检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhou, Honghong Guo, Caili Zhang, Hao Wang, Yanjun Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Beijing Laboratory of Advanced Information Networks Beijing China China Telecom Dict Application Capability Center China

In spite of the great progress in human motion prediction, it is still a challenging task to predict those aperiodic and complicated motions. We believe that capturing the correlations among human body components is the key to understand the human motion. In this paper, we propose a novel multiscale graph convolution network (MGCN) to address this problem. Firstly, we design an adaptive multiscale interactional encoding module (MIEM) which is composed of two sub modules: scale transformation module (STM) and scale interaction module (SIM) to learn the human body correlations. Secondly, we apply a coarse-to-fine decoding strategy to decode the motions sequentially. We evaluate our approach on two standard benchmark datasets for human motion prediction: Human3.6M and CMU motion capture dataset. The experiments show that the proposed approach achieves the state-of-the-art performance for both short-term and long-term prediction especially in those complicated action category. We make codes publicly available at https://***/zhouhongh/MGCN. © 2021, CC BY-NC-ND.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Exploration of Simulation Teaching Mode for Intelligent Information Network Course

Exploration of Simulation Teaching Mode for Intelligent Info...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Yue He Hui Li Yiming Li Qiang Wu Yuefeng Ji Rentao Gu Shaobin Fan Beijing Laboratory of Advanced Information Networks Beijing University of Posts and Telecommunications (BUPT) Beijing China School of Information and Communication Engineering BUPT Beijing China Beijing Key Laboratory of Network System Architecture and Convergence BUPT Beijing China China Unicom China

With the rapid development of information technology, the society’s demand for information technology talents has become particularly high; how colleges and universities devote themselves to cultivating professional information technology talents is an important direction at present. However, the teacher’s evaluation method stays at the exam-oriented education. In the university education, in order to help students with basic professional knowledge to learn more professional knowledge and skills, and to help teachers understand the characteristics of students more objectively, this article discusses how to improve the existing teaching environment and simulation teaching mode. A simulation teaching platform for the “Intelligent Information Network” course is designed with multiple modules for complex network construction. Through the online network simulation teaching platform and the feedback obtained from the platform’s use, different students’ different problems can be found objectively, and the combination of theory and engineering, the combination of new and old knowledge, and the simplicity of complex software can be realized.

关键词： Knowledge engineering Education Complex networks Software Information technology

来源：评论

学校读者我要写书评

暂无评论

An Effective Routing Mechanism Based on Fuzzy Logic for Software-Defined Data Center networks

An Effective Routing Mechanism Based on Fuzzy Logic for Soft...

引用

International Conference on Computer and Communications (ICCC)

作者： Yang Xu Wu Muqing Yao Guohao Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

In order to solve the problem of low throughput and poor performance in data center network, this paper proposes a traffic scheduling algorithm exploiting fuzzy logic inference based on Software Defined Networking (SDN). The algorithm uses the characteristics of separation of control and forwarding in SDN architecture to choose paths for data flows by the centralized control of controller. It calculates the candidate path set of accessible paths between the source host and the destination host, then comprehensively considers path hops and bandwidth utilization, evaluates the candidate path using fuzzy logic model, and selects the optimal path. The experimental results show that compared with ECMP, Hedera and FSEM, the proposed algorithm improves the network throughput and load balancing, thus improving the overall network performance of the data center.

关键词： Fuzzy logic Data centers Scheduling algorithms Throughput Inference algorithms Software defined networking Load modeling

来源：评论

学校读者我要写书评

暂无评论

Explainable Semantic Communication for Text Tasks

arXiv

引用

arXiv 2023年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Ni, Wanli Zhou, Yanquan Li, Lei Quek, Tony Q.S. The Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China Department of Electronic Engineering Tsinghua University Beijing100084 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Dept. of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore

Task-oriented semantic communication has gained increasing attention due to its ability to reduce the amount of transmitted data without sacrificing task performance. Although some prior efforts have been dedicated to developing semantic communications, the semantics in these works remains to be unexplainable. Challenges related to explainable semantic representation and knowledge-based semantic compression have yet to be explored. In this paper, we propose a triplet-based explainable semantic communication (TESC) scheme for representing text semantics efficiently. Specifically, we develop a semantic extraction method to convert text into triplets while using syntactic dependency analysis to enhance semantic completeness. Then, we design a semantic filtering method to further compress the duplicate and task-irrelevant triplets based on prior knowledge. The filtered triplets are encoded and transmitted to the receiver for completing intelligent tasks. Furthermore, we apply the propsed TESC scheme to two emblematic text tasks: sentiment analysis and question answering, in which the semantic codec is meticulously customized for each task. Experimental results demonstrate that 1) TESC scheme outperforms benchmarks in terms of Top-1 accuracy and transmission efficiency, and 2) TESC scheme enjoys about 150% performance gain compared to the traditional communication method. Copyright © 2023, 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

Design and Performance Modeling of A YARN-based GPU Resource Scheduling system 5

Design and Performance Modeling of A YARN-based GPU Resource...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Huang, Jianbo Zhou, Wenli Song, Ruoning Liu, Fang Wang, Siye Liu, Jun Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Nformation Networks and Beijing Key Laboratory of Network System Architecture and Convergence Beijing China

ISBN: (纸本)9781728147437

The training of Deep Learning (DL) model can be accelerated significantly with Graphics Processing Unit (GPU). Accessing a server with GPUs attached and training model directly on it is the most common way of using GPUs, but this way may cause unbalanced load and low GPU utilization in multiple-server-multiple-application situation. This paper gives a mathematical definition of this problem and presents a YARN-based solution. Key of the solution is to build a resource scheduling platform with a customized Application Master (AM) optimized for DL. Performance model of the platform is also presented in this paper as well as the proof of higher GPU utilization. The benchmark of training ResNet on ImageNet shows that there is little performance degradation on platform. © 2019 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Recalibration with Advanced Geometry Constraints for 3D Human Pose Estimation

Multi-scale Recalibration with Advanced Geometry Constraints...

