检索结果-内蒙古大学图书馆

21st International Learning and Technology Conference, L and T 2024

作者： Gaber, Lamya Hussein, Aziza I. Minia University Computers and Systems Engineering Department Minia Egypt Effat University Electrical and Computer Engineering Department Jeddah Saudi Arabia

ISBN: (纸本)9798350393569

With the increasing complexity and scale of digital VLSI designs, ensuring reliability in IC design necessitates effective fault detection processes during the pre-silicon stage. Many fault detection algorithms lead to significant computational time due to the problem of search space explosion. To handle the ever-growing volume of data, deep learning algorithms, a subset of machine learning techniques, can be employed. In this paper, we propose two novel approaches for fault detection (FD) of digital VLSI circuits, specifically targeting stuck-at faults. The first proposed model is semi-supervised FD model that aims to mitigate the search space explosion issue by leveraging both unsupervised and supervised learning processes. The second presented model is based on an optimizer for finding the appropriate configurations for detecting stuck-at faults in digital circuits. The initial proposed model achieves maximum validation accuracy of approximately 98% applied to circuits from ISCAS'85. This model yields a higher accuracy compared to the second approach that achieves maximum accuracy of around 95% when applied to the same circuits from the ISCAS'85 benchmark. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Fault-Ride-Through (FRT) Control of a grid-connected Fixed-Speed Wind Energy Conversion System using STATCOM 50

Fault-Ride-Through (FRT) Control of a grid-connected Fixed-S...

引用

50th Annual Conference of the IEEE industrial Electronics Society, IECON 2024

作者： Olajube, Ayobami Vedula, Satish Omiloli, Koto Anubi, Olugbenga Moses Department of Electrical and Computer Engineering FAMU-FSU College of Engineering Center for Advanced Power Systems Florida State University United States

ISBN: (纸本)9781665464543

Wind energy conversion system (WECS) is stochastic in nature and has low inertia leading to grid voltage instability, poor reactive power compensation and most importantly fault susceptibility. Variable speed WECS such as the doubly-fed induction generators (DFIG) are well known to reach steady state quickly after fault occurrence without the need for an external reactive power source because of the presence of a back-to-back converter that provides independent control of the active and reactive power unlike in the fixed-speed squirrel cage induction generator (SCIG) counterpart that can’t be stabilized unless an external source of reactive power support is present. However, controlling DFIG is complicated and costly due to complete tripping unlike the fixed-speed generators which doesn’t trip completely when fault occurs. Hence, in this work, a 48-pulse, 3-phase static synchronous compensator (STATCOM) is used to ensure reactive power compensation and fault-ride through (FRT) control of the SCIG against over-voltage emanating from fault occurrence in a grid-connected power system. The goal here is to guarantee voltage stability and fault-ride-through (FRT) control against injected faults within certain time ranges at the point of common coupling (PCC) between the AC source, the load, and the fixed-speed WECS. The numerical simulation shows the fault-ride-through capability of the STATCOM-controlled fixed-speed WECS, good voltage regulation and effective reactive power compensation. © 2024 IEEE.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

Developing Multi-Agent Wide Area Damping Controller to Mitigate False Data Injection Attacks 24

Developing Multi-Agent Wide Area Damping Controller to Mitig...

引用

24th EEEIC International Conference on Environment and electrical engineering and 8th I and CPS industrial and Commercial Power systems Europe, EEEIC/I and CPS Europe 2024

作者： Vavdareh, Masoud Babaei Ghafouri, Mohsen Ameli, Amir Concordia University Department of Information and Systems Engineering Montreal Canada Lakehead University Department of Electrical and Computer Engineering Thunder BayON Canada

ISBN: (纸本)9798350355185

The effectiveness of wide-area damping controllers (WADCs) is significantly influenced by the integrity of the measurement data collected from phasor measurement units (PMUs). These damping controllers utilize PMU data to make decisions and transmit control commands to system actuators, such as synchronous generators. However, the incorporation of communication links for transmitting these signals exposes the power system to various cyber threats, such as false data injection attacks (FDIAs). On this basis, this study proposes two methods for defending against FDIAs: (i) the utilization of a neural network-based autoencoder as an effective attack detector for FDIAs, and (ii) the development of a multi-agent control strategy to mitigate these attacks. The performance of these proposed methods is analyzied using a two-area Kundur test system, compared against conventional data-driven attack detection methods and a global WADC technique. The findings indicate that the implementation of these methods significantly enhances defense capabilities against FDIA targeting wide-area measurement signals. © 2024 IEEE.

