检索结果-内蒙古大学图书馆

2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, BMSB 2023

作者： Li, Shiwei Tan, Fangqing Liu, Qiang Guilin University of Electronic Technology Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin China Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao China

ISBN: (纸本)9798350321524

Combining cell-free massive multiple-input multiple-output (CF-mMIMO) and mobile edge computing (MEC) facilitates the processing of compute-intensive and latency-sensitive tasks in the distributed IoT. For MEC-enabled CF-mMIMO system, this paper designs a task offloading strategy for local computing and multi-access points (APs) collaboration. Under energy constraints, we aim to minimize the latency of computing offloading. According to the different data size of each user and the service of APs, the graph neural network method is adopted to deal with the link prediction between the user and APs. © 2023 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

DMAP: a distributed Morphological Attention Policy for Learning to Locomote with a Changing Body 36

DMAP: a Distributed Morphological Attention Policy for Learn...

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Chiappa, Alberto Silvio Vargas, Alessandro Marin Mathis, Alexander Ecole Polytech Fed Lausanne CH-1015 Lausanne Switzerland

ISBN: (纸本)9781713871088

Biological and artificial agents need to deal with constant changes in the real world. We study this problem in four classical continuous control environments, augmented with morphological perturbations. Learning to locomote when the length and the thickness of different body parts vary is challenging, as the control policy is required to adapt to the morphology to successfully balance and advance the agent. We show that a control policy based on the proprioceptive state performs poorly with highly variable body configurations, while an (oracle) agent with access to a learned encoding of the perturbation performs significantly better. We introduce DMAP, a biologically-inspired, attention-based policy network architecture. DMAP combines independent proprioceptive processing, a distributed policy with individual controllers for each joint, and an attention mechanism, to dynamically gate sensory information from different body parts to different controllers. Despite not having access to the (hidden) morphology information, DMAP can be trained end-to-end in all the considered environments, overall matching or surpassing the performance of an oracle agent. Thus DMAP, implementing principles from biological motor control, provides a strong inductive bias for learning challenging sensorimotor tasks. Overall, our work corroborates the power of these principles in challenging locomotion tasks. The code is available at the following link: DMAP

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence-Based Safety-as-a-Service Platform for Social IoV Environment

Edge Intelligence-Based Safety-as-a-Service Platform for Soc...

引用

IEEE International Conference on Communications (IEEE ICC)

作者： Pradhan, Patrali Roy, Chandana Misra, Sudip Chattopadhyay, Samiran Haldia Inst Technol Dept Comp Sci & Engn Haldia India Indian Inst Technol Dept Comp Sci & Engn Kharagpur W Bengal India Jadavpur Univ Dept Informat Technol Kolkata India

ISBN: (纸本)9781538674628

In this work, we introduce an edge intelligence layer into the traditional Safety-as-a-Service (Safe-aaS) platform for Social Internet of Vehicles (SIoV) networks, to minimize the network latency incurred in delivery of decisions. The prior announcement of safety-related information in social IoV environment, minimizes the rate of accidents to a significant extent. Safe-aaS provides customized safety-related decisions dynamically to the end-users. On the other hand, the timely delivery of accurate decisions to the end-users in a social IoV network is a challenging task. We introduce the concept of edge servers in the edge layer of Safe-aaS, such that the bandwidth required for uploading data is minimized, and the problems associated with processing, storage, and complex analysis of data are eliminated. We apply Artificial neural network (ANN) at the edge nodes to select the appropriate edge server and fuzzy logic at the edge server side for the generation of a decision. Here social entities are not humans rather vehicles, distributed edge servers and cloud servers all are acting as intelligent objects. Extensive simulation of our proposed architecture demonstrates that the computing density of edge servers is normally distributed. Additionally, we analyze the classification of the edge servers using training data obtained from the edge nodes and network is tested with the test dataset. We apply fuzzified decision is generated method at the edge sever. Extensive simulation results demonstrate that the delay incurred in delivery of decision is reduced by 90:58%, after introduction of edge intelligence layer.

关键词： Safety-as-a-Service Social IoV (SIoV) Edge Intelligence Ultra-low latency Decision Virtualization Artificial neural network (ANN)

来源：评论

学校读者我要写书评

暂无评论

Delay-Aware Backpressure Routing Using Graph neural networks 48

Delay-Aware Backpressure Routing Using Graph Neural Networks

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Zhao, Zhongyuan Radojicic, Bojan Verma, Gunjan Swami, Ananthram Segarra, Santiago Rice University United States University of Novi Sad Serbia Us Army's Devcom Army Research Laboratory United States

ISBN: (纸本)9781728163277

We propose a throughput-optimal biased backpressure (BP) algorithm for routing, where the bias is learned through a graph neural network that seeks to minimize end-to-end delay. Classical BP routing provides a simple yet powerful distributed solution for resource allocation in wireless multi-hop networks but has poor delay performance. A low-cost approach to improve this delay performance is to favor shorter paths by incorporating pre-defined biases in the BP computation, such as a bias based on the shortest path (hop) distance to the destination. In this work, we improve upon the widely-used metric of hop distance (and its variants) for the shortest path bias by introducing a bias based on the link duty cycle, which we predict using a graph convolutional neural network. Numerical results show that our approach can improve the delay performance compared to classical BP and existing BP alternatives based on pre-defined bias while being adaptive to interference density. In terms of complexity, our distributed implementation only introduces a one-time overhead (linear in the number of devices in the network) compared to classical BP, and a constant overhead compared to the lowest-complexity existing bias-based BP algorithms. © 2023 IEEE.

