检索结果-南通市图书馆

维普期刊数据库

Spatiotemporal Prediction of Urban Traffics Based on Deep GNN

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 265-282页

作者： ming luo Huili Dou Ning Zheng School of Computer Science Hangzhou Dianzi UniversityHangzhou310018China Zhejiang Institute of Communications Hangzhou310012China School of Cyberspace Security Hangzhou Dianzi UniversityHangzhou310018China

Traffic prediction already plays a significant role in applications like traffic planning and urban management,but it is still difficult to capture the highly non-linear and complicated spatiotemporal correlations of traffic data.As well as to fulfil both long-termand short-termprediction objectives,a better representation of the temporal dependency and global spatial correlation of traffic data is needed.In order to do this,the Spatiotemporal Graph Neural Network(S-GNN)is proposed in this research as amethod for traffic prediction.The S-GNN simultaneously accepts various traffic data as inputs and investigates the non-linear correlations between the variables.In terms of modelling,the road network is initially represented as a spatiotemporal directed graph,with the features of the samples at the time step being captured by a convolution module.In order to assign varying attention weights to various adjacent area nodes of the target node,the adjacent areas information of nodes in the road network is then aggregated using a graph network.The data is output using a fully connected layer at the end.The findings show that S-GNN can improve short-and long-term traffic prediction accuracy to a greater extent;in comparison to the control model,the RMSE of S-GNN is reduced by about 0.571 to 9.288 and the MAE(Mean Absolute Error)by about 0.314 to 7.678.The experimental results on two real datasets,Pe MSD7(M)and PEMS-BAY,also support this claim.

关键词： Urban traffic traffic temporal correlation GNN prediction

Multimodal Fusion of Brain Imaging Data: Methods and Applications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第1期21卷 136-152页

作者： Na luo Weiyang Shi Zhengyi Yang ming Song Tianzi Jiang Brainnetome Center and National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Excellence in Brain Science and Intelligence Technology Institute of AutomationChinese Academy of SciencesBeijing 100190China Research Center for Augmented Intelligence Zhejiang LaboratoryHangzhou 311100China

Neuroimaging data typically include multiple modalities,such as structural or functional magnetic resonance imaging,dif-fusion tensor imaging,and positron emission tomography,which provide multiple views for observing and analyzing the brain.To lever-age the complementary representations of different modalities,multimodal fusion is consequently needed to dig out both inter-modality and intra-modality information.With the exploited rich information,it is becoming popular to combine multiple modality data to ex-plore the structural and functional characteristics of the brain in both health and disease status.In this paper,we first review a wide spectrum of advanced machine learning methodologies for fusing multimodal brain imaging data,broadly categorized into unsupervised and supervised learning strategies.Followed by this,some representative applications are discussed,including how they help to under-stand the brain arealization,how they improve the prediction of behavioral phenotypes and brain aging,and how they accelerate the biomarker exploration of brain diseases.Finally,we discuss some exciting emerging trends and important future directions.Collectively,we intend to offer a comprehensive overview of brain imaging fusion methods and their successful applications,along with the chal-lenges imposed by multi-scale and big data,which arises an urgent demand on developing new models and platforms.

关键词： Multimodal fusion supervised learning unsupervised learning brain atlas cognition brain disorders

Morphology Study for GeV Emission of Nearby Supernova Remnant G332.5-5.6

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Research in Astronomy and Astrophysics 2024年第4期24卷 134-140页

作者： ming-Hong luo Qing-Wen Tang Xiu-Rong Mo Department of Physics School of Physics and Materials ScienceNanchang UniversityNanchang 330031China

A spatial template is important to study nearby supernova remnants(SNRs).For SNR G332.5-5.6,we report a Gaussian disk with a radius of about 1°.06 to be a potential good spatial model in the γ-ray band.Employing this new Gaussian disk,its GeV lightcurve shows a significant variability of about seven sigma.The γ-ray observations of this SNR could be explained well either by a leptonic model or a hadronic model,in which a flat spectrum for the ejected electrons/protons is required.

