检索结果-南通市图书馆

Transformer-Aided Deep Double Dueling Spatial-Temporal Q-Network for Spatial Crowdsourcing Analysis

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第4期139卷 893-909页

作者： Yu Li Mingxiao Li Dongyang Ou Junjie Guo Fangyuan Pan department of computing Hangzhou Dianzi UniversityHangzhou310018China

With the rapid development ofmobile Internet,spatial crowdsourcing has becomemore andmore *** crowdsourcing consists of many different types of applications,such as spatial crowd-sensing *** terms of spatial crowd-sensing,it collects and analyzes traffic sensing data from clients like vehicles and traffic lights to construct intelligent traffic prediction *** collecting sensing data,spatial crowdsourcing also includes spatial delivery services like DiDi and *** task assignment and worker selection dominate the service quality for spatial crowdsourcing *** research conducted task assignments via traditional matching approaches or using simple network ***,advanced mining methods are lacking to explore the relationship between workers,task publishers,and the spatio-temporal attributes in ***,in this paper,we propose a Deep Double Dueling Spatial-temporal Q Network(D3SQN)to adaptively learn the spatialtemporal relationship between task,task publishers,and workers in a dynamic environment to achieve optimal ***,D3SQNis revised through reinforcement learning by adding a spatial-temporal transformer that can estimate the expected state values and action advantages so as to improve the accuracy of task *** experiments are conducted over real data collected fromDiDi and ELM,and the simulation results verify the effectiveness of our proposed models.

关键词： Historical behavior analysis spatial crowdsourcing deep double dueling Q-networks

A hybrid memory architecture supporting fine-grained data migration

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第2期18卷 31-41页

作者： Ye CHI Jianhui YUE Xiaofei LIAO Haikun LIU Hai JIN National Engineering research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China department of Computer Science Michigan Technological UniversityMichigan 49931USA

Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually migrate data at a granularity of 4 KB pages,and thus waste memory bandwidth and DRAM *** this paper,we propose Mocha,a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically,but manages them in a cache/memory *** the commercial NVM device-Intel Optane DC Persistent Memory Modules(DCPMM)actually access the physical media at a granularity of 256 bytes(an Optane block),we manage the DRAM cache at the 256-byte size to adapt to this feature of *** design not only enables fine-grained data migration and management for the DRAM cache,but also avoids write amplification for Intel Optane *** also create an Indirect Address Cache(IAC)in Hybrid Memory Controller(HMC)and propose a reverse address mapping table in the DRAM to speed up address translation and cache ***,we exploit a utility-based caching mechanism to filter cold blocks in the NVM,and further improve the efficiency of the DRAM *** implement Mocha in an architectural *** results show that Mocha can improve application performance by 8.2%on average(up to 24.6%),reduce 6.9%energy consumption and 25.9%data migration traffic on average,compared with a typical hybrid memory architecture-HSCC.

关键词： non-volatile memory hybrid memory system data migration fine-grained caching

Plotinus:A Satellite Internet Digital Twin System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Communications and Information Networks 2024年第1期9卷 24-33页

作者： Yue Gao Kun Qiu Zhe Chen Wenjun Zhu Qi Zhang Handong Luo Quanwei Lin Ziheng Yang Wenhao Liu The Intelligent Networking and computing research Center and School of Computer Science Fudan UniversityShanghai 200433China

The development of space-air-ground integrated networks (SAGIN) requires sophisticated satellite Internet emulation tools that can handle complex, dynamic topologies and offer in-depth analysis. Existing emulation platforms struggle with challenges like the need for detailed implementation across all network layers, real-time response, and scalability. This paper proposes a digital twin system based on microservices for satellite Internet emulation,namely Plotinus,which aims to solve these problems. Plotinus features a modular design, allowing for easy replacement of the physical layer to emulate different aerial vehicles and analyze channel interference. It also enables replacing of path computation methods to simplify testing and deploying algorithms. In particular, Plotinus allows for real-time emulation with live network traffic,enhancing practical network models. The evaluation result shows Plotinus’s effective emulation of dynamic satellite networks with real-world devices. Its adaptability for various communication models and algorithm testing highlights Plotinus’s role as a vital tool for developing and analyzing SAGIN systems, offering a cross-layer,real-time,and scalable digital twin system.

