检索结果-南通市图书馆

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： m.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose m.moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(mL)models in a distributed and decentralized *** allows mL models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different mL approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： Data privacy distributed machine learning federated learning software frameworks

来源：

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

Exponentiated Generalized Inverse Flexible Weibull Distribution:Bayesian and Non-Bayesian Estimation Under Complete and TypeⅡCensored Samples with Applications

引用

Communications in mathematics and Statistics 2022年第3期10卷 413-434页

作者： m.el-morshedy m.S.eliwa A.el-Gohary Ehab m.Almetwally R.el-Desokey Department of mathematics College of Science and Humanities in Al-KharjPrince Sattam Bin Abdulaziz UniversityAl-Kharj 11942Saudi Arabia Department of mathematics Faculty of ScienceMansoura UniversityMansoura 35516Egypt Faculty of Business Administration Delta University of Science and TechnologyMansouraEgypt Faculty of Graduate Studies for Statistical Research Cairo UniversityGiza 12613Egypt

In this paper,a new 4-parameter exponentiated generalized inverse flexible Weibull distribution is *** of its statistical properties are *** aim of this paper is to estimate the model parameters via several approaches,namely,maximum likelihood,maximum product spacing and *** to Bayesian approach,several techniques are used to get the Bayesian estimators,namely,standard error function,Linex loss function and entropy loss *** estimation herein is based on complete and censored *** Chain monte Carlo simulation is used to discuss the behavior of the estimators for each ***,two real data sets are analyzed to obtain the flexibility of the proposed model.

关键词： Weibull distribution Hazard rate function maximum likelihood estimation maximum product spacing estimation Bayesian estimation Censored samples Simulation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Forecasting E-Commerce Adoption Based on Bidirectional Recurrent Neural Networks

引用

Computers, materials & Continua 2022年第3期70卷 5091-5106页

作者： Abdullah Ali Salamai Ather Abdulrahman Ageeli el-Sayed m.el-kenawy Community college Jazan UniversityJazanKingdom of Saudi Arabia Department of Communications and electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt

E-commerce refers to a system that allows individuals to purchase and sell things *** primary goal of e-commerce is to offer customers the convenience of not going to a physical store to make a *** will purchase the item online and have it delivered to their home within a few *** goal of this research was to develop machine learning algorithms that might predict e-commerce platformsales.A case study has been designed in this paper based on a proposed continuous Stochastic Fractal Search(SFS)based on a Guided Whale Optimization Algorithm(WOA)to optimize the parameter weights of the Bidirectional Recurrent Neural Networks(BRNN).Furthermore,a time series dataset is tested in the experiments of e-commerce demand ***,the results were compared to many versions of the state-of-the-art optimization techniques such as the Particle Swarm Optimization(PSO),Whale Optimization Algorithm(WOA),and Genetic Algorithm(GA).A statistical analysis has proven that the proposed algorithm can work significantly better by statistical analysis test at the P-value less than 0.05 with a one-way analysis of variance(ANOVA)test applied to confirm the performance of the proposed ensemble *** proposed Algorithm achieved a root mean square error of RmSE(0.0000359),mean(0.00003593)and Standard Deviation(0.000002162).

关键词： Neural networks e-commerce forecasting risk management machine learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Using BlazePose on Spatial Temporal Graph Convolutional Networks for Action Recognition

引用

Computers, materials & Continua 2023年第1期74卷 19-36页

作者： motasem S.Alsawadi el-Sayed m.el-kenawy miguel Rio electronic and electrical Engineering Department University College LondonLondonWC1E 7JEEngland Department of Communications and electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt

The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision ***,finding efficient solutions to extract knowledge from these sources is ***,the BlazePose system has been released for skeleton extraction from images oriented to mobile *** this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the *** hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR ***,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action ***,we propose the Enhanced-BlazePose topology that can achieve better results than its ***,we propose different skeleton detection thresholds that can improve the accuracy performance even *** reached a top-1 accuracy performance of 40.1%on the Kinetics *** the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.

