检索结果-内蒙古大学图书馆

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Varotto, Matteo Valentin, Stefan Tomasin, Stefano University of Padova Dep. of Information Engineering Padova Italy Darmstadt University of Applied Sciences Dep. of Computer Science Darmstadt Germany University of Padova Dep. of Information Engineering Dep. of Mathematics Padova Italy

ISBN: (纸本)9798350370218

Fifth-generation (5G) networks are prone to jamming attacks, which are particularly dangerous in mission-critical applications such as factory automation. In this paper, we present a simple method to detect jamming attacks with machine learning techniques operating on in-phase and quadrature (IQ) modulated signals. In particular, a convolutional autoencoder (CAE) learns the structure of the clean signal to distinguish it from jammed signals in real time. This approach requires only a loose synchronization to the OFDM symbol, while equalization and decoding are not necessary. Despite its simplicity, our technique has shown high detection rates in experiments on a 5G testbed. © 2023 IEEE.

关键词： 5G Convolutional Autoencoder IQ Signals Jamming Detection New Radio Wireless Intrusion Prevention

来源：评论

学校读者我要写书评

暂无评论

CNN-based Human Activity Recognition on Edge Computing Devices

CNN-based Human Activity Recognition on Edge Computing Devic...

引用

2023 IEEE International Conference on Omni-Layer Intelligent Systems, COINS 2023

作者： Singh, Amandeep Margaria, Tiziana Demrozi, Florenc University of Limerick Dep. of Computer Science and Information Systems Ireland University of Stavanger Dep. of Electrical Engineering and Computer Science Norway

ISBN: (纸本)9798350346473

Human Activity Recognition (HAR) is a research area that involves wearable devices integrating inertial and/or physiological sensors to classify human actions and status across various application domains, such as healthcare, sports, industry, and entertainment. However, executing HAR algorithms on remote devices or the cloud can lead to issues such as latency, bandwidth requirements, and energy consumption. Transitioning towards Edge HAR can be a more effective and versatile solution, overcoming the challenges of traditional HAR techniques. We present a novel HAR model for computation on edge devices: we design a Convolutional Neural Network (CNN) Deep Learning approach and compare its performance with cloud-computing HAR models. The paper is accompanied by a self-collected dataset. The experiments on this dataset demonstrate that the proposed edge computing model achieves promising results (\geq 92 %) in terms of Precision, Recall, and Fl-score. Furthermore, the model exhibits significantly reduced latency, with only 117 ms, and utilizes minimal memory, with a peak of 18.8 Kb RAM and 956 Kb Flash memory. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

A Review of Grid-Connected Inverters and Control Methods Under Unbalanced Grid Conditions 16

A Review of Grid-Connected Inverters and Control Methods Und...

引用

16th Annual Power Electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Marangalu, Milad Ghavipanjeh Rehman, Fazal Ur Kurkdjian, Naser Vosoughi Computer Queen's University Dep. Of Electrical and Computer Engineering KingstonON Canada University of L'Aquila Dep. Information Engineering Computer Science and Mathematics L'Aquila Italy San Diego State University Faculty of Electrical and Computer Engineering San DiegoCA92182-0001 United States

ISBN: (纸本)9798331533946

Grid-connected inverters play a pivotal role in integrating renewable energy sources into modern power systems. However, the presence of unbalanced grid conditions poses significant challenges to the stable operation of these inverters. This review paper provides a comprehensive overview of grid-connected inverters and control methods tailored to address unbalanced grid conditions. Beginning with an introduction to the fundamentals of grid-connected inverters, the paper elucidates the impact of unbalanced grid voltages on their performance. Various control strategies, including voltage and current control methods, are examined in detail, highlighting their strengths and limitations in mitigating the effects of grid imbalance. Lastly, the review identifies emerging trends and future research directions in the field, emphasizing the need for innovative solutions to address the evolving challenges posed by unbalanced grid conditions in the context of renewable energy integration. © 2025 IEEE.

