检索结果-南通市图书馆

Social Robot Detection Method with Improved Graph Neural 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 2024年第2期78卷 1773-1795页

作者： Zhenhua Yu Liangxue Bai Ou Ye Xuya Cong institute of Systems Security and Control College of Computer Science and TechnologyXi’an University of Science and TechnologyXi’an710054China

Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social *** social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social *** paper proposes a social robot detection method with the use of an improved neural ***,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships ***,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the ***,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph ***,social robots can be more accurately identified by combining user behavioral and relationship *** carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,*** with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two *** results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.

关键词： Social robot detection social relationship subgraph graph attention network feature linear modulation behavioral gene sequences

Method for triangular fuzzy multiple attribute decision making based on two-dimensional density operator method

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 Systems Engineering and Electronics 2024年第1期35卷 178-185页

作者： LIN Youliang LI Wu LIU Gang HUANG Dong School of Economics and Management Hunan Institute of Science and TechnologyYueyang 414000China Hunan Vocational College for Nationalities Yueyang 414000China School of Information science and Engineering Hunan Institute of Science and TechnologyYueyang 414000China

Aiming at the triangular fuzzy(TF)multi-attribute decision making(MADM)problem with a preference for the distribution density of attribute(DDA),a decision making method with TF number two-dimensional density(TFTD)operator is proposed based on the density operator theory for the decision maker(DM).Firstly,a simple TF vector clustering method is proposed,which considers the feature of TF number and the geometric distance of ***,the least deviation sum of squares method is used in the program model to obtain the density weight ***,two TFTD operators are defined,and the MADM method based on the TFTD operator is ***,a numerical example is given to illustrate the superiority of this method,which can not only solve the TF MADM problem with a preference for the DDA but also help the DM make an overall comparison.

关键词： fuzzy decision making clustering density operator multi-attribute decision making(MADM)

Bio-inspired surface manipulation of halloysite nanotubes for highperformance flame retardant polylactic acid nanocomposites

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第3期17卷 1595-1606页

作者： Yaru Sun Bin Yu Yan Liu Junbo Yan Zixi Xu Bo Cheng Fenglei Huang Jun Wang State Key Laboratory of Explosion science and technology Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Fire science University of Science and Technology of ChinaHefei 230026China Beijing institute of technology Chongqing Innovation Center Chongqing 401120China National Engineering Research Center of Flame Retardant Materials Beijing Institute of TechnologyBeijing 100081China

High-performance flame-retardant polylactic acid(PLA)bio-composites based on biobased fillers to meet usage requirements represents a promising direction for creating a sustainable *** flame retardant PLA composites have been reported extensively,it still remains a huge challenge to develop mechanically *** flame retardant PLA composites due to plastication effect of organic flame retardants and poor compatibility of organic fillers with the matrix lead to the severe deterioration in mechanical *** this work,a bio-inspired surface manipulation strategy for halloysite nanotubes(HNTs)was proposed via a facile and green self-assembly *** structure and morphology of bio-inspired HNTs(b-HNTs)proved that biomass nanofillers(PA-NA-Fe)grew well both within the lumen and on the surface of *** growth of biomass on the inner and outer surfaces of HNTs was inspired from wooden towards enhancing the interface compatibility and imparting multi-properties to PLA *** mechanical properties(tensile,thermomechanical and anti-impact mechanical),great fire safety(heat release and smoke emission),thermostability and improved electromagnetic interference shielding effectiveness of this well-designed PLA nanocomposite were *** mechanisms of the enhanced performances of the PLA bio-composites by loading b-HNTs were *** work presents a facile and environmentally-friendly bio-inspired modification strategy for HNTs to fabricate high-performance,multi-functional polymer composites,which is also suitable for surface modification of many other nanomaterials,including nanofibers,nanotubes,nanowires,and nanosheets.

关键词： mechanical properties thermostability fire safety electromagnetic interference shielding biomass

Experimental and numerical analyses of the effect of fibre content on the close-in blast performance of a UHPFRC beam

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Defence technology（防务技术） 2024年第1期31卷 242-261页

作者： Junbo Yan Qiyue Zhang Yan Liu Yingliang Xu Zhenqing Shi Fan Bai Fenglei Huang State Key Laboratory of Explosion science and technology Beijing Institute of TechnologyBeijing 100081China Beijing institute of technology Chongqing Innovation Center Chongqing 401120China

Limited research has been conducted on the influences of fiber content on close-in blasting characteristics for ultrahigh-performance fiber-reinforced concrete(UHPFRC)*** paper aims to address this knowledge gap through experimental and mesoscale numerical *** were conducted on ten UHPFRC beams built with varying steel fiber volumetric fractions subjected to close-in explosive ***,this study considered other parameters,such as the longitudinal reinforcement type and *** the case of UHPFRC beams featuring normal-strength longitudinal reinforcement of diametersΦ12,Φ16,andΦ20,a reduction in maximum displacement by magnitudes of19.6%,19.5%,and 17.4%was observed,respectively,as the volumetric fractions of fiber increased from1.0%to 2.5%.In addition,increasing the longitudinal reinforcement ratio and using high-strength steel longitudinal reinforcement both significantly reduced the deformation characteristics and increase the blasting resistances of UHPFRC ***,the effects on the local crushing and spalling damage were not significant.A mesoscale finite element model,which considers the impacts of fiber parameters on UHPFRC beam behaviors,was also established and well correlated with the test ***,parametric analyses were further conducted to examine the impacts of the steel fiber content and length and the hybrid effects of various types of microfibers and steel fibers on the blasting performance of UHPFRC beams.

