检索结果-内蒙古大学图书馆

13th IEEE International Conference on Electronics and Information Technologies, ELIT 2023

作者： Milyani, Danah Mohammad, Nouf Slama, Rim Qaisar, Saeed Mian Alhamdan, Alhanoof Hamour, Nora Computer Science Department Effat University Jeddah22332 Saudi Arabia Electrical and Computer Engineering Department Effat University Jeddah22332 Saudi Arabia CESI LINEACT Lyon69100 France

ISBN: (纸本)9798350383096

The arrhythmia is one of the cardiovascular diseases which has several types. In literature, researchers have presented a broad study on the strategies utilized for Electrocardiogram (ECG) signal investigation. Automated arrhythmia detection by analyzing the ECG data is reported using a number of intriguing techniques and discoveries. In order to effectively categorize arrhythmia, a novel approach based on the hybridization of the denoising filter, QRS complex segmentation, "Empirical Mode decomposition" (EMD), "Intrinsic Mode Functions" (IMFs) based features extraction, and machine learning techniques is developed in this study. To evaluate the categorization accuracy, the 10-fold cross validation (10-CV) strategy is used. Using an arrhythmia dataset that is publically available for research, the performance of our method is evaluated. A 97% average accuracy score is secured by our method for the problem of 5-class arrhythmias. These findings are comparable or better than counterparts. © 2023 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Navigating IoT Security:Insights into Architecture,Key Security Features,Attacks,Current Challenges and AI-Driven Solutions Shaping the Future of Connectivity

引用

computers, Materials & Continua 2024年第12期81卷 3499-3559页

作者： Ali Hassan N.Nizam-Uddin Asim Quddus Syed Rizwan Hassan Ateeq Ur Rehman Salil Bharany Department of Electrical Engineering HITEC UniversityTaxila47080Pakistan Department of Biomedical Engineering HITEC UniversityTaxila47080Pakistan Department of Electronics Engineering University of ChakwalChakwal48800Pakistan Department of Computer Science NFC Institute of Engineering and Fertilizer ResearchFaisalabad38000Pakistan School of Computing Gachon UniversitySeongnam-si13120Republic of Korea Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpura140401PunjabIndia

Enhancing the interconnection of devices and systems,the Internet of Things(IoT)is a paradigm-shifting *** security concerns are still a substantial concern despite its extraordinary *** paper offers an extensive review of IoT security,emphasizing the technology’s architecture,important security elements,and common *** highlights how important artificial intelligence(AI)is to bolstering IoT security,especially when it comes to addressing risks at different IoT architecture *** systematically examined current mitigation strategies and their effectiveness,highlighting contemporary challenges with practical solutions and case studies from a range of industries,such as healthcare,smart homes,and industrial *** results highlight the importance of AI methods that are lightweight and improve security without compromising the limited resources of devices and computational *** networks can ensure operational efficiency and resilience by proactively identifying and countering security risks by utilizing machine learning *** study provides a comprehensive guide for practitioners and researchers aiming to understand the intricate connection between IoT,security challenges,and AI-driven solutions.

关键词： Internet of Things(IoT) artificial intelligence(AI) IoT architecture security attacks in IoT

来源：评论

学校读者我要写书评

暂无评论

Analysis and Assessment of Wind Energy Potential of Almukalla in Yemen

引用

computers, Materials & Continua 2022年第8期72卷 3113-3129页

作者： Murad A.A.Almekhlafi Fahd N.Al-Wesabi Majdy M.Eltahir Anwer Mustafa Hilal Amin M.El-Kustaban Abdelwahed Motwakel Ishfaq Yaseen Manar Ahmed Hamza Department of Electrical Engineering–Communication Engineering Sana’a UniversityYemen Department of Computer Science King Khalid UniversityMuhayelAseerSaudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Information Systems King Khalid UniversityMuhayelAseerSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Electronic Department Faculty of EngineeringUniversity of Science and TechnologySana’aYemen

Energy is an essential element for any civilized country’s social and economic development,but the use of fossil fuels and nonrenewable energy forms has many negative impacts on the environment and the *** Republic of Yemen has very good potential to use renewable ***,we find few studies on renewable wind energy in *** the lack of a similar analysis for the coastal city,this research newly investigates wind energy’s potential near the Almukalla area by analyzing wind ***,evaluation,model identification,determination of available energy density,computing the capacity factors for several wind turbines and calculation of wind energy were extracted at three heights of 15,30,and *** wind speeds were obtained only for the currently available data of five recent years,2005–*** study involves a preliminary assessment of Almukalla’s wind energy potential to provide a primary base and useful insights for wind engineers and *** research aims to provide useful assessment of the potential of wind energy in Almukalla for developing wind energy and an efficient wind *** Weibull distribution shows a perfect approximation for estimating the intensity of Yemen’s wind *** on both theWeibullmodel and the results of the annual wind speed data analysis for the study site in Mukalla,the capacity factor for many turbines was also calculated,and the best suitable turbine was *** to the International Wind Energy Rating criteria,Almukalla falls under Category 7,which is,rated“Superb”most of the year.

