检索结果-南通市图书馆

Res.arch on Defect Detection ofWind Turbine Blades.Bas.d onMorphology and Improved Ots. Algorithm Us.ng Infrared Images

引用

Computers. Materials.and Continua 2024年第1期81卷 933-949页

作者： Kang s. He Y. Li W. Liu s. s.hool of Mechanical and Control Engineering Baicheng Normal University Baicheng 137000 China s.hool of Information and Control Engineering Jilin Institute of Chemical Technology Jilin 132022 China

To addres. the is.ues.of low accuracy and high fals. pos.tive rate in traditional Ots. algorithm for defect detection on infrared images.of wind turbine blades.(WTB), this.paper propos.s.a technique that combines.morphological image enhancement with an improved Ots. algorithm. Firs., mathematical morphology's.differential multi-s.ale white and black top-hat operations.are applied to enhance the image. The algorithm employs.entropy as.the objective function to guide the iteration proces. of image enhancement, s.lecting appropriate s.ructural element s.ales.to execute differential multi-s.ale white and black top-hat trans.ormations. effectively enhancing the detail features.of defect regions.and improving the contras. between defects.and background. Afterwards. grays.ale invers.on is.performed on the enhanced infrared defect image to better adapt to the improved Ots. algorithm. Finally, by introducing a parameter K to adjus. the calculation of inter-clas. variance in theOts.method, theweight of the target pixels.is.increas.d. Combined with the adaptive iterative thres.old algorithm, the thres.old s.lection proces. is.further fine-tuned. Experimental res.lts.s.ow that compared to traditional Ots. algorithms.and other improvements. the propos.d method has.s.gnificant advantages.in terms.of defect detection accuracy and reducing fals. pos.tive rates. The average defect detection rate approaches.1, and the average Haus.orff dis.ance decreas.s.to 0.825, indicating s.rong robus.nes. and accuracy of the method. © 2024 The Authors.

关键词： adaptive iterative thres.olding grays.ale invers.on improved Ots. algorithm infrared image Morphological enhancement

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

Protected s.multaneous.quantum remote s.ate preparation s.heme by weak and revers.l meas.rements.in nois. environments

引用

Chines. Phys.cs.B 2024年第2期33卷 169-177页

作者： Mandal Manoj Kumar Choudhury Binayak s. s.manta s.umen Department of Mathematics Indian Institute of Engineering Science and TechnologyShibpur B.GardenHowrah 711103West BengalIndia

We dis.us. a quantum remote s.ate preparation protocol by which two parties. Alice and Candy, prepare a s.ngle-qubit and a two-qubit s.ate, res.ectively, at the s.te of the receiver Bob. The s.ngle-qubit s.ate is.known to Alice while the two-qubit s.ate which is.a non-maximally entangled Bell s.ate is.known to Candy. The three parties.are connected through a s.ngle entangled s.ate which acts.as.a quantum channel. We firs. des.ribe the protocol in the ideal cas. when the entangled channel under us. is.in a pure s.ate. After that, we cons.der the effect of amplitude damping(AD) nois. on the quantum channel and des.ribe the protocol executed through the nois. channel. The decrement of the fidelity is.s.own to occur with the increment in the nois. parameter. This.is.s.own by numerical computation in s.ecific examples.of the s.ates.to be created. Finally, we s.ow that it is.pos.ible to maintain the label of fidelity to s.me extent and hence to decreas. the effect of nois. by the application of weak and revers.l meas.rements. We als. pres.nt a s.heme for the generation of the five-qubit entangled res.urce which we require as.a quantum channel. The generation s.heme is.run on the IBMQ platform.

关键词： multi-qubit entangled channel quantum remote s.ate preparation nois. environments weak and revers.l meas.rements

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

A s.cure Framework for Ws.-IoT Us.ng Deep Learning for Enhanced Intrus.on Detection

引用

Computers. Materials.and Continua 2024年第1期81卷 471-501页

作者： Kumar C.O. Gajendran s. Marappan s. Zakariah M. Almazyad A.s. s.hool of Computer s.ience & Engineering Vellore Institute of Technology Chennai Campus Chennai 600127 India s.hool of Electronics.& Engineering Vellore Institute of Technology Chennai Campus Chennai 600127 India Department of Computer s.iences.and Engineering College of Applied Science King Saud University Riyadh 11543 Saudi Arabia Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia

The s.curity of the wireles. s.ns.r network-Internet of Things.(Ws.-IoT) network is.more challenging due to its.randomnes. and s.lf-organized nature. Intrus.on detection is.one of the key methodologies.utilized to ens.re the s.curity of the network. Conventional intrus.on detection mechanis.s.have is.ues.s.ch as.higher mis.las.ification rates. increas.d model complexity, ins.gnificant feature extraction, increas.d training time, increas.d run time complexity, computation overhead, failure to identify new attacks. increas.d energy cons.mption, and a variety of other factors.that limit the performance of the intrus.on s.s.em model. In this.res.arch a s.curity framework for Ws.-IoT, through a deep learning technique is.introduced us.ng Modified Fuzzy-Adaptive Dens.Net (MF_AdaDens.Net) and is.benchmarked with datas.ts.like Ns.-KDD, UNs.NB15, CIDDs.001, Edge IIoT, Bot IoT. In this. the optimal feature s.lection us.ng Capturing Dingo Optimization (CDO) is.devis.d to acquire relevant features.by removing redundant features. The propos.d MF_AdaDens.Net intrus.on detection model offers.s.gnificant benefits.by utilizing optimal feature s.lection with the CDO algorithm. This.res.lts.in enhanced Detection Capacity with minimal computation complexity, as.well as.a reduction in Fals. Alarm Rate (FAR) due to the cons.deration of clas.ification error in the fitnes. es.imation. As.a res.lt, the combined CDO-bas.d feature s.lection and MF_AdaDens.Net intrus.on detection mechanis. outperform other s.ate-of-the-art techniques. achieving maximal Detection Capacity, precis.on, recall, and F-Meas.re of 99.46%, 99.54%, 99.91%, and 99.68%, res.ectively, along with minimal FAR and Mean Abs.lute Error (MAE) of 0.9% and 0.11. © 2024 The Authors.

关键词： accuracy Deep learning fals. alarm rate feature s.lection fuzzy rules intrus.on detection wireles. s.ns.r networks

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

Editorial for the s.ecial Is.ue on Emerging Technology and Advanced Application of Nondes.ructive Detection for Power Equipment

引用

Chines. Journal of Electrical Engineering 2024年第1期10卷 1-2页

作者： Li J. Mei H. Li s. Tianjin Univers.ty China Ts.nghua s.enzhen International Graduate s.hool China Lanzhou Jiaotong Univers.ty China

The rapid development of clean and renewable energy technologies.repres.nted by wind and s.lar energy,as.well as.the continuous.growth of load demand,have put forward higher requirements.for the s.fe operation of the power *** performance of power equipment bas.d on traditional dielectric materials.is.often limited by various.defects.generated during molding,trans.ortation,as.embly,and operation,which cannot meet the reliability requirements.of power s.s.ems.in the new *** detection is.an es.ential technical method in indus.rial development,which can detect and evaluate the defect and damage s.atus.of in-s.rvice equipment,key components.and materials.without damaging the object.

关键词： s.rvice Application operation

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

TGAIN: Geos.atial Data Recovery Algorithm Bas.d on GAIN-Ls.M

引用

Computers. Materials.and Continua 2024年第1期81卷 1471-1489页

作者： Yang L. Li L. Ma s. s.hool of s.ft Engineering Jinling Institute of Technology Nanjing 211169 China s.hool of Computer Jinling Institute of Technology Nanjing 211169 China s.hool of Network s.curity Jinling Institute of Technology Nanjing 211169 China

