检索结果-内蒙古大学图书馆

Efficient Deep CNN Model for COVID-19 Classification

computers, Materials & Continua 2022年第3期70卷 4373-4391页

作者： Walid El-Shafai Amira A.Mahmoud El-Sayed M.El-Rabaie Taha E.Taha Osama F.Zahran Adel S.El-Fishawy Mohammed Abd-Elnaby Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Coronavirus(COVID-19)infection was initially acknowledged as a global pandemic in Wuhan in *** Health Organization(WHO)stated that the COVID-19 is an epidemic that causes a 3.4%death *** X-Ray(CXR)and computerized Tomography(CT)screening of infected persons are essential in diagnosis *** are numerous ways to identify positive COVID-19 *** of the fundamental ways is radiology imaging through CXR,or CT *** comparison of CT and CXR scans revealed that CT scans are more effective in the diagnosis process due to their high ***,automated classification techniques are required to facilitate the diagnosis *** Learning(DL)is an effective tool that can be utilized for detection and classification this type of medical *** deep Convolutional Neural Networks(CNNs)can learn and extract essential features from different medical image *** this paper,a CNN architecture for automated COVID-19 detection from CXR and CT images is *** activation functions as well as three optimizers are tested and compared for this *** proposed architecture is built from scratch and the COVID-19 image datasets are directly fed to train *** performance is tested and investigated on the CT and CXR *** activation functions:Tanh,Sigmoid,and ReLU are compared using a constant learning rate and different batch *** optimizers are studied with different batch sizes and a constant learning ***,a comparison between different combinations of activation functions and optimizers is presented,and the optimal configuration is ***,the main objective is to improve the detection accuracy of COVID-19 from CXR and CT images using DL by employing CNNs to classify medical COVID-19 images in an early *** proposed model achieves a classification accuracy of 91.67%on CXR image dataset,and a classification accuracy of 100%on CT dataset with training times of 58 min and 46 min on CXR an

关键词： COVID-19 image classification CNN DL activation functions optimizers

来源：评论

学校读者我要写书评

暂无评论

DSTNet: Distinguishing Source and Target Areas for Image Copy-Move Forgery Detection 27th

DSTNet: Distinguishing Source and Target Areas for Image Cop...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Kaiqi Yuan, Xiaochen Huang, Guoheng Liu, Kun School of Cyberspace Security Shandong University of Political Science and Law Jinan China Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Technology Guangdong University of Technology Guangzhou China School of Information Science and Engineering University of Jinan Jinan China

ISBN: (纸本)9783031783111

In copy-move forgery detection, most relevant studies concern locating the copy-move areas without the distinction of source and target regions. This paper proposes an end-to-end network, DSTNet, to identify the source and target based on consistency detection between the copy-move region and the non-copy-move region. The DSTNet is composed of two stages, the Pre-processing stage and the Discrimination stage. Pre-processing Stage extracts internal information of copy-move and non-copy-move areas and conducts a series of operations to meet the requirements of network input. Discrimination stage allows multiple patches for input and classifies the input patches. Specifically, the Pre-processing stage, contains the Copy-move Patches Selection (CM Patches Selection) and Genuine Patches Selection, can select pairs of copy-move and none copy-move patches. We train the proposed DSTNet on two large synthetic datasets and use the public datasets CASIA and Comofod for evaluation. The experiment shows that our method achieves excellent results. Particularly, we achieve a 5.4% higher F1 based on ground-truth of copy-move mask (GT-CM) on CASIA dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Modeling of Complex Electrodynamic Objects Based on a Combined Approach

Modeling of Complex Electrodynamic Objects Based on a Combin...

