检索结果-南通市图书馆

Optimizing Optical Fiber Faults Detection:A Comparative Analysis of Advanced Machine Learning Approaches

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5期79卷 2697-2721页

作者： Kamlesh Kumar Soothar Yuanxiang Chen Arif hussain Magsi Cong Hu hussain Shah School of Electronics Engineering Beijing University of Posts and TelecommunicationsBeijing100876China State Key Laboratory of Integrated Services Networks Xidian UniversityXi’an710071China State Key Laboratory ofNetworking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing100876China

Efficient optical network management poses significant importance in backhaul and access network communicationfor preventing service disruptions and ensuring Quality of Service(QoS)*** emerging faultsin optical networks introduce challenges that can jeopardize the network with a variety of *** existingliterature witnessed various partial or inadequate *** the other hand,Machine Learning(ML)hasrevolutionized as a promising technique for fault detection and *** traditional fault managementsystems,this research has three-fold ***,this research leverages the ML and Deep Learning(DL)multi-classification system and evaluates their accuracy in detecting six distinct fault types,including fiber cut,fibereavesdropping,splicing,bad connector,bending,and PC ***,this paper assesses the classificationdelay of each classification ***,this work proposes a fiber optics fault prevention algorithm thatdetermines to mitigate the faults *** work utilized a publicly available fiber optics dataset namedOTDR_Data and applied different ML classifiers,such as Gaussian Naive Bayes(GNB),Logistic Regression(LR),Support Vector Machine(SVM),K-Nearest Neighbor(KNN),Random Forest(RF),and Decision Tree(DT).Moreover,Ensemble Learning(EL)techniques are applied to evaluate the accuracy of various *** addition,this work evaluated the performance of DL-based Convolutional Neural Network and Long-Short Term Memory(CNN-LSTM)hybrid *** findings reveal that the CNN-LSTM hybrid technique achieved the highestaccuracy of 99%with a delay of 360 *** the other hand,EL techniques improved the accuracy in detecting fiberoptic ***,this research comprehensively assesses accuracy and delay metrics for various classifiers andproposes the most efficient attack detection system in fiber optics.

关键词： Fiber optics fault detection multiclassification machine learning ensemble learning

Energy management of buildings with energy storage and solar photovoltaic:A diversity in experience approach for deep reinforcement learning agents

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Energy and AI 2024年第1期15卷 1-14页

作者： Akhtar hussain Petr Musilek Department of Electrical and Computer Engineering University of AlbertaEdmontonT6G 2G2ABCanada Department of Applied Cybernetics University of Hradec Králové50003Hradec KrálovéCzech Republic

Deep reinforcement learning(DRL)is a suitable approach to handle uncertainty in managing the energy consumption of buildings with energy storage ***,DRL agents are trained by randomly selecting samples from a data set,which can result in overexposure to some data categories and under/no exposure to other data ***,the trained model may be biased towards some data groups and underperform(provide suboptimal results)for data groups to which it was less *** address this issue,diversity in experience-based DRL agent training framework is proposed in this *** approach ensures the exposure of agents to all types of *** proposed framework is implemented in two *** the first step,raw data are grouped into different clusters using the K-means clustering *** clustered data is then arranged by stacking the data of one cluster on top of *** the second step,a selection algorithm is proposed to select data from each cluster to train the DRL *** frequency of selection from each cluster is in proportion to the number of data points in that cluster and therefore named the proportional selection *** analyze the performance of the proposed approach and compare the results with the conventional random selection method,two indices are proposed in this study:the flatness index and the divergence *** model is trained using different data sets(1-year,3-year,and 5-year)and also with the inclusion of solar *** simulation results confirmed the superior performance of the proposed approach to flatten the building’s load curve by optimally operating the energy storage system.

关键词： Battery energy storage Building demand management Deep reinforcement learning Diversity in experience Energy management

A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

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8期80卷 2099-2119页

作者： Tajmal hussain Jungpyo Hong Jongwon Seok Department of Information and Communication Engineering Changwon National UniversityChangwon51140Republic of Korea

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational *** technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing *** this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing ***,features are extracted by the VGG19 convolutional ***,after processing through the GAP layer,the extracted features are fed to the SVM classifier for *** this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the *** outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS ***,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

关键词： Smart manufacturing steel defect detection deep learning CNN

Contribution of hydro energy production,economic complexity and technological innovation in achieving an environmentally sustainable Asia

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geoscience Frontiers 2024年第5期15卷 515-528页

作者： Farah Rana Bilal hussain Abdelmohsen A.Nassani Ayesha hussain Mohamed Haffar Syed Asif Ali Naqvi Department of Economics Government College UniversityFaisalabadPakistan Government Graduate College Gojra Toba Tek SinghPakistan Department of Management College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh 11587Saudi Arabia Department of Home Economics Government College Women University FaisalabadPakistan Department of Management Birmingham Business SchoolUniversity of BirminghamUnited Kingdom