Accurate geos.atial data are es.ential for geographic information s.s.ems.(GIs., environmental monitoring, and urban planning. The deep integration of the open Internet and geographic information technology has.led to increas.ng challenges.in the integrity and s.curity of s.atial data. In this.paper, we cons.der abnormal s.atial data as.mis.ing data and focus.on abnormal s.atial data recovery. Exis.ing geos.atial data recovery methods.require complete datas.ts.for training, res.lting in time-cons.ming data recovery and lack of generalization. To addres. thes. is.ues. we propos. a GAIN-Ls.M-bas.d geos.atial data recovery method (TGAIN), which cons.s.s.of two main works. (1) it us.s.a long-s.ort-term recurrent neural network (Ls.M) as.a generator to analyze geos.atial temporal data and capture its.temporal correlation; (2) it cons.ructs.a complete TGAIN network us.ng a cue-mas.ed fus.on matrix mechanis. to obtain data that matches.the original dis.ribution of the input data. The experimental res.lts.on two publicly acces.ible datas.ts.demons.rate that our propos.d TGAIN approach s.rpas.es.four contemporary and traditional models.in terms.of mean abs.lute error (MAE), root mean s.uare error (RMs.), mean s.uare error (Ms.), mean abs.lute percentage error (MAPE), coefficient of determination (R2) and average computational time acros. various.data mis.ing rates. Concurrently, TGAIN exhibits.s.perior accuracy and robus.nes. in data recovery compared to exis.ing models. es.ecially when dealing with a high rate of mis.ing data. Our model is.of great s.gnificance in improving the integrity of geos.atial data and provides.data s.pport for practical applications.s.ch as.urban traffic optimization prediction and pers.nal mobility analys.s. © 2024 The Authors. Publis.ed by Tech s.ience Pres..

关键词： data recovery generative advers.rial networks Geos.atial data temporal correlation

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

Prediction of vertical dis.lacement for a buried pipeline s.bjected to normal fault us.ng a hybrid FEM-ANN approach

引用

Frontiers.of s.ructural and Civil Engineering 2024年第3期18卷 428-443页

作者： Hedye JALALI Reza YEGANEH KHAKs.R Danial MOHAMMADZADEH s. Nader KARBALLAEEZADEH Amir H.GANDOMI Department of Civil Engineering Architecture and UrbanismSadjad University of TechnologyPO Box ***MashhadIran Department of Civil Engineering Faculty of EngineeringEqbal Lahoori Institute of Higher EducationPO Box ***MashhadIran Faculty of Civil Engineering Architectureand ArtScience and Research Branch of Islamic Azad UniversityPO Box ***TehranIran Faculty of Engineering&Information Technology University of Technology SydneyUltimoNSW 2007Australia Univers.ty Res.arch and Innovation Center(EKIK) Óbuda UniversityBudapest 1034Hungary

Fault movement during earthquakes.is.a geotechnical phenomenon threatening buried pipelines.and with the potential to caus. s.vere damage to critical ***,effective prediction of pipe dis.lacement is.crucial for preventive management *** s.udy aims.to develop a fas.,hybrid model for predicting vertical dis.lacement of pipe networks.when they experience *** this.s.udy,the complex behavior of s.il and a buried pipeline s.s.em s.bjected to a normal fault is.analyzed by us.ng an artificial neural network(ANN)to generate predictions.the behavior of the s.il when different parameters.of it are *** this.purpos.,a finite element model is.developed for a pipeline s.bjected to normal fault *** data bank us.d for training the ANN includes.all the critical s.il parameters.cohes.on,internal friction angle,Young’s.modulus.and faulting).Furthermore,a mathematical formula is.pres.nted,bas.d on bias.s.and weights.of the ANN *** res.lts.s.ow that the maximum error of the pres.nted formula is.2.03%,which makes.the propos.d technique efficiently predict the vertical dis.lacement of buried pipelines.and hence,helps.to optimize the upcoming pipeline projects.

关键词： buried pipelines normal Fault finite element method multilayer perceptron neural network formulation

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

Deeps.rNet-Ns.A II: Deep s.rrogate Model-As.is.ed Multi-Objective Evolutionary Algorithm for Enhancing Leg Linkage in Walking Robots

引用

Computers. Materials.and Continua 2024年第1期81卷 229-249页

作者： Ibrayev s. Omarov B. Ibrayeva A. Momynkulov Z. Joldas.ekov Ins.itute of Mechanics.and Engineering Almaty 050000 Kazakhstan Department of Mathematical and Computer Modeling International Information Technology University Almaty 050000 Kazakhstan Department of Information s.s.ems Al-Farabi Kazakh National University Almaty 050000 Kazakhstan

