检索结果-南通市图书馆

维普期刊数据库

etsi releases middlebox security protocols framework specification

在线全文

学校读者我要写书评

暂无评论

China Standardization 2021年第1期 56-56页

作者： etsi etsi

etsi published a new specification, etsi TS 103 523-1:Part 1 of the Middlebox Security Protocol (MSP) series, which defines the security properties of a Middlebox Security *** are vital in modern networks--from new 5G deployments, with ever-faster networks that need performance management, to resisting new cyberattacks with evolved threat defense that copes with encrypted traffic, to VPN provision.

关键词： etsi releases middlebox security protocols framework specification

etsi releases standard for cyber digital evidence bag to confirm integrity of data in legal proceedings

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

China Standardization 2020年第3期 62-62页

作者： etsi etsi

The etsi Technical Committee CYBER has recently released a key standard for digital evidence bag(DEB).etsi TS 103 643 covers "techniques for assurance of digital material used in legal proceedings" and provides a set ...

关键词：

A Novel Attack on Complex APUFs Using the Evolutionary Deep Convolutional Neural Network

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第9期37卷 3059-3081页

作者： Ali Ahmadi Shahrakht Parisa Hajirahimi Omid Rostami Diego Martín Department of Industrial Engineering Sharif University of TechnologyTehran14588-89694Iran Department of Business Administration Boston UniversityBostonMA02215USA Department of Industrial Engineering University of HoustonHoustonTX77204USA etsi de Telecomunicación Universidad Politécnica de MadridMadrid28040Spain

As the internet of things(IoT)continues to expand rapidly,the significance of its security concerns has grown in recent *** address these concerns,physical unclonable functions(PUFs)have emerged as valuable tools for enhancing IoT *** leverage the inherent randomness found in the embedded hardware of IoT ***,it has been shown that some PUFs can be modeled by attackers using machine-learning-based *** this paper,a new deep learning(DL)-based modeling attack is introduced to break the resistance of complex *** training DL models is a problem that falls under the category of NP-hard problems,there has been a significant increase in the use of meta-heuristics(MH)to optimize DL ***,it is widely recognized that finding the right balance between exploration and exploitation when dealing with complex problems can pose a significant *** address these chal-lenges,a novel migration-based multi-parent genetic algorithm(MBMPGA)is developed to train the deep convolutional neural network(DCNN)in order to achieve a higher rate of accuracy and convergence speed while decreas-ing the run-time of the *** the proposed MBMPGA,a non-linear migration model of the biogeography-based optimization(BBO)is utilized to enhance the exploitation ability of GA.A new multi-parent crossover is then introduced to enhance the exploration ability of *** behavior of the proposed MBMPGA is examined on two real-world optimization *** benchmark problems,MBMPGA outperforms other MH algorithms in convergence *** proposed model are also compared with previous attacking models on several simulated challenge-response pairs(CRPs).The simulation results on the XAPUF datasets show that the introduced attack in this paper obtains more than 99%modeling accuracy even on *** addition,the proposed MBMPGA-DCNN outperforms the state-of-the-art modeling attacks in a reduced timeframe and with a smaller number of requi

关键词： IoT security PUFs modeling attacks evolutionary deep learning migration-based multi-parent genetic algorithm

Secrecy Outage Probability Minimization in Wireless-Powered Communications Using an Improved Biogeography-Based Optimization-Inspired Recurrent Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3971-3991页

作者： Mohammad Mehdi Sharifi Nevisi Elnaz Bashir Diego Martín Seyedkian Rezvanjou Farzaneh Shoushtari Ehsan Ghafourian Department of Industrial Engineering Iran University of Science and TechnologyNarmakTehran16846-13114Iran Department of Computer Science Iowa State UniversityAmesIowaIA50011USA etsi de Telecomunicación Universidad Politécnica de MadridMadrid28040Spain Department of Engineering California State University East BayHaywardCalifornia94542USA Department of Industrial Engineering Bu-Ali Sina UniversityHamedan65178-38695Iran

This paper focuses on wireless-powered communication systems,which are increasingly relevant in the Internet of Things(IoT)due to their ability to extend the operational lifetime of devices with limited *** main contribution of the paper is a novel approach to minimize the secrecy outage probability(SOP)in these *** SOP is crucial for maintaining the confidentiality and integrity of data,especially in situations where the transmission of sensitive data is *** proposed method harnesses the power of an improved biogeography-based optimization(IBBO)to effectively train a recurrent neural network(RNN).The proposed IBBO introduces an innovative migration *** core advantage of IBBO lies in its adeptness at maintaining equilibrium between exploration and *** is accomplished by integrating tactics such as advancing towards a random habitat,adopting the crossover operator from genetic algorithms(GA),and utilizing the global best(Gbest)operator from particle swarm optimization(PSO)into the IBBO *** IBBO demonstrates its efficacy by enabling the RNN to optimize the system parameters,resulting in significant outage probability *** comprehensive simulations,we showcase the superiority of the IBBO-RNN over existing approaches,highlighting its capability to achieve remarkable gains in SOP *** paper compares nine methods for predicting outage probability in wireless-powered *** IBBO-RNN achieved the highest accuracy rate of 98.92%,showing a significant performance *** contrast,the standard RNN recorded lower accuracy rates of 91.27%.The IBBO-RNN maintains lower SOP values across the entire signal-to-noise ratio(SNR)spectrum tested,suggesting that the method is highly effective at optimizing system parameters for improved secrecy even at lower SNRs.

