检索结果-南通市图书馆

维普期刊数据库

Q-Learning Based Routing Protocol for Congestion Avoidance

在线全文

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第9期68卷 3671-3692页

作者： Daniel Godfrey Beom-Su Kim Haoran Miao Babar Shah Bashir Hayat Imran Khan Tae-Eung Sung Ki-Il Kim department of computer science and engineering Chungnam National UniversityKorea College of Technological Innovation Zayed UniversityAbu DhabiUAE Institute of Management sciences PeshawarPakistan department of Electrical engineering University of Engineering and TechnologyPeshawarPakistan department of computer and Telecommunications engineering Yonsei UniversityKorea

The end-to-end delay in a wired network is strongly dependent on congestion on intermediate *** lots of feasible approaches to avoid congestion efficiently,congestion-aware routing protocols tend to search for an uncongested path toward the destination through rule-based approaches in reactive/incident-driven and distributed ***,these previous approaches have a problem accommodating the changing network environments in autonomous and self-adaptive operations *** overcome this drawback,we present a new congestion-aware routing protocol based on a Q-learning algorithm in software-defined networks where logically centralized network operation enables intelligent control and management of network *** a proposed routing protocol,either one of uncongested neighboring nodes are randomly selected as next hop to distribute traffic load to multiple paths or Q-learning algorithm is applied to decide the next hop by modeling the state,Q-value,and reward function to set the desired path toward the destination.A new reward function that consists of a buffer occupancy,link reliability and hop count is ***,look ahead algorithm is employed to update the Q-value with values within two hops *** approach leads to a decision of the optimal next hop by taking congestion status in two hops into account,***,the simulation results presented approximately 20%higher packet delivery ratio and 15%shorter end-to-end delay,compared to those with the existing scheme by avoiding congestion adaptively.

关键词： Congestion-aware routing reinforcement learning Q-learning Software defined networks

Leveraging graph convolutional networks for semi-supervised fault diagnosis of HVAC systems in data-scarce contexts

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

建筑模拟(英文) 2023年第8期16卷 1499-1517页

作者： Cheng Fan Yiwen Lin Marco Savino Piscitelli Roberto Chiosa Huilong Wang Alfonso Capozzoli Yuanyuan Ma Key Laboratory for Resilient Infrastructures of Coastal Cities Ministry of EducationShenzhen UniversityShenzhenChina Sino-Australia Joint Research Center in BIM and Smart Construction Shenzhen UniversityShenzhenChina College of Civil and transportation engineering Shenzhen UniversityShenzhenChina department of Energy TEBE research groupBAEDA LabPolitecnico di TorinoTorinoItaly

The continuous accumulation of operational data has provided an ideal platform to devise and implement customized data analytics for smart HVAC fault detection and *** practice,the potentials of advanced supervised learning algorithms have not been fully realized due to the lack of sufficient labeled *** tackle such data challenges,this study proposes a graph neural network-based approach to effectively utilizing both labeled and unlabeled operational data for optimum *** specifically,a graph generation method is proposed to transform tabular building operational data into association graphs,based on which graph convolutions are performed to derive useful insights for fault *** experiments have been designed to evaluate the values of the methods *** datasets on HVAC air-side operations have been used to ensure the generalizability of results *** data scenarios,which vary in training data amounts and imbalance ratios,have been created to comprehensively quantify behavioral patterns of representative graph convolution networks and their *** research results indicate that graph neural networks can effectively leverage associations among labeled and unlabeled data samples to achieve an increase of 2.86%–7.30%in fault classification accuracies,providing a novel and promising solution for smart building management.

关键词： fault detection and diagnosis graph convolutional networks semi-supervised learning HVAC systems machine learning

Efficient ID-Based Multi-Decrypter Encryption with Short Ciphertexts

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 computer science & Technology 2007年第1期22卷 103-108页

作者：柴震川曹珍富周渊 department of computer science and engineering Shanghai diao Tong University Shanghai 200240 China National computer Networks and Information Security Center Beijing 100031 China

Multi-decrypter encryption is a typical application in multi-user cryptographic branches. In multi-decrypter encryption, a message is encrypted under multiple decrypters＇ public keys in the way that only when all the decrypters cooperate, can the message be read. However, trivial implementation of multi-decrypter encryption using standard approaches leads to heavy computation costs and long ciphertext which grows as the receiver group expands. This consumes much precious bandwidth in wireless environment, such as mobile ad hoc network. In this paper, we propose an efficient identity based multi-decrypter encryption scheme, which needs only one or zero （if precomputed） pairing computation and the ciphertext contains only three group elements no matter how many the receivers are. Moreover, we give a formal security definition for the scheme, and prove the scheme to be chosen ciphertext secure in the random oracle model, and discuss how to modify the scheme to resist chosen ciphertext attack.