关键词： Phasor measurement units

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for skin lesion classification on iOS: implementing and optimizing a convolutional transfer learning model with Create ML

引用

International Journal of computers and Applications 2024年第8期46卷 666-685页

作者： Benedek Szabo, Aron Katona, Jozsef Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Instrumentation and Automation Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Department of Informatics GAMF Faculty of Engineering and Computer Science Kecskemét Hungary

The integration of machine learning (ML) into mobile applications presents unique challenges, particularly in resource-constrained environments such as iOS devices. Skin lesion classification is a critical task in dermatology, where accurate and efficient diagnostic tools can significantly aid in early detection of malignant lesions. This study aims to implement a machine learning-based iOS mobile application and develop a binary classification model for skin lesion images to determine whether a lesion is malignant. The research utilized Create ML to develop a convolutional neural network optimized for iOS, employing a transfer learning approach. A logistic regression model was cascaded with the convolutional neural network N to enhance classification accuracy. The model's performance was assessed through various validation metrics, ensuring its robustness and efficiency within the constraints of mobile hardware. A curated dataset from the International Skin Imaging Collaboration archive was used for training and testing. The model achieved an accuracy of 92%, a precision of 90%, a recall of 93%, and an F1-score of 91% in classifying skin lesions. These metrics validate the model's efficacy in identifying malignant lesions. Data curation involved collecting, labeling, and preparing a dataset from publicly available sources, ensuring the inclusion of diagnostically relevant features. The final model was integrated into an iOS application using Core ML and Vision frameworks. The developed application demonstrates reliable performance in classifying skin lesions with high accuracy on iOS devices. The inclusion of comprehensive performance metrics justifies the efficacy of the proposed approach. Future work will explore enhancements in model architecture and object detection capabilities to further improve diagnostic precision and application usability. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

SEF:A Smart and Energy-Aware Forwarding Strategy for NDN-Based Internet of Healthcare

引用

computers, Materials & Continua 2024年第12期81卷 4625-4658页

作者： Naeem Ali Askar Adib Habbal Hassen Hamouda Abdullah Mohammad Alnajim Sheroz Khan Department of Computer Engineering Faculty of EngineeringKarabük UniversityKarabük78050Türkiye Department ofManagement Information Systems College of Business AdministrationMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Electrical Engineering College of Engineering and Information TechnologyOnaizah CollegesQassim51911Saudi Arabia

Named Data Networking(NDN)has emerged as a promising communication paradigm,emphasizing content-centric access rather than location-based *** model offers several advantages for Internet of Healthcare Things(IoHT)environments,including efficient content distribution,built-in security,and natural support for mobility and ***,existing NDN-based IoHT systems face inefficiencies in their forwarding strategy,where identical Interest packets are forwarded across multiple nodes,causing broadcast storms,increased collisions,higher energy consumption,and *** issues negatively impact healthcare system performance,particularly for individuals with disabilities and chronic diseases requiring continuous *** address these challenges,we propose a Smart and Energy-Aware Forwarding(SEF)strategy based on reinforcement learning for NDN-based *** SEF strategy leverages the geographical distance and energy levels of neighboring nodes,enabling devices to make more informed forwarding decisions and optimize next-hop *** approach reduces broadcast storms,optimizes overall energy consumption,and extends network *** system model,which targets smart hospitals and monitoring systems for individuals with disabilities,was examined in relation to the proposed *** SEF strategy was then implemented in the NS-3 simulation environment to assess its performance in healthcare *** demonstrated that SEF significantly enhanced NDN-based IoHT ***,it reduced energy consumption by up to 27.11%,82.23%,and 84.44%,decreased retrieval time by 20.23%,48.12%,and 51.65%,and achieved satisfaction rates that were approximately 0.69 higher than those of other strategies,even in more densely populated *** forwarding strategy is anticipated to substantially improve the quality and efficiency of NDN-based IoHT systems.

关键词： Energy efficient forwarding strategy health information system internet technologies IoHT people with disabilities reinforcement learning Q-learning

来源：评论

学校读者我要写书评

暂无评论

Switching between MPPT and VSG Controls for Utility-Scale Photovoltaic Plants to Mitigate Power System Oscillations

Switching between MPPT and VSG Controls for Utility-Scale Ph...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Ratnakumar, Rajan Venayagamoorthy, Ganesh K. Clemson University Real-Time Power and Intelligent Systems Laboratory Holcombe Department of Electrical and Computer Engineering Clemson United States University of Pretoria Department of Electrical Electronic and Computer Engineering South Africa

ISBN: (纸本)9798350376067

The decline of conventional synchronous generators in the modern power system is driven by the increasing demand for low-inertia/inertia-less renewable energy sources (RES), consequently leading to the growing integration of inverter-based resources (IBRs) into the power system. The incorporation of low-inertia/inertia-less IBRs makes the monitoring and damping of low-frequency electromechanical oscillations (EMOs) crucial. While Virtual Synchronous Generator (VSG) control introduces virtual inertia into the power system, it does not maximize energy capture from RES as effectively as maximum power point tracking (MPPT) does, as it should maintain a power reserve to provide the inertial support and damping. In this study, switching IBRs between MPPT and VSG controls based on an EMO index (EMOI) threshold is proposed to mitigate the emergence of EMO. The impact of the switching control of IBRs is illustrated for a modified two-area, four-machine power system with two large solar photovoltaic plants. Typical results are presented from a simulation on real-time digital simulator (RTDS) to show improved EMOI. © 2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking Neural Networks with Dynamic Time Steps for Vision Transformers

