检索结果-内蒙古大学图书馆

Leveraging Multimodal Ensemble Fusion-Based Deep Learning for COVID-19 on Chest Radiographs

computer Systems Science & engineering 2023年第10期47卷 873-889页

作者： Mohamed Yacin Sikkandar K.Hemalatha M.Subashree S.Srinivasan Seifedine Kadry Jungeun Kim Keejun Han Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Biomedical Engineering Bannari Amman Institute of TechnologySathyamangalam638401India Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Institute of Biomedical Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea Division of Computer Engineering Hansung UniversitySeoul02876Korea

Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its *** researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their *** of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)*** the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical ***,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest *** the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly *** study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and *** major intention of the IFFO-DLEF model is to investigate the presence or absence of *** do so,the presented IFFODLEF model applies image pre-processing at the initial *** addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature ***,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify *** parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification *** experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.

关键词： COVID-19 computer vision deep learning image classification fusion model

来源：评论

学校读者我要写书评

暂无评论

Decision Trees in the Selection of Electric Vehicles Based on Various Parameters 1

Decision Trees in the Selection of Electric Vehicles Based o...

引用

1st International Conference on Cyber Physical Systems, Power Electronics and Electric Vehicles, ICPEEV 2023

作者： Joe Anand, M. Clement Priyadharshini, S. Sujitha Martin, Nivetha Anand, M. Edal Poorani, B. Mohiddin, Shaik Khaja Department of Mathematics Karnataka India Gerizim Academy of Research and Development Pvt. Ltd. Karnataka India Department of Mathematics Tamil Nadu India Cognizant Technology Solutions Karnataka India Kcg College of Technology Department of Mathematics Tamil Nadu India Koneru Lakshmaiah Education Foundation Computer Science and Engineering Andra Pradesh India

ISBN: (纸本)9798350323566

The production of electric vehicles is highly increasing in recent days to meet the demands of alternatives to fuel-based vehicles. The automobile industries are manufacturing new variants of electric vehicles which are both economical and environmentally friendly. As the number of electric vehicles is many in the market it is quite challenging for customers to make decisions on selecting electric vehicles and also the retailers of E-vehicles are confronted with the same challenges of decision making. This paper proposes a decision-making model for selecting E-vehicles by using the machine-learning technique of Decision Trees. The decision-making on selection is based on significant parameters. The data on different E-vehicles with respect to the core parameters are subjected to treatment with the supervised learning technique of Decision Trees in the R environment. In this case, the decision trees are used to classify the E-vehicles into the two categories of feasible and infeasible based on five decision parameters. On comparing the accuracy results of classification with other machine learning techniques, decision trees are found to be more optimal. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Using Sparse Autoencoders to Perform Blind Source Separation of High-Density Myoelectric Signal 33

Using Sparse Autoencoders to Perform Blind Source Separation...

引用

33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

作者： Romano, Marcelo Ramos Duarte, Leonardo Tomazeli Elias, Leonardo Abdala University of Campinas School of Applied Sciences SP Limeira Brazil University of Campinas Neural Engineering Research Laboratory Center for Biomedical Engineering SP Campinas Brazil University of Campinas Department of Electronics and Biomedical Engineering School of Electrical and Computer Engineering SP Campinas Brazil

ISBN: (纸本)9798350324112

A recent approach to address the blind source separation (BSS) problem relies on autoencoders with a discriminator as a generative adversarial network (GAN). However, this model is difficult to train due to the lack of metrics that ensure the convergence of a GAN. In this study, we try to provide an alternative solution by replacing the discriminator with appropriate regularization functions based on prior information on the sources. We tested this solution in the high-density electromyogram (HD-EMG) separation problem for a scenario with synthetic but realistic data and compared it with a classic algorithm from the literature. An interesting feature of the proposal is that it can be easily adapted for other source separation problems. Moreover, although the performance is slightly worse than the state-of the-art HD-EMG algorithm, which considers very detailed information on the problem, our proposal provides good results with a mean rate of agreement of 91.88% between the true and estimated spikes. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Game Theory-Based IoT Efficient Power Control in Cognitive UAV

