检索结果-内蒙古大学图书馆

IEEE Conference on Wireless Communications and networking

作者： Deyang Sun Hang Li Zixuan Kong Zhenghe Zhu Yawen Chen Zhaoming Lu Xiangming Wen Beijing Key Laboratory of Network System Architecture and Convergence Beijing China Beijing Laboratory of Advanced Information Networks Beijing China Beijing University of Posts and Telecommunications Beijing China Network and Information Technology Center Changchun Institute of Optics Fine Mechanics and Physics (CIOMP) Chinese Academy of Sciences Changchun China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Space-Air-Ground Integrated network (SAGIN) is emerged as a promising paradigm to realize the vision of global coverage of sixth generation (6G) communication network. As an efficient communication pattern, multicast communication can be widespread among the ever increasing communication requests in the seamless access SAG IN. However, given the extensive network scale, time varying characteristic and heterogeneity of SAG IN, the coordination of heterogeneous networks brings challenges to resource allocation. With virtualization technologies, the physical resources within SAGIN can be virtualized as Virtual network Functions (VNFs) in virtual resource pool. To ensure that multicast services can be provided, the network deploys Multicast Service Function Chains (MSFCs) where the service flows is processed by VNFs in order during the transmission. In this paper, we study the problem of jointly optimizing VNF placement and multicast routing within SAG IN while considering that different network segments are equipped with different physical network resources and cost coefficients. We formulate it as an Integer Linear Programming (ILP) problem with the objective of maximizing network revenue while minimizing resource cost of computation and bandwidth. Since it is NP-hard, a low complexity heuristic algorithm is developed to find an efficient solution within polynomial time. Simulation results demonstrate the effectiveness of our proposed model and algorithm, and the deployment cost and blocking rate can be significantly reduced in SAGIN compared with independent terrestrial network.

关键词： Costs Multicast algorithms Service function chaining Simulation Heuristic algorithms Computational modeling Space-air-ground integrated networks

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework of Data Augmentation Using Large Language Models for Text-Based Cross-Modal Retrieval

SSRN

引用

SSRN 2024年

作者： Si, Lijia Guo, Caili Li, Zheng Yang, Yang Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China China Telecom Digital Intelligence Technology Co. Ltd Beijing China

Text-based cross-modal retrieval (TCMR) is an information retrieval task that aims to find semantically equivalent content from other modalities given a textual ***, collecting well-labeled data for TCMR is very expensive and time-consuming, which highly affects the performance of ***, large language models (LLMs) have approached or even surpassed the human level on many natural language processing tasks, which inspires us to try to use LLM for data augmentation of TCMR ***, data augmentation using LLMs also faces significant challenges, particularly the hallucination problem of LLMs and the fusion of augmented data with the original *** this paper, we propose LLM-DA++, a unified framework for data augmentation using large language models that is applied to text-based cross-modal retrieval ***-DA++ includes the training and inference sub-frameworks, both leveraging LLMs to rewrite texts, enhancing vocabulary diversity and sentence structure while retaining key *** order to alleviate the hallucinations problem of LLMs, a Text Faithfulness Filter is introduced in LLM-DA++ to filter out unfaithful rewritten texts. In addition, a Balanced Sampling Strategy is introduced in LLM-DA++ to balance the contributions of original and augmented *** experiments on three cross-modal retrieval tasks, text-based audio retrieval, text-based person retrieval, and text-based motion retrieval, show that LLM-DA++ can significantly improve the retrieval performance of existing TCMR tasks, validating the effectiveness of LLM-DA++.The code is available at https://***/slj5/LLM-DA-plus-plus. © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

TSN Disciplined Oscillators for Time Synchronization in Distributed networks

TSN Disciplined Oscillators for Time Synchronization in Dist...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Zhifu Li Guochu Shou Xiaodong Zhang Li Chen Dong Zhao Xiaoyu Zhao Kai Xia Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China

This paper proposes a TSNDO scheme utilizing time-sensitive networking to discipline clocks, providing precise time for distributed networks. The experimental results demonstrate that TSNDO achieves the time accuracy ... 详细信息

ISBN: (数字)9798350379266

ISBN: (纸本)9798350379273

关键词： Accuracy Asia Prototypes Optical fiber communication Calibration Synchronization Oscillators Photonics Clocks

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient UAV Trajectory Design for Hovering-Flying Data Collection

Energy Efficient UAV Trajectory Design for Hovering-Flying D...

