检索结果-内蒙古大学图书馆

2024 IEEE PES/IAS PowerAfrica, PowerAfrica 2024

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

ISBN: (纸本)9798350389388

The integration of electric vehicles (EVs) into the smart grid has introduced new challenges and opportunities for optimizing power and energy management. This paper presents a simple method using a decision-tree to estimate allocation of electric vehicle grid interfaces (EVGIs) for EV charging/discharging, leveraging the nodal capabilities of a distribution system. The future distribution system will cater for vehicle-to-grid (V2G) transactions in addition to grid-to-vehicle (G2V) transactions, thus EVGIs allowing for bidirectional (G2V/V2G) power flows need to be deployed. The proposed decision-tree method is based on nodal power flow ratings and peak demand at the nodes assuming the nodal voltages are maintained within their stability envelopes by volt-var optimization and other voltage control methods. The allocation of EVGIs in the IEEE 34 test node feeder distribution system using the decision-tree method is illustrated. The EVGI allocation using decision-trees is a simple method that can provide insights of a typical distribution system's capability to support EV integration with emerging smart grid technologies. © 2024 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

Interactive Framework for Cybersecurity Education and Future Workforce Development 54

Interactive Framework for Cybersecurity Education and Future...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Ghimire, Sujan Chowdhury, Muhtasim Alam Tsang, Ryan Yarnell, Richard Heckert, Emma Carpenter, Jaeden Lin, Yu-Zheng Mamun, Muntasir Demara, Ronald F. Rafatirad, Setareh Satam, Pratik Salehi, Soheil University of Arizona Department of Systems and Industrial Engineering TucsonAZ85721 United States University of Arizona Department of Electrical and Computer Engineering TucsonAZ85721 United States University of California Davis Department of Electrical and Computer Engineering DavisCA95616 United States University of Central Florida Department of Electrical and Computer Engineering OrlandoFL32826 United States University of California Davis Department of Computer Science DavisCA95616 United States

ISBN: (纸本)9798350351507

This research-to-practice paper presents a novel pedagogical tool for hardware cybersecurity education and workforce development. The growing importance of hardware security has made it essential for individuals and organizations to understand hardware security principles and best practices. However, the current educational curriculum falls short of fulfilling these emerging demands due to the rapidly changing hardware security landscape and limited opportunities for hands-on training. To address these challenges, we propose and have developed the Interactive Hardware and Cybersecurity (I-HaC) Educational Framework, a pedagogical educational framework that supplements existing courses by leveraging generative AI for individualized instruction related to hardware and cybersecurity, data mining, and applied Machine Learning (ML), as well as data visualization to enhance cybersecurity education and workforce development. The framework is designed to be utilized by graduate and undergraduate electrical and computer engineering (ECE) and computer Science (CS) students for a comprehensive introduction to cybersecurity exploits and countermeasures in an interactive manner with hands-on components. Using I-HaC, we have developed tailored lab components for a diverse range of students and intend to release I-HaC as open-source for the benefit of the ECE and CS education community. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Features of Indoor Positioning systems Using Explainable AI 8

Evaluating the Features of Indoor Positioning Systems Using ...

引用

8th SLAAI - International Conference on Artificial Intelligence, SLAAI-ICAI 2024

作者： Dhananjaya, S.A.K. Lakmal, H.K.I.S. Nirmal, W.C. NSBM Green University Faculty of Engineering Department of Electrical Electronic & Systems Engineering Homagama Sri Lanka NSBM Green University Faculty of Engineering Department of Mechatronic & Industrial Engineering Homagama Sri Lanka

ISBN: (纸本)9798331509170

This paper investigates the application of Explainable AI (XAI) techniques in evaluating the features of indoor positioning systems, with a focus on improving model transparency and interpretability. Indoor positioning systems, crucial for location-based services in complex environments, rely heavily on machine learning models that often operate as black boxes. By performing SHAP (Shapley Additive explanations) and LIME (Local Interpretable Model-agnostic Explanations), this study aims to determine the most influential features by driving model predictions and provide a deeper understanding of their roles within the system. In this study, we investigate the features of RSSI values to check their importance and interactions, enhance the interpretability of the model through SHAP and LIME analyses, and guide future improvements in system accuracy and reliability. © 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

