检索结果-内蒙古大学图书馆

IEEE International Conference on Web Services (IEEE ICWS)

作者： Yang, Lipei Zhou, Ao Ma, Xiao Zhang, Yiran Li, Yuanzhe Wang, Shangguang Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350368567;9798350368550

Edge computing plays a pivotal role in supporting services necessitating sub-second latency, notably in domains like Industry 4.0 and autonomous driving. However, unpredictable failure occurring at edge servers can result in prolonged response time and decreased service reliability, posing significant risks to both safety and property. Traditional reliability mechanisms, namely re-execution and replication, are often inadequate for edge environments, with the former often struggle to meet latency requirements and the latter imposing a high resource consumption burden on resource-limited edge clouds. To address this issue, this paper introduces a novel "Flexible Shadow" mechanism, where the backup instance, referred to as the "Flexible Shadow", is allocated fewer computation resources compared to its primary instance to conserve computation resources, and temporally preempts a portion of resources from neighboring shadows to accelerate when necessary. To tackle the implementation challenges of this framework arising from diverse service requirements, dynamic nature of edge environments and potential deadlock in the reconfiguration process, we devised the Flexible Shadow Deployment Algorithm for accurate shadow deployment and the Flexible Shadow Reconfiguration Algorithm for dynamic strategy adjustment. We have implemented our Flexible Shadow framework on Docker and evaluated it via comprehensive experiments. The experiment results demonstrate a nearly 60% reduction in computing resource consumption while ensuring sub-second latency.

关键词： Edge computing reliability task replication

来源：评论

学校读者我要写书评

暂无评论

A Semantic Communication System for Point Cloud

引用

IEEE TRANSACTIONS ON VEHICULAR technology 2025年第1期74卷 894-910页

作者： Liu, Xiaoyi Liang, Haotai Bao, Zhicheng Dong, Chen Xu, Xiaodong Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Peng Cheng Lab Dept Broadband Commun Shenzhen 518066 Peoples R China

Point cloud, as a 3D representation, finds wide applications in domains such as autonomous driving, virtual reality (VR), and augmented reality (AR). However, traditional communication systems are not well-suited for large-scale point cloud data transmissions, as such systems operate at the bit level without leveraging the inherent semantic information of the point cloud. This paper introduces a point cloud-based semantic communication system (PCSC) that leverages AI-based encoding techniques to extract semantic information from the point cloud. Furthermore, joint source-channel coding (JSCC) technology is employed to overcome noise channel distortion and address the "cliff effect" prevalent in traditional communication methods. Additionally, the proposed system achieves controllable coding rates without requiring extensive network fine-tuning. By analyzing the significance of the encoded semantic vector, the method discards semantically-unimportant information, enhancing transmission efficiency. Moreover, the PCSC is integrated with the recently proposed model division multiple access (MDMA) technology, resulting in a multi-user point cloud MDMA transmission system (M-PCSC). Experimental results demonstrate that the proposed method surpasses traditional approaches by 10 dB under the PSNR D1 and PSNR D2 metrics while effectively mitigating the "cliff effect" in transmission.

关键词： Semantics Point cloud compression Communication systems Physical layer Feature extraction Data mining Wireless communication Semantic communications point cloud transmission controllable coding rate model division multiple access

来源：评论

学校读者我要写书评

暂无评论

Efficient Throughput and Loop-Free Routing: An Adaptive Second-Order Backpressure Algorithm

Efficient Throughput and Loop-Free Routing: An Adaptive Seco...

引用

IEEE Conference on Computer Communications (IEEE INFOCOM)

作者： Yin, Yuexi Zhuang, Zirui Wang, Jingyu Qi, Qi Sun, Haifeng Fu, Xiaoyuan Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350384482;9798350384475

The backpressure routing method offers a dynamic resource allocation approach that achieves optimal throughput. However, the method's sole dependence on the first-order backlog difference between nodes leads to poor convergence and may result in unnecessarily long paths, potentially causing loops when unrestricted. In this work, we address both transmission cost and computational complexity concerns. We introduce a second-order backpressure algorithm (SBP) featuring adaptive shortest routing, a second-order backlog metric, and a two-level queue mapping structure. We validate this novel backlog metric through Lyapunov optimization techniques. Simulation results demonstrate that while ensuring throughput, our approach effectively reduces end-to-end delay and eliminates routing loops without imposing specific constraints.

关键词： Backpressure routing Delay reduction Queueing Lyapunov optimization

来源：评论

学校读者我要写书评

暂无评论

Safeguarding Sustainable Cities: Unsupervised Video Anomaly Detection through Diffusion-based Latent Pattern Learning 33

Safeguarding Sustainable Cities: Unsupervised Video Anomaly ...