关键词： control strategy fault conditions grid-connected inverters Photovoltaic systems

来源：评论

学校读者我要写书评

暂无评论

Traffic sign recognition based on CNN vs different transfer learning techniques 5

Traffic sign recognition based on CNN vs different transfer ...

引用

5th Symposium on Pattern Recognition and Applications, SPRA 2024

作者： Ghouse, Mohammed Farag, Saber Butt, Usman Engineering and Environment Dep. Northumbria University London United Kingdom Computer and Information Science Dep. British University in Dubai Dubai United Arab Emirates

ISBN: (数字)9781510688803

ISBN: (纸本)9781510688797

Traffic sign detection and recognition (TSDR) is a pivotal component of contemporary transportation systems, designed to enhance road safety and operational efficiency. In an era where automation is indispensable, TSDR stands out as a critical tool for optimizing driving experiences. This study presents the development of a TSDR model employing advanced deep learning techniques, with a particular emphasis on convolutional neural networks (CNNs). Utilizing the German Traffic Sign Recognition Benchmark (GTSRB) dataset, which comprises annotated images of various traffic signs captured under diverse environmental conditions, we achieved remarkable results. Our CNN models demonstrated a 99% detection rate, underscoring their efficacy in traffic sign recognition tasks. Furthermore, transfer learning models yielded impressive accuracies, with VGG19 achieving 99.64%, EfficientNetB7 reaching 99%, and ASNet attaining 99.72%. Despite these promising results, we identified several limitations, including dataset-specific dep.ndencies and the need for further enhancements in model design and training methodologies. Addressing these challenges is necessary for ensuring the robustness and reliability of intelligent transportation systems, thereby significantly improving road traffic management, safety, and efficiency. Copyright © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A SENSITIVITY ANALYSIS ON THE EFFECT OF HYPERPARAMETERS IN DEEP NEURAL OPERATORS APPLIED TO SOUND PROPAGATION 10

A SENSITIVITY ANALYSIS ON THE EFFECT OF HYPERPARAMETERS IN D...

引用

10th Convention of the European Acoustics Association, EAA 2023

作者： Borrel-Jensen, Nikolas Engsig-Karup, Allan P. Jeong, Cheol-Ho Technical University of Denmark Dep. of Electrical and Photonics Engineering Denmark Technical University of Denmark Dep. of Applied Mathematics and Computer Science Denmark

ISBN: (纸本)9788888942674

Deep neural operators have seen much attention in the scientific machine learning community over the last couple of years due to their capability of efficiently learning the nonlinear operators mapping from input function spaces to output function spaces showing good generalization properties. This work will show how to set up a per-formant DeepONet architecture in acoustics for predicting 2-D sound fields with parameterized moving sources for real-time applications. A sensitivity analysis is carried out with a focus on the choice of network architectures, activation functions, Fourier feature expansions, and data fidelity to gain insight into how to tune these models. Specifically, a default feed-forward neural network (FNN), a modified FNN, and a convolutional neural network will be compared. This work will de-mystify the DeepONet and provide helpful knowledge from an acoustical point of view. © 2023 Nikolas Borrel-Jensen et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Intelligent Reflecting Surfaces for 5G/6G-Enabled Future Smart Industries with a Focus on Millimeter-Wave Band Communications 59

Performance Analysis of Intelligent Reflecting Surfaces for ...

引用

2024 Annual IEEE International Conference on Communications Workshops, ICC Workshops 2024

作者： Khan, Muhammad Farhan Raza, Ali Iqbal, Adeel Rashid, Adnan Jamshed, Muhammad Ali Pesch, Dirk School of Computer Science and Information Technology University College Cork Cork Ireland Comsats University Islamabad Dep. of Electrical and Computer Engineering Pakistan Yeungnam University Dep. of Info. & Com. Engineering Gyeongsan-si38541 Korea Republic of Politecnico di Bari Dep. of Electrical & Information Engineering Bari Italy James Watt School of Engineering University of Glasgow Glasgow United Kingdom

