检索结果-南通市图书馆

Reinforcement Learning with an Ensemble of Binary Action Deep Q-Networks

Computer Systems Science & Engineering 2023年第9期46卷 2651-2666页

作者： A.M.Hafiz M.Hassaballah Abdullah Alqahtani Shtwai Alsubai mohamed abdel hameed Department of Electronics&Communication Engineering Institute of TechnologyUniversity of KashmirSrinagarJ&K190006India Department of Computer Science Faculty of Computers and InformationSouth Valley UniversityQenaEgypt College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAlkhrjKSA Department of Computer Science Faculty of Computers and InformationLuxor UniversityLuxorEgypt

With the advent of Reinforcement Learning(RL)and its continuous progress,state-of-the-art RL systems have come up for many challenging and real-world *** the scope of this area,various techniques are found in the *** such notable technique,Multiple Deep Q-Network(DQN)based RL systems use multiple DQN-based-entities,which learn together and communicate with each *** learning has to be distributed wisely among all entities in such a scheme and the inter-entity communication protocol has to be carefully *** more complex DQNs come to the fore,the overall complexity of these multi-entity systems has increased many folds leading to issues like difficulty in training,need for high resources,more training time,and difficulty in fine-tuning leading to performance *** a cue from the parallel processing found in the nature and its efficacy,we propose a lightweight ensemble based approach for solving the core RL *** uses multiple binary action DQNs having shared state and *** benefits of the proposed approach are overall simplicity,faster convergence and better performance compared to conventional DQN based *** approach can potentially be extended to any type of DQN by forming its *** extensive experimentation,promising results are obtained using the proposed ensemble approach on OpenAI Gym tasks,and Atari 2600 games as compared to recent *** proposed approach gives a stateof-the-art score of 500 on the Cartpole-v1 task,259.2 on the LunarLander-v2 task,and state-of-the-art results on four out of five Atari 2600 games.

关键词： Deep Q-networks ensemble learning reinforcement learning OpenAI Gym environments

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

Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

引用

Digital Communications and Networks 2024年第2期10卷 404-415页

作者： mohamed abdel-Basset Hossam Hawash Nour Moustafa Imran Razzak mohamed Abd Elfattah Faculty of Computers and Informatics Zagazig UniversityZagazigSharqiyah44519Egypt School of Engineering and Information Technology University of New South Wales@ADFACanberraACT2600Australia Deakin University Geelong Waurn Ponds CampusAustralia Computer Science Department Misr Higher Institute for Commerce and ComputersMansoura35511Egypt

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber *** complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning *** Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT *** though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d *** is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other *** paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d ***-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each *** PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 *** empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

关键词： Privacy preservation Federated learning Deep learning Fog computing Smart cities

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

Geochemistry of island arc assemblage in the Eastern Desert of Egypt and the role of Pan-African magmatism in crustal growth of the Arabian–Nubian Shield:A review

引用

Acta Geochimica 2024年第3期43卷 588-622页

作者： abdel-Aal Mabdel-Karim mohamed MHamdy Adel A.Surour Geology Department Faculty of ScienceZagazig UniversityZagazig 44519Egypt Geology Department Faculty of ScienceTanta UniversityTanta 31527Egypt Department of Geological Sciences Faculty of ScienceNew Galala City 43511Egypt Geology Department Faculty of ScienceCairo UniversityGiza 12613Egypt

Neoproterozoic island arc assemblage of the Arabian–Nubian Shield(ANS)in the Eastern Desert(ED)of Egypt comprises juvenile suites of metavolcanics(MV),large amounts of meta-sedimentary rocks(MS),and voluminous metagabbros-diorites(MGD)and syn-tectonic intrusions of older granitoids(OG).We report here the updates of these four rock units in terms of classification,distribution,chemical characteristics,geodynamic evolution,metamorphism,and *** addition,we discuss these integrated data to elucidate a reasonable and reliable model for crustal evolution in the *** main features of these rock units indicate their relation to each other and the geodynamic environment dominated by early immature oceanic island arcs to primitive continental *** information of the island arc metavolcanic and plutonic rocks(gabbros,diorites,tonalites,and granodiorites)furnish evidence of the genetic *** include proximity and a coeval nature in the field;all protolith magmas are subalkaline in nature following calc-alkaline series with minor tholeiitic affinities;common geochemical signature of the arc rocks and subduction-related magmatism;their similar enrichment in LREEs;and similar major element compositions with mafic melts derived from metasomatized mantle *** volcano-sedimentary and the OG rocks underwent multiphase deformation events whereas the MGD complexes deformed *** on the magmatic,sedimentological,and metamorphic evolutions constrained by geochronological data as well as the progressive evolutionary trend from extensional to compressional regimes,a possible gradual decrease in the subducted slab dip angle is the most infl uential in any geodynamic model for arc assemblage in the ED of Egypt.

