检索结果-南通市图书馆

Machine Learning Analysis of Impact of Western US Fires on Central US Hailstorms

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第7期41卷 1450-1462页

作者： Xinming LIN Jiwen fan Yuwei ZHANG ZJason HOU Pacific Northwest National Laboratory RichlandWA 99354USA Argonne National Laboratory LemontIL 60439USA

Fires,including wildfires,harm air quality and essential public services like transportation,communication,and *** fires can also influence atmospheric conditions,including temperature and aerosols,potentially affecting severe convective ***,we investigate the remote impacts of fires in the western United States(WUS)on the occurrence of large hail(size:≥2.54 cm)in the central US(CUS)over the 20-year period of 2001–20 using the machine learning(ML),Random Forest(RF),and Extreme Gradient Boosting(XGB)*** developed RF and XGB models demonstrate high accuracy(>90%)and F1 scores of up to 0.78 in predicting large hail occurrences when WUS fires and CUS hailstorms coincide,particularly in four states(Wyoming,South Dakota,Nebraska,and Kansas).The key contributing variables identified from both ML models include the meteorological variables in the fire region(temperature and moisture),the westerly wind over the plume transport path,and the fire features(i.e.,the maximum fire power and burned area).The results confirm a linkage between WUS fires and severe weather in the CUS,corroborating the findings of our previous modeling study conducted on case simulations with a detailed physics model.

关键词： wildfire severe convective storm hailstorm machine learning

Discriminatively Constrained Semi-Supervised Multi-View Nonnegative Matrix Factorization with Graph Regularization

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2024年第1期7卷 55-74页

作者： Guosheng Cui Ye Li Jianzhong Li Jianping fan Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Joint Engineering Research Center for Health Big Data Intelligent Analysis Technology Shenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China School of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Nonnegative Matrix Factorization(NMF)is one of the most popular feature learning technologies in the field of machine learning and pattern *** has been widely used and studied in the multi-view clustering tasks because of its *** study proposes a general semi-supervised multi-view nonnegative matrix factorization *** algorithm incorporates discriminative and geometric information on data to learn a better-fused representation,and adopts a feature normalizing strategy to align the different *** specific implementations of this algorithm are developed to validate the effectiveness of the proposed framework:Graph regularization based Discriminatively Constrained Multi-View Nonnegative Matrix Factorization(GDCMVNMF)and Extended Multi-View Constrained Nonnegative Matrix Factorization(ExMVCNMF).The intrinsic connection between these two specific implementations is discussed,and the optimization based on multiply update rules is *** on six datasets show that the effectiveness of GDCMVNMF and ExMVCNMF outperforms several representative unsupervised and semi-supervised multi-view NMF approaches.

关键词： multi-view semi-supervised clustering discriminative information geometric information feature normalizing strategy

Silicon dioxide-protection boosting the peroxidase-like activity of Fe single-atom catalyst for combining chemo-photothermal therapy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2024年第6期17卷 4924-4933页

作者： Yu fan Yu Yi Hongpan Rong Jiatao Zhang Beijing Key Laboratory of Construction-Tailorable Advanced Functional Materials and Green Applications School of Materials Science&EngineeringBeijing Institute of TechnologyBeijing 100081China CAS Center for Excellence in Nanoscience CAS KeyLaboratory for Biomedical Effects of Nanomaterials and NanosafetyNational Center for Nanoscience and Technology(NCNST)Beijing 100190China Key Laboratory of Medical Molecule Science and Pharmaceutics Engineering Ministry of Industry and Information TechnologySchool of Chemistry&Chemical EngineeringBeijing Key Laboratory of Construction-Tailorable Advanced Functional Materials and Green ApplicationsSchool of Materials Science and EngineeringBeijing Institute of TechnologyBeijing 100081China

Carbon-based single-atom catalysts(SACs)have been widely studied in the field of biomedicine due to their excellent catalytic ***,carbon-based SACs usually aggregate during pyrolysis,which leads to the reduction of catalytic ***,we describe a method to improve the monodispersion of SACs using silicon dioxide as a protective *** decoration of silicon dioxide serves as a buffer layer for individual nanoparticles,which is not destroyed during the pyrolysis process,ensuring the single-particle dispersion of the nanoparticles after *** approach increased the hydroxyl groups on the surface of Fe-SAC(Fe-SAC-SE)and improved its water solubility,resulting in a four times enhancement of the peroxidase(POD)-like activity of Fe-SAC-SE(58.4 U/mg)than that of non-protected SACs(13.9 U/mg).The SiO_(2)-protection approach could also improve the catalytic activities of SACs with other metals such as Mn,Co,Ni,and Cu,indicating its generality for SACs *** advantage of the high POD-like activity,photothermal properties,and large specific surface area of Fe-SAC-SE,we constructed a synergistic therapeutic system(Fe-SAC-SE@DOX@PEG)for combining the photothermal therapy,catalytic therapy,and *** was verified that the photothermal properties of Fe-SAC-SE@DOX@PEG could effectively improve its POD-like activity,exhibiting excellent tumor-killing performance at the cellular *** work may provide a general approach to improve the performances of SACs for disease therapy and diagnosis.