引用

computers, Materials & Continua 2022年第7期72卷 1561-1578页

作者： Fadhil Mukhlif Norafida Ithnin Omar B.Abdulghafoor Faiz Alotaibi Nourah Saad Alotaibi Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia Electronic and Telecommunication Department College of EngineeringThe American University of KurdistanIraq Faculty of Computer Science and Information Technology Universiti Putra MalaysiaSelangorMalaysia Computer Department Faculty of Applied CollegeImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia

With the help of network densification,network coverage as well as the throughput can be improved via ultra-dense networks(UDNs).In tandem,Unmanned Aerial Vehicle(UAV)communications have recently garnered much attention because of their high agility as well as widespread *** this paper,a cognitive UAV is proposed for wireless nodes power pertaining to the IoT ground ***,the UAV is included in the IoT system as the source of power for the wireless nodes as well as for resource *** quality of service(QoS)related to the cognitive node was considered as a utility function based on pricing scheme that was modelled as a non-cooperative game theory in order to maximise users’net utility ***,an energy efficiency non-cooperative game theory power allocation with pricing scheme(EE-NGPAP)is proposed to obtain an efficient power control within IoT wireless ***,uniqueness and existence of the Nash equilibrium have been demonstrated mathematically and through *** results show that the proposed energy harvest algorithm demonstrated considerable decrease in transmitted power consumption in terms of average power reduction,which is regarded to be apt with the 5Gnetworks’***,the proposed algorithm requires around 4 iterations only to converge to NE which makes the algorithm more suitable in practical heterogeneous scenarios.

关键词： UAV drones WSN IoT game theory energy efficiency 5G&B5G networks

来源：评论

学校读者我要写书评

暂无评论

Energy Landscape of the European Union: Assessing Convergence and Import Dependency

Energy Landscape of the European Union: Assessing Convergenc...

引用

International Conference on Advanced computer Information Technologies (ACIT)

作者： Nataliia Dziubanovska Vadym Maslii Iryna Hural Department of Applied Mathematics West Ukrainian National University Ternopil Ukraine Department of Computer Engineering West Ukrainian National University Ternopil Ukraine

ISBN: (数字)9798350350043

ISBN: (纸本)9798350350050

This research aims to analyze energy convergence and import dependency in European Union (EU) countries. By applying cluster analysis, the authors identified three main groups of EU countries based on their level of energy efficiency, each characterized by distinct energy landscapes. Using multifactor regression analysis, the study examined the influence of various factors such as the diversity index of energy supply, energy self-reliance, share of renewable energy sources, final energy consumption, and production energy on countries’ dependency levels on energy imports. The results confirmed the significance of these factors in reducing countries’ energy dependency. This study contributes to understanding the dynamics of energy policies in EU countries and directs attention towards developing more resilient and efficient energy strategies.

关键词： Energy consumption Stability criteria Europe Production Energy efficiency Regression analysis Security Information technology Investment Convergence

来源：评论

学校读者我要写书评

暂无评论

An Efficient Solution for the Collusion Problem of DECO

An Efficient Solution for the Collusion Problem of DECO

引用

Information Security and Cryptology (ISCTURKEY), International Conference on

作者： Uğur Şen Murat Osmanoğlu Ali Aydin Selçuk Institute of Applied Mathematics Middle East Technical University Ankara Turkey Department of Computer Engineering Ankara University Ankara Turkey Department of Computer Engineering TOBB University of Economics and Technology Ankara Turkey

ISBN: (数字)9798331533649

ISBN: (纸本)9798331533656

DECO is one of the state-of-the-art TLS evidence protocols that enables privacy-preserving verification without necessitating server-side modifications. It allows applications to extract verifiable data from websites. However, DECO is vulnerable to collusion attacks, where the prover and verifier may secretly conspire, even if DECO itself remains secure. This vulnerability limits DECO's ability to transfer data to smart contracts. To address the collusion issue, decentralized oracle networks have been integrated with DECO, involving multiple executions for the same attestation and relying on majority consensus to determine the correct outcome. While this approach mitigates collusion risk, it is inefficient. In this paper, we address the collusion vulnerability in DECO by proposing an enhanced approach that expands the verifier's role to a set of $n$ verifiers within a single DECO execution, utilizing a Distributed Verifiable Random Function (DVRF). This method requires the prover to obtain consensus from all $n$ verifiers, thereby increasing the difficulty of collusion and enhancing the security of the system. Furthermore, the proposed solution is more efficient than executing $n$ separate DECO protocols and provides verifiable features that facilitate integration with slashing and reward mechanisms, thereby improving its applicability in decentralized systems.