关键词： Island arc assemblage Magmatism Crustal growth Neoproterozoic Arabian–Nubian Shield Eastern Desert Egypt

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

Model Predictive Current Control for Low-Cost Shunt Active Power Filter

引用

CSEE Journal of Power and Energy Systems 2024年第4期10卷 1589-1598页

作者： Ali A.abdel-Aziz mohamed A.Elgenedy Barry W.Williams the Electronic and Electrical Engineering Department Strathclyde UniversityGlasgowG11XQUK School of Computing Engineering and the Built Environment(SCEBE)Glasgow Caledonian UniversityGlasgowG40BAUK

Performance of a three-phase shunt active power filter(SAPF)relies on the capability of the controller to track the reference ***,designing an accurate current controller is crucial to guarantee satisfactory SAPF *** paper presents a model predictive current controller(MPCC)for a low-cost,four-switch,shunt active power filter for power quality improvement.A four-switch,B4,converter topology is adopted as an SAPF,hence offering a simple,robust,and low-cost *** addition,to further reduce overall cost,only two interfacing filter inductors,instead of three,are used to eliminate switching current *** proposed SAPF model MPCC is detailed for implementation,where simulation and experimental results validate effectiveness of the proposed control algorithm showing a 20%improvement in total harmonic distortion compared with a conventional hysteresis band current controller.

关键词： Four-switch converter harmonic distortion model predictive current control power quality shunt active power filter

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

Thermal noise-driven resonant sensors

引用

Microsystems & Nanoengineering 2024年第3期10卷 259-271页

作者： Yan Qiao Alaaeldin Elhady mohamed Arabi Eihab abdel-Rahman Wenming Zhang School of Mechanical Engineering Shanghai Jiao Tong UniversityShanghaiChina Department of Systems Design Engineering University of WaterlooWaterlooONCanada

MEMS/NEMS resonant sensors hold promise for minute mass and force ***,one major challenge is that conventional externally driven sensors inevitably encounter undesired intrinsic noise,which imposes a fundamental limitation upon their signal-to-noise ratio(SNR)and,consequently,the ***,this restriction becomes increasingly pronounced as sensors shrink to the *** this work,we propose a counterintuitive paradigm shift that turns intrinsic thermal noise from an impediment to a constituent of the sensor by harvesting it as the driving force,obviating the need for external actuation and realizing‘noise-driven’*** sensors employ the dynamically amplified response to thermal noise at resonances for stimulus *** demonstrate that lightly damped and highly compliant nano-structures with high aspect ratios are promising candidates for this class of *** overcome the phase incoherence of the drive force,three noise-enabled quantitative sensing mechanisms are *** validated our sensor paradigm by experimental demonstrating noise-driven pressure and temperature ***-driven sensors offer a new opportunity for delivering practical NEMS sensors that can function at room temperature and under ambient pressure,and a development that suggests a path to cheaper,simpler,and low-power-consumption sensors.