System Strength Beyond Fault Level

引用

IEEE Access 2025年 13卷 104184-104200页

作者： Ghazavi Dozein, M. Berry, B. Milanoviae, J.V. Mancarella, P. Monash University Department of Electrical and Computer Systems Engineering ClaytonVIC3800 Australia Curious Insights United Kingdom University of Manchester ManchesterM13 9PL United Kingdom The University of Melbourne School of Electrical and Electronic Engineering ParkvilleVIC3010 Australia

System Strength (SS) is becoming increasingly important while more and more inverter-based resources (IBRs) get connected to weak parts of the grid. There is still, however, a level of ambiguity with respect to formal SS definition. It is to a large extent legacy from conventional systems dominated by synchronous generators, often only simplistically associated with fault level. To overcome these issues and encourage discussion that will lead to more formal SS definition, this paper proposes a new inclusive concept of SS and technical framework to clarify its fundamental technical aspects. Starting from a comprehensive review of existing definitions, assessment metrics, and observed real-life challenges and solutions, the paper identifies the gaps between the technical fundamentals of the SS concept and its legacy perception. This is followed by identification of the key SS components relevant for assessment of both steady-state and dynamic system performance. The paper proposes a new SS classification where the SS "umbrella concept" is broken down into small-signal strength, large-signal strength, and short-circuit strength with relevant SS factors, which may also be used in the context of ancillary services market developments. We indeed highlight how the overall SS can be influenced by a combination of factors, not only by fault level, and recommend that a "voltage-behind-an-impedance" parametrization and model may be more effective in defining SS in many circumstances. Finally, the capabilities of different types of IBRs in providing SS products are discussed along with relevant complexity and limitations. © 2013 IEEE.

关键词： Short circuit currents

来源：评论

学校读者我要写书评

暂无评论

Design of a Pushbroom NIR Optimized System for Citrus Spectral Data Acquisition 18

Design of a Pushbroom NIR Optimized System for Citrus Spectr...

引用

18th National Meeting on Optics and the 9th Andean and Caribbean Conference on Optics and its Applications, ENO-CANCOA 2024

作者： Gomez, Pablo Ardila Leal, Sebastian Orduz Florez, Lineth Julieth Gomez Giraldo, Robert Alexis Garcia, Hans Arguello, Henry Universidad Industrial de Santander Department of Electrical Engineering Bucaramanga Colombia Universidad Industrial de Santander Department of Computer Science Bucaramanga Colombia

ISBN: (纸本)9798350387858

The characterization of citrus fruits is crucial to optimize agricultural production and increase economic benefits for both producers and consumers. However, traditional characterization methods, such as chemical techniques and thermogravimetry, are destructive and invasive to the fruit during data acquisition. In response to this limitation, the acquisition of spectral signatures using the visible and near-infrared (NIR) range for characterization has been implemented. Consequently, this signature is obtained through scanning methodologies such as Whiskbroom or Pushbroom, whose spectral resolution generates multiple equally spaced bands in the range of 400 [nm] to 1000 [nm], offering a non-invasive and highly efficient alternative for extracting fundamental characteristics of citrus fruits. For the analysis of the information contained in the spectral signature, it would be optimal to cover a higher resolution due to overlapping regions. Given this scenario, we propose the design of a diffraction grating to optimize the resolution of the Pushbroom system, allowing control over the physical phenomenon of diffraction to highlight the most important spectral regions. Consequently, we designed a diffractive structure to achieve the best and highest spectral resolution. Subsequently, the three proposed models were compared with the reference model in terms of spectral dispersion and performance in the classification of citrus fruits, resulting in a 2% improvement in precision. © 2024 IEEE.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Enhanced Failure Detection in Induction Motors Using Supervised Learning and Data Smoothing Techniques 8

Enhanced Failure Detection in Induction Motors Using Supervi...