关键词： Blast performance Close-in blast Fiber content Mesoscale approach UHPFRC beams

Unsupervised Multi-Expert Learning Model for Underwater Image Enhancement

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 708-722页

作者： Hongmin Liu Qi Zhang Yufan Hu Hui Zeng Bin Fan the School of Intelligence science and technology and the institute of Artificial Intelligence University of Science and Technology BeijingBeijing 100083China the School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China IEEE

Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded *** methods feed the whole image directly into the model for ***,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the *** address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color ***,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater *** on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater ***,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,*** addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced *** experiments on public datasets demonstrate that our method achieves more pleasing results in vision *** metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.

关键词： Multi-expert learning underwater image enhancement unsupervised learning

Investigation of high rate mechanical flow followed by ignition for high-energy propellant under dynamic extrusion loading

在线全文

学校读者我要写书评

暂无评论

Defence technology（防务技术） 2024年第2期32卷 336-347页

作者： Liying Dong Yanqing Wu Kun Yang Xiao Hou State Key Laboratory of Explosion science and technology Beijing Institute of TechnologyBeijing 100081China School of Aerospace Engineering Beijing Institute of TechnologyBeijing 100081China

Investigating the ignition response of nitrate ester plasticized polyether(NEPE) propellant under dynamic extrusion loading is of great significant at least for two cases. Firstly, it helps to understand the mechanism and conditions of unwanted ignition inside charged propellant under accident ***, evaluates the risk of a shell crevice in a solid rocket motor(SRM) under a falling or overturning scene. In the present study, an innovative visual crevice extrusion experiment is designed using a dropweight apparatus. The dynamic responses of NEPE propellant during extrusion loading, including compaction and compression, rapid shear flow into the crevice, stress concentration, and ignition reaction, have been firstly observed using a high-performance high-speed camera. The ignition reaction is observed in the triangular region of the NEPE propellant sample above the crevice when the drop weight velocity was 1.90 m/s. Based on the user material subroutine interface UMAT provided by finite element software LS-DYNA, a viscoelastic-plastic model and dual ignition criterion related to plastic shear dissipation are developed and applied to the local ignition response analysis under crevice extrusion conditions. The stress concentration occurs in the crevice location of the propellant sample, the shear stress is relatively large, the effective plastic work is relatively large, and the ignition reaction is easy to occur. When the sample thickness decreases from 5 mm to 2.5 mm, the shear stress increases from 22.3 MPa to 28.6 MPa, the critical value of effective plastic work required for ignition is shortened from 1280 μs to 730 μs, and the triangular area is easily triggering an ignition reaction. The propellant sample with a small thickness is more likely to stress concentration, resulting in large shear stress and effective work, triggering an ignition reaction.

关键词： NEPE propellant Crevice extrusion Shear flow Sample thickness Ignition reaction

Microstructure and magnetocaloric properties of melt-extracted SmGdDyCoAl high-entropy amorphous microwires

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2024年第3期43卷 1234-1242页

作者： Shi-Jie Wei Hong-Xian Shen Lun-Yong Zhang Lin Luo Xin-Xing Tang Jian-Fei Sun Xiao-Qing Li School of Materials science and Engineering Harbin Institute of TechnologyHarbin150001China Applied Materials Physics Department of Materials Science and EngineeringKTH-Royal Institute of Technology10044StockholmSweden

This paper presents a systematic investigation of the microstructure and magnetocaloric properties of melt-extracted Sm_(20)Gd_(20)Dy_(20)Co_(20)Al_(20)high-entropy *** fabricated wires exhibited an amorphous structure,and the temperature interval of the undercooled liquid AT was 45 *** microwires underwent a second-order magnetic transition from a ferromagnetic to a paramagnetic state near the Curie temperature(T_(C)=52 K),The maximum magnetic entropy change(-ΔS_M^(max)),the relative cooling power and the refrigeration capacity reached 6.34 J·kg^(-1)·K^(-1).422.09 J·kg^(-1)and 332.94 J·kg^(-1),respectively,under a magnetic field change of 5 *** addition,the temperature-averaged entropy changes with two temperature lifts(3 and 10 K)were 6.32 and 6.27 J·kg^(-1)·K^(-1),*** good magnetocalorie performance highlights the significant potential for the Sm_(20)Gd_(20)Dy_(20)Co_(20)Al_(20)microwires to be used as magnetic refrigerant materials in low-temperature region *** work will serve as a valuable reference for future investigations on low-temperature high-entropy magnetocaloric materials.