关键词： Action recognition BlazePose graph neural network OpenPose skeleton spatial temporal graph convolution network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automated COVID-19 Detection Based on Single-Image Super-Resolution and CNN models

引用

Computers, materials & Continua 2022年第1期70卷 1141-1157页

作者： Walid el-Shafai Anas m.Ali el-Sayed m.el-Rabaie Naglaa F.Soliman Abeer D.Algarni Fathi E.Abd el-Samie Department electronics and electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Alexandria Higher Institute of Engineering&Technology(AIET) AlexandriaEgypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

In developing countries,medical diagnosis is expensive and time ***,automatic diagnosis can be a good cheap *** task can be performed with artificial intelligence tools such as deep Convolutional Neural Networks(CNNs).These tools can be used on medical images to speed up the diagnosis process and save the efforts of *** deep CNNs allow direct learning from the medical ***,the accessibility of classified data is still the largest challenge,particularly in the field of medical *** learning can deliver an effective and promising solution by transferring knowledge from universal object detection CNNs to medical image ***,because of the inhomogeneity and enormous overlap in intensity between medical images in terms of features in the diagnosis of Pneumonia and COVID-19,transfer learning is not usually a robust ***-Image Super-Resolution(SISR)can facilitate learning to enhance computer vision functions,apart from enhancing perceptual image ***,it helps in showing the main features of *** by the challenging dilemma of Pneumonia and COVID-19 diagnosis,this paper introduces a hybrid CNN model,namely SIGTra,to generate super-resolution versions of X-ray and CT *** depends on aGenerative Adversarial Network(GAN)for the super-resolution reconstruction ***,Transfer learning with CNN(TCNN)is adopted for the classification of *** different categories of chest X-ray and CT images can be classified with the proposed model.A comparison study is presented between the proposed SIGTra model and the other relatedCNNmodels for COVID-19 detection in terms of precision,sensitivity,and accuracy.

关键词： medical images SIGTra GAN CT and X-ray images SISR TCNN

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optimization Ensemble Weights model for Wind Forecasting System

引用

Computers, materials & Continua 2022年第11期73卷 2619-2635页

作者： Amel Ali Alhussan el-Sayed m.el-kenawy Hussah Nasser AlEisa m.el-SAID Sayed A.Ward Doaa Sami Khafaga Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Communications and electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt electrical Engineering Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Delta Higher Institute of Engineering and Technology(DHIET) Mansoura35111Egypt Department of electrical Engineering Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt Faculty of Engineering Delta University for Science and TechnologyGamasaMansoura11152Egypt

Effective technology for wind direction forecasting can be realized using the recent advances in machine ***,the stability and safety of power systems are expected to be significantly ***,the unstable and unpredictable qualities of the wind predict the wind direction a challenging *** paper proposes a practical forecasting approach based on the weighted ensemble of machine learning *** weighted ensemble is optimized using a whale optimization algorithm guided by particle swarm optimization(PSO-Guided WOA).The proposed optimized weighted ensemble predicts the wind direction given a set of input *** conducted experiments employed the wind power forecasting dataset,freely available on Kaggle and developed to predict the regular power generation at seven wind farms over forty-eight *** recorded results of the conducted experiments emphasize the effectiveness of the proposed ensemble in achieving accurate predictions of the wind *** addition,a comparison is established between the proposed optimized ensemble and other competing optimized ensembles to prove its ***,statistical analysis using one-way analysis of variance(ANOVA)and Wilcoxon’s rank-sum are provided based on the recorded results to confirm the excellent accuracy achieved by the proposed optimized weighted ensemble.

