检索结果-南通市图书馆

Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adaptation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

data Intelligence 2024年第1期6卷 183-200页

作者： Yuhong Zhang Jianqing Wu Qi Zhang Xuegang Hu School of Computer and Information engineering Hefei University of TechnologyHefei 230601China Key Laboratory of knowledge engineering with Big data(Hefei University of Technology) The Ministry of Education of ChinaHefei 230009China

Domain adaptation aims to transfer knowledge from the labeled source domain to an unlabeled target domain that follows a similar but different ***,adversarial-based methods have achieved remarkable success due to the excellent performance of domain-invariant feature presentation ***,the adversarial methods learn the transferability at the expense of the discriminability in feature representation,leading to low generalization to the target *** this end,we propose a Multi-view Feature Learning method for the Over-penalty in Adversarial Domain ***,multi-view representation learning is proposed to enrich the discriminative information contained in domain-invariant feature representation,which will counter the over-penalty for discriminability in adversarial ***,the class distribution in the intra-domain is proposed to replace that in the inter-domain to capture more discriminative information in the learning of transferrable *** experiments show that our method can improve the discriminability while maintaining transferability and exceeds the most advanced methods in the domain adaptation benchmark datasets.

关键词： domain adaptation adversarial learning multi-view learning

Effects of vacancy and external electric field on the electronic properties of the MoSi_(2)N_(4)/graphene heterostructure

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 Physics B 2024年第3期33卷 542-550页

作者：梁前罗祥燕钱国林王远帆梁永超谢泉 College of Big data and Information engineering Institute of New Optoelectronic Materials and TechnologyGuizhou UniversityGuiyang 550025China

Recently,the newly synthesized septuple-atomic layer two-dimensional(2D)material MoSi_(2)N_(4)(MSN)has attracted attention *** work delves into the effect of vacancies and external electric fields on the electronic properties of the MSN/graphene(Gr)heterostructure using first-principles *** find that four types of defective structures,N-in,N-out,Si and Mo vacancy defects of monolayer MSN and MSN/Gr heterostructure are stable in ***,vacancy defects can effectively modulate the charge transfer at the interface of the MSN/Gr heterostructure as well as the work function of the pristine monolayer MSN and MSN/Gr ***,the application of an external electric field enables the dynamic switching between n-type and p-type Schottky *** work may offer the possibility of exceeding the capabilities of conventional Schottky diodes based on MSN/Gr heterostructures.

关键词： MoSi_(2)N_(4) vacancy defects external electric field Schottky contacts

Graphene effectively activating "dead" water molecules between manganese dioxide layers in potassium-ion battery

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第6期93卷 306-315,I0008页

作者： Xinhai Wang Wensheng Yang Shengshang Lu Shangshu Peng Tong Guo Quan Xie Qingquan Xiao Yunjun Ruan institute of Advanced Optoelectronic Materials and Technology College of Big Data and Information EngineeringGuizhou UniversityGuiyang 550025GuizhouChina

Aqueous potassium-ion batteries(APIBs),recognized as safe and reliable new energy devices,are considered as one of the alternatives to traditional *** MnO_(2),serving as the main cathode,exhibits a lower specific capacity in aqueous electrolytes compared to organic systems and operates through a different reaction *** application of highly conductive graphene may effectively enhance the capacity of APIBs but could complicate the potassium storage *** this study,a MnO_(2) cathode pre-intercalated with K~+ions and grown on graphene(KMO@rGO) was developed using the microwave hydrothermal method for ***@rGO achieved a specific capacity of 90 mA h g^(-1) at a current density of 0.1 A g^(-1),maintaining a capacity retention rate of>90% after 5000 cycles at 5 A g^(-1).In-situ and exsitu characterization techniques revealed the energy-storage mechanism of KMO@rGO:layered MnO_(2)traps a large amount of "dead" water molecules during K~+ions ***,the introduction of graphene enables these water molecules to escape during K~+ ions insertion at the *** galvanostatic intermittent titration technique and density functional theory confirmed that KMO@rGO has a higher K~+ions migration rate than MnO_(2).Therefore,the capacity of this cathode depends on the interaction between dead water and K~+ions during the energy-storage *** optimal structural alignment between layered MnO_(2) and graphene allows electrons to easily flow into the external *** charge compensation forces numerous low-solvent K~+ions to displace interlayer dead water,enhancing the *** unique reaction mechanism is unprecedented in other aqueous battery studies.