关键词： Melt-extraction High-entropy amorphous microwires Magnetocaloric effect Magnetic refrigeration

Mixed-dimensional stacked nanocomposite structures for a specific wavelength-selectable ambipolar photoresponse

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第6期17卷 5549-5558页

作者： Young Jae Park Jaeho Shim Joo Song Lee Kyu Seung Lee Ji-Yeon Kim Kang Bok Ko Sang-Youp Yim Seongjun Kim Hoon-Kyu Shin Donghee Park Yong Ju Yun Dong Ick Son institute of Advanced Composite Materials Korea Institute of Science and TechnologyJeollabuk-do 55324Republic of Korea National institute for Nanomaterials technology Pohang University of Science and TechnologyGyeongsangbuk-do 37673Republic of Korea Department of Semiconductor science and technology Semiconductor Physics Research CenterJeonbuk National UniversityJeonju 54896Republic of Korea Advanced Photonics Research institute Gwangju Institute of Science and TechnologyGwangju 61005Republic of Korea Center for Opto-Electronic Materials and Devices Post-Silicon Semiconductor InstituteKorea Institute of Science and TechnologySeoul 02792Republic of Korea Graduate School of Energy and Environment(KU-KIST Green School) Korea UniversitySeoul 02841Republic of Korea KIST School Department of Nanomaterials and Nano ScienceUniversity of Science and Technology(UST)Daejeon 34113Republic of Korea

Mixed-dimensional composite structures using zero-dimensional(0D)quantum dots(QDs)and two-dimensional(2D)transition metal dichalcogenides(TMDs)materials are expected to attract great interest in optoelectronics due to the potential to generate new optical ***,we report on the unique optical characteristics of a devices with mixed dimensional vertically stacked structures based on tungsten diselenide(WSe_(2))/CdSeS QDs monolayer/molybdenum disulfide(MoS_(2))(2D/0D/2D).Specifically,it exhibits an ambipolar photoresponse characteristic,with a negative photoresponse observed in the 400-600 nm wavelength range and a positive photoresponse appeared at 700 nm *** resulted in the high negative responsivity of up to 52.22 mA·W^(−1)under 400 nm,which is 163 times higher than that of the photodetector without CdSeS *** also demonstrated the negative photoresponse,which could be due to increased carrier collision probability and non-radiative *** modeling and simulation reveal that Auger recombination among the types of non-radiative recombination is the main cause of negative photocurrent ***,we discovered ambipolar photoresponse near a specific wavelength corresponding to the energy of quantum *** study revealed interesting phenomenon in the mixed low-dimensional stacked structure and paved the way to exploit it for the development of innovative photodetection materials as well as for optoelectronic applications.

关键词： mixed-dimension quantum dot heterostructure photodetector ambipolar photoresponse

A Survey on Blockchain-Based Federated Learning:Categorization,Application and Analysis

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6期139卷 2451-2477页

作者： Yuming Tang Yitian Zhang Tao Niu Zhen Li Zijian Zhang Huaping Chen Long Zhang School of Cyberspace science&technology Beijing Institute of TechnologyBeijing100081China School of Computer science&technology Beijing Institute of TechnologyBeijing100081China Southeast institute of Information technology Beijing Institute of TechnologyPutian351100China Qianxin technology Group Co. Ltd.Beijing100044China

Federated Learning(FL),as an emergent paradigm in privacy-preserving machine learning,has garnered significant interest from scholars and engineers across both academic and industrial *** its innovative approach to model training across distributed networks,FL has its vulnerabilities;the centralized server-client architecture introduces risks of single-point ***,the integrity of the global model—a cornerstone of FL—is susceptible to compromise through poisoning attacks by malicious *** attacks and the potential for privacy leakage via inference starkly undermine FL’s foundational privacy and security *** these reasons,some participants unwilling use their private data to train a model,which is a bottleneck in the development and industrialization of federated *** technology,characterized by its decentralized ledger system,offers a compelling solution to these *** inherently prevents single-point failures and,through its incentive mechanisms,motivates participants to contribute computing ***,blockchain-based FL(BCFL)emerges as a natural progression to address FL’s *** study begins with concise introductions to federated learning and blockchain technologies,followed by a formal analysis of the specific problems that FL *** discusses the challenges of combining the two technologies and presents an overview of the latest cryptographic solutions that prevent privacy leakage during communication and incentives in *** addition,this research examines the use of BCFL in various fields,such as the Internet of Things and the Internet of ***,it assesses the effectiveness of these solutions.

关键词： Federated learning blockchain privacy-preserving