关键词： ISM:supernova remnants gamma rays:ISM

维普期刊数据库

Structure regulating of metal clusters in carbonized metallic organic frameworks for high-efficient microwave absorption via tuning interaction strength between metals and ligands

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 1699-1709页

作者： Chang Sun Kun-Yan Zhao ming-Lu Huang Cheng-Long luo Xu-Dong Chen ming Wang School of Chemistry and Chemical Engineering Chongqing Key Laboratory of Soft-Matter Material Chemistry and Function ManufacturingSouthwest UniversityChongqing 400715China Jieyang Branch of Chemistry and Chemical Engineering Guangdong Laboratory(Rongjiang Laboratory) Jieyang 515200China

Carbonized metallic organic frameworks(CMOF)have been attracting attention in microwave absorption(MA)research area because of their diverse structures,tunable compositions,and rich porosity.Herein,structure regulation on metal clusters in CMOF is achieved by tuning the interaction strength between metals and ligands to enhance microwave absorption performance.Due to relatively weak interaction among copper cations and ligands,copper nanoclusters(CuNC)can be uniformly formed and embedded within the cobalt/zinc(Co/Zn)CMOF.Firstly,copper cations are added to the Co/Zn bimetallic zeolitic imidazolate frameworks(ZIFs).Secondly,the CMOF composite particles with CuNCs(CuNCs/CoZn-CMOF)were developed by a pyrolysis process.The CuNCs/CoZn-CMOF with an appropriate amount of CuNCs can harmonize both dielectric and magnetic losses.As a result,the minimum reflection loss(RLmin)reaches–45.1 dB at a matching thickness of 2.30 mm and the effective absorption bandwidth(EAB)is 8.80 GHz at a thickness of 3.10 mm.The broadband response to electromagnetic waves is attributed to interfacial polarization at CuNCs surface and heterogeneous interfaces,impedance matching and multiple scattering of electromagnetic waves.This study provides a feasible method to develop CMOF microwave absorption materials with high EAB values.

关键词： heterogeneous interface carbonized metallic organic frameworks microwave absorption interfacial polarization

Geometric error measuring,modeling,and compensation for CNC machine tools:A review

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 Aeronautics 2024年第2期37卷 163-198页

作者： Zhao ZHANG Feng JIANG ming luo Baohai WU Dinghua ZHANG Kai TANG Engineering Research Center of Advanced Manufacturing Technology for Aero Engine(Northwestern Polytechnical University) Ministry of EducationXi’an 710072China Key Laboratory of High Performance Manufacturing for Aero Engine(Northwestern Polytechnical University) Ministry of Industry and Information TechnologyXi’an 710072China Department of Mechanical and Aerospace Engineering Hong Kong University of Science and TechnologyHong KongChina

Geometric error,mainly due to imperfect geometry and dimensions of machine components,is one of the major error sources of machine tools.Considering that geometric error has significant effects on the machining quality of manufactured parts,it has been a popular topic for academic and industrial research for many years.A great deal of research work has been carried out since the 1970s for solving the problem and improving the machining accuracy.Researchers have studied how to measure,detect,model,identify,reduce,and compensate the geometric errors.This paper presents a thorough review of the latest research activities and gives an overview of the state of the art in understanding changes in machine tool performance due to geometric errors.Recent advances in measuring the geometrical errors of machine tools are summarized,and different kinds of error identification methods of translational axes and rotation axes are illustrated respectively.Besides,volumetric geometric error modeling,tracing,and compensation techniques for five-axis machine tools are emphatically introduced.Finally,research challenges in order to improve the volumetric accuracy of machine tools are also highlighted.

关键词： Error compensation Error identification Error measurement Error modeling Geometric error Machine tools

维普期刊数据库

Construction of a Metallacyclopentadiene Ring through the Attack of Carbanions to M≡C Bond Followed by C—H Activation

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Chemistry 2024年第3期42卷 235-242页

作者： Chun Tang Shengjie Zhang Zhengyu Lu Qian Li ming luo Dafa Chen Haiping Xia State Key Laboratory of Physical Chemistry of Solid Surfaces College of Chemistry and Chemical EngineeringCollaborative Innovation Center of Chemistry for Energy MaterialsXiamen UniversityXiamenFujian361005 China Shenzhen Grubbs Institute and Guangdong Provincial Key Laboratory of Catalysis Department of ChemistrySouthern University of Science and TechnologyShenzhenGuangdong518055 China

Metallacyclopentadienes are important metallacycles and regarded as intermediates in many reactions,therefore,new methods to achieve them are anticipated.In this study,a formal[3+2]method,through the reactions of an osmapentalyne with benzyl carbanions,was developed.The reactions underwent a nucleophilic attack of carbanions to the Os≡C bond,followed by C—H activation to form the five-membered osmacyclopentadiene ring.Most of the reactions were carried out at room temperature,the substituents on the aromatic rings of benzyl carbanions are diverse,and the resulting products contain an Os—H bond,representing a novel type of 10C-carbolong complexes.This work provides a new convenient route to construct metallacyclopentadienes,which is expected to further promote the development of such a type of substances.