关键词： Graphene K-ion batteries Mn-based layered oxide Water molecules Density functional theory

Theoretical Exploration of Alloying Effects on Stabilities and Mechanical Properties ofγʹPhase in Novel Co–Al–Nb-Base Superalloys

在线全文

学校读者我要写书评

暂无评论

Acta Metallurgica Sinica(English Letters) 2024年第7期37卷 1238-1248页

作者： Guan-Cheng Gu Zhao-Jing Han Ze-Yu Chen Zhao-Xuan Li Sheng-Bao Xia Zheng-Ning Li Hua Jin Wei-Wei Xu Xing-Jun Liu Shenzhen Research institute of Xiamen University School of Aerospace EngineeringXiamen UniversityXiamen361005China institute of Materials Genome and Big data Harbin Institute of TechnologyShenzhen518055China

The new developedγ/γʹCo–Al–Nb-base alloys show great potentials as high-temperature ***,finding appropriate compositions to improve performance of alloys still poses a great challenge to the development of Co–Al–Nb-base *** by the lack of alloying effects on fundamental properties of criticalγʹphase,we systematically performed a theoretical investigation on the effect of alloying elements TM(TM:Ti,V,Cr,Zr,Mo,Ta,W,Re,and Ru)on phase stabilities and mechanical properties of L1_(2)-typeγʹ(Co,Ni)_(3)(Al,Nb).By analyzing the stability ofγʹphase with respect to its competitive B2 and D0_(19) phases,the results shown that Ti,V,and Cr enhance the L1_(2) stability and widen the L1_(2)–D0_(19) energy barrier,in which V yields the maximum *** analysis of electronic structure indicated that the alternation of valence electrons at fermi level would be the atomic origin for doping TM inγʹ*** calculated results of mechanical properties shown that V and Cr are expected to be optimal dopant for enhancing the strength and the ductility ofγʹ*** addition of Ta is also beneficial for enhancing the strength at the slight expense of ductility ofγʹ*** drawing the mechanical maps,the preferred composition range for the phases with desired properties is roughly demarcated in theory for the multi-addition of V/Cr and V/Ta inγʹ*** findings would be useful for optimizing the performance of novelγ/γʹCo–Al–Nb-base superalloys.

关键词： Co-Al-Nb-base superalloys γ/γʹdual-phase Phase stability Mechanical properties First-principle methods

Perpendicular-Cutdepth:Perpendicular Direction Depth Cutting data Augmentation 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

Computers, Materials & Continua 2024年第4期79卷 927-941页

作者： Le Zou Linsong Hu Yifan Wang Zhize Wu Xiaofeng Wang Anhui Provincial engineering Laboratory of Big data Technology Application forUrban Infrastructure School ofArtificial Intelligence and Big DataHefei UniversityHefei230601China institute of Applied Optimization School of Artificial Intelligence and Big DataHefei UniversityHefei230601China

Depth estimation is an important task in computer *** data at scale for monocular depth estimation is challenging,as this task requires simultaneously capturing RGB images and depth ***,data augmentation is crucial for this *** data augmentationmethods often employ pixel-wise transformations,whichmay inadvertently disrupt edge *** this paper,we propose a data augmentationmethod formonocular depth estimation,which we refer to as the Perpendicular-Cutdepth *** method involves cutting realworld depth maps along perpendicular directions and pasting them onto input images,thereby diversifying the data without compromising edge *** validate the effectiveness of the algorithm,we compared it with existing convolutional neural network(CNN)against the current mainstream data augmentation ***,to verify the algorithm’s applicability to Transformer networks,we designed an encoder-decoder network structure based on Transformer to assess the generalization of our proposed *** results demonstrate that,in the field of monocular depth estimation,our proposed method,Perpendicular-Cutdepth,outperforms traditional data *** the indoor dataset NYU,our method increases accuracy from0.900 to 0.907 and reduces the error rate from0.357 to *** the outdoor dataset KITTI,our method improves accuracy from 0.9638 to 0.9642 and decreases the error rate from 0.060 to 0.0598.

关键词： Perpendicular depth estimation data augmentation

Reinforcement learning based edge computing in B5G

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第1期10卷 1-6页

作者： Jiachen Yang Yiwen Sun Yutian Lei Zhuo Zhang Yang Li Yongjun Bao Zhihan Lv School of Electrical and Information engineering Tianjin UniversityTianjin300072China Technology and data Center ***Beijing100176China School of data Science and Software engineering Qingdao UniversityQingdao266101China

The development of communication technology will promote the application of Internet of Things,and Beyond 5G will become a new technology *** the same time,Beyond 5G will become one of the important supports for the development of edge computing *** paper proposes a communication task allocation algorithm based on deep reinforcement learning for vehicle-to-pedestrian communication scenarios in edge *** trial and error learning of agent,the optimal spectrum and power can be determined for transmission without global information,so as to balance the communication between vehicle-to-pedestrian and *** results show that the agent can effectively improve vehicle-to-infrastructure communication rate as well as meeting the delay constraints on the vehicle-to-pedestrian link.

