检索结果-南通市图书馆

Improving Federated Learning through Abnormal Client Detection and Incentive

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4期139卷 383-403页

作者： Hongle Guo Yingchi Mao Xiaoming He Benteng zhang Tianfu Pang Ping Ping College of Computer and Information Hohai UniversityNanjing211100China Key Laboratory ofWater Big Data Technology of Ministry ofWater Resources Hohai UniversityNanjing211100China

Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central *** reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their *** central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective *** reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize *** this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated *** build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection *** them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational ***,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively *** training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in *** to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.

关键词： Federated learning abnormal clients incentive credit score abnormal score detection

Multi-Scale Feature Fusion Model for Bridge Appearance Defect Detection

在线全文

维普期刊数据库

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 1-11页

作者： Rong Pang Yan Yang Aiguo Huang Yan Liu Peng zhang Guangwu Tang School of Computing and Artificial Intelligence Southwest Jiaotong UniversityChengdu 611756China China Merchants Chongqing Road Engineering Inspection Center Co. Ltd.Chongqing 400067China State Key Laboratory of Bridge Engineering Structural Dynamics Chongqing 400067China

Although the Faster Region-based Convolutional Neural Network(Faster R-CNN)model has obvious advantages in defect recognition,it still cannot overcome challenging problems,such as time-consuming,small targets,irregular shapes,and strong noise interference in bridge defect *** deal with these issues,this paper proposes a novel Multi-scale Feature Fusion(MFF)model for bridge appearance disease ***,the Faster R-CNN model adopts Region Of Interest(ROl)pooling,which omits the edge information of the target area,resulting in some missed detections and inaccuracies in both detecting and localizing bridge ***,this paper proposes an MFF based on regional feature Aggregation(MFF-A),which reduces the missed detection rate of bridge defect detection and improves the positioning accuracy of the target ***,the Faster R-CNN model is insensitive to small targets,irregular shapes,and strong noises in bridge defect detection,which results in a long training time and low recognition ***,a novel Lightweight MFF(namely MFF-L)model for bridge appearance defect detection using a lightweight network EfficientNetV2 and a feature pyramid network is proposed,which fuses multi-scale features to shorten the training speed and improve recognition ***,the effectiveness of the proposed method is evaluated on the bridge disease dataset and public computational fluid dynamic dataset.

关键词： defect detection Multi-scale Feature Fusion(MFF) Region Of Interest(ROl)alignment lightweight network

Combined effects of climate and land-use changes on the alpha and beta functional diversities of terrestrial mammals in China

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(Life Sciences) 2024年第10期67卷 2224-2233页

作者： Chao zhang Yumei Li Wei Wang Zexuan Gao Hanqing Liu Yonggang Nie Key Laboratory of Animal Ecology and Conservation Biology Institute of ZoologyChinese Academy of SciencesBeijing 100101China College of Life Sciences Hebei UniversityBaoding 071002China University of Chinese Academy of Sciences Beijing 100049China

Climate and land-use changes are predicted to impact biodiversity,threatening ecosystem services and ***,their combined effects on the functional diversity of mammals at the regional scale remain unclear,especially at the beta ***,we use projected climate and land-use changes in China to investigate their potential effects on the alpha and beta functional diversities of terrestrial mammals under low-and high-emission *** the current projection,we showed strong positive spatial correlations between functional richness and species *** evenness(FEve),functional specialization(FSpe),and functional originality(FOri)decreased with species richness,and functional divergence(FDiv)increased first and then *** beta diversity was dominated by its nestedness component,in contrast to the taxonomic *** changes in species richness are more strongly influenced by land-use change under the low-emission scenario,while under the high-emission scenario,they are more strongly influenced by climate *** in functional richness(FRic)were inconsistent with those in species richness,with a magnitude of decreases greater than predicted from species ***,mammal assemblages showed potential functional differentiation(FD)across the country,and the trends exceeded those towards taxonomic differentiation(TD).Our findings help us understand the processes underlying biodiversity responses to global changes on multiple facets and provide new insight for conservation plans.