ISBN: (纸本)9798350304053

Industry 4.0's emergence necessitates reliable communication systems. Millimeter-wave (mmWave) communication is a promising solution, but challenges like limited coverage and atmospheric absorption persist. The Intelligent Reflecting Surfaces (IRS) offers transformative potential by dynamically manipulating wave propagation to improve millimeter-wave (mmWave) communication. This research investigates the impact of the distance of Industrial User Equipment (iUE) from the IRS and Base Station (BS), and the height of the IRS from the ground, along with the impact of sum throughput by increasing the number of IRS elements. The IRS-assisted system exhibits enhanced performance within the mmWave frequency band compared to the sub-6 GHz band. The observed achievable rate gains, exceeding 200% on average, underscore the significant performance enhancement enabled by IRS dep.oyments. Moreover, increasing the number of IRS elements significantly enhances the overall throughput. The decrease in required transmit power with an increasing number of Intelligent Reflecting Surfaces IRS elements can be attributed to the enhanced ability of IRS to efficiently reflect and manipulate electromagnetic waves. As more IRS elements are dep.oyed, they collectively contribute to optimizing signal propagation, allowing for better control and redirection of the transmitted signals. This phenomenon enables the system to achieve the desired communication objectives with less overall transmit power. Additionally, the attainable capacity of the examined IRS-assisted wireless communication system exhibits growth alongside an increase in the elevation of the IRS installation. Results showcase the potential of IRSs to enhance coverage and communication reliability, providing valuable insights for designing efficient wireless systems in smart factories and Industry 4.0 applications. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Robust Spoofing Detection: A Chi-Square-based Machine Learning Approach 2

Feature Selection for Robust Spoofing Detection: A Chi-Squar...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Al-Na'amneh, Qais Aljaidi, Mohammad Gharaibeh, Hasan Nasayreh, Ahmad Emhamed Al Mamlook, Rabia Almatarneh, Sattam Alzu'bi, Dalia Suliman Husien, Abla Applied Science Private University Dep. of Cyber Security Amman Jordan Zarqa University Dep. of Computer Science Zarqa Jordan Yarmouk University Dep. Computer Science Irbid Jordan Trine University Dep. of Business Administration Indiana United States University of Zawia Department of Industrial Engineering Tripoli Libya Zarqa University Dep. of Data Science and Artificial Intelligence Zarqa Jordan Concordia University Dep. Information and Systems Engineering Montreal Canada

ISBN: (纸本)9798350373363

Nowadays, the Internet of Things (IoT) system is vulnerable to spoofing attacks that can easily where attackers can easily pose as a legal entity of the network. A 'spoofing attack' refers to a type of cyber-attack when an attacker purposefully impersonates or masquerades as someone or something else to deceive the target or obtain unauthorized access to systems, information, or resources. In such attacks, the attacker alters their name, IP address, or other attributes to fool the victim into thinking they are engaging with a legitimate entity. Spoofing attacks can take place via a variety of channels, including, ARP and DNS spoofing. Therefore. Spoofing attacks can have serious consequences. We proposed a new approach based on three machine learning models LightGBM, Gradient Boost, and XGBoost to classify attacks on spoofing, we used Chi-square to select the best features to get the highest performance, and we demonstrated that the results using Chi-square achieved higher results than without Chi-square and improved the result with a rate three percent of accuracy. In terms of results, LightGBM outperformed other models by achieving 89%, 91 %, 87 %, and 89 % for accuracy, precision, recall, and f1-score, respectively. This shows the potential and efficiency of Chi-square to achieve the best performance by selecting the best features, thus providing a secure system and identifying cyber-attacks on systems. © 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

Logistic Regression Classification for Assessing the Risk of Kidney Tumor 2

Logistic Regression Classification for Assessing the Risk of...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Alzubi, Dalia Al Mamlook, Rabia Emhamed Nasayreh, Ahmad Aljaidi, Mohammad Alazab, Rami Gharaibeh, Hasan Al-Naamneh, Qais Concordia University Dep. Information and Systems Engineering Montreal Canada Trine University Dep. of Business Administration IN United States University Zawia Department of Industrial Engineering Tripoli Libya Yarmouk University Dep. Computer Science Irbid Jordan Zarqa University Dep. of Computer Science Zarqa Jordan Jordan University of Science and Technology Dep. Surgery and Urology Irbid Jordan Applied Science Private University Dep. of Cyber Security Amman Jordan