关键词： Almukalla energy potential Rayleigh distribution Weibull distribution wind power density wind speed

来源：评论

学校读者我要写书评

暂无评论

Image Reconstruction Via Autoencoding Sequential Deep Image Prior 38

Image Reconstruction Via Autoencoding Sequential Deep Image ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Alkhouri, Ismail R. Liang, Shijun Bell, Evan Qu, Qing Wang, Rongrong Ravishankar, Saiprasad Department of Computational Mathematics Science & Engineering Michigan State University United States Department of Electrical Engineering & Computer Science University of Michigan Ann Arbor United States Department of Biomedical Engineering Michigan State University United States Department of Mathematics Michigan State University United States

Recently, Deep Image Prior (DIP) has emerged as an effective unsupervised one-shot learner, delivering competitive results across various image recovery problems. This method only requires the noisy measurements and a forward operator, relying solely on deep networks initialized with random noise to learn and restore the structure of the data. However, DIP is notorious for its vulnerability to overfitting due to the overparameterization of the network. Building upon insights into the impact of the DIP input and drawing inspiration from the gradual denoising process in cutting-edge diffusion models, we introduce Autoencoding Sequential DIP (aSeqDIP) for image reconstruction. This method progressively denoises and reconstructs the image through a sequential optimization of network weights. This is achieved using an input-adaptive DIP objective, combined with an autoencoding regularization term. Compared to diffusion models, our method does not require training data and outperforms other DIP-based methods in mitigating noise overfitting while maintaining a similar number of parameter updates as Vanilla DIP. Through extensive experiments, we validate the effectiveness of our method in various image reconstruction tasks, such as MRI and CT reconstruction, as well as in image restoration tasks like image denoising, inpainting, and non-linear deblurring. Our code is available at the GitHub repository aSeqDIP. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Fault Classification in Rotating Machinery Using the K-Nearest Neighbor Algorithm 1

Efficient Fault Classification in Rotating Machinery Using t...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Kumar, Sujit Kumari, Alka Priya, Shalu Bharti, Nisha Nandani, Durgesh Kumar, Manish Government Engineering College Banka Electrical Engineering Department Bihar India Government Engineering College Banka Electronics and Communication Engineering Department Bihar India Government Engineering College Banka Computer Science Engineering Department Bihar India Indian Institute of Technology Patna Electrical Engineering Department Bihar India

ISBN: (纸本)9798350377002

Rotating machines are widely used in industries. Rolling bearings, which are essential components of these ma-chines, are prone to damage. Therefore, diagnosing faults in rolling bearings quickly and accurately is crucial for maintenance purposes. Machine learning has become a very effective tool for diagnosing faults in rolling bearings. The KNN Algorithm is one such technique that effectively categorizes faults. This study proposes an intelligent fault classification system for bearing faults based on the KNN Algorithm. The proposed model accurately identifies different types of fault conditions in rolling bearings. Our proposed model achieves superior results and has been compared with existing methods. © 2024 IEEE.

关键词： Rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Efficiency of Interactive Communication Media Algorithms in Networking Applications 2

Analyzing the Efficiency of Interactive Communication Media ...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Garg, Devesh Takuli, Arun Kumar Upadhyay, Deepak Dixit, Krishna Kant Kaur, Gagandeep Raj Kumar Goel Institute of Technology Department of Computer Science and Engineering Ghaziabad India Gl Bajaj Institute of Technology & Management Department of Information Technology Up Greater Noida India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Gla University Department of Electrical Engineering UP Mathura India Chandigarh University Department of Uic Chandigarh India