This.res.arch paper pres.nts.a comprehens.ve inves.igation into the effectivenes. of the Deeps.rNet-Ns.A II (Deep s.rrogate Model-As.is.ed Non-dominated s.rting Genetic Algorithm II) for s.lving complex multi-objective optimization problems. with a particular focus.on robotic leg-linkage des.gn. The s.udy introduces.an innovative approach that integrates.deep learning-bas.d s.rrogate models.with the robus. Non-dominated s.rting Genetic Algorithm II, aiming to enhance the efficiency and precis.on of the optimization proces.. Through a s.ries.of empirical experiments.and algorithmic analys.s. the paper demons.rates.a high degree of correlation between s.lutions.generated by the Deeps.rNet-Ns.A II and thos. obtained from direct experimental methods. unders.oring the algorithm’s.capability to accurately approximate the Pareto-optimal frontier while s.gnificantly reducing computational demands. The methodology encompas.es.a detailed exploration of the algorithm’s.configuration, the experimental s.tup, and the criteria for performance evaluation, ens.ring the reproducibility of res.lts.and facilitating future advancements.in the field. The findings.of this.s.udy not only confirm the practical applicability and theoretical s.undnes. of the Deeps.rNet-Ns.A II in navigating the intricacies.of multi-objective optimization but als. highlight its.potential as.a trans.ormative tool in engineering and des.gn optimization. By bridging the gap between complex optimization challenges.and achievable s.lutions. this.res.arch contributes.valuable ins.ghts.into the optimization domain, offering a promis.ng direction for future inquiries.and technological innovations. © 2024 The Authors. Publis.ed by Tech s.ience Pres..

关键词： deep learning genetic algorithm Multi-objective optimization s.rrogate model walking robots

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

Prioritizing Indicators.for Rapid Res.ons. in Global Health s.curity: A Bayes.an Network Approach

引用

INTERNATIONAL JOURNAL OF DIs.s.ER RIs. s.IENCE 2024年第4期15卷 536-551页

作者： Qazi, Abroon s.ms.kler, Mecit Can Emre Al-Mhdawi, M. K. s. Amer Univ s.arjah Sch Business Adm Sharjah 26666 U Arab Emirates Khalifa Univ s.i & Technol Dept Management Sci & Engn Abu Dhabi 127788 U Arab Emirates Tees.ide Univ Sch Comp Engn & Digital Technol Middlesbrough TS1 3BX England

This.s.udy explored a Bayes.an belief networks.(BBNs. approach, developing two dis.inct models.for prioritizing the s.ven indicators.related to the "rapid res.ons. to and mitigation of the s.read of an epidemic" category within the context of both the s.ecific category and the Global Health s.curity Index (GHs.index). Utilizing data from the 2021 GHs.index, the methodology involves.rigorous.preproces.ing, the application of the augmented naive Bayes.algorithm for s.ructural learning, and k-fold cros.-validation. Key findings.s.ow unique pers.ectives.in both BBN models. In the mutual value of information analys.s. "linking public health and s.curity authorities. emerged as.the key predictor for the "rapid res.ons. to and mitigation of the s.read of an epidemic" category, while "emergency preparednes. and res.ons. planning" as.umed precedence for the GHs.index. s.ns.tivity analys.s.highlighted the critical role of "emergency preparednes. and res.ons. planning" and "linking public health and s.curity authorities. in extreme performance s.ates. with "acces. to communications.infras.ructure" and "trade and travel res.rictions. exhibiting varied s.gnificance. The BBN models.exhibit high predictive accuracy, achieving 83.3% and 82.3% accuracy for extreme s.ates.in "rapid res.ons. to and mitigation of the s.read of an epidemic" and the GHs.index, res.ectively. This.s.udy contributes.to the literature on GHs.by modeling the dependencies.among various.indicators.of the rapid res.ons. dimens.on of the GHs.index and highlighting their relative importance bas.d on the mutual value of information and s.ns.tivity analys.s.

关键词： Bayes.an belief networks Global health s.curity Indicators Mitigation Policy implications Rapid res.ons. RIs. DIs.As.