引用

IEEE Globecom Workshops

作者： Zijing Chen Yijun Guo Jianjun Hao Yu Du Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing Language and Culture University

ISBN: (纸本)9781665459761

In this paper, we consider a UAV-aided data collection network where the UAV provides communication service for sensor nodes (SNs) which are distributed randomly on the ground with hovering-flying mode. We aim at minimizing the total energy consumption for the UAV to collect data from SNs, including both hovering energy and flying energy, by jointly optimizing the number of hovering points and the UAV trajectory. We use block coordinate decent (BCD) and successive convex optimization (SCO) techniques by decomposing it into two sub-problems to solve the original non-convex problem, which are alternately solved until the algorithm converges. Numerical results show that the proposed solution saves the consumed energy effectively.

关键词： Energy consumption Conferences Data collection Energy efficiency Convex functions Trajectory Numerical models

来源：评论

学校读者我要写书评

暂无评论

Research on optimized design of antenna based on improved whale optimization algorithm 4

Research on optimized design of antenna based on improved wh...

引用

4th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2021

作者： Fan, Wenmin Wang, Zhixin Hong, Weijun Beijing Laboratory of Advanced Information Network Beijing University of Posts and Telecommunications Beijing China State Radio Regulation of China Beijing China Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665432030

In order to improve the efficiency of antenna design, various intelligent optimization algorithms are used for settling the complex nonlinear problems involved. The whale optimization algorithm (WOA) is one of the relatively novel and well-performing swarm intelligence optimization algorithms. In this article, an improved whale optimization algorithm (IWOA) is proposed in view of the shortcomings of WOA. First, the nonlinear control parameter, adaptive weight and Cauchy disturbance are introduced to improve algorithm performance. Then a CEC benchmark function set is selected to test the feasibility and effectiveness of IWOA. The results show that IWOA has obvious advantages in terms of convergence speed, convergence accuracy and stability. Finally, the algorithm is used for the optimization of structural parameters of two ultra-wideband (UWB) antennas. The automated design of antenna is realized by MATLAB and HFSS joint simulation. © 2021 IEEE

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Roadside 3D Extended Object Tracking by Fusing Sparse Radar Points and Pixel keypoints

引用

IEEE Sensors Journal 2025年

作者： Deng, Jiayin Hu, Zhiqun Xia, Yuxuan Lu, Zhaoming Wen, Xiangming Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Networks Beijing 100876 China Linköping University Department of Electrical Engineering Linköping 58183 Sweden

Roadside perception is a key component in intelligent transportation systems. In this paper, we present a novel three-dimensional (3D) extended object tracking (EOT) method, which simultaneously estimates the object kinematics and extent state, in roadside perception using both the radar and camera data. Because of the influence of sensor viewing angle and limited angle resolution, radar measurements from objects are sparse and non-uniformly distributed, leading to inaccuracies in object extent and position estimation. To address this problem, we present a novel spherical Gaussian function weighted Gaussian mixture model. This model assumes that radar measurements originate from a series of probabilistic weighted radar reflectors on the vehicle’s extent. Additionally, we utilize visual detection of vehicle keypoints to provide additional information on the positions of radar reflectors. Since keypoints may not always correspond to radar reflectors, we propose an elastic skeleton fusion mechanism, which constructs a virtual force to establish the relationship between the radar reflectors on the vehicle and its extent. Furthermore, to better describe the kinematic state of the vehicle and constrain its extent state, we develop a new 3D constant turn rate and velocity motion model, considering the complex 3D motion of the vehicle relative to the roadside sensor. Finally, we apply variational Bayesian approximation to the intractable measurement update step to enable recursive Bayesian estimation of the object’s state. Simulation results using Carla simulator and experimental results on the nuScenes dataset demonstrate the effectiveness and superiority of the proposed method in comparison to several state-of-the-art 3D EOT methods. © 2001-2012 IEEE.

关键词： camera and radar fusion Extended object tracking pixel keypoints radar point clouds roadside perception variational approximation

来源：评论

学校读者我要写书评

暂无评论

A multipath-assisted localization algorithm under 5G-based opensource testbed

A multipath-assisted localization algorithm under 5G-based o...

引用

International Conference on Computer and Communications (ICCC)

作者： Yuye Lu Wei Zheng Xinghe Chu Zhaoming Lu Ruoqian Hu Meiling Li Beijing University of Posts and Telecommunications Beijing China Beijing Laboratory of Advanced Information Networks Beijing China Beijing Key Laboratory of Network System Architecture and Convergence Beijing China Taiyuan University of Science and Technology Taiyuan China

