检索结果-内蒙古大学图书馆

A Federated Unlearning-Based Secure Management Scheme to Enable Automation in Smart Consumer Electronics Facilitated by Digital Twin

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Islam, Anik Karimipour, Hadis Gadekallu, Thippa Reddy Zhu, Yaodong Deptartment of Electrical and Software Engneering Schulich School of Engineering University of Calgary Calgary Canada Division of Research and Development Lovely Professional University Phagwara India Jiaxing University School of Information Science and Engineering Jiaxing Zhejiang China

In consumer electronics, integrating the Internet of Things (IoT) and Artificial Intelligence (AI) has transformed everyday devices into smart, interconnected systems. However, this progress brings significant challenges in resource management, privacy, and security, particularly with the increasing reliance on data-centric technologies like Deep Learning (DL). The introduction of the Right to Be Forgotten (RBF) policy further complicates data management in DL models. This paper presents a new method for automating consumer electronic devices using Federated Learning (FL). This approach involves training devices with the help of a Digital Twin (DT) and securely storing data on a redactable blockchain after each training cycle. An unlearning mechanism in FL is adapted to meet RBF policy requirements, with the redactable blockchain facilitating the necessary data adjustments. Dual authentication methods are used to prevent malicious attacks: a hampel filter and performance checks during training, and a two-phase system comprising an XoR filter and continuous counter checks for request validation. A proof of concept confirms the system’s effectiveness, demonstrating its superior performance compared to existing methods. IEEE

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Statistical data Mining with Slime Mould Optimization for Intelligent Rainfall Classification

引用

Computer Systems Science & engineering 2023年第10期47卷 919-935页

作者： Ramya Nemani G.Jose Moses Fayadh Alenezi K.Vijaya Kumar Seifedine Kadry Jungeun Kim Keejun Han Department of Mathematics Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Engineering University Institute of Engineering and Technology(UIET)Guru Nanak UniversityHyderabadIndia Department of Electrical Engineering College of EngineeringJouf UniversitySaudi Arabia Department of Computer Science and Engineering GITAM School of TechnologyVishakhapatnam CampusGITAM(Deemed to be a University)VishakhapatnamIndia 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

Statistics are most crucial than ever due to the accessibility of huge counts of data from several domains such as finance,medicine,science,engineering,and so *** data mining(SDM)is an interdisciplinary domain that examines huge existing databases to discover patterns and connections from the *** varies in classical statistics on the size of datasets and on the detail that the data could not primarily be gathered based on some experimental strategy but conversely for other ***,this paper introduces an effective statistical data Mining for Intelligent Rainfall Prediction using Slime Mould Optimization with Deep Learning(SDMIRPSMODL)*** the presented SDMIRP-SMODL model,the feature subset selection process is performed by the SMO algorithm,which in turn minimizes the computation *** rainfall *** neural network with long short-term memory(CNN-LSTM)technique is *** last,this study involves the pelican optimization algorithm(POA)as a hyperparameter *** experimental evaluation of the SDMIRP-SMODL approach is tested utilizing a rainfall dataset comprising 23682 samples in the negative class and 1865 samples in the positive *** comparative outcomes reported the supremacy of the SDMIRP-SMODL model compared to existing techniques.

关键词： Statistical data mining predictive models deep learning rainfall prediction parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Super-Resolution and Denoising on MRI via Conditional Stochastic Normalizing Flow

Simultaneous Super-Resolution and Denoising on MRI via Condi...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Zhenhong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences The Department of Computer Science School of Engineering The University of Manchester United Kingdom Department of Cardiovascular Sciences The Department of Electrical Engineering Ku Leuven Leuven Belgium Lan Turing Institute London United Kingdom

ISBN: (纸本)9798350337488

Magnetic resonance imaging (MRI) scans often suffer from noise and low-resolution (LR), which affect the diagnosis and treatment results obtained for patients. LR images and noise come together with MRI, and the existing methods solve image super-resolution (SR) reconstruction and denoising tasks in a step-by-step manner, which influences the overall real distribution of the MRI data. In this paper, we present a simultaneous SR and denoising algorithm based on a stochastic normalizing flow (SNF), named the MR image SR and denoising model based on an SNF (SRDSNF). SRDSNF adds the encoded information of the input image as the conditional information to each reverse step of the stochastic normalizing flow, which realizes a consistent description of the spatial distribution between the reconstruction result and the input image. We introduce rangenull space decomposition and subsequence sampling strategies to enhance the consistency of the input and output data and increase the generation speed of the model. Simultaneous SR and denoising tasks experiment is carried out using the BrainWeb and NFBS datasets. The experimental results show that good SR and denoising results are obtained with fewer sampling steps, these results are consistent with the ground truths, and the structural similarity and peak signal-to-noise ratio of the results are also higher than those of the comparison methods. The proposed method demonstrates potential clinical promise. © 2023 IEEE.