引用

2022 International Siberian Conference on Control and Communications, SIBCON 2022

作者： Lvovich, Igor Lvovich, Yakov Preobrazhenskiy, Andrey Preobrazhenskiy, Yuriy Avetisyan, Tatyana Faculty of Informatics Voronezh Institute of High Technologies Voronezh Russia Voronezh State Technical University Faculty of Information Technology and Computer Security Voronezh Russia

ISBN: (纸本)9781665476287

The paper deals with the problem of assessing the characteristics of electromagnetic wave scattering on electrodynamic objects with a complex shape. A combined approach, which is based on the use of statistical methods, methods of fuzzy estimation, and expert analysis, is proposed. A numerical estimate was determined for the index characterizing the level of scattered electromagnetic fields. Linguistic values of the indicators based on expert evaluations were compared. Numerical evaluations of the characteristics of the electrodynamic objects surveyed were given. Based on the formed information base, the frequency of occurrence of different responses was calculated for the analyzed groups, which included objects with over reflections (which was considered as the main group, and objects without over reflections (which was considered as the control group). The values of the electromagnetic wave scattering angle limits under the analyzed scattering conditions were demonstrated. © 2022 IEEE.

关键词： Electrodynamics

来源：评论

学校读者我要写书评

暂无评论

Effective Density-Based Concept Drift Detection for Evolving Data Streams 24th

Effective Density-Based Concept Drift Detection for Evolving...

引用

24th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2023

作者： Cui, Zelin Tian, Hui Shen, Hong Institute of Information Security Engineering Chinese Academy of Sciences Beijing China School of Information and Communication Technology Griffith University Brisbane Australia Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9789819982103

Concept drift is a common phenomenon appearing in evolving data streams of a wide range of applications including credit card fraud protection, weather forecast, network monitoring, etc. For online data streams it is difficult to determine a proper size of the sliding window for detection of concept drift, making the existing dataset-distance based algorithms not effective in application. In this paper, we propose a novel framework of Density-based Concept Drift Detection (DCDD) for detecting concept drifts in data streams using density-based clustering on a variable-size sliding window through dynamically adjusting the size of the sliding window. Our DCDD uses XGBoost (eXtreme Gradient Boosting) to predict the amount of data in the same concept and adjusts the size of the sliding window dynamically based on the collected information about concept drifting. To detect concept drift between two datasets, DCDD calculates the distance between the datasets using a new detection formula that considers the attribute of time as the weight for old data and calculates the distance between the data in the current sliding window and all data in the current concept rather than between two adjacent windows as used in the exiting work DCDA [2]. This yields an observable improvement on the detection accuracy and a significant improvement on the detection efficiency. Experimental results have shown that our framework detects the concept drift more accurately and efficiently than the existing work. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Modeling the Characteristics of Antenna Based on the Flat Focusing Reflector 24

Modeling the Characteristics of Antenna Based on the Flat Fo...

引用

24th International Conference on Digital Signal Processing and its Applications, DSPA 2022

作者： Lvovich, Igor Lvovich, Yakov Preobrazhenskiy, Andrey Preobrazhenskiy, Yuriy Voronezh Institute of High Technologies Faculty of Informatics Voronezh Russia Voronezh State Technical University Faculty of Information Technology and Computer Security Voronezh Russia

ISBN: (纸本)9781665494434

The paper considers the problem associated with the construction of an antenna, based on the flat focusing reflector with waveguide slots of a square profile, filled with a homogeneous dielectric. Algorithms for antenna modeling and optimization are presented. Optimization is based on the use of a multi-criteria approach. The antenna directional diagram for the main frequency is demonstrated. Frequency dependences of antenna efficiency and aperture efficiency are shown. The illustration of the phase distribution that will correspond to the surface of the aperture for boundary frequencies is demonstrated. The illustration is given of the phase distribution at the emitting aperture at frequency for cutoff frequencies. © 2022 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

A Scalable and Lightweight Authentication Architecture for the Internet of Things (IoT) in Smart Home Applications 2

A Scalable and Lightweight Authentication Architecture for t...