关键词： Metallacyclopentadiene Carbolong chemistry Osmium C–H activation Nucleophilic addition

A survey on model-based reinforcement learning

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) 2024年第2期67卷 59-84页

作者： Fan-ming luo Tian XU Hang LAI Xiong-Hui CHEN Weinan ZHANG Yang YU National Key Laboratory for Novel Software Technology Nanjing University Polixir. ai Department of Computer Science and Engineering Shanghai Jiao Tong University

Reinforcement learning(RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning(MBRL) is believed to be a promising direction, as it constructs environment models in which trial-and-errors can occur without incurring actual costs. In this survey, we investigate MBRL with a particular focus on the recent advancements in deep RL. There is a generalization error between the learned model of a non-tabular environment and the actual environment. Consequently, it is crucial to analyze the disparity between policy training in the environment model and that in the actual environment, guiding algorithm design for improved model learning, model utilization, and policy training. In addition, we discuss the recent developments of model-based techniques in other forms of RL, such as offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Furthermore,we discuss the applicability and benefits of MBRL for real-world tasks. Finally, this survey concludes with a discussion of the promising future development prospects for MBRL. We believe that MBRL has great unrealized potential and benefits in real-world applications, and we hope this survey will encourage additional research on MBRL.

关键词： reinforcement learning model-based reinforcement learning planning model learning model learning with reduced error model usage

Monitoring Xylem Transport in the Stem of Lilium lancifolium Using Fluorescent Dye 5(6)-Carboxyfluorescein Diacetate

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Phyton-International Journal of Experimental Botany 2024年第5期93卷 1057-1066页

作者： Yulin luo Panpan Yang Mengmeng Bi Leifeng Xu Fang Du Jun ming College of Horticulture Shanxi Agricultural UniversityJinzhong030801China State Key Laboratory of Vegetable Biobreeding Institute of Vegetables and FlowersChinese Academy of Agricultural SciencesBeijing100081China College of Urban and Rural Construction Shanxi Agricultural UniversityJinzhong030801China

The xylem undergoes physiological changes in response to various environmental conditions during the process of plant growth.To understand these physiological changes,it is extremely important to observe the transport of xylem.In this study,the distribution and structure of vascular bundle in Lilium lancifolium were observed using the method of semithin section.Methods for introducing a fluorescent tracer into the xylem of the stems were evaluated.Then,the transport rule of 5(6)-Carboxyfluorescein diacetate(CFDA)in the xylem of the stem of L.lancifolium was studied by fluorescence dye in live cells tracer technology.The results showed that the vascular bundles of L.lancifolium were scattered in the basic tissue,the peripheral vascular bundles were smaller and densely distributed,and the closer to the center,the larger the volume of vascular bundles and the more sparsely distributed.The vascular bundles of L.lancifolium are limited external tenacity vascular bundles,which are composed of phloem and xylem.The most suitable method for CFDA labeling the xylem of isolated stem segments of L.lancifolium was solution soaking for 24 h.The running speed of CF in the isolated stem was 0.3 cm/h,which was consistent with the running speed of the material in the field.CF could be transported between the xylem and parenchyma cells,indicating that the material transport in the xylem could be through the symplastic pathway.The above results laid a foundation for the study of the xylem transport mechanism and the xylem pathogen disease of lily.

关键词： Lilium xylem transport stem fluorescent dye CFDA

Two-stage extraction by partial grinding of impacted mandibular third molar in close proximity to the inferior alveolar nerve

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Clinical Cases 2024年第10期12卷 1728-1732页

作者： Guang-ming luo Zhang-Shun Yao Wei-Xiang Huang Lei-Yan Zou Yan Yang Kunbaida Outpatient Department Kunming Medical University School and Hospital of StomatologyKunming 650106Yunnan ProvinceChina Yunnan Key Laboratory of Stomatology Kunming 650106Yunnan ProvinceChina

BACKGROUND Extraction of impacted third molars often leads to severe complications caused by damage to the inferior alveolar nerve(IAN).AIM To proposes a method for the partial grinding of an impacted mandibular third molar(IMM3)near the IAN to prevent IAN injury during IMM3 extraction.METHODS Between January 1996 and March 2022,25 patients with IMM3 roots near the IAN were enrolled.The first stage of the operation consisted of grinding a major part of the IMM3 crown with a high-speed turbine dental drill to achieve sufficient space between the mandibular second molar and IMM3.After 6 months,when the root tips were observed to be away from the IAN on X-ray examination,the remaining part of the IMM3 was completely removed.RESULTS All IMM3s were extracted easily without symptoms of IAN injury after extraction.CONCLUSION Partial IMM3 grinding may be a good alternative treatment option to avoid IAN injury in high-risk cases.

关键词： Partial grinding Impacted mandibular third molar Inferior alveolar nerve Cone-beam computed tomography