Posts and Telecommunications Beijing100876 China

Aiming at the problem of communication signal service type identification, the author proposes a polynomial fitting factor that extracts the power spectrum of the signal using the linear regression algorithm and the polynomial fitting model in machine learning field as a unified feature of the signal to construct the training set. A multi-layer fully connected neural network classifier model was built on depth learning platform. Compared with the traditional ones, this method has advantages of unifying the radio signal without the need of individual service to extract the personalized features. The power spectrum data of code division multiple access(CDMA) uplink, CDMA downlink, extended global system for mobile(EGSM) uplink, EGSM downlink, wireless local area networks (WLAN) and long time evolution (LTE) signals in the actual radio monitoring data are selected as data set, and 97% classification accuracy is verified. that this method is proven feasible. © 2018, Editorial Department of Journal of Beijing University of Posts and Telecommunications. All right reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

4-5 SF-TAP: Scalable and flexible traffic analysis platform

引用

Journal of the National Institute of Information and Communications Technology 2016年第2期63卷 103-112页

作者： Takano, Yuuki Cybersecurity Laboratory Cybersecurity Research Institute Computer Architecture Network System Network Security Japan

Application-level network traffic analysis is a fundamental technology, which could be widely adopted such as intrusion detection system. However, network traffic analysis algorithms consuming considerable computational resources can not be adopted by using conventional network capturing technologies. In addition, developing an application protocol analyzer is a tedious and time consuming task. Therefore, in this paper, we propose a scalable and exible traffic analysis platform (SF-TAP) that provides an efficient and exible application-level stream analysis of high-bandwidth network traffic. Because SF-TAP is horizontally scalable, such heavy algorithms can be adopted for high-bandwidth networks. Furthermore, because of the modularity of SF-TAP, developers can easily implement network traffic analyzers by using SF-TAP.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

New Collaborative Intrusion Detection architecture Based on Multi Agent systems

引用

通讯和计算机（中英文版） 2016年第1期13卷 1-10页

作者： Mohssine EL AJJOURI Siham BENHADOU Hicham MEDROMI Systems Architecture Team Laboratory of Computer System and Renewable Energy University Hassan H Casablanca ENSEMCasablanca 20200 Morocco

来源：评论

学校读者我要写书评

暂无评论

Echo state transfer learning for data correlation aware resource allocation in wireless virtual reality

arXiv

引用

arXiv 2017年

作者： Chen, Mingzhe Saad, Walid Yin, Changchuan Debbah, Mérouane Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing100876 China Wireless-VT Bradley Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States Mathematical and Algorithmic Sciences Lab Huawei France R & D Paris France

In this paper, the problem of data correlation-aware resource management is studied for a network of wireless virtual reality (VR) users communicating over cloud-based small cell networks (SCNs). In the studied model, small base stations (SBSs) with limited computational resources act as VR control centers that collect the tracking information from VR users over the cellular uplink and send them to the VR users over the downlink. In such a setting, VR users may send or request correlated or similar data (panoramic images and tracking data). This potential spatial data correlation can be factored into the resource allocation problem to reduce the traffic load in both uplink and downlink. This VR resource allocation problem is formulated as a noncooperative game that allows jointly optimizing the computational and spectrum resources, while being cognizant of the data correlation. To solve this game, a transfer learning algorithm based on the machine learning framework of echo state networks (ESNs) is proposed. Unlike conventional reinforcement learning algorithms that must be executed each time the environment changes, the proposed algorithm can intelligently transfer information on the learned utility, across time, to rapidly adapt to environmental dynamics due to factors such as changes in the users' content or data correlation. Simulation results show that the proposed algorithm achieves up to 16.7% and 18.2% gains in terms of delay compared to the Q-learning with data correlation and Q-learning without data correlation. The results also show that the proposed algorithm has a faster convergence time than Q-learning and can guarantee low delays. Copyright © 2017, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

QoS-aware transmission management for energy harvesting wireless sensor networks

QoS-aware transmission management for energy harvesting wire...