ISBN: (纸本)9798350373363

The kidneys have the important function of filtering waste products and toxins from the blood in the human body. Any problems affecting the kidneys can potentially impact their efficiency and overall function. Kidney Tumor (KT) is a disease that specifically affects kidney cells and causes the abnormal growth of tissue in one or both kidneys. Assessing the risk of developing a kidney tumor and identifying the key factors that contribute to this risk are crucial for ensuring patient well-being. Additionally, this information assists doctors and specialists in making faster and more accurate diagnoses, determining appropriate treatment methods, and potentially influencing the course of the disease to minimize its severity and impact. Machine learning algorithms have recently been introduced to evaluate disease risks, and in this study, we specifically focus on examining the risk of kidney tumor development and investigating the influencing factors. We employed a logistic regression model to predict if a patient is at risk of developing a kidney tumor or not, and further categorized the samples into high-risk and low-risk groups. Our model was trained and tested using a unique dataset obtained from the (KAUH) hospital in Jordan, consisting of well-balanced metadata from 120 patients with kidney issues. Our work demonstrated accuracy results ranging from 90% to 98%. Ultimately, specialists can utilize our model as an additional tool to enhance the speed and accuracy of patient diagnoses © 2023 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

RF-Based Lightweight Machine Learning for Comprehensive Drone Activity Classification 2

RF-Based Lightweight Machine Learning for Comprehensive Dron...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Alqodah, Mohammed A. Tahsin, Mahdia Omari, Mohammad H. Matalgah, Mustafa M. Harrison, David University of Mississippi Dep. of Electrical & Computer Engineering UniversityMS United States University of Mississippi Dept. of Computer and Information Science UniversityMS United States

ISBN: (纸本)9798331529529

The rapid rise of commercially available drones, driven by miniaturization and affordability, has introduced potential security risks alongside numerous societal benefits. While drones serve various industries, their unregulated use necessitates robust detection and classification methods. This paper proposes a novel, efficient model for classifying unwanted drone activity. We leverage statistical and time-domain features extracted from radio frequency (RF) signals and machine learning (ML) classifiers. This approach aims to not only detect drones but also distinguish their models and operational modes. Utilizing the DroneRF dataset, our feature selection strategy prioritizes informative signals in the low-band spectrum, achieving {100%} accuracy in both drone detection and drone model identification tasks. Furthermore, our hybrid model, combining time-domain and frequency-domain features, achieves an accuracy of {97.66%} in classifying different flight modes. This demonstrates the effectiveness of this comprehensive feature extraction approach for drone activity classification. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Detecting 5G Signal Jammers Using Spectrograms with Supervised and Unsupervised Learning

arXiv

引用

arXiv 2024年

作者： Varotto, Matteo Valentin, Stefan Tomasin, Stefano Dep. of Computer Science Darmstadt University of Applied Sciences Germany Dep. of Information Engineering Dep. of Mathematics University of Padova Italy

Cellular networks are potential targets of jamming attacks to disrupt wireless communications. Since the fifth generation (5G) of cellular networks enables mission-critical applications, such as autonomous driving or smart manufacturing, the resulting malfunctions can cause serious damage. This paper proposes to detect broadband jammers by an online classification of spectrograms. These spectrograms are computed from a stream of in-phase and quadrature (IQ) samples of 5G radio signals. We obtain these signals experimentally and describe how to design a suitable dataset for training. Based on this data, we compare two classification methods: a supervised learning model built on a basic convolutional neural network (CNN) and an unsupervised learning model based on a convolutional autoencoder (CAE). After comparing the structure of these models, their performance is assessed in terms of accuracy and computational complexity. © 2024, CC BY.

关键词： Convolution

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

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

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：