引用

33rd International Joint Conference on Artificial Intelligence (IJCAI)

作者： Zhang, Menghao Wang, Jingyu Qi, Qi Ren, Pengfei Sun, Haifeng Zhuang, Zirui Zhang, Lei Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9781956792041

Sustainable cities requires high-quality community management and surveillance analytics, which are supported by video anomaly detection techniques. However, mainstream video anomaly detection techniques still require manually labeled data and do not apply to real-world massive videos. Without labeling, unsupervised video anomaly detection (UVAD) is challenged by the problem of pseudo-labeled noise and the openness of anomaly detection. In response, a diffusion-based latent pattern learning UVAD framework is proposed, called DiffVAD. The method learns potential patterns by generating different patterns of the same event through diffusion models. The detection of anomalies is realized by evaluating the pattern distribution. The different patterns of normal events are diverse but correlated, while the different patterns of abnormal events are more diffuse. This manner of detection is equally effective for unseen normal events in the training set. In addition, we design a refinement strategy for pseudo-labels to mitigate the effects of the noise problem. Extensive experiments on six benchmark datasets demonstrate the design's promising generalization ability and high efficiency. Specifically, DiffVAD obtains an AUC score of 81.9% on the ShanghaiTech dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fair Communication Resource Scheduling in 6G and Digital Twin-Driven Virtual Power Plants

Fair Communication Resource Scheduling in 6G and Digital Twi...

引用

IEEE/CIC International Conference on Communications in China (ICCC)

作者： Liu, Xiao Yu, Peng Fang, Honglin Tan, Can Zhou, Fanqin Li, Wenjing Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350377675;9798350377682

A virtual power plant (VPP) is a technology and management system that integrates distributed energy resources, offering significant advantages for the access and management of these distributed energy resources. With the development of distributed energy, higher requirements are being placed on the communication resource scheduling capabilities of virtual power plants. For dense source-load-storage devices, the high bandwidth, low latency, and high energy efficiency characteristics of 6G networks can meet the control requirements of virtual power plants for these devices. Digital twins are currently widely used in the industrial sector, providing positive effects such as real-time monitoring, prediction, and performance optimization. Applying digital twins to the communication resource scheduling of virtual power plants enables real-time perception of resource allocation and timely resource scheduling. This paper proposes a communication resource scheduling algorithm based on deep reinforcement learning, leveraging digital twin technology and the 6G distributed subnet architecture. This algorithm aims to efficiently utilize limited resources such as resource blocks, spectrum, and power to balance system throughput, fairness, and scheduling latency, thereby ensuring the QoS of source-load-storage device scheduling tasks. Simulation results demonstrate that the proposed resource scheduling algorithm enhances system throughput and fairness while meeting scheduling latency requirements, thereby satisfying the QoS needs of scheduling tasks.

关键词： virtual power plants Digital Twin channel resource scheduling power allocation 6G deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Tile-Based Adaptive Streaming for 360-Degree Video-on-Demand Systems 24

Efficient Tile-Based Adaptive Streaming for 360-Degree Video...

引用

15th ACM Multimedia Systems Conference (ACM MMSys)

作者： Sheng, Daoxu Gao, Baoqi Liu, Guangtian Qi, Qi Wang, Jingyu Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798400704123

In the field of 360-degree video streaming, the optimization of visual quality within the viewer's field of view, alongside the minimization of system resource consumption, is a critical concern. The considerable file sizes associated with high-quality 360-degree videos pose significant challenges for efficient transmission. Current strategies primarily employ a tile-based approach to address these issues. However, these approaches face two core challenges: the methodology for tile segmentation, and the strategy for downloading tiles. To address these challenges, this paper presents a tile-based solution designed specifically for adaptive 360-degree video-on-demand streaming. Our method surpasses baseline methods in extensive simulations, positioning it as one of the leading solutions in the MMSys'24 Grand Challenge.

关键词： 360-degree video tile-based adaptive streaming viewport adaptation quality of experience

来源：评论

学校读者我要写书评

暂无评论

A Multi-Slot Load Balancing Scheme for LEO Satellite Communication Handover Target Selection 25

A Multi-Slot Load Balancing Scheme for LEO Satellite Communi...

