检索结果-内蒙古大学图书馆

International Conference on Advanced Communications and Machine Intelligence, MICA 2023

作者： Pamula, Narendra Babu Khan, Ajoy Kumar Sarkar, Arindam Department of Computer Engineering Mizoram Central University Aizawl796004 India Department of Computer Science and Electronics Ramakrishna Mission Vidyamandira Belur Math West Bengal Howrah711202 India

ISBN: (纸本)9789819762217

Federated learning (FL) is a networked gadget learning (ML) framework. FL allows numerous customers to collaborate so that it will deal with not unusual places allotted ML issues at the same time as maintaining their neighborhood privacy. A central server in charge of this manages the process. The common FL issues that need to be resolved are then described. Maintaining localized data while training statistical models over remote devices or siloed data centers, such as corporate offices or hospitals, is a requirement of federated learning. When training in diverse and possibly enormous networks, a considerable departure from the conventional approaches for large-scale system learning, allotted optimization, and privacy-maintaining statistics evaluation is needed. The study also examines the security of federated learning and its applications, as well as the many threats and assaults that the applications must deal with. The current level of the use of federated learning is reviewed, along with the introduction of some common privacy protection techniques. Last but not least, a summary and outlook on the use and security of federated learning. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Computational Efficiency of Deep Learning-Based Super Resolution Methods for 5G-NR Channel Estimation

Computational Efficiency of Deep Learning-Based Super Resolu...

引用

2024 IEEE Latin-American Conference on Communications, LATINCOM 2024

作者： Goez, David Beyazit, Esra A. Slamnik-Krijestorac, Nina Marquez-Barja, Johann M. Gaviria, Natalia Latre, Steven Camelo, Miguel University of Antwerp - imec IDLab - Department of Computer Science Belgium Universidad de Antioquia Electronics Engineering Department Colombia University of Antwerp - imec IDLab - Faculty of Applied Engineering Belgium

ISBN: (纸本)9798331521110

The increasing demand for high-quality and efficient Channel Estimation (CE) in 5G New Radio (5G-NR) systems has prompted the exploration of advanced Deep Learning (DL) techniques. While traditional methods, such as Linear Interpolation (LI) and Least Squares (LS), provide reasonable accuracy and are practical for real-time physical layer processing, recent DL-based CE approaches have primarily focused on accuracy, often without evidence of real-time capabilities. In this paper, we present a comprehensive evaluation of DL-based Super-resolution (SR) methods for CE, comparing models like Super Resolution Convolutional Neural Network (SRCNN), ChannelNet, and Enhanced Deep Super-Resolution (EDSR) in both 1D and 2D convolutional architectures. We optimize these models using NVIDIA TensorRT to reduce computational complexity and latency. Our results show that the optimized 1D-EDSR model achieves the best performance with a Mean Squared Error (MSE) of 0.0126, outperforming all other models in terms of accuracy. However, the optimized 1D-EDSR model fails to meet real-time constraints due to additional computational overhead (0.6798 ms/sample). In contrast, the 1D-SRCNN model offers a balanced trade-off between MSE (0.01738) and inference time (0.0866ms/sample), achieving 40% higher accuracy than LS (0.0288) while maintaining the best energy efficiency (1.48 mJ/sample). © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Use of Polygram Substitution in Spotting the Swindler in Secret Sharing 11th

Use of Polygram Substitution in Spotting the Swindler in Sec...

引用

11th International Conference on Intelligent Computing and Applications, ICRTC 2023

作者： Yadav, Poonam Satheesh Kumar, S. Muthukumaran, V. Sandeep Kumar, mathivanan Radhika, E.K. Department of Computer Science School of Applied Sciences Reva University Bangalore India Department of Mathematics College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur 603203 India School of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida203201 India Department of Computer Science and Applications Sindhi College Bangalore560024 India

ISBN: (纸本)9789819717231

In the polygram substitution, one set of characters is replaced by another set based on algorithm. The model is proposed for calculating and estimating secure online secret shares, where dynamic modification in any of the shares will be identified if number of the shares are more than specified threshold value. The security is based on the intractability of factoring as it uses Lagrange polynomial function. This is further enhanced by a graphical masking and unmasking technique;it includes two phases: encryption of the individual secrets and sharing of the data. The generation of the shares is done by masking using Polygram substitution, and the shares are regenerated and unmasking of the qualified shares is done to find original secret. Masking is done on original secret, then shares are generated. Each encrypted share contains information which is different than original secret. Masking by Polygram substitution gives additional protection of secret data on the Internet. Moreover, we achieve efficient recovery of the original secret data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IoT) in Smart Cities: A Statistical Survey 2

Internet of Things (IoT) in Smart Cities: A Statistical Surv...