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking N...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Datta, Gourav Liu, Zeyu Li, Anni Beerel, Peter A. Dept. of Electrical Computer & Systems Engineering Case Western Reserve University Cleveland United States Ming Hsieh Dept. of Electrical and Computer Engineering University of Southern California Los Angeles United States

ISBN: (纸本)9798350368741

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensemble-based Disease Prediction in Medical Image Data 3

Ensemble-based Disease Prediction in Medical Image Data

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Kumar, Mukesh Das, Dipti Singh, Nisha Mishra, Shivansh Kumar, Dharmendra Panda, Nibedan School of Computer Engineering Kalinga Institute of Industrial Technology 751024 India School of Computer Engineering Kalinga Institute of Industrial Technology 751024 India Varanasi221005 India PDPM IIITDM Jabalpur Khamaria M.P. Jabalpur482005 India Department of Electrical and Instrumentation Engineering Thapar Institute of Engineering and Technology Punjab Patiala147004 India School of Computer Engineering Kalinga Institute of Industrial Technology 751024 India

Disease prediction is crucial in the healthcare industry. Early detection and diagnosis of sickness can result of in better patient outcomes and cheaper medical expenses. Machine learning (ML) algorithms have shown considerable potential for sickness prediction jobs due to their ability to learn from vast datasets and find subtle patterns that may not be evident to humans. Multiple machine learning models are used in ensemble learning, a potent method for disease prediction, to increase prediction accuracy and robustness. This paper introduces an ensemble-based method for medical data-driven illness prediction, focusing on chest X-ray datasets for viral pneumonia, lung opacity, normal, and COVID-19. Our goal is to leverage the potential of ensemble methods to increase prediction accuracy and offer practical insights into these diseases. To assess the effectiveness of our ensemble strategy, we have used various machine learning (ML) algorithms such as Support vector machine (SVM), K-nearest Neighbour (K-NN), Naive Bays and Logistic Regression. The ensemble methods used are Random Forest, XgBoost, Decision Tree classifier, stacking and voting. We have compared and analysed the result with various training testing ratio on three well known datasets with five performance measure like AUC, Accuracy, Precision, Recall, and F1-score. As a result of all the models, XgBoost, stacking, voting, and random forest produce the best results. © 2025 The Author(s).

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Wireless Power Transmission Using Additively Manufactured Ferrite Pad 1

Wireless Power Transmission Using Additively Manufactured Fe...

引用

1st IEEE International Conference on Smart and Sustainable Developments in electrical engineering, SSDEE 2025

作者： Bhnadari, Shreejan Khanal, Samip Akter, Taslima Li, Frank X Yelamanchi, Bharat Itapu, Srikanth Borra, Vamsi Youngstown State University Electrical and Computer Engineering YoungstownOH United States Chemical Engineering Youngstown State University YoungstownOH United States Industrial and Systems Engineering Youngstown State University YoungstownOH United States Alliance University Engineering and Technology Karnataka Bengaluru India

ISBN: (纸本)9798331542108

Wireless power transfer (WPT) is a promising technology for various purposes, but efficiency remains a key challenge. This research investigates using additively manufactured ferrite pads to enhance wireless power transmission efficiency. By utilizing manganese-zinc ferrite cores with precise 3D-printed geometries, the study aims to improve magnetic flux coupling and reduce energy losses. Using ANSYS Maxwell simulations and experimental setups with AWG 40 Litz wire coils, the research explored how ferrite materials impact power transfer performance. The findings demonstrate the significant improvements: simulations achieved a transfer efficiency of 89% while the experimental data showed output results increasing from 26.27 mV to 40.46 mV when using a ferrite pad. The study addresses critical WPT challenges such as coil misalignment, distance variations, and power density, offering insights into developing more efficient wireless charging solutions and other applications. © 2025 IEEE.

关键词： Electric losses

来源：评论

学校读者我要写书评

暂无评论

Using Interim Recommitment to Reduce the Operational-cost Impacts of Wind Uncertainty

引用

Journal of Modern Power systems and Clean Energy 2022年第4期10卷 839-849页

作者： Mahan A.Mansouri Ramteen Sioshansi Department of Integrated Systems Engineering The Ohio State UniversityColumbusOH 43210USA Department of Integrated Systems Engineering Department of Electrical and Computer Engineeringand Center for Automotive ResearchThe Ohio State UniversityColumbusOH 43210USA

Using wind-availability forecasts in day-ahead unit commitment can require expensive real-time operational *** examine the benefit of conducting interim recommitment between day-ahead unit commitment and real-time *** a simple stylized example and a case study that is based on ISO New England,we compare system-operation costs with and without interim *** find an important tradeoff—later recommitment provides better wind-availability forecasts,but the system has less flexibility due to operating *** the time windows that we examine,hour-20 recommitment provides the greatest operational-cost reduction.

关键词： Power-system operation power-system economics unit commitment economic dispatch wind generation.

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：