The impact of hydro energy production,economic complexity,urbanization,technological innovation and financial development on environmental sustainability between 1995 and 2017 is examined for a panel of thirteen Asian economies using two environmental proxies—their ecological footprint and CO_(2)*** non-parametric Driscoll-Kraay standard error method and the Dumitrescu-Hurlin panel causality test are applied to the *** findings show that hydro energy production and technological innovation have a significant negative impact on the environment,thus promoting environmental *** complexity significantly lowers environmental sustainability while the non-linear effect of economic complexity favors environmental sustainability;this confirms the existence of an economic-complexity-based inverted-U-shaped environmental Kuznets curve ***,urbanization and financial development significantly decrease environmental *** results of our study confirm the feedback causality between hydro energy production and carbon dioxide *** recommend expansionary policies regarding hydro energy production that are beneficial for substituting fossil fuel *** paves a path towards environmental sustainability in this era of global boiling.

关键词： Hydro energy production Environmental sustainability Global boiling Economic complexity Asian countries Panel corrected standard error

Attitude-adjusting dynamical behavior of cubic rover on low-gravity testbed

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Astrodynamics 2024年第1期8卷 149-159页

作者： Bowen Jiang Muhammad Talha hussain Xiangyuan Zeng School of Automation Beijing Institute of TechnologyBeijing100081China

Cubic rovers that traverse by hopping systems are promising in low-gravity *** several analyses of the control methods and mobility of the cubic rover are available,investigations of its attitude-adjusting behavior are still *** study derives the dynamic equations of the two attitude-adjusting modes of the cubic rover,referred to as walking and *** relationships between the speed threshold and rotation angle of the cubic rover were investigated in both rigid and regolith environments using a self-designed low-gravity *** studies were conducted by considering the experimental and simulated *** results of this study can be interesting for roving mission planning when exploring planetary moons and small celestial bodies.

关键词： low-gravitytestbed attitude-adjusting motion cubic rover experimental study

Accelerated Particle Swarm Optimization Algorithm for Efficient Cluster Head Selection in WSN

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 3585-3629页

作者： Imtiaz Ahmad Tariq hussain Babar Shah Altaf hussain Iqtidar Ali Farman Ali Institute of Computer Sciences and Information Technology The University of AgriculturePeshawarPakistan School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhouChina College of Technological Innovation Zayed UniversityDubaiUnited Arab Emirates School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Department of Applied AI School of ConvergenceCollege of Computing and InformaticsSungkyunkwan UniversitySeoul03063South Korea

Numerous wireless networks have emerged that can be used for short communication ranges where the infrastructure-based networks may fail because of their installation and *** of them is a sensor network with embedded sensors working as the primary nodes,termed Wireless Sensor Networks(WSNs),in which numerous sensors are connected to at least one Base Station(BS).These sensors gather information from the environment and transmit it to a BS or gathering *** have several challenges,including throughput,energy usage,and network lifetime *** strategies have been applied to get over these *** may,therefore,be thought of as the best way to solve such ***,it is crucial to analyze effective Cluster Head(CH)selection to maximize efficiency throughput,extend the network lifetime,and minimize energy *** paper proposed an Accelerated Particle Swarm Optimization(APSO)algorithm based on the Low Energy Adaptive Clustering Hierarchy(LEACH),Neighboring Based Energy Efficient Routing(NBEER),Cooperative Energy Efficient Routing(CEER),and Cooperative Relay Neighboring Based Energy Efficient Routing(CR-NBEER)*** the help of APSO in the implementation of the WSN,the main methodology of this article has taken *** simulation findings in this study demonstrated that the suggested approach uses less energy,with respective energy consumption ranges of 0.1441 to 0.013 for 5 CH,1.003 to 0.0521 for 10 CH,and 0.1734 to 0.0911 for 15 *** sending packets ratio was also raised for all three CH selection scenarios,increasing from 659 to *** number of dead nodes likewise dropped for the given combination,falling between 71 and *** network lifetime was deemed to have risen based on the results found.A hybrid with a few valuable parameters can further improve the suggested APSO-based *** to underwater,WSN can make use of the proposed *** overall results have been evaluated and

关键词： Wireless sensor network cluster head selection low energy adaptive clustering hierarchy accelerated particle swarm optimization

Intelligent algorithm-based maximum power point tracker for an off-grid photovoltaic-powered direct-current irrigation system

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Clean Energy 2024年第3期8卷 48-61页

作者： hussain Attia Maen Takruri Ali Al-Ataby Department of Electrical Electronics and Communications EngineeringAmerican University of Ras Al KhaimahRas Al KhaimahUnited Arab Emirates

This research aims to enhance the performance of photovoltaic(PV)systems on a 2-fold ***,it introduces an advanced deep artificial neural network algorithm for accurate and fast maximum power point tracking,ensuring optimal extraction of electrical power from PV ***,it proposes the use of 96-V,2.98-kW direct-current(DC)water pumps for farm irrigation,aiming to improve efficiency,reduce cost and complexity,and overcome challenges associated with connecting faraway farm irrigation systems to the utility *** this study,it has been demonstrated that the use of DC pumps greatly improves system performance and efficiency by eliminating the need for isolation transformers,power passive filters and inverters,therefore simplifying the architecture of the *** efficacy of the proposed methodology is confirmed by MATLAB®/Simulink®simulation results,whereby the proposed algorithm attains a mean squared error of 6.5705×10^(-5)and a system efficiency approaching 99.8%,ensuring a steady voltage under varying load conditions.