关键词： single-atom catalysts peroxidase-like activity SiO2-protection photothermal therapy catalytic therapy chemotherapy

FMSA:a meta-learning framework-based fast model stealing attack technique against intelligent network intrusion detection systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cybersecurity 2024年第1期7卷 110-121页

作者： Kaisheng fan Weizhe Zhang Guangrui Liu Hui He School of Cyberspace Science Harbin Institute of TechnologyHarbin 150001China Department of New Networks Peng Cheng LaboratoryShenzhen 518055GuangdongChina

Intrusion detection systems are increasingly using machine *** machine learning has shown excellent performance in identifying malicious traffic,it may increase the risk of privacy *** paper focuses on imple-menting a model stealing attack on intrusion detection *** model stealing attacks are hard to imple-ment in practical network environments,as they either need private data of the victim dataset or frequent access to the victim *** this paper,we propose a novel solution called Fast Model Stealing Attack(FMSA)to address the problem in the field of model stealing *** also highlight the risks of using ML-NIDS in network ***,meta-learning frameworks are introduced into the model stealing algorithm to clone the victim model in a black-box ***,the number of accesses to the target model is used as an optimization term,resulting in minimal queries to achieve model ***,adversarial training is used to simulate the data distribution of the target model and achieve the recovery of privacy *** experiments on multiple public datasets,compared to existing state-of-the-art algorithms,FMSA reduces the number of accesses to the target model and improves the accuracy of the clone model on the test dataset to 88.9%and the similarity with the target model to 90.1%.We can demonstrate the successful execution of model stealing attacks on the ML-NIDS system even with protective measures in place to limit the number of anomalous queries.

关键词： AI security Model stealing attack Network intrusion detection Meta learning

A Review of Deep Learning-Based Vulnerability Detection Tools for Ethernet Smart Contracts

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7期140卷 77-108页

作者： Huaiguang Wu Yibo Peng Yaqiong He Jinlin fan School of Computer Science and Technology Zhengzhou University of Light IndustryZhengzhou450001China

In recent years,the number of smart contracts deployed on blockchain has ***,the issue of vulnerability has caused incalculable *** to the irreversible and immutability of smart contracts,vulnerability detection has become particularly *** the popular use of neural network model,there has been a growing utilization of deep learning-based methods and tools for the identification of vulnerabilities within smart *** paper commences by providing a succinct overview of prevalent categories of vulnerabilities found in smart ***,it categorizes and presents an overview of contemporary deep learning-based tools developed for smart contract *** tools are categorized based on their open-source status,the data format and the type of feature extraction they *** we conduct a comprehensive comparative analysis of these tools,selecting representative tools for experimental validation and comparing them with traditional tools in terms of detection coverage and ***,Based on the insights gained from the experimental results and the current state of research in the field of smart contract vulnerability detection tools,we suppose to provide a reference standard for developers of contract vulnerability detection ***,forward-looking research directions are also proposed for deep learning-based smart contract vulnerability detection.

关键词： Smart contract vulnerability detection deep learning

Post-transcriptional regulation of DEAD-box RNA helicases in hematopoietic malignancies

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Genes & Diseases 2024年第5期11卷 315-323页

作者： Jiankun fan Zhigang Li Li Pei Yu Hou Institute of Life Sciences Chongqing Medical UniversityChongqing 400016China Department of Hematology Southwest HospitalThird Military Medical University(Army Medical University)Chongqing 400038China

Hematopoiesis represents a meticulously regulated and dynamic biological *** aberrations affecting blood cells,induced by various factors,frequently give rise to hematological *** instances are often accompanied by a multitude of abnormal post-transcriptional regulatory events,including RNA alternative splicing,RNA localization,RNA degradation,and ***,post-transcriptional regulation plays a pivotal role in preserving hematopoietic *** DEAD-Box RNA helicase genes emerge as crucial post-transcriptional regulatory factors,intricately involved in sustaining normal hematopoiesis through diverse mechanisms such as RNA alternative splicing,RNA modification,and ribosome *** review consolidates the existing knowledge on the role of DEAD-box RNA helicases in regulating normal hematopoiesis and underscores the pathogenicity of mutant DEADBox RNA helicases in malignant *** is placed on elucidating both the positive and negative contributions of DEAD-box RNA helicases within the hematopoietic system.