关键词： ID-based cryptography multi-user cryptography proven security random oracle

A Blockchain-Assisted Distributed Edge Intelligence for Privacy-Preserving Vehicular 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

computers, Materials & Continua 2023年第9期76卷 2959-2978页

作者： Muhammad Firdaus Harashta Tatimma Larasati Kyung-Hyune Rhee department of Artificial Intelligence Convergence Pukyong National UniversityBusan48513Korea School of Electrical engineering.and Informatics Institut Teknologi BandungBandung40132Indonesia College of Information Technology and Convergence Division of Computer Engineering and AIPukyong National UniversityBusan48513Korea

The enormous volume of heterogeneous data fromvarious smart device-based applications has growingly increased a deeply interlaced cyber-physical *** order to deliver smart cloud services that require low latency with strong computational processing capabilities,the Edge Intelligence System(EIS)idea is now being employed,which takes advantage of Artificial Intelligence(AI)and Edge Computing Technology(ECT).Thus,EIS presents a potential approach to enforcing future Intelligent transportation Systems(ITS),particularly within a context of a Vehicular Network(VNets).However,the current EIS framework meets some issues and is conceivably vulnerable tomultiple adversarial attacks because the central aggregator server handles the entire ***,this paper introduces the concept of distributed edge intelligence,combining the advantages of Federated Learning(FL),Differential Privacy(DP),and blockchain to address the issues raised *** performing decentralized data management and storing transactions in immutable distributed ledger networks,the blockchain-assisted FL method improves user privacy and boosts traffic prediction ***,DP is utilized in defending the user’s private data from various threats and is given the authority to bolster the confidentiality of data-sharing *** model has been deployed in two strategies:First,DP-based FL to strengthen user privacy by masking the intermediate data during model ***,blockchain-based FL to effectively construct secure and decentralized traffic management in vehicular *** simulation results demonstrated that our framework yields several benefits for VNets privacy protection by forming a distributed EIS with privacy budget(ε)of 4.03,1.18,and 0.522,achieving model accuracy of 95.8%,93.78%,and 89.31%,respectively.

关键词： Edge intelligence federated learning differential privacy blockchain vehicular networks

Algorithmic approaches for optimizing electronic control unit time using multi-rate sampling

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Control Theory and Technology 2018年第3期16卷 173-190页

作者： Rajorshee RAHA Pallab DASGUPTA Soumyajit DEY department of computer science and engineering Indian Institute of Technology Kharagpur India

With the emerging migration of automotive and other distributed control platforms from federated to integrated architectures, the need for optimal utilization of ECU （electronic control unit） bandwidth will become a key requirement in the implementation of embedded control features. This paper advocates the partitioning of the operating space of the plant and the use of minimal sampling rates in each partition without compromising the overall quality of control. At the heart of the proposed methodology are our algorithms that enable the choice of the partitions and the sampling rate for each partition. We demonstrate the efficacy of our methods on two case studies, namely an anti-lock braking system and a lane departure warning system. We also study the use of a supervisory controller that controls the switching among sampling rates for a combination of the two features.

关键词： Sampling period adaptive control stability automotive software embedded control system

Slope analysis based on local strength reduction method and variable-modulus elasto-plastic model

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 Central South university 2014年第5期21卷 2041-2050页

作者：杨光华钟志辉傅旭东张玉成温勇张明飞 School of Civil and Architectural engineering Wuhan University Guangdong Research Institute of Water Resources and Hydropower Geotechnical engineering.Technology Center of Guangdong Province School of Civil engineering.and transportation South China University of Technology

Employing an ideal elasto-plastic model,the typically used strength reduction method reduced the strength of all soil elements of a ***,this method was called the global strength reduction method(GSRM).However,the deformation field obtained by GSRM could not reflect the real deformation of a slope when the slope became *** most slopes,failure occurs once the strength of some regional soil is sufficiently weakened; thus,the local strength reduction method(LSRM)was proposed to analyze slope *** contrast with GSRM,LSRM only reduces the strength of local soil,while the strength of other soil remains ***,deformation by LSRM is more reasonable than that by *** addition,the accuracy of the slope's deformation depends on the constitutive model to a large degree,and the variable-modulus elasto-plastic model was thus *** constitutive model was an improvement of the Duncan–Chang model,which modified soil's deformation modulus according to stress level,and it thus better reflected the plastic feature of *** importantly,the parameters of the variable-modulus elasto-plastic model could be determined through in-situ tests,and parameters determination by plate loading test and pressuremeter test were ***,it is easy to put this model into ***,LSRM and the variable-modulus elasto-plastic model were used to analyze Egongdai ancient *** factor,deformation field,and optimal reinforcement measures for Egongdai ancient landslide were obtained based on the proposed method.