关键词： Guided Whale Optimization Algorithm(Guided WOA) forecasting machine learning weighted ensemble model wind direction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Dipper Throated Optimization Algorithm for Unconstrained Function and Feature Selection

引用

Computers, materials & Continua 2022年第7期72卷 1465-1481页

作者： Ali E.Takieldeen el-Sayed m.el-kenawy mohammed Hadwan Rokaia m.Zaki Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Communications and electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaizYemen Intelligent Analytics Group(IAG) College of ComputerQassim UniversityBuraydahSaudi Arabia Higher Institute of Engineering and Technology KafrelsheikhEgypt Department of electrical Engineering Shoubra Faculty of EngineeringBenha UniversityEgypt

Dipper throated optimization(DTO)algorithm is a novel with a very efficient metaheuristic inspired by the dipper throated *** has its unique hunting technique by performing rapid bowing *** show the efficiency of the proposed algorithm,DTO is tested and compared to the algorithms of Particle Swarm Optimization(PSO),Whale Optimization Algorithm(WOA),Grey Wolf Optimizer(GWO),and Genetic Algorithm(GA)based on the seven unimodal benchmark ***,ANOVA and Wilcoxon rank-sum tests are performed to confirm the effectiveness of the DTO compared to other optimization ***,to demonstrate the proposed algorithm’s suitability for solving complex realworld issues,DTO is used to solve the feature selection *** strategy of using DTOs as feature selection is evaluated using commonly used data sets from the University of California at Irvine(UCI)*** findings indicate that the DTO outperforms all other algorithms in addressing feature selection issues,demonstrating the proposed algorithm’s capabilities to solve complex real-world situations.

关键词： metaheuristic optimization swarmoptimization feature selection function optimization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Spirulina platensis extract improves the production and defenses of the common bean grown in a heavy metals-contaminated saline soil

引用

Journal of Environmental Sciences 2023年第7期129卷 240-257页

作者： mostafa m.Rady Ahmed S.elrys Eman Selem Ahmed A.A.mohsen Safaa m.A.I.Arnaout Ahmed H.el-Sappah Khaled A.el-Tarabily el-Sayed m.Desoky Botany Department Faculty of AgricultureFayoum UniversityFayoum 63514Egypt College of Tropical Crops Hainan UniversityHaikou 570228China Soil Science Department Faculty of AgricultureZagazig UniversityZagazig 44511Egypt Botany and microbiology Department Faculty of ScienceZagazig UniversityZagazig 44511Egypt Horticulture Department Faculty of AgricultureZagazig UniversityZagazig 44511Egypt Botany Department Faculty of AgricultureZagazig UniversityZagazig 44511Egypt Genetics Department Faculty of AgricultureZagazig UniversityZagazig 44511Egypt Department of Biology College of ScienceUnited Arab Emirates UniversityAl-Ain 15551United Arab Emirates Khalifa Center for Genetic Engineering and Biotechnology United Arab Emirates UniversityAl-Ain 15551United Arab Emirates Harry Butler Institute Murdoch UniversityMurdoch 6150Australia

Plants have to cope with several abiotic stresses,including salinity and heavymetals(Hms).Under these stresses,several extracts have been used as effective natural biostimulants,however,the use of Spirulina platensis(SP)extract(SPE)remains *** effects of SPE were evaluated as soil addition(SA)and/or foliar spraying(FS)on antioxidant defenses and Hms content of common bean grown in saline soil contaminated with ***(40 or 80 mg SPE/hill added as SA or 20 or 40 mg SPE/plant added as FS)or integrative(SA+FS)applications of SPE showed significant improvements in the following order:SA-80+FS-40>SA-80+FS-20>SA-40+FS-40>SA-40+FS-20>SA-80>SA-40>FS-40>FS-20>***,the integrative SA+FS with 40 mg SP/plant was the most effective treatment in increasing plant growth and production,overcoming stress effects and minimizing contamination of the edible *** significantly increased plant growth(74%–185%)and yield(107%–227%)by enhancing net photosynthetic rate(78.5%),stomatal conductance(104%),transpiration rate(124%),and contents of carotenoids(60.0%),chlorophylls(49%–51%),and NPK(271%–366%).These results were concurrent with the marked reductions in malondialdehyde(61.6%),hydrogen peroxide(42.2%),nickel(91%–94%),lead(80%–9%),and cadmium(74%–91%)contents due to the improved contents of glutathione(87.1%),ascorbate(37.0%),andα-tocopherol(77.2%),and the activities of catalase(18.1%),ascorbate peroxidase(18.3%),superoxide dismutase(192%),and glutathione reductase(52.2%)as reinforcing ***,this most effective treatment is recommended to mitigate the stress effects of salinity and Hms on common bean production while minimizing Hms in the edible part.

