检索结果-南通市图书馆

Object Helps U-Net Based Change Detectors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 548-550页

作者： lan Yan qiang Li Kenli Li College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Dear Editor,This letter focuses on leveraging the object information in images to improve the performance of the U-Net based change *** detection is fundamental to many computer vision *** existing solutions based on ... 详细信息

关键词： Net computer networks

LRChain:data protection and sharing method of learning archives based on consortium blockchain

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2024年第4期31卷 28-42页

作者： lan Lina gao Yuhan Shi Ruisheng Wu Fenfen School of Humanities Beijing University of Posts and TelecommunicationsBeijing 100876China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and TelecommunicationsMinistry of EducationBeijing 100876China

Learning archives management in traditional systems faces challenges such as inadequate security,weak tamper resistance,and limited sharing *** address these issues,this paper proposes LRChain,a method based on consortium blockchain,for lifelong learning archives data protection and *** employs a combination of on-chain and off-chain cooperative storage using a consortium chain and inter planetary file system(IPFS)to enhance data security and *** also enables fine-grained verification of learning archives through selective disclosure principles,ensuring privacy protection of sensitive ***,an attributebased encryption(ABE)algorithm is utilized to establish authorized access control for learning archives,facilitating safe and trusted *** evaluations and security analyses demonstrate that this method exhibits decentralization,strong security,tamper resistance,and performs well,effectively meeting the requirements for secure sharing of learning archive data.

关键词： learning archives consortium blockchain collaborative storage secure sharing

Recent Advances in Asymmetric Structural Composites for Excellent Electromagnetic Interference Shielding: A Review

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第6期42卷 693-710页

作者： Ying Zhou Bai Xue lan Xie Chang-Mei Wu qiang Zheng Department of Polymer Materials and Engineering College of Materials and Metallurgy Guizhou University National Engineering Research Center for Compounding and Modification of Polymer Materials National and Local Joint Engineering Research Center for Functional Polymer Membrane Materials and Membrane Processes State Key Laboratory of Public Big Data Guizhou University Department of Polymer Science and Engineering Zhejiang University

Since electromagnetic pollution is detrimental to human health and the environment, numerous efforts have been successively made to achieve excellent electromagnetic interference shielding effectiveness(EMI SE) via designing the hierarchical structures for electromagnetic interference(EMI) shielding polymer composites. Among the plentiful structures, the asymmetric structures are currently a hot spot, principally categorizing into multi-layered, porous, fibrous, and segregated asymmetric structures, which endows the high EMI shielding performance for polymer composites incorporated with magnetic, conductive, and/or dielectric micro/nano-fillers, due to the “absorption-reflection-reabsorption” shielding mechanism. Therefore, this review provides the retrospection and summary of the efforts with respect to abundant asymmetric structures and multifunctional micro/nano-fillers for enhancing EMI shielding properties, which is conducive to the booming development of polymeric EMI shielding materials for the promising prospect in modern electronics and 5-generation(5G) technology.

关键词： Asymmetric structure Microano functional filler Polymer composite Electromagnetic interference shielding

Wind disturbance compensated path-following control for fixed-wing UAVs in arbitrarily strong winds

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第2期37卷 431-445页

作者： Hao LU lan gao Yunda YAN Mingzhe HOU Chenliang WANG Hangzhou Innovation Institute Beihang UniversityHangzhou 310051China School of Information Science and Technology Hangzhou Normal UniversityHangzhou 311121China Department of Computer Science University College LondonLondon WC1E 6BTUnited Kingdom Center for Control Theory and Guidance Technology Harbin Institute of TechnologyHarbin 150001China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China

Wind is the primary challenge for low-speed fixed-wing unmanned aerial vehicles to follow a predefined flight *** cope with various wind conditions,this paper proposes a wind disturbance compensated path following control strategy where the wind disturbance estimate is incorporated with the nominal guiding vector field to provide the desired airspeed direction for the *** the control input vector for the outer-loop kinematic subsystem needs to satisfy a magnitude constraint,a scaling mechanism is introduced to tune the proportions of the compensation and nominal ***,an optimization problem is formulated to pursue a maximum wind compensation in strong winds,which can be solved analytically to yield two scaling factors.A cascaded inner-loop tracking controller is also designed to fulfill the outer-loop wind disturbance compensated guiding vector ***-fidelity simulation results under sensor noises and realistic winds demonstrate that the proposed path following algorithm is less sensitive to sensor noises,achieves promising accuracy in normal winds,and mitigates the deviation from a desired path in wild winds.