关键词： Wireless-powered communications secrecy outage probability improved biogeography-based optimization recurrent neural network

Compressive strength prediction and optimization design of sustainable concrete based on squirrel search algorithm-extreme gradient boosting technique

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2023年第9期17卷 1310-1325页

作者： Enming LI Ning ZHANG Bin XI Jian ZHOU Xiaofeng GAO etsi Minas y Energía Universidad Politécnica de MadridMadrid 28003Spain Leibniz Institute of Ecological Urban and Regional Development(IOER) Dresden 01217Germany Department of Civil and Environmental Engineering Politecnico Di MilanoMilano 20133Italy School of Resources and Safety Engineering Central South UniversityChangsha 410083China Key Laboratory of the Three Gorges Reservoir Region’s Eco-Environment(Ministry of Education) College of Environment and EcologyChongqing UniversityChongqing 400045China

Concrete is the most commonly used construction ***,its production leads to high carbon dioxide(CO_(2))emissions and energy ***,developing waste-substitutable concrete components is *** the sustainability and greenness of concrete is the focus of this *** this regard,899 data points were collected from existing studies where cement,slag,fly ash,superplasticizer,coarse aggregate,and fine aggregate were considered potential influential *** complex relationship between influential factors and concrete compressive strength makes the prediction and estimation of compressive strength *** of the traditional compressive strength test,this study combines five novel metaheuristic algorithms with extreme gradient boosting(XGB)to predict the compressive strength of green concrete based on fly ash and blast furnace *** intelligent prediction models were assessed using the root mean square error(RMSE),coefficient of determination(R^(2)),mean absolute error(MAE),and variance accounted for(VAF).The results indicated that the squirrel search algorithm-extreme gradient boosting(SSA-XGB)yielded the best overall prediction performance with R^(2) values of 0.9930 and 0.9576,VAF values of 99.30 and 95.79,MAE values of 0.52 and 2.50,RMSE of 1.34 and 3.31 for the training and testing sets,*** remaining five prediction methods yield promising ***,the developed hybrid XGB model can be introduced as an accurate and fast technique for the performance prediction of green ***,the developed SSA-XGB considered the effects of all the input factors on the compressive *** ability of the model to predict the performance of concrete with unknown proportions can play a significant role in accelerating the development and application of sustainable concrete and furthering a sustainable economy.

关键词： sustainable concrete fly ash slay extreme gradient boosting technique squirrel search algorithm parametric analysis

维普期刊数据库

Fungal diversity and community composition responses to the reintroduction of fire in a non-managed Mediterranean shrubland ecosystem

在线全文

学校读者我要写书评

暂无评论

Forest Ecosystems 2023年第2期10卷 268-278页

作者： Juncal Espinosa Tatek Dejene Mercedes Guijarro Xim Cerdá Javier Madrigal Pablo Martín-Pinto Centre for the Research and Technology of Agro-Environmental and Biological Sciences University of Trás-os-Montes e Alto DouroVila RealPortugal Sustainable Forest Management Research Institute University of ValladolidPalenciaSpain Ethiopian Forestry Development Addis AbabaEthiopia Instituto de Ciencias Forestales(ICIFOR-INIA) CSICMadridSpain Estaciógica de Doñana CSICSevillaSpain University Polytechnic of Madrid ETSI MontesForestal y Medio NaturalMadridSpain

Background:More than a decade of fire suppression has changed the structure of fire-adapted shrubland ecosystems in Spain’s National Parks,which are now at extreme risk of uncontrolled *** burning can mitigate the risk of wildfires by reducing the fuel load but prescribed burning may also alter the soil properties and reduce microbial and fungal activity,causing changes in the availability of nutrients deep in the soil *** fungal communities are a vital part of post-fire restoration,some fire effects remain *** examine the short-term effects of prescribed burning on soil fungal communities in Doñana Biological Reserve(SW Spain),we collected soil samples pre-burn and 1 day,6 and 12 months post-burn from burned plots to perform physicochemical and metabarcode DNA ***:Prescribed burning had no significant effect on the total fungal operational taxonomic unit richness and ***,changes in soil pH,nitrogen and potassium content post-burn affected fungal community *** non-significant changes in pH and phosphorous affected the composition of ectomycorrhizal ***:The ectomycorrhizal fungal community appears to be resilient to the effects of low-to moderate-intensity fires and saprotrophic taxa may benefit from this kind of *** finding revealed that prescribed burning is a potentially valuable management tool for reducing fire hazards in shrublands that has little effect on the total richness and abundance of fungal communities.