关键词： climate change land-use change functional diversity terrestrial mammals biodiversity conservation

In-Vehicle Network Injection Attacks Detection Based on Feature Selection and Classification

在线全文

学校读者我要写书评

暂无评论

Automotive Innovation 2024年第1期7卷 138-149页

作者： Haojie Ji Liyong Wang Hongmao Qin Yinghui Wang Junjie zhang Biao Chen Key Laboratory of Modern Measurement and Control Technology Ministry of EducationBeijing Information Science and Technology UniversityBeijing 100192China State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body College of Mechanical and Vehicle EngineeringHunan UniversityChangsha 410082China School of Transportation Science and Engineering Beihang UniversityBeijing 100191China Hefei Innovation Research Institute Beihang UniversityHefei 230012China

Detecting abnormal data generated from cyberattacks has emerged as a crucial approach for identifying security threats within in-vehicle *** transmission of information through in-vehicle networks needs to follow specific data for-mats and communication protocols ***,statistical algorithms are employed to learn these variation rules and facilitate the identification of abnormal ***,the effectiveness of anomaly detection outcomes often falls short when confronted with highly deceptive in-vehicle network *** this study,seven representative classification algorithms are selected to detect common in-vehicle network attacks,and a comparative analysis is employed to identify the most suitable and favorable detection *** consideration of the communication protocol characteristics of in-vehicle networks,an optimal convolutional neural network(CNN)detection algorithm is proposed that uses data field characteristics and classifier selection,and its comprehensive performance is *** addition,the concept of Hamming distance between two adjacent packets within the in-vehicle network is introduced,enabling the proposal of an enhanced CNN algorithm that achieves robust detection of challenging-to-identify abnormal *** paper also presents the proposed CNN classifica-tion algorithm that effectively addresses the issue of high false negative rate(FNR)in abnormal data detection based on the timestamp feature of data *** experimental results validate the efficacy of the proposed abnormal data detection algorithm,highlighting its strong detection performance and its potential to provide an effective solution for safeguarding the security of in-vehicle network information.

关键词： Classification algorithm Anomaly detection In-vehicle network Feature extraction Injecting attack

Full-Scale Isogeometric Topology Optimization of Cellular Structures Based on Kirchhoff-Love Shells

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 2479-2505页

作者： Mingzhe Huang Mi Xiao Liang Gao Mian Zhou Wei Sha Jinhao zhang State Key Lab of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan430074China

Cellular thin-shell structures are widely applied in ultralightweight designs due to their high bearing capacity and strength-to-weight *** this paper,a full-scale isogeometric topology optimization(ITO)method based on Kirchhoff-Love shells for designing cellular tshin-shell structures with excellent damage tolerance ability is *** method utilizes high-order continuous nonuniform rational B-splines(NURBS)as basis functions for Kirchhoff-Love shell *** geometric and analysis models of thin shells are unified by isogeometric analysis(IGA)to avoid geometric approximation error and improve computational *** topological configurations of thin-shell structures are described by constructing the effective density field on the *** volume constraints are imposed in the proximity of each control point to obtain bone-like cellular *** facilitate numerical implementation,the p-norm function is used to aggregate local volume constraints into an equivalent global *** numerical examples are provided to demonstrate the effectiveness of the proposed *** simulation and comparative analysis,the results indicate that the cellular thin-shell structures optimized by the proposed method exhibit great load-carrying behavior and high damage robustness.