关键词： Denoising Diffusion model MR image Stochastic normalizing flow Super-resolution

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Classification Using VGG-19 Based Faster-RCNN 7th

Plant Disease Classification Using VGG-19 Based Faster-RCNN

引用

Proceedings of the 7th International Conference on Advances in Computing and data Sciences, ICACDS 2023

作者： Nawaz, Marriam Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering University of Engineering and Technology Taxila Taxila47050 Pakistan Faculty of Computing Department of Computer Science Riphah International University Gulberg Green Campus Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Early plant disease diagnosis can help farmers avoid spending money on costly crop pesticides and aid them to boost food production. Scientists have put a lot of effort to classify plant diseases, but it is difficult to quickly locate and identify different crop abnormalities due to the high degree of resemblance between the normal and damaged parts of plant leaves. Additionally, the procedure of detecting plant diseases has been made more challenging due to the extensive color, size, shape, and intensity variations in the background and foreground of the plant images. To address the existing difficulties, we have introduced an effective deep learning (DL) based system called Faster-RCNN o recognize and classify various types of plant diseases. The suggested method consists of 3 basic steps. In order to identify the area of interest in investigated samples, we first create annotations for them which are later used for Faster-RCNN training. The Faster-RCNN model employs the VGG-19 network to extract the relevant keypoints from the given images which are later passed to the regressor and classification units to identify and categorize the various crop diseases using the estimated features. We evaluated our method on a widely used standard plant sample repository called the PlantVillage database, and the findings show that our approach is reliable for classifying plant diseases under a variety of image-capturing scenarios. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from the Smart City Concept Implementation in West Lombok Regency, West Nusa Tenggara Province

Lessons Learned from the Smart City Concept Implementation i...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Wikan Danar Sunindyo Alfrojems Knowledge and Software Engineering Research Group School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Indonesia Business Coalition for Women Empowerment South Jakarta Indonesia

Accelerating regional economic growth is needed to be able to catch up with a region, especially if the region has economic potential, especially in terms of natural capital, such as a beautiful environment. However, in practice, a development process will experience obstacles as an inseparable part. This condition certainly requires appropriate treatment efforts based on empirical evidence data. This also happened to West Lombok. Where in fact the regions that get the opportunity to become Smart City pilots certainly have a positive impact, but the challenges that must be carried out also go hand in hand with the process of implementing these efforts. Referring to this background, the purpose of this research is to be able to explore and analyze the challenges experienced by West Lombok in implementing the Smart City program in its region. The method used is qualitative with data collection techniques in the form of documentation studies, observations, interviews, and focus group discussions. This study involved 50 informants with various backgrounds but still in accordance with the characteristics of the informants determined by the researcher through the use of purposive sampling technique. The results of this study are that there are four challenges that need to get more attention from the local government of West Lombok and its stakeholders as an effort to realize West Lombok as a smart city. The four challenges include policy, infrastructure, human capital, and environment. The need for strategic efforts carried out by West Lombok to be able to encourage the achievement of the target of becoming a smart city in Indonesia, especially in West Nusa Tenggara Province.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer for Object Re-Identification: A Survey

arXiv

引用

arXiv 2024年

作者： Ye, Mang Chen, Shuoyi Li, Chenyue Zheng, Wei-Shi Crandall, David Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China School of Data and Computer Science Sun Yat-sen University Guangzhou China Luddy School of Informatics Computing and Engineering Indiana University United States

Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision. For a prolonged period, this field has been predominantly driven by deep learning technology based on convolutional neural networks. In recent years, the emergence of Vision Transformers has spurred a growing number of studies delving deeper into Transformer-based Re-ID, continuously breaking performance records and witnessing significant progress in the Re-ID field. Offering a powerful, flexible, and unified solution, Transformers cater to a wide array of Re-ID tasks with unparalleled efficacy. This paper provides a comprehensive review and in-depth analysis of the Transformer-based Re-ID. In categorizing existing works into Image/Video-Based Re-ID, Re-ID with limited data/annotations, Cross-Modal Re-ID, and Special Re-ID Scenarios, we thoroughly elucidate the advantages demonstrated by the Transformer in addressing a multitude of challenges across these domains. Considering the trending unsupervised Re-ID, we propose a new Transformer baseline, UntransReID, achieving state-of-the-art performance on both single/cross modal tasks. For the under-explored animal Re-ID, we devise a standardized experimental benchmark and conduct extensive experiments to explore the applicability of Transformer for this task and facilitate future research. Finally, we discuss some important yet under-investigated open issues in the large foundation model era, we believe it will serve as a new handbook for researchers in this field. A periodically updated website will be available at https://***/mangye16/ ReID-Survey. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