关键词： Path following Guiding vector field Wind disturbance Disturbance rejection Fixed wings

Electromagnetic wave absorption performance and rheological behavior of rubber composites with low mass filling rate carbon nanofiber aerogel

在线全文

学校读者我要写书评

暂无评论

Journal of Materiomics 2024年第4期10卷 928-936页

作者： Zhiyi Zhang Bicheng Zhou lan Jia Wenwen Yu qiang Zheng College of Materials Science and Engineering Taiyuan University of TechnologyTaiyuan030024China Shanxi-Zheda Institute of Advanced Materials and Chemical Engineering Taiyuan030000China rd Research Institute of China Electronics Technology Group Corporation Taiyuan030032China Department of Polymer Science&Engineering Zhejiang UniversityHangzhou310027China

With the development of electronic information science and technology,electromagnetic information security and electromagnetic pollution become more and more *** wave absorption(EMWA)rubber based on the absorbent of carbon with low density and good corrosion resistance is a kind of good EMWA materials for solving electromagnetic information security and electromagnetic *** this article,three-dimensional network structure carbon nanofiber aerogels(3DNSCAs)are prepared by vacuum annealing of three-dimensional network structure agarose/zinc acetate obtained by freeze-drying of agarose/zinc acetate *** EMWA rubber composites with 2.2%(in mass)3DNSCAs have almost the same density as silicone rubber(PDMS),and the dispersity of 3DNSCAs in PDMS is studied by rheological *** effective absorption bandwidth(EAB,frequency for reflection loss<–10 dB)of the 2 mm thick PDMS/C-800 is 4 GHz,and the minimum value of reflection loss(RL_(min))is−52 dB with the thickness of 3.5 *** PDMS/C-1000 with the thickness of 3.5 mm has an EAB up to 4.8 *** cross section(RCS)reduction of PDMS/C-800 can achieve 20 dB⋅m2 at the frequency of 6 GHz.

关键词： Electromagnetic wave absorption Rubber composite Carbon aerogel Rheological behavior Power loss density

Alarm Log Data Augmentation Algorithm Based on a GAN Model and Apriori

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 2024年第4期39卷 951-966页

作者： Yang Yang Yu-Ting Li Yong-Hua Huo Zhi-Peng gao lan-lan Rui State Key Laboratory of Network and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China The 54th Research Institute of China Electronics Technology Group Corporation Shijiazhuang 050081China

The complexity of alarm detection and diagnosis tasks often results in a lack of alarm log *** to the strong rule associations inherent in alarm log data,existing data augmentation algorithms cannot obtain good results for alarm log *** address this problem,this paper introduces a new algorithm for augmenting alarm log data,termed APRGAN,which combines a generative adversarial network(GAN)with the Apriori *** generates alarm log data under the guidance of rules mined by the rule ***,we propose a new dynamic updating mechanism to alleviate the mode collapse problem of the *** addition to updating the real reference dataset used to train the discriminator in the GAN,we dynamically update the parameters and the rule set of the Apriori algorithm according to the data generated in each *** extensive experimentation on two public datasets,it is demonstrated that APRGAN surpasses other data augmentation algorithms in the domain with respect to alarm log data augmentation,as evidenced by its superior performance on metrics such as BLEU,ROUGE,and METEOR.