关键词： network emulation framework dynamic topology adjustment microservice architecture

Precise control of page cache for containers

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第2期18卷 17-30页

作者： Kun WANG Song WU Shengbang LI Zhuo HUANG Hao FAN Chen YU Hai JIN National Engineering research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

Container-based virtualization isbecoming increasingly popular in cloud computing due to its efficiency and *** isolation is a fundamental property of *** works have indicated weak resource isolation could cause significant performance degradation for containerized applications and enhanced resource ***,current studies have almost not discussed the isolation problems of page cache which is a key resource for *** leverage memory cgroup to control page cache ***,existing policy introduces two major problems in a container-based ***,containers can utilize more memory than limited by their cgroup,effectively breaking memory ***,the Os kernel has to evict page cache to make space for newly-arrived memory requests,slowing down containerized *** paper performs an empirical study of these problems and demonstrates the performance impacts on containerized *** we propose pCache(precise control of page cache)to address the problems by dividing page cache into private and shared and controlling both kinds of page cache separately and *** do so,pCache leverages two new technologies:fair account(f-account)and evict on demand(EoD).F-account splits the shared page cache charging based on per-container share to prevent containers from using memory for free,enhancing memory *** EoD reduces unnecessary page cache evictions to avoid the performance *** evaluation results demonstrate that our system can effectively enhance memory isolation for containers and achieve substantial performance improvement over the original page cache management policy.

关键词： page cache memory cgroup container isolation cloud computing

Answering reachability queries with ordered label constraints over labeled graphs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第1期18卷 105-117页

作者： Daoliang HE Pingpeng YUAN Hai JIN National Engineering research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science&TechnologyHuazhong University of Science and TechnologyWuhan 430074China

Reachability query plays a vital role in many graph analysis *** researches proposed many methods to efficiently answer reachability queries between vertex *** many real graphs are labeled graph,it highly demands Label-Constrained Reachability(LCR)query inwhich constraint includes a set of labels besides vertex *** researches proposed several methods for answering some LCR queries which require appearance of some labels specified in constraints in the *** that constraint may be a label set,query constraint may be ordered labels,namely OLCR(Ordered-Label-Constrained Reachability)queries which retrieve paths matching a sequence of ***,no solutions are available for ***,we propose DHL,a novel bloom filter based indexing technique for answering OLCR *** can be used to check reachability between vertex *** the answers are not no,then constrained DFS is ***,we employ DHL followed by performing constrained DFS to answer OLCR *** show that DHL has a bounded false positive rate,and it's powerful in saving indexing time and *** experiments on 10 real-life graphs and 12 synthetic graphs demonstrate that DHL achieves about 4.8-22.5 times smaller index space and 4.6-114 times less index construction time than two state-of-art techniques for LCR queries,while achieving comparable query response *** results also show that our algorithm can answer OLCR queries effectively.

关键词： graph ordered-label-constrained reachability partial index bloom filter query processing

Influence of Methane-Hydrogen Mixture Characteristics on Compressor Vibrations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fluid Dynamics & Materials Processing 2024年第5期20卷 1031-1043页

作者： Vladimir Ya.Modorskii Ivan E.Cherepanov High Performance computing Center Perm National Research Polytechnic UniversityPerm614990Russia