关键词： DEAD-box RNA helicase Hemopoietic system Post-transcriptional regulation Ribosomes assembly RNA alternative splicing

Carbon sink response of terrestrial vegetation ecosystems in the Yangtze River Delta and its driving mechanism

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 Geographical Sciences 2024年第1期34卷 112-130页

作者： ZHAO Haixia fan Jinding GU Binjie CHEN Yijiang Nanjing Institute of Geography and Limnology CASNanjing 210008China School of Environmental Science and Engineering Suzhou University of Science and TechnologySuzhou 215009JiangsuChina Nanjing College University of Chinese Academy of SciencesNanjing 211135China School of Agricultural and Food Science The University of QueenslandQueensland 4072Australia

The carbon cycle of terrestrial ecosystems is influenced by global climate change and human *** remote sensing data and land cover products,the spatio-temporal variation characteristics and trends of NEP in the Yangtze River Delta from 2000 to 2020 were analyzed based on the soil respiration *** driving influences of ecosystem structure evolution,temperature,rainfall,and human activities on NEP were *** results show that the NEP shows an overall distribution pattern of high in the southeast and low in the *** area of carbon sinks is larger than that of the carbon *** spatial heterogeneity is *** change trend is basically unchanged or significantly *** future change trend in most areas will be continuous *** with temperature,NEP are more sensitive to *** positive influence of human activities on NEP is mainly observed in north-central Anhui and northern Jiangsu coastal areas,while the negative influence is mainly found in highly urbanized *** the process of ecosystem structure,the contribution of unchanged areas to NEP change is greater than that of changed areas.

关键词： carbon sinks terrestrial vegetation ecosystems driving mechanisms climate change human activities ecosystem structure Yangtze River Delta

Image Inpainting Technique Incorporating Edge Prior and Attention Mechanism

维普期刊数据库

同方期刊数据库评论

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 999-1025页

作者： Jinxian Bai Yao fan Zhiwei Zhao Lizhi Zheng College of Information Engineering Xizang Minzu UniversityXianyang712000China

Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged ***,these methods often struggle to produce satisfactory results when dealing with missing images with large holes,leading to distortions in the structure and blurring of *** address these problems,we combine the advantages of transformers and convolutions to propose an image inpainting method that incorporates edge priors and attention *** proposed method aims to improve the results of inpainting large holes in images by enhancing the accuracy of structure restoration and the ability to recover texture *** method divides the inpainting task into two phases:edge prediction and image ***,in the edge prediction phase,a transformer architecture is designed to combine axial attention with standard *** design enhances the extraction capability of global structural features and location *** also balances the complexity of self-attention operations,resulting in accurate prediction of the edge structure in the defective *** the image inpainting phase,a multi-scale fusion attention module is *** module makes full use of multi-level distant features and enhances local pixel continuity,thereby significantly improving the quality of image *** evaluate the performance of our *** experiments are conducted on several datasets,including CelebA,Places2,and *** experiments show that our method outperforms the other mainstream ***,it improves Peak Signal-to-Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)by 1.141~3.234 db and 0.083~0.235,***,it reduces Learning Perceptual Image Patch Similarity(LPIPS)and Mean Absolute Error(MAE)by 0.0347~0.1753 and 0.0104~0.0402,*** experiments reveal that our method excels at reconstructing images with complete structural information and c

关键词： Image inpainting transformer edge prior axial attention multi-scale fusion attention

Metric and Upper Dimension of Extended Annihilating-Ideal Graphs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Algebra Colloquium 2024年第2期31卷 221-238页

作者： S.Nithya G.Elavarasi Genghua fan Department of Mathematics St.Xavier's College(Autonomous)Palayamkottai 627002Tamil NaduIndia Afiliated to Manonmaniam Sundaranar University Abishekapatti Tirunelveli 627012Tamil NaduIndia PG and Research Department of Mathematics St.Xavier's College(Autonomous)Palayamkottai 627002Tamil NaduIndia Affiliated to Manonmaniam Sundaranar University Abishekapatti Tirunelveli 627012Tamil NaduIndia 不详

The metric dimension problem is called navigation problem due to its application to robot navigation in *** this concept has wide applications in motion planning,sonar and loran station,and so *** this paper,we study certain results on the metric dimension,upper dimension and resolving number of extended annihilating-ideal graph EAG(R)associated to a commutative ring R,denoted by dim M(EAG(R)),dim+(EAG(R))and res(EAG(R)),*** we prove the finiteness conditions of dim M(EAG(R))and dim+(EAG(R)).In addition,we characterize dim M(EAG(R)),dim+(EAG(R))and res(EAG(R))for artinian rings and the direct product of rings.

关键词： extended annihilating-ideal graph metric dimension upper dimension resolving number