关键词： noise resonant overcome

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

Explainable Conformer Network for Detection of COVID-19 Pneumonia from Chest CT Scan: From Concepts toward Clinical Explainability

引用

Computers, Materials & Continua 2024年第1期78卷 1171-1187页

作者： mohamed abdel-Basset Hossam Hawash mohamed Abouhawwash S.S.Askar Alshaimaa A.Tantawy Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Statistics and Operations Research College of ScienceKing Saud UniversityP.O.Box 2455Riyadh11451Saudi Arabia

The early implementation of treatment therapies necessitates the swift and precise identification of COVID-19 pneumonia by the analysis of chest CT *** study aims to investigate the indispensable need for precise and interpretable diagnostic tools for improving clinical decision-making for COVID-19 *** paper proposes a novel deep learning approach,called Conformer Network,for explainable discrimination of viral pneumonia depending on the lung Region of Infections(ROI)within a single modality radiographic CT ***,an efficient U-shaped transformer network is integrated for lung image ***,a robust transfer learning technique is introduced to design a robust feature extractor based on pre-trained lightweight Big Transfer(BiT-L)and finetuned on medical data to effectively learn the patterns of infection in the input ***,this work presents a visual explanation method to guarantee clinical explainability for decisions made by Conformer *** evaluation of real-world CT data demonstrated that the diagnostic accuracy of ourmodel outperforms cutting-edge studies with statistical *** Conformer Network achieves 97.40% of detection accuracy under cross-validation *** model not only achieves high sensitivity and specificity but also affords visualizations of salient features contributing to each classification decision,enhancing the overall transparency and trustworthiness of our *** findings provide obvious implications for the ability of our model to empower clinical staff by generating transparent intuitions about the features driving diagnostic decisions.

关键词： Deep learning COVID-19 multi-modal medical image fusion diagnostic image fusion

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

Ultralong hydroxyapatite-based forward osmosis membrane for freshwater generation

引用

Frontiers of Chemical Science and Engineering 2024年第9期18卷 37-49页

作者： mohamed Gamal Gomaa Hamdy Maamoun abdel-Ghafar Francesco Galiano Francesca Russo Alberto Figoli El-Sayed Ali abdel-Aal abdel-Hakim Taha Kandil Bahaa Ahmed Salah Central Metallurgical Research and Development Institute(CMRDI) 11421 CairoEgypt Chemistry Department Faculty of ScienceHelwan University11795 CairoEgypt Institute on Membrane Technology(CNR-ITM) 87036 RendeItaly

Increasing global water shortages are accelerating the pace of membrane manufacturing,which generates many environmentally harmful *** challenges need a radical rethink of developing innovative membranes that can address freshwater production without generating environmentally harmful *** work utilized the synthesized ultra-long hydroxyapatite(UHA)by the solvothermal method using the green solvent oleic acid in preparing UHA-based forward osmosis *** membranes were developed using different loading ratios of graphene oxide(GO)by vacuum-assisted filtration *** prepared GO/UHA membranes were identified using X-ray diffraction,scanning electron microscope,Fourier-transform infrared spectroscopy,and X-ray photoelectron *** contact angle and pore size distribution were determined for the obtained GO/UHA *** obtained hierarchical porous structure in the prepared membranes with interconnected channels results in a stable water flux with reverse salt *** best water flux rate of 42±2 L·m^(–2)·h^(–1)was achieved using the 50 mg GO/UHA membrane,which is 3.3 times higher than the pristine membrane,and a reverse salt flux of 67 g·m^(-2)·h^(–1).The obtained results showed a promising capability of a new generation of sustainable inorganic-based membranes that can be utilized in freshwater generation by energy-efficient techniques such as forward osmosis.

关键词： forward osmosis ultra-long hydroxyapatite graphene oxide inorganic-based membrane

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

Oil-source correlation and Paleozoic source rock analysis in the Siwa Basin,Western Desert:Insights from well-logs,Rock-Eval pyrolysis,and biomarker data

引用

Energy Geoscience 2024年第3期5卷 313-327页

作者： mohamed I.abdel-Fattah mohamed Reda mohamed Fathy Diaa A.Saadawi Fahad Alshehri mohamed S.Ahmed Petroleum Geosciences and Remote Sensing Program Department of Applied Physics and AstronomyCollege of SciencesUniversity of SharjahSharjah27272United Arab Emirates Geology Department Faculty of ScienceSuez Canal UniversityIsmailiaEgypt Faculty of Science Geology DepartmentAl-Azhar UniversityP.O.Box 11884Nasr CityCairoEgypt Abdullah Alrushaid Chair for Earth Science Remote Sensing Research Geology and Geophysics DepartmentCollege of ScienceKing Saud UniversityRiyadh11451Saudi Arabia