Indoor localization services are playing an important role in a variety of emerging industries. Traditional positioning methods suffer from insufficient accuracy or high deployment costs in indoor environments, and with the rapid development of cellular mobile communication systems, positioning under cellular networks has been more widely used due to its low cost and easy deployment. In the indoor environment, the number of available base stations is limited, and positioning by direct radius information provided by only one base station suffers from insufficient accuracy. In this paper, we designed a method for indoor localization based on cellular networks, which considering the localization information carried by the multi-path, to verify the performance of this algorithm in practical scene. We implement this algorithm in a 5G-based testbed based on software-defined radio (SDR) technologies. The results show that our algorithm can meet the requirements of indoor cases defined in 3GPP 38.855.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Precise Timing over Beyond 5G networks for Intelligent Transport in the Smart City

Precise Timing over Beyond 5G Networks for Intelligent Trans...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Hongxing Li Guochu Shou Yaqiong Liu Yihong Hu State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

The need for precise timing is increasing with the development of the smart city, and intelligent transport is a key application that often relies on the distribution of accurate timing. Existing time synchronization solutions cannot adequately meet the precise timing needs for practical applications in intelligent transportation. Global Navigation Satellite systems (GNSS) signals, for instance, can be obstructed, weakened, or deflected in urban canyon environments. While certain sectors like telecommunications and smart grids have successfully adopted IEEE 1588 for high-precision time synchronization, its dependence on standalone networks and limited application within local area networks poses challenges when catering to the wide-ranging and mobile demands of intelligent transportation applications. This paper categorizes the time synchronization requirements of intelligent transport and proposes a time synchronization scheme over converged networks, which separates time transmission and precision compensation based on software-defined networking (SDN) principles, and makes it possible to provide precise timing for intelligent transport devices, including on-board units (OBUs) and roadside units (RSUs), over wired and wireless communication networks. Experimental results indicate that the proposed scheme achieves a relative time error of less than 1.2 microseconds over the converged networks.

关键词： Wireless communication Global navigation satellite system Accuracy Smart cities Transportation Telecommunications Smart grids Synchronization Software defined networking Local area networks

来源：评论

学校读者我要写书评

暂无评论

Optimization of SVM and ANN Based on GAPA and Its Application in Short-Term Load Forecasting

Optimization of SVM and ANN Based on GAPA and Its Applicatio...

引用

IEEE International Conference on Energy Internet (ICEI)

作者： Jingyi Zhang Yueting Wang Wenpeng Jing Zhaoming Lu Xiangming Wen Yong Liu Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

Widespread employment of renewable energy such as wind and solar pushes power grids to move towards comprehensive data and predictive analysis. At present, a large number of researches have been conducted especially on machine learning methods to achieve load forecast. However, premature convergence and redundant iteration are two major defects of existing machine learning-based load forecasting methods, resulting in poor prediction effect and high time consumption. In this paper, a novel combined intelligent optimization algorithm based on genetic algorithm (GA), artificial fish swarm algorithm (AFSA) and particle swarm optimization (PSO) is proposed for optimizing machine learning-based load forecasting models. By replacing GA's mutation process with AFSA operator and PSO operator, the proposed algorithm named GA-AFSA-PSO Algorithm (GAPA) enhances both global search ability and local search ability, leading to its high prediction accuracy and fast convergence speed. To validate its effectiveness, GAPA is applied to the optimization of support vector machine (SVM) and artificial neural network (ANN) to predict one-day ahead load data. Moreover, two different sets of comparative tests are carried out to confirm the advantages of GAPA. The simulation results illustrate that, compared with GA, AFSA, PSO, AFSA-GA and GA-PSO, GAPA brings forth advancement in prediction accuracy, convergence rate and global search ability.

关键词： Support vector machines Machine learning algorithms Load forecasting Simulation Artificial neural networks Prediction algorithms Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Joint Source-Channel Coding for Wireless Image Transmission with Semantic Importance

Deep Joint Source-Channel Coding for Wireless Image Transmis...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Qizheng Sun Caili Guo Yang Yang Jiujiu Chen Rui Tang Chuanhong Liu Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665454698

The sixth-generation mobile communication system proposes the vision of smart interconnection of everything, which requires accomplishing communication tasks while ensuring the performance of intelligent tasks. A joint source-channel coding method based on semantic importance is proposed, which aims at preserving semantic information during wireless image transmission and thereby boosting the performance of intelligent tasks for images at the receiver. Specifically, we first propose semantic importance weight calculation method, which is based on the gradient of intelligent task’s perception results with respect to the features. Then, we design the semantic loss function in the way of using semantic weights to weight the features. Finally, we train the deep joint source-channel coding network using the semantic loss function. Experiment results demonstrate that the proposed method achieves up to 57.7% and 9.1% improvement in terms of intelligent task’s performance compared with the source-channel separation coding method and the deep source-channel joint coding method without considering semantics at the same compression rate and signal-to-noise ratio, respectively.

关键词： Wireless communication Vehicular and wireless technologies Image coding Image communication Semantics Receivers Encoding

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：