关键词：理想弹塑性模型强度折减法变形模量边坡稳定性坡度土壤元素平板载荷试验本构模型

维普期刊数据库

Vibration-based hypervelocity impact identification and localization

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic engineering 2022年第4期23卷 515-529页

作者： Jiao BAO Lifu LIU Jiuwen CAO department of computer engineering Chengdu Technological UniversityChengdu611730China Machine Learning and I-health International Cooperation Base of Zhejiang Province Hangzhou Dianzi UniversityHangzhou310018China Artificial Intelligence Institute Hangzhou Dianzi UniversityHangzhou310018China

Hypervelocity impact(HVI)vibration source identification and localization have found wide applications in many fields,such as manned spacecraft protection and machine tool collision damage detection and *** this paper,we study the synchrosqueezed transform(SST)algorithm and the texture color distribution(TCD)based HVI source identification and localization using impact *** extracted SST and TCD image features are fused for HVI image *** achieve more accurate detection and localization,the optimal selective stitching features OSSST+TCD are obtained by correlating and evaluating the similarity between the sample label and each dimension of the *** conventional classification and regression models are merged by voting and stacking to achieve the final detection and *** demonstrate the effectiveness of the proposed algorithm,the HVI data recorded from three kinds of high-speed bullet striking on an aluminum alloy plate is used for *** experimental results show that the proposed HVI identification and localization algorithm is more accurate than other ***,based on sensor distribution,an accurate four-circle centroid localization algorithm is developed for HVI source coordinate localization.

关键词： Ensemble learning Synchrosqueezied transform Gray-level co-occurrence matrix Image entropy Distance estimation

维普期刊数据库

Expeditious management plan towards digital earth

在线全文

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2014年第8期7卷 635-649页

作者： Naveen Kumar Sidda Aneta J.Florczyk Francisco J.Lopez-Pellicer Dinesh Babu I.V Ruben Bejar F.Javier Zarazaga-Soria department of computer science and System engineering University of ZaragozaZaragozaSpain department of Wood science forestry and GeomaticsUniversity LavalSainte-FoyQCCanada

The breakthrough developments in geospatial technologies and the increasing availability of spatial data make geoinformation a business and a decisional element to the ***,it is important to have a management plan to factor in practical and feasible data sources,in building geo *** authors of this paper are motivated by the fact that right data sources could outclass in-house resources in various application *** paper outlines pragmatic cases for the tangible benefits of the existing potential data and expeditious patterns for digital *** work also proposes‘good-enough’solutions based on the pragmatic cases,available literature,and the 3D city model developed that could be sufficient in contriving the objectives of the common public usage and open business *** demonstrate this approach,the paper encapsulated the low-cost development of virtual 3D city model using publicly available cadastral data and web services.

关键词： spatial data sources geo management web services APIs cadastral data

Saturated coordinated control of multiple underactuated unmanned surface vehicles over a closed curve

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2017年第7期60卷 40-53页

作者： Lu LIU Dan WANG Zhouhua PENG Hugh H.T.LIU School of Marine engineering Dalian Maritime University department of computer science City University of Hong Kong Institute for Aerospace Studies University of Toronto

This paper presents a design method for saturated coordinated control of multiple underactuated unmanned surface vehicles(USVs) on a closed curve, holding a symmetric formation pattern. Each vehicle is subject to unknown sideslip, uncertain vehicle kinetics, and limited control torques. First, the course angle and surge velocity are considered as immediate signals to stabilize the along-track and cross-track path following errors. In the vehicle kinematics, a reduced-order extended state observer is utilized to compensate for the effect of the unknown sideslip. Next, a bounded neural network control law is constructed at the kinetic level with the aid of the a saturated function, a projection operator, and a dynamic surface design method. Finally, a parameter cyclic pursuit approach is presented to guarantee that the vehicles are evenly spaced over the closed curve for achieving a symmetric formation pattern. The input-to-state stability of the closed-loop system is analyzed via cascade theory. Comparative studies are given to show the effectiveness of the proposed method.

关键词： symmetric formation pattern parameter cyclic pursuit reduced-order extended state observer neural networks saturated control