引用

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

作者： Iqbal, Muhammad Waseem Khaliq, Khowla Al-Dmour, Nidal A. Aqeel, Muhammad Ali, Nasir Hamid, K. Superior University Department of Software Engineering Lahore54000 Pakistan Superior University Department of Computer Sciecnce Lahore54000 Pakistan Mutah University College of Engineering Department of Computer Engineering Jordan NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan

ISBN: (纸本)9798350335644

Internet of things is progressing very rapidly and involving multiple domains of everyday life including environment, governance, healthcare system, transportation system, energy management system, etc. smart city is a platform for collecting and storing the information that is accessed through various sensor-based IoT devices and make their information available in required and authorized domains. This interoperability can be achieved by semantic web technology. In this paper, I have reviewed multiple papers related to IoT in Smart Cities and presented a comparison among the semantic parameters. Moreover, I've presented my future domain of research which is about delivering the COVID-19 patients report to the concerned domains by the healthcare system domain. © 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

R1 CIDS: A Hybrid Dual Filters Intrusion Detection System

R1 CIDS: A Hybrid Dual Filters Intrusion Detection System

引用

2023 Congress in computer science, computer engineering, and applied Computing, CSCE 2023

作者： Wang, Zichun Temesgen, Samuel Wu, Fred West Virginia State University Institute Department of Math Engineering and Computer Science United States

ISBN: (纸本)9798350327595

To cope with the growing number and changing nature of malicious cyber-attacks, machine learning techniques have been extensively employed to develop intrusion detection systems (IDS) for intelligent detection. However, these systems face numerous challenges, given the continually evolving nature of these attacks and their sheer volume. In here, a new hybrid intelligent IDS employing a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is proposed. This model aims to classify audit data and predict potential security breaches by leveraging the strengths of both CNN and LSTM. The new hybrid model has shown a significant improvement in detection accuracy while reducing the detection time. © 2023 IEEE.

关键词： CNN Deep Learning IDS LSTM R1CIDS

来源：评论

学校读者我要写书评

暂无评论

CNN Based Features Extraction and Selection Using EPO Optimizer for Cotton Leaf Diseases Classification

引用

computers, Materials & Continua 2023年第9期76卷 2779-2793页

作者： Mehwish Zafar JaveriaAmin Muhammad Sharif Muhammad Almas Anjum Seifedine Kadry Jungeun Kim Department of Computer Science COMSATS University IslamabadWah CampusWah Cantt47040Pakistan Department of Computer Science University ofWahWah Cantt47040Pakistan National University of Technology(NUTECH) Islamabad44000Pakistan 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

Worldwide cotton is the most profitable cash *** year the production of this crop suffers because of several *** an early stage,computerized methods are used for disease detection that may reduce the loss in the production of *** several methods are proposed for the detection of cotton diseases,however,still there are limitations because of low-quality images,size,shape,variations in orientation,and complex *** to these factors,there is a need for novel methods for features extraction/selection for the accurate cotton disease *** in this research,an optimized features fusion-based model is proposed,in which two pre-trained architectures called EfficientNet-b0 and Inception-v3 are utilized to extract features,each model extracts the feature vector of length N×*** that,the extracted features are serially concatenated having a feature vector lengthN×*** prominent features are selected usingEmperor PenguinOptimizer(EPO)*** method is evaluated on two publically available datasets,such as Kaggle cotton disease dataset-I,and Kaggle *** EPO method returns the feature vector of length 1×755,and 1×824 using dataset-I,and dataset-II,*** classification is performed using 5,7,and 10 folds *** Quadratic Discriminant Analysis(QDA)classifier provides an accuracy of 98.9%on 5 fold,98.96%on 7 fold,and 99.07%on 10 fold using Kaggle cotton disease dataset-I while the Ensemble Subspace K Nearest Neighbor(KNN)provides 99.16%on 5 fold,98.99%on 7 fold,and 99.27%on 10 fold using Kaggle cotton-leaf-infection dataset-II.

关键词： Deep learning cotton disease detection features selection classification efficientnet-b0 inception-v3 quadratic discriminant analysis subspace KNN

来源：评论

学校读者我要写书评

暂无评论

IOT and Machine Learning Based Real-Time Protection Against Cyber-Physical Threat Mitigation 4

IOT and Machine Learning Based Real-Time Protection Against ...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Saini, Harnit Mohammad, Faz Singh, Manoj Kumar Sharma, Kapil Kumar Shukla, Meenu Singh, Ramendra Ajay Kumar Garg Engineering College Department of Computer Science Ghaziabad India Gl Bajaj Institute of Technology and Management Department of Applied Computational Science and Engineering Greater Noida India Ims Engineering College Department of Computer Science & Engineering Ghaziabad India Ims Engineering College Department of Mca Ghaziabad India Maharishi University of Information Technology School of Engineering and Technology Noida India Ghaziabad India

ISBN: (纸本)9798350360165

An investigation is carried out into the dynamic relationship between machine learning algorithms used in IoT security, with detailed scrutiny of performance indicators to give a fuller view of what happens. The study pays particular attention to metrics like accuracy, precision, recall, and F1 score when ten varied samples are being examined. As a result, all the algorithms exhibit excellent performance with 95.5 %-98.2 % accuracy values, inspiring high reliability under diverse scenarios. Precision and recall metrics also depict the models' capabilities. Balancing precision and recall can be observed in F1 scores that are between 95.2% and 98.0%, and these numbers show that the approach based on this understanding of trade-offs is characterized by its operationalization. At the other end, results obtained from performance metrics go beyond numerical benchmarks to give a holistic appreciation of the algorithms' strength and areas for possible enhancement. The paper also does not provide only a theoretical approach to machine learning related to security in the IoT environment but also provides information about security considerations for the successful deployment of powerful, adaptive models into real-life scenarios. In this case, findings of the research help in understanding how to make sure that smart and effective measures are implemented during the process of developing security solutions considering all related issues in connection with the IoT technology landscape. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Robustness of Model-Predictive Control using GMMs as Outlier Detection 12

Enhancing the Robustness of Model-Predictive Control using G...