ISBN: (纸本)9798350371055

This paper examines the efficiency of interactive communiqué media algorithms in networking applications. It specializes in the 2 important algorithms used inside the communication procedure in networking applications, namely, Dijkstra's and Bellman-Ford algorithms. It evaluates the right community Protocol (SNP) approach, which enables the excellent performance of the 2 algorithms. furthermore, this paper discusses the differences between those algorithms in phrases of complexity, communiqué cost, and overall performance. The consequences of this paper display that the two algorithms provide different networks based totally upon the respective wishes and requirements of a utility, and that their performance degree relies upon on the verbal exchange protocol strategy used. It also identifies more than a few of factors that can impact the overall performance of each algorithm. finally, the paper gives a few ability tips for similarly research to further improve the overall performance of those algorithms Interactive communication media (ICM) algorithms are techniques for intelligently optimizing packet routing and congestion manipulate on networks. In current years, the advances in ICM algorithms have enabled higher community overall performance and advanced the reliability of transmitted information. This paper evaluates the performance of 3 present day ICM algorithms, along with the adaptive digital community topology (Avnet), the weighted spherical robin (WRR) and the technique based on most anticipated postpone (Mad), in more than a few networking programs. Experiments are performed for each set of rules on specific sizes of networks and distinctive visitor's situations, such as exclusive document sizes and one-of-a-kind media delivery protocols. consequences display large variations within the performance of every set of rules, with Avnet being the maximum green typical in phrases of general overhead and facts shipping latency. A dialogue is supplied on the trad

关键词： Algorithms Applications Networking Situations Suitability

来源：评论

学校读者我要写书评

暂无评论

Detecting Lung Cancer with Federated and Transfer Learning 26

Detecting Lung Cancer with Federated and Transfer Learning

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Mostafa, G. Hamidi, Md Shifat Farid, Dewan Md. United International University Department of Computer Science and Engineering United City Madani Avenue Badda Dhaka1212 Bangladesh Ahsanullah University of Science and Technology Department of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

Lung cancer is a disease that affects and causes abnormalities in the lungs. The current methods to find and treat lung cancer require precise and timely detection to improve patient outcomes and survival rates. However, traditional approaches to lung cancer detection face challenges due to the extensive patient information spread across different medical institutions and research centers. Concerns about data privacy and the need to keep data controlled have prevented the consolidation of this valuable data into a central repository for analysis. As a result, the development of effective and accurate detection models has been limited by restricted access to diverse and comprehensive datasets. To overcome these challenges, federated learning (FL) has emerged as a promising approach in the healthcare field. It has great potential in the healthcare or medical sector where we can get a better Machine learning model while ensuring patient data privacy. This paper presents an FL approach for detecting lung cancer in medical images after setting an initial weight using Transfer Learning. Using this approach, we achieved a break a hand accuracy of 91.03% in detecting lung cancer. This demonstrates the potential of FL for accurate and privacy-preserving medical diagnosis. © 2023 IEEE.

关键词： Cancer Detection Data Privacy EfficientNetB4 Federated Learning ImageNet Lung Cancer Machine Learning Medical Data MobileNetV2 ResNet15 Transfer Learning VGG16 Xception

来源：评论

学校读者我要写书评

暂无评论

Sand Cat Swarm Optimization with Deep Transfer Learning for Skin Cancer Classification

引用

computer Systems science & engineering 2023年第11期47卷 2079-2095页

作者： C.S.S.Anupama Saud Yonbawi G.Jose Moses E.Laxmi Lydia Seifedine Kadry Jungeun Kim Department of Electronics and Instrumentation Engineering V.R.Siddhartha Engineering CollegeVijayawada520007India Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Computer Science and Engineering University Institute of Engineering and Technology(UIET)Guru Nanak UniversityHyderabadIndia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India 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

Skin cancer is one of the most dangerous *** of the high melanoma death rate,skin cancer is divided into non-melanoma and *** dermatologist finds it difficult to identify skin cancer from dermoscopy images of skin ***,pathology and biopsy examinations are required for cancer *** studies have formulated computer-based systems for detecting skin cancer from skin lesion *** recent advancements in hardware and software technologies,deep learning(DL)has developed as a potential technique for feature ***,this study develops a new sand cat swarm optimization with a deep transfer learning method for skin cancer detection and classification(SCSODTL-SCC)*** major intention of the SCSODTL-SCC model lies in the recognition and classification of different types of skin cancer on dermoscopic ***,Dull razor approach-related hair removal and median filtering-based noise elimination are ***,the U2Net segmentation approach is employed for detecting infected lesion regions in dermoscopic ***,the NASNetLarge-based feature extractor with a hybrid deep belief network(DBN)model is used for ***,the classification performance can be improved by the SCSO algorithm for the hyperparameter tuning process,showing the novelty of the *** simulation values of the SCSODTL-SCC model are scrutinized on the benchmark skin lesion *** comparative results assured that the SCSODTL-SCC model had shown maximum skin cancer classification performance in different measures.