引用

IEEE Wireless Communications and networking Conference (IEEE WCNC)

作者： Chen, Hongrui Nie, Gaofeng Tian, Hui Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350303582;9798350303599

The Low-Earth-Orbit (LEO) constellation has emerged as a promising component for seamless and fast global connectivity. With the increasing number of satellites in LEO constellations, multiple satellites can simultaneously cover the same geographical area. The selection of a user's handover (HO) target can significantly impact the quality of service (QoS) for communication and the load status of the satellite network. Motivated by this, the paper introduces a multi-slot load balancing (MSLB) scheme to offer users HO target selection strategies. An optimization problem is formulated to determine the HO sequence for users according to the MSLB scheme. Subsequently, a HO sequence graph mapping (HSGM) algorithm and an iterative shortest path solving (ISPS) algorithm are developed to address this optimization problem by transforming it into a shortest path searching problem. Simulation results demonstrate that, in comparison to traditional single-slot schemes, the MSLB scheme exhibits superior performance in load balancing and improving user communication QoS.

关键词： LEO QoS load multi-slot handover

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning

Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhang, Menghao Wang, Jingyu Qi, Qi Sun, Haifeng Zhuang, Zirui Ren, Pengfei Ma, Ruilong Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9798350353006

Recent progress in video anomaly detection suggests that the features of appearance and motion play crucial roles in distinguishing abnormal patterns from normal ones. However, we note that the effect of spatial scales of anomalies is ignored. The fact that many abnormal events occur in limited localized regions and severe background noise interferes with the learning of anomalous changes. Mean-while, most existing methods are limited by coarse-grained modeling approaches, which are inadequate for learning highly discriminative features to discriminate subtle differences between small-scale anomalies and normal patterns. To this end, this paper address multi-scale video anomaly detection by multi-grained spatio-temporal representation learning. We utilize video continuity to design three proxy tasks to perform feature learning at both coarse-grained and fine-grained levels, i.e., continuity judgment, discontinuity localization, and missing frame estimation. In particular, we formulate missing frame estimation as a contrastive learning task in feature space instead of a reconstruction task in RGB space to learn highly discriminative features. Experiments show that our proposed method outperforms state-of-the-art methods on four datasets, especially in scenes with small-scale anomalies.

关键词： representation learning video anomaly detection

来源：评论

学校读者我要写书评

暂无评论

FedIDE: Federated Semi-Supervised Learning With Instance Discrimination & LocalEMA 59

FedIDE: Federated Semi-Supervised Learning With Instance Dis...

引用

59th Annual IEEE International Conference on Communications (IEEE ICC)

作者： Gao, Zhipeng Niu, Shaolong Zhao, Chen Yang, Yang Beijing Univ Posts & Telecommun State Key Lab Switching & Networking Technol Beijing Peoples R China

ISBN: (纸本)9781728190549

Federated Learning is a promising paradigm, offering advantages such as access to extensive datasets and robust data privacy preservation. However, a notable challenge arises from the predominant reliance of most federated learning algorithms on labeled data for model training, leaving a limited presence of algorithms capable of effectively utilizing unlabeled data. In real-world scenarios, individuals using electronic devices inadvertently generate copious volumes of unlabeled data, often accompanied by a small fraction of labeled data. This wealth of unlabeled data harbors valuable information, underscoring the importance of developing high-quality federated semi-supervised learning algorithms adept at harnessing both labeled and unlabeled data. This paper introduces FedIDE, an advanced federated semi-supervised learning algorithm. Our approach integrates the principles of pseudo-labeling and instance discrimination, drawing inspiration from contrastive learning, to unlock the potential of unlabeled data. Concurrently, supervised learning is applied to a labeled dataset to enhance model performance. Additionally, we design the LocalEMA local model update algorithm, which amalgamates local and global models during local training, yielding a hybrid model. FedIDE undergoes extensive testing across multiple datasets, surpassing state-of-the-art baselines.

关键词： federated learning semi-supervised learning pseudo labeling contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Device Performance Anomaly Detection Method Based on Graph Convolutional Neural Network 13th

Device Performance Anomaly Detection Method Based on Graph C...

引用

13th International Conference on Computer Engineering and Networks (CENet)

作者： Liu, Aolun Yang, Yang Guo, Yanpeng Gao, Zhipeng Rui, Lanlan Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9789819992454;9789819992430;9789819992423

In this article, we discuss the key task of equipment anomaly detection, which is a major challenge in modern industrial and technological fields. We propose a new deep learning framework, which is based on Long short-term memory neural network and graph convolutional neural network. By fully capturing the spatio-temporal characteristics of equipment performance data, we can capture the complex dependencies and interactions among various indicators, which are often difficult to deal with by traditional Feature engineering methods. In addition, to improve the accuracy of anomaly detection, we have also introduced storage modules and data-driven adaptive threshold strategies. This strategy dynamically adjusts the anomaly threshold based on the real-time state of the system, improving the performance of our method in dynamic environments. Our research provides new insights and tools for device anomaly detection, and the effectiveness of our proposed method has been proven through multiple comparative experiments.

关键词： Anomaly detection Graph convolutional neural networks Time series analysis Data-driven adaptive threshold

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：