检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Environment and Electrical Engineering and 2023 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2023

作者： Guerrero, José M. Serrano-Jiménez, Daniel Mahtani, Kumar Platero, Carlos A. Mondragon University Electronic and Computing Department Arrasate/Mondragon Spain Universidad Politécnica de Madrid Energy and Fuels Department Madrid Spain Universidad Politécnica de Madrid Automatic Electric and Electronic Engineering and Industrial Informatics Department Madrid Spain

ISBN: (纸本)9798350347432

The application of Direct Current (DC) railway systems is more and more noticeable as they conform most of urban tram feeding systems and, step-by-step, it is being introduced in high-speed train power systems. Despite of their high efficiency, the risk of ground faults is latent due to environmental problems and aging in the catenary. These faults can interrupt the service for hours until it is repaired, then a quick maintenance is needed. In order to help in this issue, this paper proposes a ground fault location method for catenaries in DC railway systems based on the DC voltage and earth current measurement in each DC traction substation (TS). The normalized currents respecting the global fault current are compared with a model-based data pool allowing the method to locate the fault along the protected catenary. To corroborate the method, simulations have been performed in a three-TS DC railway model in Matlab-Simulink obtaining promising results. © 2023 IEEE.

关键词： Railroads

来源：评论

学校读者我要写书评

暂无评论

Questionable Fairness in Federated Learning 8

Questionable Fairness in Federated Learning

引用

8th International Conference on Data Science and Machine Learning Applications, CDMA 2025

作者： Alharbi, Raed Nguyen, Truc Yousefzadeh, Nooshin Aljohani, Ahmed National Renewable Energy Laboratory Computatioual Science Center GoldenCO United States University of Florida Computer and Information Science and Engineering Department GainesvilleFL United States College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia University of North Texas Computer Science and Engineering Denton United States

ISBN: (纸本)9798331539696

Federated learning (FL) has emerged as a powerful framework for training deep learning models across numerous distributed clients, where a central server distributes and aggregates model updates without accessing clients' raw data, ensuring privacy. However, this decentralized approach introduces significant challenges regarding fairness. Existing research shows that non-i.i.d. data distributions among clients can lead to biased global models, particularly affecting decisions based on sensitive attributes. This paper aims to investigate these fairness issues rigorously by analyzing how disparities in client data distribution impact model fairness. We conduct experiments using various models and datasets to evaluate and mitigate biases. We also propose novel data partitioning strategies to reflect real-world client data distributions accurately. Our finding shows that FL is highly vulnerable to the fairness problem due to the Non-IID property. The experiment's code can be found here: https://***/raed19/Questionable-Fairness-in-Federated-Learning. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Smart Grid Stability Using AI Techniques: A Systematic Literature Review

Enhancing Smart Grid Stability Using AI Techniques: A System...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Muhamme Ibrahim Moamin A Mahmoud Noor Islam Saraswathy Shamini Gunasekara Department of Information System College of Graduate studies Universiti Tenaga Nasional Selangor Malaysia Nigerian Army University Biu Borno Nigeria College of Computing and Informatics Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Selangor Malaysia Jasim College of Graduate Studies Universiti Tenaga Nasional Selangor Malaysia

ISBN: (数字)9798331522193

ISBN: (纸本)9798331522209

The modern smart grid leverages advanced technologies to enhance electricity distribution's efficiency, reliability, and sustainability, enabling two-way energy and data exchange. This systematic literature review (SLR) explores how artificial intelligence (AI) addresses the challenge of smart grid stability. From 1,181 records identified via Scopus and Web of Science, 41 studies were analyzed in-depth. The SLR evaluates AI techniques such as machine learning, deep learning, neural networks, hierarchical clustering, and explainable AI across functions like fault detection, stability analysis, energy forecasting, and demand response. Findings reveal AI's role in enhancing grid stability through predictive capabilities and adaptive controls. This study contributes a taxonomy of AI applications, identifies research gaps, and outlines a future research direction. Key challenges include scalability, data privacy, and model interpretability, while opportunities lie in hybrid models, and integration with blockchain and IoT. The study provides actionable insights for researchers, policymakers, and stakeholders.

关键词： Adaptation models Fault detection Power system stability Stability analysis Data models Smart grids Security Artificial intelligence Sustainable development Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

A Review on Privacy-Preserving Techniques in Data Analytics 6

A Review on Privacy-Preserving Techniques in Data Analytics

引用

6th International Conference on Signal and Image Processing, ICSIP 2021

作者： Khairul Anuar, Norsyahirah Abu Bakar, Asmidar Abu Bakar, Aishah Uniten RandD Sdn. Bhd. Selangor Kajang Malaysia Universiti Tenaga Nasional College of Computing and Informatics Selangor Kajang Malaysia Institute of Informatics and Computing Energy Universiti Tenaga Nasional Selangor Kajang Malaysia

ISBN: (纸本)9780738133737

This paper reviews privacy-preserving techniques in data analytics. Data analytics is a concept of processing raw data and analysing the output for various beneficial reasons. There are four types of data analytics stated in this paper, those are descriptive analytics, diagnostic analytics, predictive analytics, and prescriptive analytics. Data itself contains unstructured, semi-structured and structured data. We compare the privacy-preserving techniques in data analytics to see whether the techniques are suitable or unsuitable to be applied in data analytics. © 2021 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning Botnet Detection Techniques based on Network Traffic Log

A Review of Machine Learning Botnet Detection Techniques bas...