引用

12th IEEE International Conference on Intelligent Systems, IS 2024

作者： Féret, Leander J. Gepperth, Alexander Lambeck, Steven Jumo GmbH & Co. Kg Think Tank Fulda Germany Fulda University of Applied Sciences Applied Computer Science Department Fulda Germany Fulda University of Applied Sciences Electrical Engineering Department Fulda Germany

ISBN: (纸本)9798350350982

This article proposes a flexible control strategy to improve the reliability of data-driven model-predictive control (MPC). Prediction models are usually trained on logged data, which may be incomplete, leading to model failure within the optimization algorithm of the MPC. To counter this, we propose a Gaussian Mixture Model (GMM) for detecting outliers during live operation. These outliers are found in the observed system states as well as the calculated control signals regarding the logged training data of the ai-model. If an outlier is detected, we assume that the data-driven prediction model will be inaccurate, and an appropriate fallback strategy is used instead, which includes but is not limited to an alternative controller or a complete system-shutdown. In addition, outliers are stored for subsequent improvement of the prediction model. This outlier-protected control (OPC) architecture is evaluated in terms of control quality using the integrated squared error (ISE) on three nonlinear dynamical systems. The outcomes indicate a significant enhancement in control quality in comparison to an unprotected but otherwise equivalent architecture. These findings suggest that a very simple and efficient outlier detection can greatly benefit data-driven MPC in general whenever feasible fallback strategies exist. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Development of ANFIS Controller for Trajectory Tracking Control Using ROBO2L MATLAB Toolbox for KUKA Industrial Robot via RSI 21

Development of ANFIS Controller for Trajectory Tracking Cont...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Mousa, Mohamed Al-Mahasneh, Ahmad Baniyounis, Mohammed Biesenbach, Rolf Falkenhain, Jan Philadelphia University Mechatronics Engineering Department Amman Jordan Institute for Automation and Industry 4.0 Bochum University of Applied Sciences Bochum Germany Bochum University of Applied Sciences Electrical Engineering and Computer Science Department Bochum Germany

ISBN: (纸本)9798350374131

A new control scheme is proposed in the MATLAB/Simulink environment based on ANFIS technology using ROBO2L MATLAB toolbox with RSI to control the motion of the real KUKA robot. In detail, the control system has two subsystems designed for trajectory tracking error regulation in closed-loop control. One is a fuzzy logic controller, and the other is an ANFIS controller. These two controllers were used to control the velocity of the KUKA robot located inside the Hochschule Bochum laboratory. The testing process for these controllers was done by switching between FLC and ANFIS controllers and then studying each response separately. The results were compared with a linear controller produced in Hochschule Bochum experiments. The ROBO2L MATLAB toolbox provides many functions, such as sending and receiving positions and rotation for the end effector via UDP/IP communication, which RSI established to provide remote control for the robot using a PC. This work mainly emphasizes the ability to track the trajectories supported by the robotics toolbox in smooth motion. After observing the simulation results, the comparison between the linear, FLC, and ANFIS controllers is confirmed. The performance of the proposed approach is efficient for trajectory tracking control for the manipulator. © 2024 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Detection of Osteoarthritis Based on EHO Thresholding

引用

computers, Materials & Continua 2022年第6期71卷 5783-5798页

作者： R.Kanthavel R.Dhaya Kanagaraj Venusamy Department of Computer Engineering King Khalid UniversityAbhaSaudi Arabia Department of Computer Science King Khalid UniversitySarat Abidha CampusAbhaSaudi Arabia Department of Engineering University of Technology and Applied SciencesAl MussanahSultanate of Oman

Knee Osteoarthritis(OA)is a joint disease that is commonly observed in people around the *** commonly affects patients who are obese and those above the age of 60.A valid knee image was generated by Computed Tomography(CT).In this work,efficient segmentation of CT images using Elephant Herding Optimization(EHO)optimization is *** initial stage employs,the CT image normalization and the normalized image is incited to image enhancement through histogram ***,the enhanced image is segmented by utilizing Niblack and Bernsen ***(EHO)optimized outcome is evaluated in two *** initial step includes image enhancement with the measure of Mean square error(MSE),Peak signal to noise ratio(PSNR)and Structural similarity index(SSIM).The following step includes the segmentation which includes the measure ofAccuracy,Sensitivity and *** comparative analysis of EHO provides 95%of accuracy,94%of specificity and 93%of sensitivity than that of Active contour and Otsu threshold.

关键词： Osteoarthritis CT images correlation histogram thresholding Niblack&Bernsen algorithm EH optimization

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：