Understanding the origins of potential source rocks and unraveling the intricate connections between reservoir oils and their source formations in the Siwa Basin(Western Desert,Egypt)necessitate a thorough oil-source correlation *** objective is achieved through a meticulous analysis of well-log responses,Rock-Eval pyrolysis,and biomarker *** analysis of Total Organic Carbon across 31 samples representing Paleozoic formations in the Siwa A-1X well reveals a spectrum of organic richness ranging from 0.17 wt%to 2.04 wt%,thereby highlighting diverse levels of organic content and the presence of both Type II and Type III *** of the fingerprint characteristics of eight samples from the well suggests that the Dhiffah Formation comprises a blend of terrestrial and marine organic ***,a significant contribution from more oxidized residual organic matter and gas-prone Type III kerogen is ***,the Desouky and Zeitoun formations exhibit mixed organic matter indicative of a transitional environment,and thus featuring a pronounced marine influence within a more reducing setting,which is associated with Type II *** analysis of five oil samples from different wells—SIWA L-1X,SIWA R-3X,SIWA D-1X,PTAH 5X,and PTAH 6X,it is evident that terrestrial organic matter,augmented by considerable marine input,was deposited in an oxidizing environment,and contains Type III *** scrutiny confirms the coexistence of mixed terrestrial organic matter within varying redox *** is the uniformity of identified kerogen Types II and III across all samples,known to have potential for hydrocarbon *** discovery presented in this paper unveils captivating prospects concerning the genesis of oil in the Jurassic Safa reservoir,suggesting potential links to Paleozoic sources or even originating from the Safa Member *** revelations mark a substantial advancement in understanding source

关键词： Biomarker data Oil-source correlation Rock-Eval pyrolysis Source rocks Siwa Basin

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

Garlic Clove Catalyzed Biginelli Reaction in Water at Ambient Temperature

引用

Green and Sustainable Chemistry 2013年第4期3卷 141-145页

作者： Hishame Abd-Elnabi Afaf mohamed abdel hameed Ramadan Ahmed Mekheimer Reham R. Awed Kamal Usef Sadek Department of Chemistry Faculty of Science El-Minia University El-Minia Egypt Department of Chemistry Faculty of Science El-Minia University El-Minia Egypt Department of Chemistry Faculty of Science for Girls King Abdulaziz University Jeddah KSA

A simple, green and highly efficient procedure for the Biginelli condensation reaction of aldehydes, β-ketoesters, urea or thiourea catalyzed by crushed garlic clove at ambient temperature is reported.

关键词： Garlic Glove Biocatalysis Water Biginelli Reaction

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 new technique for fault diagnosis in transformer insulating oil based on infrared spectroscopy measurements

引用

High Voltage 2024年第2期9卷 319-335页

作者： mohamed M.F.Darwish mohamed H.A.Hassan Nagat M.K.abdel-Gawad Matti Lehtonen Diaa-Eldin A.Mansour Department of Electrical Engineering Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of Electrical Engineering and Automation School of Electrical EngineeringAalto UniversityEspooFinland Department of Electrical Power Engineering Egypt-Japan University of Science and Technology(E-JUST)New Borg El-Arab CityEgypt Department of Electrical Power and Machines Engineering Faculty of EngineeringTanta UniversityTantaEgypt

Condition monitoring of the insulating system within power transformers has a massive importance according to the electrical *** gas analysis(DGA)is frequently used for this ***,DGA lacks the necessary level of accuracy to identify all equipment faults,particularly in their initial stages of ***,it does not have the capability for real-time monitoring and relies on manual sampling and laboratory testing,causing potential delays in fault ***,the interpretation of DGA data necessitates specialised expertise,which may pose difficulties for smaller entities that have limited access to ***,the contribution of this research is to use infrared spectroscopy measurements as a new effective technique substituting the DGA method for fault diagnosis in insulating *** inception faults that were considered in this study were the electrical fault(discharges of high energy)and the thermal fault(300°C

关键词： fault diagnosis spectroscopy

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：