关键词： Backpressure routing bias graph neural networks independent set scheduling duty cycle shortest path

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Real-Time Federated Learning for Anomaly Detection in Microservice Cloud Applications

IEEE TRANSACTIONS ON MACHINE LEARNING IN COMMUNICATIONS AND ...

引用

IEEE TRANSACTIONS ON MACHINE LEARNING IN COMMUNICATIONS AND networkING 2025年 3卷 176-194页

作者： Raeiszadeh, Mahsa Ebrahimzadeh, Amin Glitho, Roch H. Eker, Johan Mini, Raquel A. F. Concordia Univ CIISE Montreal PQ H3G 1M8 Canada Ericsson Res S-22362 Lund Sweden

The complexity and dynamicity of microservice architectures in cloud environments present substantial challenges to the reliability and availability of the services built on these architectures. Therefore, effective anomaly detection is crucial to prevent impending failures and resolve them promptly. distributed data analysis techniques based on machine learning (ML) have recently gained attention in detecting anomalies in microservice systems. ML-based anomaly detection techniques mostly require centralized data collection and processing, which may raise scalability and computational issues in practice. In this paper, we propose an Asynchronous Real-Time Federated Learning (ART-FL) approach for anomaly detection in cloud-based microservice systems. In our approach, edge clients perform real-time learning with continuous streaming local data. At the edge clients, we model intra-service behaviors and inter-service dependencies in multi-source distributed data based on a Span Causal Graph (SCG) representation and train a model through a combination of Graph neural network (GNN) and Positive and Unlabeled (PU) learning. Our FL approach updates the global model in an asynchronous manner to achieve accurate and efficient anomaly detection, addressing computational overhead across diverse edge clients, including those that experience delays. Our trace-driven evaluations indicate that the proposed method outperforms the state-of-the-art anomaly detection methods by 4% in terms of F-1 -score while meeting the given time efficiency and scalability requirements.

关键词： Microservice architectures Anomaly detection Real-time systems Computational modeling Machine learning Data models Computer architecture Image edge detection Federated learning Servers distributed data federated learning microservice trace

来源：评论

学校读者我要写书评

暂无评论

distributed optical fibre sensor for condition monitoring of mining conveyor using wavelet transform and artificial neural network

引用

STRUCTURAL CONTROL & HEALTH MONITORING 2021年第11期28卷 e2827-e2827页

作者： Wijaya, Hendrik Rajeev, Pathmanathan Gad, Emad Vivekanamtham, Ravi Swinburne Univ Technol Dept Civil & Construct Engn Melbourne Vic 3122 Australia Hawk Measurement Syst Engn & R&D Div Melbourne Vic Australia

Condition monitoring of mining conveyors is highly essential, not only to reduce economic loss due to sudden component breakdown but also to prevent safety risks to maintenance personnel. The vibration measurement by means of distributed Optical Fibre Sensors (DOFS) is a potential solution to provide cost-effective real-time monitoring of mining conveyors. However, an effective application of detecting early damage and damage progression mainly depends on collection quality of optical signal and robust signal processing methods. Therefore, this study focuses on the identification of an effective signal processing method for real-time monitoring of mining conveyor systems. A prototype conveyor system with various levels of idler damages was built to run experimental tests and to collect optical signals for further analysis. A wavelet-based damage detection method is proposed, and its efficiency is evaluated. Additionally, Artificial neural network (ANN) is integrated to develop a smart fault detection technology for fast detection and damage classification. The proposed method has 99% accuracy in classify damage condition under varying coveyor operating speed.

关键词： acoustic damage detection real-time monitoring signal processing vibration

来源：评论

学校读者我要写书评

暂无评论

TurboMGNN: Improving Concurrent GNN Training Tasks on GPU With Fine-Grained Kernel Fusion

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第6期34卷 1968-1981页

作者： Wu, Wenchao Shi, Xuanhua He, Ligang Jin, Hai Huazhong Univ Sci & Technol Natl Engn Res Ctr Big Data Technol & Syst Sch Comp Sci & Technol Serv Comp TechnolCluster & Grid Comp Lab Wuhan 430074 Peoples R China Univ Warwick Dept Comp Sci Coventry CV4 7AL England