关键词： Deep learning skin cancer dermoscopic images sand cat swarm optimization machine learning

来源：评论

学校读者我要写书评

暂无评论

Studying Physical Properties of Gas-To-Liquid Compared with Mineral Oil under Accelerated Thermal Aging 25

Studying Physical Properties of Gas-To-Liquid Compared with ...

引用

25th International Middle East Power System Conference, MEPCON 2024

作者： Badawi, Mohamed Ibrahim, Shimaa A. Mansour, Diaa-Eldin A. El-Faraskoury, Adel Ward, Sayed A. Benha University Faculty of Engineering at Shoubra Department of Electrical Engineering Egypt Egypt-Japan University of Science and Technology School of Electronics Communications and Computer Engineering Electrical Power Engineering Department Alexandria Egypt Tanta University Faculty of Engineering Electrical Power and Machines Engineering Department Tanta Egypt Egyptian Electricity Holding Company Extra High Voltage Research Centre Egypt Delta University for Science and Technology Faculty of Engineering Department of Electrical Engineering Egypt

ISBN: (纸本)9798350379648

Mineral oil (MO) has long been utilized in high-voltage power transformers, as a cooling and dielectric medium;because of it is availability as it is extracted from fossil oil. Recently, Gas-To-Liquid (GTL) has a significant increase in use due to its superior performance, its purity and chemical consistency over conventional mineral oils. This paper presents examination of the temperature effects on mineral (Diala S2) and gas to liquid (Diala S4) oil physical properties. Fresh oil and aged oil samples, of the two oil types, have been tested in this paper. Accelerated thermal aging test have been conducted in laboratory to simulate the heat stress experienced by transformers during operation. Three aged oil samples, of the two types of oil, have been prepared in laboratory (3, 6, and 10 days). Density and viscosity measurements were performed on these fresh and aged oil samples. The results concluded that during the initial years, chemical changes cause a minor drop in the density of the mineral oil. Conversely, GTL oil has superior qualities since it stays more stable over time. Over time, the density of both oils exhibits comparable stability, however GTL oil is favored over mineral oil due to its consistency and stability. Diala S4 and Diala S2 oils have higher viscosity, suggesting superior cooling performance before aging. However, Diala S2 dropped to 10.649 mm2/s after three years, indicating its long-term consequences. Diala S4 oil had higher flow efficiency, enhancing transformer cooling and insulating performance within thermal aging. This is due to GTL oil, derived from natural gas, has higher resistance to chemical deterioration, allowing it to sustain its viscosity stability over extended periods. These results emphasize the importance of choosing oils, especially GTL oil type based on their apparent and physical stability over time. © 2024 IEEE.

关键词： Viscosity

来源：评论

学校读者我要写书评

暂无评论

Hybrid Segmentation Approach for Different Medical Image Modalities

引用

computers, Materials & Continua 2022年第11期73卷 3454-3471页

作者： Walid El-Shafai Amira A.Mahmoud El-Sayed M.El-Rabaie Taha E.Taha Osama F.Zahran Adel S.El-Fishawy Naglaa F.Soliman Amel A.Alhussan Fathi E.Abd El-Samie Department Electronics and Electrical Communications Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia

The segmentation process requires separating the image region into sub-regions of similar *** sub-region has a group of pixels having the same characteristics,such as texture or *** paper suggests an efficient hybrid segmentation approach for different medical image modalities based on particle swarm optimization(PSO)and improved fast fuzzy C-means clustering(IFFCM)*** extensive comparative study on different medical images is presented between the proposed approach and other different previous segmentation *** existing medical image segmentation techniques incorporate clustering,thresholding,graph-based,edge-based,active contour,region-based,and watershed *** paper extensively analyzes and summarizes the comparative investigation of these ***,a prediction of the improvement involves the combination of these techniques is *** obtained results demonstrate that the proposed hybrid medical image segmentation approach provides superior outcomes in terms of the examined evaluation metrics compared to the preceding segmentation techniques.

关键词： Image segmentation ultrasonic images X-ray images CT images PET images MR images fuzzy c-mean morphological operations active contour

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：