关键词： artificial neural network photovoltaic arrays maximum power point tracking buck converter direct-current irrigation systems MATLAB/Simulink

PdCu alloy anchored defective titania for photocatalytic conversion of carbon dioxide into methane with 100% selectivity

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 Energy Chemistry 2024年第4期91卷 254-265页

作者： Lina Zhang Sajjad hussain Qiuye Li Jianjun Yang National&Local Joint Engineering Research Center for Applied Technology of Hybrid Nanomaterials Henan UniversityKaifeng 475004HenanChina

The photoreduction of CO_(2)into CH_(4)with simultaneous high activity and selectivity is a promising strategy to increase energy supply and alleviate global ***,the absence of the active sites that is responsible for the adsorption and activation of CO_(2)and the generation of CO and H2via side reactions often lead to poor efficiency and low selectivity of the ***,Cu,Pd,and PdCu metal clusters cocatalyst-anchored defective TiO_(2)nanotubes(Cu/TiO_(2)-SBO,Pd/TiO_(2)-SBO,and Pd1Cu1/TiO_(2)-SBO)were designed via a simple solution impregnation reduction and applied for photocatalytic conversion of CO_(2)to CH_(4).The Pd1Cu1/TiO_(2)-SBO photocatalyst exhibits excellent catalytic performance among the other catalysts for photoreduction of CO_(2)into CH_(4).More interestingly,the product selectivity of CH_(4)reaches up to 100%with a rate of 25μmol g^(-1)h^(-1).In-situ diffuse reflectance infrared Fourier transform spectroscopy(DRIFTS)and density functional theory(DFT)simulations indicate that the main reasons for the high selectivity of CH_(4)are attributed to the PdCu alloy and oxygen vacancies,which jointly enhance the photoinduced carrier separation and lower energy barriers of key ***,due to the tunable d-band center of the Cu site in the PdCu alloy,the generated intermediates can be well prevented from poisoning and promoted to participate in further ***,the current study will provide insight into the development of new,highly selective photocatalysts for the visible light-catalytic reduction of CO_(2)into CH_(4).

关键词： PdCu alloy Defective TiO_(2) Photoreduction of CO_(2) Photocatalytic mechanism

Deep Learning for Financial Time Series Prediction:A State-of-the-Art Review of Standalone and HybridModels

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

Computer Modeling in Engineering & Sciences 2024年第4期139卷 187-224页

作者： Weisi Chen Walayat hussain Francesco Cauteruccio Xu Zhang School of Software Engineering Xiamen University of TechnologyXiamen361024China Peter Faber Business School Australian Catholic UniversityNorth Sydney2060Australia Department of Information Engineering Polytechnic University of MarcheAncona60121Italy

Financial time series prediction,whether for classification or regression,has been a heated research topic over the last *** traditional machine learning algorithms have experienced mediocre results,deep learning has largely contributed to the elevation of the prediction ***,the most up-to-date review of advanced machine learning techniques for financial time series prediction is still lacking,making it challenging for finance domain experts and relevant practitioners to determine which model potentially performs better,what techniques and components are involved,and how themodel can be designed and *** review article provides an overview of techniques,components and frameworks for financial time series prediction,with an emphasis on state-of-the-art deep learning models in the literature from2015 to 2023,including standalonemodels like convolutional neural networks(CNN)that are capable of extracting spatial dependencies within data,and long short-term memory(LSTM)that is designed for handling temporal dependencies;and hybrid models integrating CNN,LSTM,attention mechanism(AM)and other *** illustration and comparison purposes,models proposed in recent studies are mapped to relevant elements of a generalized framework comprised of input,output,feature extraction,prediction,and related *** the state-of-the-artmodels,hybrid models like CNNLSTMand CNN-LSTM-AM in general have been reported superior in performance to stand-alone models like the CNN-only *** remaining challenges have been discussed,including non-friendliness for finance domain experts,delayed prediction,domain knowledge negligence,lack of standards,and inability of real-time and highfrequency *** principal contributions of this paper are to provide a one-stop guide for both academia and industry to review,compare and summarize technologies and recent advances in this area,to facilitate smooth and informed implementation,and t

关键词： Financial time series prediction convolutional neural network long short-term memory deep learning attention mechanism finance