关键词： Smart contracts Blockchains Security Data mining Interoperability

来源：评论

学校读者我要写书评

暂无评论

Detection and Replay of Distributed Denial of Service Attacks in Smart Cities Using a Hybrid Deep Learning Approach 2

Detection and Replay of Distributed Denial of Service Attack...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Iqbal, Muhammad Waseem Issa, Ghassan F. Yousif, Muhammad Atif, Muhammad Superior University Department of Software Engineering Lahore Pakistan Skyline University College School of Information Technology Sharjah United Arab Emirates Department of Computer Science NCBAE Lahore Pakistan Applied Science Research Center Applied Science Private University Amman11937 Jordan

ISBN: (纸本)9798350335644

Infrastructure for smart cities is presently being built, mostly because of the (IoT) platform, which connects a wide variety of things by using the website's underlying infrastructure. As a result, it is possible to employ a uniform platform to automate the services that are delivered. Smart city infrastructure, on the other hand, is susceptible to cyberattacks owing to security flaws in IoT networks. Distributing denial of service (DDoS) and replay assaults, for example, violate the requirements for certification in smart cities. The lack of citations in this part backs up many of the statements it makes. Who needs a citation? Both assaults have the potential to substantially damage smart city infrastructure, which might also cost money and even result in human fatalities. This paper covers the creation of a blended deep- learning algorithm for replay and DDoS intrusion prevention on a growth-oriented smart city platform. This is made possible by combining proven machine-learning approaches with more recent advances in artificial intelligence. We simulate scattered denial of service and replay attacks on three datasets acquired from real-world smart cities to assess the efficacy of the proposed hybrid strategy on environmental, smart river, and smart soil dataset. The suggested model has shown excellent rates of accuracy. The ecosystem collection has an accuracy level of 98.37%, the smart riverbed dataset must have an accuracy of 98.13%, and the smart mud dataset must have an accuracy of 99.51%. The findings demonstrated that the proposed model outperformed past instances of evolutionary computation and machine learning techniques employed in the corpus of academic literature. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Advanced SMS Spam Detection using Deep Complex Models and Sine-Cosine Algorithm

Advanced SMS Spam Detection using Deep Complex Models and Si...

引用

Conference on Information and Knowledge Technology

作者： Sepehr Rezaei Mohammadreza Shams Mohsen Alambardar Meybodi Department of Applied Mathematics and Computer Science Faculty of Mathematics and Statistics University of Isfahan Isfahan Iran Department of Computer Engineering Shahreza Campus University of Isfahan Isfahan Iran

With the increasing use of mobile phones and messaging services, SMS spam has become a significant issue for users. In this paper, we propose a novel approach 1 to tackle this problem by using Sine-Cosine Algorithm (SCA) and Complex Multi-Layer Perceptron (C-MLP). Specifically, we apply the SCA method to reduce the dimensionality of the feature space and CMLP to improve the performance of spam detection. Also, in this paper, we investigate the effectiveness of different classification algorithms, including Support Vector Machines, Random Forests, K-nearest neighbors, Naive Bayes, bagging, and voting approaches. Our experimental results show that the proposed approach achieves high accuracy and outperforms existing methods in terms of both accuracy and F-measure. The proposed approach can be helpful in designing effective SMS spam filters and improving the overall user experience. 1 All the code used in this research is publicly available on the first author’s GitHub repository: https://***/seper-sw/***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooling Yb-Doped Silica Fibers and Fiber Lasers with Anti-Stokes Pumping 5

Cooling Yb-Doped Silica Fibers and Fiber Lasers with Anti-St...