关键词： data augmentation alarm log data Apriori generative adversarial network(GAN)

Synergistic effects and kinetics analysis for co-pyrolysis of vacuum residue and plastics

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 Chemical Science and Engineering 2024年第5期18卷 71-81页

作者： Chao Wang Xiaogang Shi Aijun Duan Xingying lan Jinsen gao Qingang Xiong State Key Laboratory of Heavy Oil Processing China University of Petroleum-BeijingBeijing 102249China State Key Laboratory of Pulp and Paper Engineering South China University of TechnologyGuangzhou 510640China

This study utilizedathermogravimetric analyzer to assess the thermal decomposition behaviors and kinetics properties of vacuum residue(VR)and low-density polyethylene(LDPE)*** kinetic parameters were calculated using the Friedman *** demonstrate the interactive effects between LDPE and VR during the co-pyrolysis process,the disparity in mass loss and mass loss rate between the experimental and calculated values was *** co-pyrolysis curves obtained through estimation and experimentation exhibited significantdeviations,whichwerei influencedby temperature and mixing ratio.A negative synergistic interaction was observed between LDPE and VR,although this inhibitory effect could be mitigated or eliminated by reducing the LDPE ratio in the mixture and increasing the ***-pyrolysisprocess resulted in a reduction in carbon residue,which could be attributed to the interaction between LDPE and the heavy fractions,particularly resin and asphaltene,present in *** findings align with the pyrolysis behaviors exhibited by the four VR ***,it was observed that the co-pyrolysis process exhibited lower activation energy as the VR ratio increased,indicating a continuous enhancement in the reactivity of the mixed samples during co-pyrolysis.

关键词： co-pyrolysis heavy residual oil polyethylene thermogravimetric analysis synergistic effects

A data-driven model of drop size prediction based on artificial neural networks using small-scale data sets

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第2期66卷 71-83页

作者： Bo Wang Han Zhou Shan Jing qiang Zheng Wenjie lan Shaowei Li Institute of Nuclear and New Energy Technology Tsinghua UniversityBeijing 100084China State Key Laboratory of Heavy Oil Processing China University of Petroleum(Beijing)Beijing 102249China State Key Laboratory of Chemical Engineering Tsinghua UniversityBeijing 100084China

An artificial neural network(ANN)method is introduced to predict drop size in two kinds of pulsed columns with small-scale data *** training,the deviation between calculate and experimental results are 3.8%and 9.3%,*** ANN model,the influence of interfacial tension and pulsation intensity on the droplet diameter has been *** size gradually increases with the increase of interfacial tension,and decreases with the increase of pulse *** can be seen that the accuracy of ANN model in predicting droplet size outside the training set range is reach the same level as the accuracy of correlation obtained based on experiments within this *** two kinds of columns,the drop size prediction deviations of ANN model are 9.6%and 18.5%and the deviations in correlations are 11%and 15%.

关键词： Artificial neural network Drop size Solvent extraction Pulsed column Two-phase flow Hydrodynamics

Deep reinforcement learning using least-squares truncated temporal-difference

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第2期9卷 425-439页

作者： Junkai Ren Yixing lan Xin Xu Yichuan Zhang qiang Fang Yujun Zeng College of Intelligence Science and Technology National University of Defense TechnologyChangshaChina State Key Laboratory of Astronautic Dynamics Xi'an Satellite Control CenterXi'anChina

Policy evaluation(PE)is a critical sub-problem in reinforcement learning,which estimates the value function for a given policy and can be used for policy ***,there still exist some limitations in current PE methods,such as low sample efficiency and local convergence,especially on complex *** this study,a novel PE algorithm called Least-Squares Truncated Temporal-Difference learning(LST2D)is *** LST2D,an adaptive truncation mechanism is designed,which effectively takes advantage of the fast convergence property of Least-Squares Temporal Difference learning and the asymptotic convergence property of Temporal Difference learning(TD).Then,two feature pre-training methods are utilised to improve the approximation ability of ***,an Actor-Critic algorithm based on LST2D and pre-trained feature representations(ACLPF)is proposed,where LST2D is integrated into the critic network to improve learning-prediction *** simulation studies were conducted on four robotic tasks,and the corresponding results illustrate the effectiveness of *** proposed ACLPF algorithm outperformed DQN,ACER and PPO in terms of sample efficiency and stability,which demonstrated that LST2D can be applied to online learning control problems by incorporating it into the actor-critic architecture.

关键词： Deep reinforcement learning policy evaluation temporal difference value function approximation