Graph neural networks (GNN) have evolved as powerful models for graph representation learning. Many works have been proposed to support GNN training efficiently on GPU. However, these works only focus on a single GNN training task such as operator optimization, task scheduling, and programming model. Concurrent GNN training, which is needed in the applications such as neural network structure search, has not been explored yet. This work aims to improve the training efficiency of the concurrent GNN training tasks on GPU by developing fine-grained methods to fuse the kernels from different tasks. Specifically, we propose a fine-grained Sparse Matrix Multiplication (SpMM) based kernel fusion method to eliminate redundant accesses to graph data. In order to increase the fusion opportunity and reduce the synchronization cost, we further propose a novel technique to enable the fusion of the kernels in forward and backward propagation. Finally, in order to reduce the resource contention caused by the increased number of concurrent, heterogeneous GNN training tasks, we propose an adaptive strategy to group the tasks and match their operators according to resource contention. We have conducted extensive experiments, including kernel- and model-level benchmarks. The results show that the proposed methods can achieve up to 2.6X performance speedup.

关键词： Task analysis Training Graphics processing units Kernel Graph neural networks Computational modeling Fuses GNN training concurrent multi-tasks GPU kernel fusion

来源：评论

学校读者我要写书评

暂无评论

Image stitching tampering detection in social networks 22

Image stitching tampering detection in social networks

引用

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Zhang, Jin Sa, RuLa An, Qi Gao, QiaoMei Pang, Xiliang Yu, Meiju Inner Mongolia University School of Computer Science Hohhot China

ISBN: (纸本)9798331509712

Social media, with its immediacy and convenience, has become an important channel for people to exchange information. However, this freedom of information dissemination also provides a breeding ground for the spread of disinformation. Because the image will inevitably leave traces in the process of tampering and compression. Therefore, this paper proposes a convolutional neural network model SE-CNN, which, combined with the SE attention module, designs two inputs, on the one hand accepting the original image and on the other hand converting the image into error Level Analysis (ELA) format. The open source dataset CASIA V1.0 was selected for testing in this article. The experimental results show that the accuracy of this model on this dataset is 99.22%, which has stronger generalization ability than the traditional CNN model. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ethereum Phishing Detection Using Hyperbolic neural networks and Temporal Information 22

Ethereum Phishing Detection Using Hyperbolic Neural Networks...

引用

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Xu, Rong Zhang, Jun Zhu, Xiaoyue Song, Zhaoxiong Yu, Zhi Inner Mongolia University College of Computer Science Hohhot China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331509712

In recent years, the frequent occurrence of phishing scams on Ethereum has posed serious threats to transaction security and the financial safety of users. This paper proposes an Ethereum phishing scam detection method based on Hyperbolic neural networks (HGNNs) and temporal information. The method maps the Ethereum transaction network to hyperbolic space for structural feature extraction, effectively capturing hierarchical structures and complex relationships within the graph, thereby improving the accuracy of phishing scam detection. The model includes a structural feature extraction module and a temporal feature extraction module. It uses HGNN and self-attention mechanism to extract the structural features of the transaction graph, and uses a multi-head attention mechanism to capture the dynamic evolution pattern of the graph. Experimental validation on real Ethereum datasets demonstrates that the proposed model outperforms benchmark models, showcasing its effectiveness. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

A Point Cloud Video Recognition Acceleration Framework Based on Tempo-Spatial Information

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2023年第12期34卷 3224-3237页

作者： Song, Zhuoran Liu, Wanzhen Yang, Tao Liu, Fangxin Jing, Naifeng Liang, Xiaoyao Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai Peoples R China Huawei Technol Co Ltd Shenzhen 518129 Peoples R China

In point cloud video recognition (PVR) tasks, deep neural networks (DNNs) have been widely adopted to enhance accuracy. However, real-time processing is hindered due to the increasing volume of points and frames that require processes. Point clouds represent 3D-shaped discrete objects using a multitude of points. Consequently, these points often exhibit an uneven distribution in the view space, resulting in strong spatial similarity within each point cloud frame. Taking advantage of this observation, this article introduces PRADA, a Point Cloud Recognition Acceleration algorithm via Dynamic Approximation. PRADA approximates and eliminates the similar local pairs' computations and recovers their results by copying dissimilar local pairs' features for speedup with negligible accuracy loss. Furthermore, considering the slow changes in point cloud frames that lead to the high temporal similarity among points across multiple frames, we design PointV, a Point Cloud Video Recognition Acceleration algorithm, to minimize unnecessary computations of similar points in the temporal domain. Moreover, we propose the PRADA and PointV architectures to accelerate the PRADA and PointV algorithms. These two architectures can be integrated to gain higher performance improvement. Our experiments on a wide variety of datasets show that PRADA averagely achieves about 7 x speedup over 1080TI GPU. In addition, the experimental results show that the PointV architecture and the integrated architecture can respectively achieve 11.7x and 13.9x performance improvement with acceptable accuracy compared to the 1080TI GPU.

关键词： Point cloud compression Task analysis Heuristic algorithms Streaming media Computer architecture Approximation algorithms Artificial neural networks Point cloud video recognition task deep neural network acceleration tempo-spatial information accelerator

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：