CNN segmentation of skin melanoma in pre-processed dermoscopy images 2

CNN segmentation of skin melanoma in pre-processed dermoscop...

引用

2nd International Conference on Machine Learning and data engineering, ICMLDE 2023

作者： Kadry, Seifedine Verdú, Elena Damasevicius, Robertas Abualigah, Laith Singh, Vijendra Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Higher School of Engineering and Technology Universidad Internacional de la Rioja Logroño26006 Spain Department of Applied Informatics Vytautas Magnus University Kaunas53361 Lithuania Computer Science Department Al Al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu's thresholding, (iii) Kapur's thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database. © 2024 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Automatic liver-vessel examination from CT slice using Kapur's thresholding and watershed algorithm 2

Automatic liver-vessel examination from CT slice using Kapur...

引用

2nd International Conference on Machine Learning and data engineering, ICMLDE 2023

作者： Kadry, Seifedine Abualigah, Laith González Crespo, Rubén Verdú, Elena Damasevicius, Robertas Singh, Vijendra Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand Norway Ajman University Ajman346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Computer Science Department Al Al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan MEU Research Unit Middle East University Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Higher School of Engineering and Technology Universidad Internacional de la Rioja Logroño26006 Spain Department of Applied Informatics Vytautas Magnus University Kaunas53361 Lithuania School of Computer Science University of Petroleum and Energy Studies Dehradun248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602105 India

Computerized medical image examination (CMIE) plays a significant role in modern hospitals to achieve the necessary tasks, like segmentation and classification. By segmenting an image, we can extract a particular section for examination. A two-dimensional computed tomography (CT) slice was used for liver-vessel examination (LiVE). A simple automatic technique for supporting LiVE is being developed in this research. A CT slice is collected, a 3D to 2D conversion is done, (ii) Kapur's tri-level thresholding and Hummingbird-Optimizer is used to enhance the CT slice, (iii) the watershed algorithm (WA) is used to extract the vessel, and (iv) the WA is compared and verified against the segmentation methods chosen. WA provides better segmentation results than other methods because it is an automatic approach. Using the chosen image database, the proposed technique achieves an overall segmentation accuracy of >97%. Other segmentation problems can be used in the future to verify the merit of this scheme. © 2024 Elsevier B.V.. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Detecting Model Poisoning Attacks Via Dummy Symbol Insertion for Secure Over-the-Air Federated Learning

Detecting Model Poisoning Attacks Via Dummy Symbol Insertion...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Hang Zhou Yi-Han Chiang Caijuan Chen Xiaoyan Wang Yusheng Ji Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan Department of Electrical and Electronic Systems Engineering Osaka Metropolitan University Osaka Japan Graduate School of Science and Engineering Ibaraki University Hitachi Japan

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

With the rapid advancement of intelligent IoT services, the need for high-quality and efficient wireless communication has become increasingly critical for information exchanges and collaborations among intelligent edge devices such as autonomous mobile robots (AMRs), robots in smart factories, and surveillance cameras, etc., Federated Learning (FL) is a promising distributed learning framework by exploring the computation capability on edge devices while protecting data privacy of users. On the other hand, Over-the-Air (OTA) computation techniques is a new paradigm of integrated computation and communication. OTA based FL (OTA-FL) can enhance spectrum efficiency by leveraging the superposition properties of wireless channels for model aggregations. The implementation of OTA-FL on edge devices can further protect user data privacy for clients, improve the throughput of inter-device communications, and enhance the distributed learning performance. However, despite these advantages, the convergence of OTA-FL systems remain vulnerable to model poisoning attacks, presenting significant challenges. In this study, we address these vulnerabilities by proposing a two-phase detection mechanism that secures OTA-FL system while preserving high spectral efficiency. Our simulation results demonstrate that under varying conditions, our approach can make distributed learning more secure and communication-efficient.

关键词： Computer aided instruction data privacy Federated learning Distance learning Wireless networks Computational modeling Surveillance Symbols Throughput Convergence

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：