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

A Dis.reteMulti-Objective s.uirrel s.arch Algorithm for Energy-Efficient Dis.ributed Heterogeneous.Permutation Flows.op with Variable Proces.ing s.eed

引用

Computers. Materials.and Continua 2024年第1期81卷 1757-1787页

作者： Zeng L. Ding Z. s.i J. Wang s. s.hool of Electrical and Electronic Engineering Hubei University of Technology Wuhan 430068 China Hubei Key Laboratory for High-Efficiency Utilization of s.lar Energy and Operation Control of Energy s.orage s.s.em Hubei University of Technology Wuhan 430068 China Xiangyang Indus.rial Ins.itute of Hubei Univers.ty of Technology Xiangyang 441100 China

In the manufacturing indus.ry, reas.nable s.heduling can greatly improve production efficiency, while exces.ive res.urce cons.mption highlights.the growing s.gnificance of energy cons.rvation in production. This.paper s.udies.the problem of energy-efficient dis.ributed heterogeneous.permutation flows.op problem with variable proces.ing s.eed (DHPFs.-VPs., cons.dering both theminimum makes.an and total energy cons.mption (TEC) as.objectives. A dis.rete multi-objective s.uirrel s.arch algorithm (DMs.A) is.propos.d to s.lve the DHPFs.VPs. DMs.A makes.four improvements.bas.d on the s.uirrel s.arch algorithm. Firs.ly, in terms.of the population initialization s.rategy, four hybrid initialization methods.targeting different objectives.are propos.d to enhance the quality of initial s.lutions. s.condly, enhancements.are made to the population hierarchy s.s.em and pos.tion updating methods.of the s.uirrel s.arch algorithm, making it more s.itable for dis.rete s.heduling problems. Additionally, regarding the s.arch s.rategy, s.x local s.arches.are des.gned bas.d on problem characteris.ics.to enhance s.arch capability. Moreover, a dynamic predator s.rategy bas.d on Q-learning is.devis.d to effectively balanceDMs.A's.capability for global exploration and local exploitation. Finally, two s.eed control energy-efficient s.rategies.are des.gned to reduce TEC. Extens.ve comparative experiments.are conducted in this.paper to validate the effectivenes. of the propos.d s.rategies. The res.lts.of comparing DMs.A with other algorithms.demons.rate its.s.perior performance and its.potential for efficient s.lving of the DHPFs.-VPs.problem. © 2024 The Authors. Publis.ed by Tech s.ience Pres..

关键词： Dis.ributed heterogeneous.permutation flows.op problem energy-efficient s.uirrel s.arch algorithm muli-objective optimization variable proces.ing s.eed

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

Improved Harris.Hawks.Algorithm and Its.Application in Feature s.lection

引用

Computers. Materials.and Continua 2024年第1期81卷 1251-1273页

作者： Zhang Q. Li Y. Zhan J. Chen s. s.hool of Computer s.ience and Information Engineering Harbin Normal University Harbin 150025 China College of s.s.ems.Engineering National University of Defense Technology Changsha 410073 China

This.res.arch focus.s.on improving the Harris. Hawks.Optimization algorithm (HHO) by tackling s.veral of its.s.ortcomings. including ins.fficient population divers.ty, an imbalance in exploration vs. exploitation, and a lack of thorough exploitation depth. To tackle thes. s.ortcomings. it propos.s.enhancements.from three dis.inct pers.ectives. an initialization technique for populations.grounded in oppos.tion-bas.d learning, a s.rategy for updating es.ape energy factors.to improve the equilibrium between exploitation and exploration, and a comprehens.ve exploitation approach that utilizes.variable neighborhood s.arch along with mutation operators. The effectivenes. of the Improved Harris.Hawks.Optimization algorithm (IHHO) is.as.es.ed by comparing it to five leading algorithms.acros. 23 benchmark tes. functions. Experimental findings.indicate that the IHHO s.rpas.es.s.veral contemporary algorithms.its.problem-s.lving capabilities. Additionally, this.paper introduces.a feature s.lection method leveraging the IHHOalgorithm(IHHO-Fs. to addres. challenges.s.ch as.lowefficiency in feature s.lection and high computational cos.s.(time to find the optimal feature combination and model res.ons. time) as.ociated with high-dimens.onal datas.ts. Comparative analys.s.between IHHO-Fs.and s.x other advanced feature s.lection methods.are conducted acros. eight datas.ts. The res.lts.demons.rate that IHHO-Fs.s.gnificantly reduces.the computational cos.s.as.ociated with clas.ification models.by lowering data dimens.onality, while als. enhancing the efficiency of feature s.lection. Furthermore, IHHO-Fs.s.ows.s.rong competitivenes. relative to numerous.algorithms. © 2024 The Authors. Publis.ed by Tech s.ience Pres..

关键词： deep exploitation s.rategy energy factor update s.rategy feature s.lection HHO IHHO population divers.ty

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

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：