关键词： Cellular thin-shell structures isogeometric analysis full-scale topology optimization Kirchhoff–Love shells

Security defense strategy algorithm for Internet of Things based on deep 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

High-Confidence Computing 2024年第1期4卷 7-13页

作者： Xuecai Feng Jikai Han Rui zhang Shuo Xu Hui Xia School of Computer Science and Technology Ocean University of ChinaQingdao 266100China

Currently,important privacy data of the Internet of Things(IoT)face extremely high risks of *** persistently engage in continuous attacks on terminal devices to obtain private data of crucial *** significant progress has been made in recent years in deep reinforcement learning defense strategies,most defense methods still face problems such as low defense resource allocation efficiency and insufficient defense coordination *** solve the above problems,this paper constructs a novel adversarial security scenario and proposes a security game model that integrates defense resource allocation and patrol *** the above game model,this paper designs a deep reinforcement learning algorithm named SDSA to calculate its security defense *** calculates the allocation strategy of the best patrolling strategy that is most suitable for the defender by searching the policy on a multi-dimensional discrete action space,and enables multiple defense agents to cooperate efficiently by training a multi-intelligent Dueling Double Deep Q-Network(D3QN)with prioritized experience ***,the experimental results show that the SDSA-learned security defense strategy can provide a feasible and effective security protection strategy for defenders against attacks compared to the MADDPG and OptGradFP methods.

关键词： Internet of Things Cyber security Deep reinforcement learning Game theory

Construction and performance test of charged particle detector array for MATE

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2024年第8期35卷 92-100页

作者： Xiao‑Bin Li Long‑Hui Ru Zhi‑Chao zhang Bing‑Feng Lv Ning‑Tao zhang Jin‑Long zhang Chen‑Gui Lu Bing‑Shui Gao Jun‑Bing Ma Fu‑Shuai Shi Satoru Terashima Xiao‑Dong Xu Zhen Bai Shi‑Wei Xu Yan‑Yun Yang Hooi‑Jin Ong Xiao‑Dong Tang Institute of Modern Physics(IMP) Chinese Academy of SciencesLanzhou 730000China School of Nuclear Science and Technology University of Chinese Academy of SciencesBeijing 100049China Research Center for Nuclear Physics Osaka UniversityIbarakiOsaka 567‑0047Japan RIKEN Nishina Center WakoSaitama 351‑0198Japan Joint Department for Nuclear Physics Lanzhou University and Institute of Modern PhysicsChinese Academy of SciencesLanzhou 730000China

A charged particle array named MATE-PA,which serves as an auxiliary detector system for a Multi-purpose Active-target Time projection chamber used in nuclear astrophysical and exotic beam Experiments(MATE),was *** array comprised of 20 single-sided strip-silicon detectors covering approximately 10%of the solid *** detectors facilitated the detection of reaction-induced charged particles that penetrate the active volume of the *** performance of MATE-PA has been experimentally studied using an alpha source and a 36-MeV 14 N beam injected into the MATE chamber on the radioactive ion beam line in Lanzhou(RIBLL).The chamber was filled with a gas mixture of 95%4 He and 5%CO_(2) at a pressure of 500 *** results indicated good separation of light-charged particles using the forward double-layer silicon detectors of *** energy resolution of the Si detectors was deduced to be approximately 1%(σ)for an energy loss of approximately 10 MeV caused by theα*** inclusion of MATE-PA improves particle identification and increases the dynamic range of the kinetic energy of charged particles,particularly that of theαparticles,up to approximately 15 MeV.

关键词： Silicon detector array Active target Time projection chamber

Effects of Volcanic Activity on Organic Matter Sources and the Paleoenvironment:Geochemical Evidence from Upper Carboniferous Source Rocks(Batamayineishan Formation)in Eastern Junggar,NW China

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年第5期35卷 1482-1498页

作者： Ming Shao Tianzhu Lei Shuncun zhang Shengyin zhang Yu Pei Sen Song Northwest Institute of Eco-Environment and Resources Chinese Academy of SciencesLanzhou 730000China Key Laboratory of Petroleum Resources Exploration and Evaluation Gansu ProvinceLanzhou 730000China State Key Laboratory of Baiyunobo Rare Earth Resource Researches and Comprehensive Utilization Baotou Research Institute of Rare EarthsBaotou 014060China