引用

2nd Zimbabwe Conference on information Communication and technology, ZCICT 2023

作者： Gamundani, Attlee M. Phillips, Amelia Muyingi, Hippolyte N. Namibia University of Science and Technology Faculty of Computing & Informatics Cyber Security Department Windhoek Namibia University of the Cumberlands School of Computer and Information Sciences WilliamsburgKY United States Namibia University of Science and Technology Faculty of Computing & Informatics Windhoek Namibia

ISBN: (纸本)9798350318128

In the evolving landscape of smart home applications, ensuring robust and efficient authentication within the Internet of Things (IoT) environments is paramount. This paper presents a scalable, lightweight authentication architecture for IoT-driven smart homes. The proposed architecture, drawing inspiration from cloud computing mechanisms, introduces a trusted, smart home agent, integrating the Data-information-Knowledge-Wisdom (DIKW) model to facilitate efficient and secure data exchange within smart homes. Our solution addresses the challenges of minimal computation and processing overheads, essential in resource-constrained IoT devices, and focuses on device-level authentication to reduce computational costs. A comparative analysis with existing models demonstrates the superiority of our architecture in terms of computational efficiency, making it an ideal candidate for scalable deployments. The architecture successfully navigates the complexities of ensuring secure communication among autonomous IoT devices, balancing the dual needs of computational efficiency and robust security, thereby promising resilience against common security threats in the smart home ecosystem. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Efficient Convolutional Neural Network Based Side Channel Attacks Based on AES Cryptography 21

Efficient Convolutional Neural Network Based Side Channel At...

引用

21st IEEE Student Conference on Research and Development, SCOReD 2023

作者： Ahmed, Amjed Abbas Hasan, Mohammad Kamrul Aman, Azana Hafizah Abdulkadir, Rabiu Aliyu Islam, Shayla Farhan, Basim Abdulkareem Center for Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia Department of Computer Techniques Engineering Baghdad10011 Iraq Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur56000 Malaysia

ISBN: (纸本)9798350318821

In recent years, profiled side-channel attacks have emerged as a particularly potent kind of side-channel attack that can circumvent cryptographic equipment's security. Convolutional neural networks (CNNs) have been widely used as deep learning infrastructure for attacks in recent research that has examined a new kind of profiled attack based on deep learning. The design of CNNs will have a significant impact on attack effectiveness. However, image recognition fields are frequently the foundation of the CNN architecture currently used for profiled attacks. Additionally, it is still challenging to choose the proper parameters and CNN infrastructure concerning adaptation to profiled assault types. In the current study, an effective CNN-based profiled attack was suggested that can be used against masking-protected cryptographic devices. The Grey Wolf Optimization (GWO) approach obtains the CNN architecture parameters proposed in this research. The characteristics of intriguing areas on the power trace determine these parameters. The proposed attacks were tested using experiments over a tracing set gathered from an intelligent card Atmega8515 processing the ASCAD public dataset. © 2023 IEEE.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using Cuckoo Search Algorithm for Feature Selection with LSTM Model 2

Bitcoin Price Prediction Using Cuckoo Search Algorithm for F...

引用

2nd International Engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Radmand, Elnaz Pirgazi, Jamshid Odeh, Mahmoud Sorki, Ali Ghanbari University of Science and Technology of Mazandaran Faculty of Electrical and Computer Engineering Behshahr Iran School of Information Technology Zarqa University Cyber Security Department Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798350373363

Deep learning is now a top method for predicting the price of Bitcoin, providing an excellent and well thought out strategy. This technique makes use of a wealth of historical data from reliable sources covering the first ten years of Bitcoin. Technical data and complex patterns are deeply integrated into the dataset to enhance the model's comprehension of complex Bitcoin price patterns. These additions greatly deepen our understanding of the various factors affecting the price of Bitcoin. This method is based on a strategic procedure that involves the careful selection of certain high-performing characteristics. These traits go through a stringent screening process that uses advanced algorithms such as the Cuckoo algorithm. The chosen features are then smoothly incorporated into an encoder-decoder model of LSTM (Long Short-Term Memory), improving the model's ability to predict Bitcoin prices. In this case, it is critical to apply deep learning methods, especially the LSTM encoder-decoder model. Through the integration of technical indicators and sophisticated selection techniques with historical Bitcoin data, this approach leverages deep learning capabilities to identify intricate patterns in Bitcoin pricing movements. In the end, this gives the model the ability to forecast future changes in the price of Bitcoin with accuracy. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Determinants Influencing E- Payment Adoption Amidst COVID-19: A Conceptual Framework 7