引用

International Conference on Computer and Communications (ICCC)

作者： Meng Xiao Hailun Xia Ziwei Xie Chunyan Feng Beijing Key Laboratory of Networks System Architecture and Convergence Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

Estimating 3D human poses from a single RGB image is a challenging task in computer vision due to depth ambiguity and lack of unconstrained 3D datasets. Poor exploiting of image cues will lead to inaccurate pose predictions. Previous works try to constrain illegal spatial relations and exploit 2D annotations of in-the-wild images as weak labels. In this paper, we propose to use multi-scale recalibration with stronger geometry constraints to regress 3D pose. The overall network is end-to-end which consists of a 2D pose estimation sub-network and a depth regression subnetwork. Firstly, by adding the residual multi-scale recalibration module to the depth regression sub-network, our approach works better on exploiting the structural information of human poses. Secondly, the advanced geometry constraints are introduced to restrict the human pose from the bone length and joint angle orientation, which shows a better result. Experimental results on the Human3.6m and in-the-wild MPII datasets show the effectiveness and robustness of our method.

关键词： Geometry Three-dimensional displays Pose estimation Two dimensional displays Robustness Task analysis Videos

来源：评论

学校读者我要写书评

暂无评论

MultiModal, Robust and Accurate Hand Tracking

MultiModal, Robust and Accurate Hand Tracking

引用

International Conference on Computer and Communications (ICCC)

作者： Tianyang Zhang Hailun Xia Changjian Zhang Zhimin Zeng Beijing Key Laboratory of Networks System Architecture and Convergence Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

3D hand tracking has a wide application prospect, for instance, in the field of human-computer interaction. Existing generative methods based on model fitting typically obtain good accuracy, but are far less robust to rapid hand motions and gestures with self-occlusions. We thus present a multimodal hand tracking system aiming to boost both accuracy and robustness. An efficient initialization strategy based on image data and inertial sensor data is designed to improve the robustness. A new optimization algorithm is proposed to improve the accuracy further by introducing gradient descent into APSO (Adaptive Particle Swarm Optimization). In addition, we construct a cylinder-cuboid hand model and establish a corresponding cost function. The proposed hand tracking method is evaluated on MSRA14 Dataset and achieves the state-of-the-art result.

关键词： Human computer interaction Three-dimensional displays Tracking Inertial sensors Fitting Robustness Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A Survey on Indoor Visible Light Positioning systems: Fundamentals, Applications, and Challenges

arXiv

引用

arXiv 2024年

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang The Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Faculty of Applied Science School of Engineering The University of British Columbia KelownaBCV1V 1V7 Canada The Chinese University of Hong Kong Shenzhen518172 China

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Virtual Network Embedding Based on Hybrid Adaptive Genetic Algorithm 5

Virtual Network Embedding Based on Hybrid Adaptive Genetic A...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： Boyang, Liu Muqing, Wu Haosen, Zou Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing100876 China

ISBN: (纸本)9781728147437

Virtual network embedding (VNE) is one of the central parts of network virtualization, and its main objective is to maximize the revenue of substrate networks(SN). In the previous studies, heuristic algorithms are widely used to solve the embedding problems, but they are liable to trap in local optimum. In addition, they also have slow convergence rates which are caused by ignoring the intrinsic characteristics of the VNE. In this paper, on the first hand, we improve the cross operator of traditional genetic algorithm (GA) to an adaptive cross operator, in order to increase the convergence speed;on the other hand, a simulated annealing algorithm is used to replace the mutation operation, and the simulated annealing idea is adopted to modify the selection operation to avoid the local optimization. The simulation results show that the proposed algorithm has a significant improvement in the VNE acceptance rate and the revenue-to-cost ratio. © 2019 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

An LSTM Acceleration Engine for FPGAs Based on Caffe Framework 5

An LSTM Acceleration Engine for FPGAs Based on Caffe Framewo...

引用

5th IEEE International Conference on Computer and Communications, ICCC 2019

作者： He, Junhua He, Dazhong Yang, Yang Liu, Jun Yang, Jie Wang, Siye Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Network System Architecture and Convergence Beijing100876 China

ISBN: (纸本)9781728147437

Recently, Long Short Term Memory (LSTM) networks have been widely used in sequence-related problem. LSTMs outperform conventional feed-forward neural networks and RNNs in many ways, since they remember patterns selectively for long durations of time. However, due to the recurrent property of LSTMs, it is hard to implement a high computing parallelism on general processors such as CPUs and GPUs. Besides, the huge energy consumption of GPU and CPU computing is a non-negligible issue for data centers. In order to solve the problems above, FPGA emerges as an ideal solution. It has the characteristics of low power and latency, which has natural advantages for the implementation of recurrent neural networks, such as LSTMs. In this paper, we propose to implement an acceleration engine for LSTM network based on FPGAs. By employing fixed-point arithmetic, systolic arrays for matrix multiplication and look up table for activate function, we optimize the LSTM on FPGA in depth. Additionally, we integrate the acceleration engine into Caffe, one of the most popular deep learning framework, to make it easier to deploy. According to the experimental results, our acceleration engine achieves 8.8X and 2.2X gains for performance, 16.9X and 9.6X gains for energy efficiency compared with CPU and GPU, respectively. © 2019 IEEE.

关键词： Field programmable gate arrays (FPGA)

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：