The mudstone,gray tuffite and carbonaceous shale in the Upper Carboniferous Batamayineishan Formation(Bashan Formation)are essential source rocks for the volcanic reservoir in eastern Junggar,northwestern *** kerogen components,vitrinite reflectance,Rock-Eval pyrolysis,lipid biomarkers and isotope compositions were measured to understand the provenance and depositional environment of Bashan Formation under the background of volcanic *** were 10 and 4 periods of volcanic eruptions identified in the wells CS and DZ,*** source rocks developed in the late or intermittent phase of volcanic *** original island arcs of the Early Carboniferous evolved into the Wucaiwan sag and the Dishuiquan sag in the Bashan *** Wucaiwan sag inherited the restricted,closed residual sea,which had a slightly anoxic and hypersaline *** Dishuiquan sag was generally an oxidizing lacustrine environment,influenced by a marine transgression that may have occurred at the end of the DZ_(Ⅲ)period during the Late *** the total organic matter decreased due to the volcanic eruption,ash could cause an increase of aquatic organisms,coinciding with increases in salinity and reducibility in the Dishuiquan sag.

关键词： organic geochemistry volcanic activity paleoenvironment upper carboniferous east-ern Junggar petroleumgeology

Two antibodies show broad,synergistic neutralization against SARS-CoV-2 variants by inducing conformational change within the RBD

在线全文

学校读者我要写书评

暂无评论

Protein & Cell 2024年第2期15卷 121-134页

作者： Hui Sun Tingting Deng Yali zhang Yanling Lin Yanan Jiang Yichao Jiang Yang Huang Shuo Song Lingyan Cui Tingting Li Hualong Xiong Miaolin Lan Liqin Liu Yu Li Qianjiao Fang Kunyu Yu Wenling Jiang Lizhi Zhou Yuqiong Que Tianying zhang Quan Yuan Tong Cheng Zheng zhang Hai Yu Jun zhang Wenxin Luo Shaowei Li Qingbing Zheng Ying Gu Ningshao Xia State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics School of Public HealthSchool of Life SciencesXiamen UniversityXiamen 361102China National Institute of Diagnostics and Vaccine Development in Infectious Diseases School of Public HealthSchool of Life SciencesXiamen UniversityXiamen 361102China State Key Laboratory of Vaccines for Infectious Diseases School of Public HealthSchool of Life SciencesXiamen UniversityXiamen 361102China Xiang An Biomedicine Laboratory Xiamen 361102China Institute for Hepatology National Clinical Research Center for Infectious DiseaseShenzhen Third People's HospitalSchool of MedicineSouthem University of Science and TechnologyShenzhen 518112China The Second Affliated Hospital School of MedicineSouthern University of Science and TechnologyShenzhen 518112China Research Unit of Frontier Technology of Structural Vaccinology Chinese Academy of Medical SciencesXiamen 361102China

Continual evolution of the severe acute respiratory syndrome coronavirus(SARS-CoV-2)virus has allowed for its gradual evasion of neutralizing antibodies(nAbs)produced in response to natural infection or *** rapid nature of these changes has incited a need for the development of superior broad nAbs(bnAbs)and/or the rational design of an antibody cocktail that can protect against the mutated virus ***,we report two angiotensin-converting enzyme 2 competing nAbs—8H12 and 3E2—with synergistic neutralization but evaded by some Omicron ***-electron microscopy reveals the two nAbs synergistic neutralizing virus through a rigorous pairing permitted by rearrangement of the 472-489 loop in the receptor-binding domain to avoid steric *** antibodies based on these two nAbs tremendously extend the neutralizing breadth and restore neutralization against recent variants including currently dominant ***,these findings expand our understanding of the potential strategies for the neutralization of SARS-CoV-2 variants toward the design of broad-acting antibody therapeutics and vaccines.

关键词： SARS-CoV-2 broad neutralizing antibody rearrangement synergistic neutralization