引用

International Conference on Telecommunications (ICT)

作者： Dan Liu Yan Sun Yuanyuan Yao Changchuan Yin Beijing Key Laboratory of Network System Architecture Convergence Beijing University of Posts and Telecommunications China School of Electronic Engineering and Computer Science Queen Mary University of London London UK

Wireless sensor networks (WSNs) are widely deployed in many fields nowadays. However, the limited energy storage ability of sensor nodes causes great detrimental effect on the performance of the WSNs. Energy harvesting has been proved as one of the promising ways to replenish the energy constrained sensors for prolonging WSNs lifetime. Another exacerbated problem introduced by non-uniform energy distribution and nonoptimal energy management in WSNs also causes great challenge to WSNs. For realizing the efficient energy utilization and improving the performance of energy harvesting enabled WSNs, two transmission management schemes, Markov decision based packets aggregation allocation (MDPA) and partial Kalman filter with best-match aggregation (PKBPA), are proposed respectively in this paper. MDPA focuses on the node's own energy capabilities to decide the packets number for aggregation, while PKBPA decides the number of packets to be aggregated and transmitted based on the estimated energy state information of the node and its next hop. Simulation results show that the PKBPA scheme outperforms other schemes, especially when the energy is insufficient for the packets transmission.

关键词： Wireless sensor networks Buffer storage Energy harvesting Quality of service Resource management Markov processes Energy states

来源：评论

学校读者我要写书评

暂无评论

Vision-based Unmanned Aerial Vehicle detection and tracking for sense and avoid systems

Vision-based Unmanned Aerial Vehicle detection and tracking ...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Krishna Raj Sapkota Steven Roelofsen Artem Rozantsev Vincent Lepetit Denis Gillet Pascal Fua Alcherio Martinoli Computer Vision Laboratory School of Communication and Computer Sciences école Polytechnique Fédérale de Lausanne (EPFL) Switzerland Distributed Intelligent Systems and Algorithms Laboratory School of Architecture Civil and Environmental Engineering EPFL Switzerland Institute for Computer Graphics and Vision TU Graz Austria Coordination and Interaction System Group School of Engineering EPFL Switzerland

ISBN: (纸本)9781509037636

We propose an approach for on-line detection of small Unmanned Aerial Vehicles (UAVs) and estimation of their relative positions and velocities in the 3D environment from a single moving camera in the context of sense and avoid systems. This problem is challenging both from a detection point of view, as there are no markers on the targets available, and from a tracking perspective, due to misdetection and false positives. Furthermore, the methods need to be computationally light, despite the complexity of computer vision algorithms, to be used on UAVs with limited payload. To address these issues we propose a multi-staged framework that incorporates fast object detection using an AdaBoost-based approach, coupled with an on-line visual-based tracking algorithm and a recent sensor fusion and state estimation method. Our framework allows for achieving real-time performance with accurate object detection and tracking without any need of markers and customized, high-performing hardware resources.

关键词： Target tracking Object detection Collision avoidance Cameras Visualization Detectors

来源：评论

学校读者我要写书评

暂无评论

A New ETL Approach Based on Data Virtualization

引用

Journal of computer Science & Technology 2015年第2期30卷 311-323页

作者：郭树盛袁子牧孙傲冰岳强 State Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100190 China Cloud Computing Center Chinese Academy of Sciences Dongguan 523808 China

ETL （Extract-Transform-Load） usually includes three phases： extraction, transformation, and loading. In building data warehouse, it plays the role of data injection and is the most time-consuming activity. Thus it is necessary to improve the performance of ETL. In this paper, a new ETL approach, TEL （Transform-Extract-Load） is proposed. The TEL approach applies virtual tables to realize the transformation stage before extraction stage and loading stage, without data staging area or staging database which stores raw data extracted from each of the disparate source data systems. The TEL approach reduces the data transmission load, and improves the performance of query from access layers. Experimental results based on our proposed benchmarks show that the TEL approach is feasible and practical.

关键词： cloud computing big data ETL heterogeneous database data virtualization

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：