引用

Photonic Heat Engines: Science and Applications V 2023

作者： Frey, Benjamin N. Balliu, Enkeleda Vigneron, Pierre-Baptiste Knall, Jenny Hawkins, Thomas W. Meehan, Bailey Cahoon, Mary Ann Ballato, John Engholm, Magnus Dragic, Peter D. Yu, Nanjie Boilard, Tommy Bernier, Martin Digonnet, Michel J.F. Applied Physics Department Stanford University CA United States Department of Engineering Mathematics and Science Education Mid Sweden University Sundsvall Sweden Department of Materials Science and Engineering Clemson University South Carolina United States Department of Electrical Computer Engineering U. of Illinois at Urbana-Champaign IL United States Université Laval Québec Canada

ISBN: (纸本)9781510659797

Optical cooling in Yb-doped silica fibers using anti-Stokes fluorescence has become a subject of great interest in the fiber laser community. This paper provides an update on the development of silica fibers designed specifically to enhance their cooling properties. This growing list includes a new, nearly single-mode fiber with a borophosphosilicate core that produced –65 mK of cooling with only 260 mW of 1040-nm pump power. The silica compositions that have now been successfully cooled at atmospheric pressure by anti-Stokes fluorescence by our team include aluminosilicate, aluminofluorosilicate, borophosphosilicate, and aluminosilicate doped with one of three different alkali-earth nanoparticles (Ba, Sr, and Ca). By fitting the measured temperature dependence of the cooled fiber on pump power, two key parameters that control the degree of cooling are inferred, namely the critical quenching concentration and the absorptive loss due to impurities. The inferred values compiled for the fibers that cooled indicate that the extracted heat is highest when the Yb concentration is 2 wt.% or more (to maximize heat extraction), the Al concentration is ~0.8 wt.% or greater (to reduce quenching), and the absorptive loss is below approximately 15 dB/km, and ideally below 5 dB/km (to minimize heating due to pump absorption). Only two of the reported fibers, an LaF3-doped and an LuF3-doped nanoparticle fiber, did not cool, because their Yb and Al concentrations were not sufficiently high. This analysis shows that through careful composition control (especially the Al and Yb concentrations) and minimization of the OH contamination, a new generation of Yb-doped silica fibers is emerging with higher Yb concentrations, greater resistance to quenching, and lower residual loss than commercial Yb-doped fibers. They can be expected to have a significant impact not only on optically cooled devices but also on a much broader range of fiber lasers and amplifiers. © 2023 SPIE.

关键词： Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Hashgraph consensus-based simultaneous, asynchronous and big-data supported blockchain mechanism for IT-OT enabled critical infrastructure sectors

引用

Journal of Ambient Intelligence and Humanized Computing 2025年 1-13页

作者： Hasan, Mohammad Kamrul Ghazal, Taher M. Issa, Ghassan Islam, Shayla Ismail, Ahmad Fadzil Kabir, S. Rayhan Bangi43600 Malaysia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman11937 Jordan School of Computing Skyline University College University City Sharjah Skyline University College Sharjah1797 United Arab Emirates Institue of Computer Science and Digitial Innovation UCSI University Malaysia Kuala Lumpur56000 Malaysia Department of Electrical and Computer Engineering International Islamic University of Malaysia Kuala Lumpur53000 Malaysia

Critical Infrastructure (CI) refers to the essential areas made up of public, private, and business sectors for the security of a country's development, such as electricity, water, health, education, etc. where information technologies (ITs) and operational technologies (OTs) enable automation services of CI. Currently, blockchain is being experimented in various CI sectors and any CI sector accumulates the data of millions of people in a country or nation from which big data is being generated. Big data connections are seen with large-scale blockchain networks because as the size of the blockchain network increases, so does the amount of connected data. Typically, the blockchain does not support asynchronous and simultaneous processes that indicate multiple block compilation does not allow at the same time for the blockchain systems. That is why high energy consumption, high bandwidth dependency, long-time computation, high mining process, and system slowness issues are seen on large-scale blockchain networks where big data is also connected. However, Hashgraph is an alternative distributed ledger technology (DLT) to blockchain and is also considered a consensus method that supports Asynchronous Byzantine Fault Tolerance (ABFT) as well as simultaneous process. Moreover, Hashgraph does not need mining and network node verification processes which saves bandwidth. In this research, we proposed a Hashgraph-enabled blockchain model for reducing the above issues and illustrated the adoption of IT-enabled OT to support CI. In addition, this manuscript discusses how the proposed model can create positive impacts in CI areas by replacing traditional blockchain systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Critical infrastructures

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：