引用

computing (ICOCO), IEEE International Conference on

作者： Zul-Azri Ibrahim Rina Azlin Razali Saiful Adli Ismail Iman Hakimi Khairil Azhar Fiza Abdul Rahim Ahmad Muzafaraidil Ahmad Azilan Institute of Informatics and Computing in Energy College of Computing and Informatics Universiti Tenaga Nasional Kajang Selangor Malaysia Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Wilayah Persekutuan Kuala Lumpur Kuala Lumpur Malaysia Department of Computing College of Computing and Informatics Universiti Tenaga Nasional Kajang Selangor Malaysia

ISBN: (纸本)9781665489973

Cyber-attacks are a common issue in this modern era because of the introduction of high-speed networks and the use of new technologies like Internet of Things (IoT) devices, which fuel the rapid expansion of cyber-attack. One of the common cyber-attacks is botnet attacks. Hackers use botnet attacks to exploit newly discovered vulnerabilities in order to conduct intensive scraping, distributed denial of service (DDoS) attacks, and other large-scale cybercrime. With their adaptable and dynamic character, botnets work with a botmaster to plan their activities, modify their codes, and update the bots regularly to avoid detection. Researchers use numerous techniques to detect the botnet. However, botmasters nowadays have improved due to avoiding security in detection. As the communication can leave traces that allow researchers to detect the botnet’s existence, this paper will review 15 related works on botnet detection that utilize machine learning to predict the botnet communication with the command-and-control (C&C or C2) center based on the network traffic log. This paper summarizes the related works based on the dataset, environment, botnet type, features employed, and machine learning techniques.

关键词： High-speed networks Computer hacking Botnet Machine learning Telecommunication traffic Denial-of-service attack Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Medical Image Analysis Using Deep Learning and Distribution Pattern Matching Algorithm

引用

Computers, Materials & Continua 2022年第8期72卷 2175-2190页

作者： Mustafa Musa Jaber Salman Yussof Amer S.Elameer Leong Yeng Weng Sura Khalil Abd Anand Nayyar Institute of Informatics and Computing in Energy Universiti Tenaga NasionalMalaysia Department of Computer Science Dijlah University CollageBaghdad10021Iraq Biomedical Informatics College University of Information Technology and CommunicationsBaghdadIraq Faculty of Information Technology Duy Tan UniversityDa Nang550000Viet Nam Graduate School Duy Tan UniversityDa Nang550000Viet Nam Department of Computer Science Al-turath University CollegeBaghdadIraq

Artificial intelligence plays an essential role in the medical and health *** convolution networks offer valuable services and help create automated systems to perform medical image ***,convolution networks examine medical images effectively;such systems require high computational complexity when recognizing the same disease-affected ***,an optimized deep convolution network is utilized for analyzing disease-affected regions in this *** disease-relatedmedical images are selected and examined pixel by pixel;this analysis uses the gray wolf optimized deep learning *** method identifies affected pixels by the gray wolf hunting *** convolution network uses an automatic learning function that predicts the disease affected by previous imaging *** optimized algorithm-based selected regions are further examined using the distribution pattern-matching *** pattern-matching process recognizes the disease effectively,and the system’s efficiency is evaluated using theMATLAB implementation *** process ensures high accuracy of up to 99.02%to 99.37%and reduces computational complexity.

关键词： Artificial intelligence medical field gray wolf-optimized deep convolution networks distribution pattern-matching rule

来源：评论

学校读者我要写书评

暂无评论

Using Drones and Robots for Social Distancing: Literature Review, Challenges and Issues

Using Drones and Robots for Social Distancing: Literature Re...

引用

Panhellenic Conference on Electronics and Telecommunications (PACET)

作者： Sallar Salam Murad Rozin Badeel Reham A. Ahmed Salman Yussof Institute of Informatics and Computing in Energy University Tenaga Nasional (UNITEN) Kajang Malaysia Department of Communication Technology and Network University Putra Malaysia (UPM) Seri Kembangan Malaysia

Since the number of recorded instances of COVID-19 and the number of deaths linked with the virus are both on the rise, it is crucial to maintain an appropriate level of social distance and wear masks to prevent the transmission of coronavirus. The goal of the Social Distancing is to determine if a given pair of persons is keeping a suitable amount of space from one another. Quarantining infected areas and limiting the spread of viruses in both social and physical settings have been made easier with the help of a number of promising robotic technologies that aid people and healthcare experts in the tracking of virus symptoms, the care of infected individuals, and the avoidance of further infection and spread. In this study, we examine the most up-to-date strategies, structures, and tools for utilizing drones in non-social contexts. Additionally, difficulties, problems, and restrictions within the existing literature are addressed. The primary goal of this study is to aid and educate developers and readers interested in deploying drones and robots' technology to battle COVID-19, and to expose the challenges observed in the previous studies to allow the researcher to improve their methods and systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusion of Infrared and Visible Images Using Fuzzy Based Siamese Convolutional Network