引用

8th SLAAI - International Conference on Artificial Intelligence, SLAAI-ICAI 2024

作者： Nirmal, W.C. Lakmal, H.K.I.S. Dhananjaya, S.A.K. NSBM Green University Faculty of Engineering Department of Mechatronic & Industrial Engineering Homagama Sri Lanka NSBM Green University Faculty of Engineering Electronic & Systems Engineering Department of Electrical Homagama Sri Lanka

ISBN: (纸本)9798331509170

Production machinery failures often cause significant financial losses, and traditional maintenance methods may struggle to mitigate these issues effectively. Predictive maintenance offers a modern solution by forecasting failures before they occur. This study applies supervised learning algorithms to pre-collected vibration data from a single-phase induction motor under normal and simulated abnormal working conditions. Data smoothing techniques such as Moving Average Filter, Kalman Filter, and FFT were employed to enhance data quality. Supervised algorithms including Logistic Regression, Decision Tree, Random Forest, SVM, Naive Bayes, and kNN were implemented and evaluated. Performance metrics such as accuracy, precision, recall, and F1 score were used to compare these algorithms. Results indicate that data smoothing significantly improves model performance, with the Moving Average Filter achieving the highest accuracy for Random Forest at \mathbf{9 9. 7 7 \%}. These findings highlight the potential of advanced machine learning techniques combined with data preprocessing for predictive maintenance in industrial settings. By reducing downtime and maintenance costs, these models enhance operational reliability and efficiency. This study contributes to the growing knowledge on applying machine learning for predictive maintenance, offering practical insights for improving the sustainability and productivity of manufacturing processes. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Robust Score-Based Quickest Change Detection

引用

IEEE Transactions on Information Theory 2025年第7期71卷 5539-5555页

作者： Moushegian, Sean Wu, Suya Diao, Enmao Ding, Jie Banerjee, Taposh Tarokh, Vahid Duke University Department of Electrical and Computer Engineering DurhamNC27708 United States University of Minnesota Twin Cities School of Statistics MinneapolisMN55455 United States University of Pittsburgh Department of Industrial Engineering PittsburghPA15213 United States

Methods in the field of quickest change detection rapidly detect in real-time a change in the data-generating distribution of an online data stream. Existing methods have been able to detect this change point when the densities of the pre-and post-change distributions are known. Recent work has extended these results to the case where the pre-and post-change distributions are known only by their score functions. This work considers the case where the pre-and post-change score functions are known only to correspond to distributions in two disjoint sets. This work selects a pair of least-favorable distributions from these sets to robustify the existing score-based quickest change detection algorithm, the properties of which are studied. This paper calculates the least-favorable distributions for specific model classes and provides methods of estimating the leastfavorable distributions for common constructions. Simulation results are provided demonstrating the performance of our robust change detection algorithm. © 1963-2012 IEEE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Fixed-Wing Tail-Sitter Tethered VTOL Drone with Custom Autopilot and Robust Control Techniques 16th

Design and Development of a Fixed-Wing Tail-Sitter Tether...

引用

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

作者： Safaee, Ahmad Aguiar, A. Pedro Santos, Filipe Neves Moreira, Antonio Paulo SYSTEC-ARISE Research Center for Systems and Technologies Faculty of Engineering University of Porto Porto4200-465 Portugal INESC-TEC-Institute for Systems and Computer Engineering Technology and Science CRIIS-Centre for Robotics in Industry and Intelligent Systems Porto4200-465 Portugal INESC-TEC-Institute for Systems and Computer Engineering and DEEC/FEUP - Department of Electrical and Computer Engineering Faculty of Engineering of the University of Porto Porto4200-465 Portugal