关键词： Antioxidant defense system Biostimulants Heavy metals microalgae extracts Saline soil Soil pollution

来源：

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

Impact of the injected water salinity on oil recovery from sandstone formations:Application in an Egyptian oil reservoir

引用

Petroleum 2022年第1期8卷 53-65页

作者： m.Fouad Snosy mahmoud Abu el ela Ahmed el-Banbi Helmy Sayyouh General Petroleum Company Egypt Cairo University Egypt The American University in Cairo Egypt

In the last decade,there has been an increasing interest in understanding the effects of changing injected water salinity on the performance of oil *** paper aims to investigate the effects of injected water salinity on oil recovery of an Egyptian oil reservoir(Bahariya formation).An experimental work program has been performed using 25 core plugs and 5 different water salinities to study the effects of changing water salinity during both secondary and tertiary stages of *** objectives of the experimental work were to(1)investigate the effects of the low water salinity on oil recovery and(2)identify the optimum water salinity and the main reservoir parameters for application of low salinity waterflooding project(LSWF)in Bahariya *** results revealed that there is an optimum salinity for waterflooding in the secondary flooding ***,for the tertiary flooding stage,the results showed that the controlling factor is not decreasing the salinity,but rather changing the salinity(*** increasing or decreasing).It was also clear that applying the optimum salinity in the secondary recovery stage is more effective than applying it in the tertiary recovery ***,the results showed that the positive impact of LSWF may be expected in reservoirs with high amount of kaolinite,high values of CEC,and low amounts of plagioclase *** study is an original contribution to develop guidelines for designing optimum salinity waterflooding projects in sandstone reservoirs.

关键词： Low salinity Waterflooding LSWF Sandstone Bahariya formation Western desert

来源：

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

Advantages and disadvantages of nuclear reactions used in reactors or cyclotrons,in addition to a theoretical study based on photodisintegration on natural indium for^(111)Ag production

引用

Nuclear Science and Techniques 2022年第2期33卷 1-13页

作者： Khaled m.el-Azony Nader m.A.mohamed Dalal A.Aloraini Radioactive Isotopes and Generators Department Hot Labs.CenterEgyptian Atomic Energy AuthorityP.O.Box 13759CairoEgypt Reactors Department Egyptian Atomic Energy AuthorityP.O.Box 13759CairoEgypt Physics Department College of SciencePrincess Nourah Bint Abdulrahman UniversityRiyadhKingdom of Saudi Arabia

Production routes were recorded on available reactions for^(111)Ag production from nuclear reactors or cyclotrons using a natural palladium target based on^(110)Pd(n,γ)and^(110)pd(d,n)reactions,respectively.^(nat)Cd(γ,x)based on^(110)Cd(γ,p)has also been studied as a prospective reaction for the production of^(111)***,these nuclear reactions are difficult to utilize because,in some cases,they reduce the specific activity of^(111)*** is a consequence of the stable silver isotopes produced in high *** isotopes include^(107,109)Ag and,in other cases,the high impurity of silver radioisotopes,such as^(110)m,^(106)m,^(105)Ag,that are produced during parallel nuclear *** to a scarcity of data regarding the(γ,α)reaction,the gamma reaction on natural indium for^(111)Ag production based on the^(115)In(γ,α)reaction was *** ^(nat)In(γ,α)reaction satisfies the criteria as a possible reaction to produce^(111)Ag with a sufficient yield and purity as consequence of the high^(115)In(95.7%)abundance as an enriched form and a relatively soft background caused by the parallel nuclear reactions.

关键词： Silver-111 Nuclear data Natural cadmium Natural palladium Natural indium

来源：

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

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：