引用

Computers, Materials & Continua 2022年第3期70卷 5503-5518页

作者： Kanika Bhalla Deepika Koundal Surbhi Bhatia Mohammad Khalid Imam Rahmani Muhammad Tahir Department of Electrical Engineering National Taipei University of TechnologyTaipei10608Taiwan Department Virtualization School of Computer ScienceUniversity of Petroleum&Energy StudiesDehradunIndia College of Computer Science and Information technology King Faisal University36362Saudi Arabia College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia

Traditional techniques based on image fusion are arduous in integrating complementary or heterogeneous infrared(IR)/visible(VS)*** in various kind of features in these images are vital to preserve in the single fused ***,simultaneous preservation of both the aspects at the same time is a challenging ***,most of the existing methods utilize the manual extraction of features;and manual complicated designing of fusion rules resulted in a blurry artifact in the fused ***,this study has proposed a hybrid algorithm for the integration of multi-features among two heterogeneous ***,fuzzification of two IR/VS images has been done by feeding it to the fuzzy sets to remove the uncertainty present in the background and object of interest of the ***,images have been learned by two parallel branches of the siamese convolutional neural network(CNN)to extract prominent features from the images as well as high-frequency information to produce focus maps containing source image ***,the obtained focused maps which contained the detailed integrated information are directly mapped with the source image via pixelwise strategy to result in fused *** parameters have been used to evaluate the performance of the proposed image fusion by achieving 1.008 for mutual information(MI),0.841 for entropy(EG),0.655 for edge information(EI),0.652 for human perception(HP),and 0.980 for image structural similarity(ISS).Experimental results have shown that the proposed technique has attained the best qualitative and quantitative results using 78 publically available images in comparison to the existing discrete cosine transform(DCT),anisotropic diffusion&karhunen-loeve(ADKL),guided filter(GF),random walk(RW),principal component analysis(PCA),and convolutional neural network(CNN)methods.

关键词： Convolutional neural network fuzzy sets infrared and visible image fusion deep learning

来源：评论

学校读者我要写书评

暂无评论

Cyber-Crime Detection: Experimental Techniques Comparison Analysis

Cyber-Crime Detection: Experimental Techniques Comparison An...

引用

Visualization, informatics and Technology Conference (IVIT), International

作者： Ebraheem Fahad Aljarboua Marina Bte Md. Din Asmidar Abu Bakar Institute of Informatics and Computing in Energy (IICE) Universiti Tenaga Nasional Kajang Selangor Malaysia

ISBN: (纸本)9781665486491

Cyber-crime is one of the main problems the world face, and machine learning plays a key part in contemporary operating systems for giving better transformation in the security environment and cybercrime detection. While detecting cybercrimes is difficult, it is possible to gain advantages from machine learning to generate models to assist in predicting and detecting cybercrimes. The researchers have proven that the majority of the models can work effectively in identifying cybercrime, they can span from 70% to 90% in accuracy measuring. The objective of this research paper is to conduct experimental techniques comparison analysis for cyber-crime detection by reviewing all possible machine learning algorithms for automatic detection. The key focus of the study is on the use of eight classifiers models which are Logistic Regression (LR), Decision Tree (DT), K-nearest Neighbors (KNN), Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and Multiple layer perception (MLP). From the experiment conducted, the high prediction came from MLP which is 96% accuracy of the cyber-crime methods based on existing cyber-crime data.

关键词： Support vector machines Radio frequency Machine learning algorithms Operating systems Predictive models Security Computer crime

来源：评论

学校读者我要写书评

暂无评论

Drona: A Smart Drone Architecture

Drona: A Smart Drone Architecture

引用

2022 Advances in Science and Engineering Technology International Conferences, ASET 2022

作者： Siouf, Saif Jamjoum, Mohammad Abdelsalam, Emad Amierh, Zayna Ibrawish, Enas Taamneh, Hashem Al-Hussein Technical University Department of Energy Engineering Amman Jordan Al-Hussein Technical University Department of Electrical Engineering Amman Jordan Al-Hussein Technical University School of Computing and Informatics Amman Jordan

ISBN: (纸本)9781665418010

This work presents a novel design of a modular- based drone. The modules are standalone sensors with standard interface that allow for plug-and-play configurations suitable for flexible drone applications. In this paper, a web-based interface with a smart portable patient monitoring module was presented. Initial prototype was built and tested to proof the conceptual model. A functional web-based interface was developed. The web interface included a two-way video and audio communication capability, map location of the drone, an analog box that shows the point of view of the drone itself. Furthermore, the web interface provides multiple important information such as the battery voltage, flight mode, drone speed, altitude, and numeric GPS coordinates. The results showed that the design was fully functional to provide the intended features. © 2022 IEEE.

关键词： Drones

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：