ISBN: (纸本)9783031817236

The need for aerial platforms capable of sustained operation is critical in fields such as surveillance, agricultural monitoring, disaster response, and temporary telecommunication systems. Traditional unmanned aerial vehicles (UAVs) are hampered by limited battery capacity and inefficient energy utilization. This paper introduces an autonomous vertical flight drone tethered to a ground-based platform, which overcomes these limitations. The drone is designed to optimize its position and energy usage by harnessing wind currents, functioning similarly to a kite when conditions permit. This is enabled by a custom-designed autopilot system comprising both hardware and software tailored for this application. We detail the model identification process for three vertical take-off and landing (VTOL) drone systems, employing authentic data that measures lateral positional errors from the tether. Robust mixed sensitivity controllers are developed and implemented. The effectiveness of these controllers is validated through simulations showing their capability to handle uncertainties. Furthermore, the practical application and robust performance of the system are confirmed by a real-world case study, highlighting its potential in real operational environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： VTOL/STOL aircraft

来源：评论

学校读者我要写书评

暂无评论

ASSESSMENT OF THE SIGNIFICANCE OF FEATURES FOR THE IDENTIFICATION OF DOMESTIC APPLIANCES 27

ASSESSMENT OF THE SIGNIFICANCE OF FEATURES FOR THE IDENTIFIC...

引用

27th International Conference on Electricity Distribution, CIRED 2023

作者： Ma, Liya Schmidt, Maximilian Schegner, Peter Technische Universitaet Dresden Institute of Electrical Power Systems and High Voltage engineering Faculty of Electrical and Computer Engineering Dresden Germany

ISBN: (纸本)9781839539596

The load identification technologies in the domestic field, also called Non-Intrusive Load Monitoring (NILM), aim to break down the total electricity consumption at household level to the appliance level. This detailed information helps to identify the behaviour of users, deduce energy saving concepts, or provide live assistance for the residents. The NILM approaches are carried out with appliance features, such as the absorbed power, the voltage and current profile. They are defined as appliance-specific characteristics or features, which supposed to make the appliance clearly distinguishable from others. However, most of the publications focus on the identification algorithms. There is barely a contribution to analyse the significance of features. Hereby, the significance means, how consistent and reliable a feature differs from one appliance to another. This paper works on this question. Based on analyses of publications and own measurements, this paper gives an overview of the significance of representative features. Furthermore, suitable features for one-second data are selected and NILM is carried out. © The Institution of engineering and Technology 2023.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks 41

Provable Multi-Task Representation Learning by Two-Layer ReL...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Collins, Liam Hassani, Hamed Soltanolkotabi, Mahdi Mokhtari, Aryan Shakkottai, Sanjay Department of Electrical and Computer Engineering University of Texas at Austin AustinTX United States Department of Electrical and Systems Engineering University of Pennsylvania PhiladelphiaPA United States Department of Electrical and Computer Engineering University of Southern California Los AngelesCA United States

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong downstream performance in a variety of contexts, demonstrating that multitask pretraining leads to effective feature learning. Although several recent theoretical studies have shown that shallow NNs learn meaningful features when either (i) they are trained on a single task or (ii) they are linear, very little is known about the closer-to-practice case of nonlinear NNs trained on multiple tasks. In this work, we present the first results proving that feature learning occurs during training with a nonlinear model on multiple tasks. Our key insight is that multi-task pretraining induces a pseudo-contrastive loss that favors representations that align points that typically have the same label across tasks. Using this observation, we show that when the tasks are binary classification tasks with labels depending on the projection of the data onto an r-dimensional subspace within the d rdimensional input space, a simple gradient-based multitask learning algorithm on a two-layer ReLU NN recovers this projection, allowing for generalization to downstream tasks with sample and neuron complexity independent of d. In contrast, we show that with high probability over the draw of a single task, training on this single task cannot guarantee to learn all r ground-truth features. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：