Determinants Influencing E- Payment Adoption Amidst COVID-19...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Hammood, Waleed A. Abdullah, Khairul Hafezad Hammood, Omar A. Aminuddin, Afrig Asti Astuti, Ika Hadi Purwanto, Ibnu University of Anbar Faculty of Computer Science and Information Technology Department of Information Systems Ramadi Iraq School of Business Management Universiti Utara Malaysia Social Security Management Center of Excellence Utara Malaysia University of Fallujah Faculty of Administration and Economics Business Administration Department Fallujah Iraq Universitas Amikom Yogyakarta Faculty of Computer Science Sleman Indonesia

ISBN: (纸本)9798350307504

In recent years, there has been a significant surge in the demand for electronic payments (e-payments), particularly during the COVID-19 pandemic. E-payments have played a crucial role in promoting social distancing and mitigating the spread of the COVID-19 virus. Several studies have examined user goals and intentions in this context. The primary objective of this research is to develop a conceptual model that integrates the technology Acceptance Model (TAM) with the Health Belief Model (HBM) to explore the factors influencing people's willingness to embrace e-payment methods. Both TAM and HBM serve as foundational frameworks in this study. Consequently, this research contributes to our understanding of how perceived usefulness and ease of use impact the adoption of e-payments. The study introduces a proposed framework yet to undergo empirical testing, emphasizing the need for empirical investigations to validate its suitability. This framework can be a valuable tool for bankers, managers, and practitioners in assessing their clients' inclination toward adopting e-payment services. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Based Automated Fault Diagnosis in Industrial IoT Applications

引用

computers, Materials & Continua 2023年第4期75卷 183-196页

作者： Samah Alshathri Ezz El-Din Hemdan Walid El-Shafai Amged Sayed Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Computer Science Department Security Engineering LabPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Electrical Energy Engineering College of Engineering&TechnologyArab Academy for Science Technology&Maritime TransportSmart Village CampusEgypt

In recent years, Digital Twin (DT) has gained significant interestfrom academia and industry due to the advanced in information technology,communication systems, Artificial Intelligence (AI), Cloud Computing (CC),and Industrial Internet of Things (IIoT). The main concept of the DT isto provide a comprehensive tangible, and operational explanation of anyelement, asset, or system. However, it is an extremely dynamic taxonomydeveloping in complexity during the life cycle that produces a massive amountof engendered data and information. Likewise, with the development of AI,digital twins can be redefined and could be a crucial approach to aid theInternet of Things (IoT)-based DT applications for transferring the data andvalue onto the Internet with better decision-making. Therefore, this paperintroduces an efficient DT-based fault diagnosis model based on machinelearning (ML) tools. In this framework, the DT model of the machine isconstructed by creating the simulation model. In the proposed framework,the Genetic algorithm (GA) is used for the optimization task to improvethe classification accuracy. Furthermore, we evaluate the proposed faultdiagnosis framework using performance metrics such as precision, accuracy,F-measure, and recall. The proposed framework is comprehensively examinedusing the triplex pump fault diagnosis. The experimental results demonstratedthat the hybrid GA-ML method gives outstanding results compared to MLmethods like LogisticRegression (LR), Na飗e Bayes (NB), and SupportVectorMachine (SVM). The suggested framework achieves the highest accuracyof 95% for the employed hybrid GA-SVM. The proposed framework willeffectively help industrial operators make an appropriate decision concerningthe fault analysis for IIoT applications in the context of Industry 4.0.

关键词： Automated fault diagnosis control system ML AI CC IIoT digital twins genetic algorithm GA-ML technique

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：