关键词： Doñana National Park Ectomycorrhizal fungi Fire ecology Forest management Global change Prescribed burning Wildfire Saprotrophic fungi

维普期刊数据库

Drilling Titanium Aluminides with Twist Drills

在线全文

学校读者我要写书评

暂无评论

材料科学与工程（中英文版） 2011年第2期5卷 161-164页

作者： Beranoagirre Aitor Lopez de Lacalle L.N. Lamikiz A. Olvera D. Urbicain G. University of the Basque Country UPV-EUP Plaza Europa nal San Sebastion 20018 Spain University of the Basque Country UPV-ETSI Alameda Urquijo s/n Bilbao 48013 Spain

A Deep Reinforcement Learning-Based Technique for Optimal Power Allocation in Multiple Access Communications

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2024年第1期39卷 93-108页

作者： Sepehr Soltani Ehsan Ghafourian Reza Salehi Diego Martín Milad Vahidi Department of Industrial Engineering College of EngineeringUniversity of HoustonHoustonTX77204USA Department of Computer Science Iowa State UniversityAmesIowaUSA etsi de Telecomunicación Universidad Politécnica de MadridMadridSpain Faculty of School of Plant and Environmental Sciences Virginia Polytechnic Institute and StateUniversityBlacksburgVirginia24060USA

Formany years,researchers have explored power allocation(PA)algorithms driven bymodels in wireless networks where multiple-user communications with interference are ***,data-driven machine learning methods have become quite popular in analyzing wireless communication systems,which among them deep reinforcement learning(DRL)has a significant role in solving optimization issues under certain *** this purpose,in this paper,we investigate the PA problem in a k-user multiple access channels(MAC),where k transmitters(e.g.,mobile users)aim to send an independent message to a common receiver(e.g.,base station)through wireless *** this end,we first train the deep Q network(DQN)with a deep Q learning(DQL)algorithm over the simulation environment,utilizing offline ***,the DQN will be used with the real data in the online training method for the PA issue by maximizing the sumrate subjected to the source ***,the simulation results indicate that our proposedDQNmethod provides better performance in terms of the sumrate compared with the available DQL training approaches such as fractional programming(FP)and weighted minimum mean squared error(WMMSE).Additionally,by considering different user densities,we show that our proposed DQN outperforms benchmark algorithms,thereby,a good generalization ability is verified over wireless multi-user communication systems.

关键词： Deep reinforcement learning deep Q learning multiple access channel power allocation

Enhancing Hyper-Spectral Image Classification with Reinforcement Learning and Advanced Multi-Objective Binary Grey Wolf Optimization

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 3469-3493页

作者： Mehrdad Shoeibi Mohammad Mehdi Sharifi Nevisi Reza Salehi Diego Martín Zahra Halimi Sahba Baniasadi TheWPI Business School Worcester Polytechnic InstituteWorcesterMassachusetts01609-2280USA Department of Industrial Engineering Iran University of Science and TechnologyNarmakTehran16846-13114Iran etsi de Telecomunicación Universidad Politécnica de MadridAv.Complutense 30Madrid28040Spain Department of Civil and Environmental Engineering University of MarylandCollege ParkMaryland20742USA Department of Industrial Engineering College of EngineeringUniversity of HoustonHoustonTexas77204USA

Hyperspectral(HS)image classification plays a crucial role in numerous areas including remote sensing(RS),agriculture,and the monitoring of the *** band selection in HS images is crucial for improving the efficiency and accuracy of image *** process involves selecting the most informative spectral bands,which leads to a reduction in data *** on these key bands also enhances the accuracy of classification algorithms,as redundant or irrelevant bands,which can introduce noise and lower model performance,are *** this paper,we propose an approach for HS image classification using deep Q learning(DQL)and a novel multi-objective binary grey wolf optimizer(MOBGWO).We investigate the MOBGWO for optimal band selection to further enhance the accuracy of HS image *** the suggested MOBGWO,a new sigmoid function is introduced as a transfer function to modify the wolves’*** primary objective of this classification is to reduce the number of bands while maximizing classification *** evaluate the effectiveness of our approach,we conducted experiments on publicly available HS image datasets,including Pavia University,Washington Mall,and Indian Pines *** compared the performance of our proposed method with several state-of-the-art deep learning(DL)and machine learning(ML)algorithms,including long short-term memory(LSTM),deep neural network(DNN),recurrent neural network(RNN),support vector machine(SVM),and random forest(RF).Our experimental results demonstrate that the Hybrid MOBGWO-DQL significantly improves classification accuracy compared to traditional optimization and DL ***-DQL shows greater accuracy in classifying most categories in both datasets *** the Indian Pine dataset,the MOBGWO-DQL architecture achieved a kappa coefficient(KC)of 97.68%and an overall accuracy(OA)of 94.32%.This was accompanied by the lowest root mean square error(RMSE)of 0.94,indicating very precise

关键词： Hyperspectral image classification reinforcement learning multi-objective binary grey wolf optimizer band selection