关键词： Reinforcement learning Edge computing Beyond 5G Vehicle-to-pedestrian

Physical information-enhanced graph neural network for predicting phase separation

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 Physics B 2024年第7期33卷 278-283页

作者：张亚强王煦文王雅楠郑文 institute of Public-Safety and Big data College of Computer Science and Technology(College of Data Science)Taiyuan University of TechnologyJinzhong 030600China Shanxi engineering Research Centre for Intelligent data Assisted Treatment Changzhi Medical CollegeChangzhi 046000China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai 200050China

Although phase separation is a ubiquitous phenomenon, the interactions between multiple components make it difficult to accurately model and predict. In recent years, machine learning has been widely used in physics simulations. Here,we present a physical information-enhanced graph neural network(PIENet) to simulate and predict the evolution of phase separation. The accuracy of our model in predicting particle positions is improved by 40.3% and 51.77% compared with CNN and SVM respectively. Moreover, we design an order parameter based on local density to measure the evolution of phase separation and analyze the systematic changes with different repulsion coefficients and different Schmidt *** results demonstrate that our model can achieve long-term accurate predictions of order parameters without requiring complex handcrafted features. These results prove that graph neural networks can become new tools and methods for predicting the structure and properties of complex physical systems.

关键词： graph neural network phase separation machine learning dissipative particle dynamics

Privacy Protection for Blockchain-Based Healthcare IoT Systems:A Survey

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8期11卷 1757-1776页

作者： Minfeng Qi Ziyuan Wang Qing-Long Han Jun Zhang Shiping Chen Yang Xiang the School of Science Computing and Engineering Technologies Swinburne University of Technology the Faculty of data Science City University of Macau School of Science Computing and Engineering Technologies Swinburne University of Technology IEEE CSIRO data61

To enable precision medicine and remote patient monitoring, internet of healthcare things(IoHT) has gained significant interest as a promising technique. With the widespread use of IoHT, nonetheless, privacy infringements such as IoHT data leakage have raised serious public concerns. On the other side, blockchain and distributed ledger technologies have demonstrated great potential for enhancing trustworthiness and privacy protection for IoHT systems. In this survey, a holistic review of existing blockchain-based IoHT systems is conducted to indicate the feasibility of combining blockchain and IoHT in privacy protection. In addition, various types of privacy challenges in IoHT are identified by examining general data protection regulation(GDPR). More importantly, an associated study of cutting-edge privacy-preserving techniques for the identified IoHT privacy challenges is presented. Finally, several challenges in four promising research areas for blockchain-based IoHT systems are pointed out, with the intent of motivating researchers working in these fields to develop possible solutions.

关键词： Blockchains Privacy Internet of Things data privacy Monitoring Medical services Biomedical monitoring

Benchmark experiment on slab^(238)U with D-T neutrons for validation of evaluated nuclear data

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第2期35卷 145-159页

作者： Yan-Yan Ding Yang-Bo Nie Yue Zhang Zhi-Jie Hu Qi Zhao Huan-Yu Zhang Kuo-Zhi Xu Shi-Yu Zhang Xin-Yi Pan Chang-Lin Lan Jie Ren Xi-Chao Ruan Key Laboratory of Nuclear data China Institute of Atomic EnergyBeijing 102413China School of Nuclear Science and Technology Lanzhou UniversityLanzhou 730000China institute of Fluid Physics China Academy of Engineering PhysicsMianyang 62100China

A benchmark experiment on^(238)U slab samples was conducted using a deuterium-tritium neutron source at the China institute of Atomic *** leakage neutron spectra within energy levels of 0.8-16 MeV at 60°and 120°were measured using the time-of-flight *** samples were prepared as rectangular slabs with a 30 cm square base and thicknesses of 3,6,and 9 *** leakage neutron spectra were also calculated using the MCNP-4C program based on the latest evaluated files of^(238)U evaluated neutron data from CENDL-3.2,ENDF/B-Ⅷ.0,JENDL-5.0,and *** on the comparison,the deficiencies and improvements in^(238)U evaluated nuclear data were *** results showed the following.(1)The calculated results for CENDL-3.2 significantly overestimated the measurements in the energy interval of elastic scattering at 60°and 120°.(2)The calculated results of CENDL-3.2 overestimated the measurements in the energy interval of inelastic scattering at 120°.(3)The calculated results for CENDL-3.2 significantly overestimated the measurements in the 3-8.5 MeV energy interval at 60°and 120°.(4)The calculated results with JENDL-5.0 were generally consistent with the measurement results.

关键词： Leakage neutron spectra Uranium D-T neutron source Evaluated nuclear data