A transition to clean hydrogen energy will not be possible until the issues related to its production, transportation,storage, etc., are adequately resolved. Currently, however, it is possible to use methane-hydrogen *** gas can be transported using a pipeline system with the required pressure being maintained by gascompression stations. This method, however, is affected by some problems too. Compressors emergency stopscan be induced by vibrations because in some cases, mechanical methods are not able to reduce the vibrationamplitude. As an example, it is known that a gas-dynamic flow effect in labyrinth seals can lead to increasedvibrations. This paper presents the numerical simulation of rotor oscillations taking into account a gas-dynamicload. The influence of a transported mixture on the oscillatory process is investigated. Mixtures consisting ofmethane and hydrogen in various proportions and an air mixture are considered. The results are discussed forvarious operating pressures and include the rotor motion trajectories and oscillation frequency spectra obtainednumerically. It is shown that the gas mixture composition has a significant effect on the oscillations and theiroccurrence. Hydrogen as a working fluid reduces the vibration amplitude. Operating a compressor with hydrogenleads to a decrease in the resonant frequency, bringing it closer to the operating one. However, the operatingpressure at which maximum oscillations are observed depends slightly on the gas mixture composition.

关键词： Seal stabilities vibration FSI CFD multiphase flows hydrogen

A Pair of Pseudo-differential Operators Involving Index Whittaker Transform in L_(2)^(a) (R_(+);m_(a)(x)dx)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2024年第6期40卷 1420-1430页

作者： Jeetendrasingh MAAN Akhilesh PRASAD department of Mathematics and computing Indian Institute of Technology(Indian School of Mines)Dhanbad-826004India

Pseudo-differential operators(PDO)Q(x,L_(a,x))and Q(x,L_(a,x))involving the index Whittaker transform are *** for these operators in Hilbert space L_(2)^(a)(R+;m_(a)(x)dx)are obtained.A symbol classΩis *** product an... 详细信息

关键词： Pseudo-differential operator index Whittaker transform confluent hypergeometric functions Hilbert space

XGCN:a library for large-scale graph neural network recommendations

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第3期18卷 247-249页

作者： Xiran SONG Hong HUANG Jianxun LIAN Hai JIN National Engineering research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Microsoft research Asia Beijing 100080China

1 Introduction Graph Neural Networks(GNNs)have gained widespread adoption in recommendation systems,and nowadays there is a pressing need to effectively manage large-scale graph data[1].When it comes to large graphs,GNNs may encounter the scalability issue stemming from their multi-layer messagepassing ***,scaling GNNs has emerged as a crucial research area in recent years,with numerous scaling strategies being proposed.

关键词： scaling gained operations

Anomaly-Based Intrusion DetectionModel Using Deep Learning for IoT Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第10期141卷 823-845页

作者： Muaadh A.Alsoufi Maheyzah Md Siraj Fuad A.Ghaleb Muna Al-Razgan Mahfoudh Saeed Al-Asaly Taha Alfakih Faisal Saeed Faculty of computing Universiti Teknologi Malaysia(UTM)Johor Bahru81310Malaysia DAAI research Group College of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11345Saudi Arabia

The rapid growth of Internet of Things(IoT)devices has brought numerous benefits to the interconnected ***,the ubiquitous nature of IoT networks exposes them to various security threats,including anomaly intrusion *** addition,IoT devices generate a high volume of unstructured *** intrusion detection systems often struggle to cope with the unique characteristics of IoT networks,such as resource constraints and heterogeneous data *** the unpredictable nature of network technologies and diverse intrusion methods,conventional machine-learning approaches seem to lack *** numerous research domains,deep learning techniques have demonstrated their capability to precisely detect *** study designs and enhances a novel anomaly-based intrusion detection system(AIDS)for IoT ***,a Sparse Autoencoder(SAE)is applied to reduce the high dimension and get a significant data representation by calculating the reconstructed ***,the Convolutional Neural Network(CNN)technique is employed to create a binary classification *** proposed SAE-CNN approach is validated using the Bot-IoT *** proposed models exceed the performance of the existing deep learning approach in the literature with an accuracy of 99.9%,precision of 99.9%,recall of 100%,F1 of 99.9%,False Positive Rate(FPR)of 0.0003,and True Positive Rate(TPR)of *** addition,alternative metrics,such as training and testing durations,indicated that SAE-CNN performs better.

关键词： IoT anomaly intrusion detection deep learning sparse autoencoder convolutional neural network