检索结果-内蒙古大学图书馆

Securing MIMO Wiretap Channel With Learning-Based Friendly Jamming Under Imperfect CSI

IEEE Internet of Things Journal 2025年第11期12卷 16009-16022页

作者： Minh Tuan, Bui Nguyen, Diep N. Linh Trung, Nguyen Nguyen, Van-Dinh Van Huynh, Nguyen Thai Hoang, Dinh Krunz, Marwan Dutkiewicz, Eryk University of Technology Sydney School of Electrical and Data Engineering SydneyNSW2007 Australia University of Engineering and Technology Vietnam National University Faculty of Electronics and Telecommunications Hanoi100000 Viet Nam College of Engineering and Computer Science VinUniversity Hanoi100000 Viet Nam University of Liverpool Department of Electrical Engineering and Electronics LiverpoolL69 3GJ United Kingdom The University of Arizona Department of Electrical and Computer Engineering TucsonAZ85721 United States

Wireless communications are particularly vulnerable to eavesdropping attacks due to their broadcast nature. To effectively deal with eavesdroppers, existing security techniques usually require accurate channel state information (CSI), e.g., for friendly jamming (FJ), and/or additional computing resources at transceivers, e.g., cryptography-based solutions, which unfortunately may not be feasible in practice. This challenge is even more acute in low-end IoT devices. We thus introduce a novel deep learning-based FJ framework that can effectively defeat eavesdropping attacks with imperfect CSI and even without CSI of legitimate channels. In particular, we first develop an autoencoder-based communication architecture with FJ, namely, AEFJ, to jointly maximize the secrecy rate and minimize the block error rate (BLER) at the receiver without requiring perfect CSI of the legitimate channels. In addition, to deal with the case without CSI, we leverage the mutual information neural estimation (MINE) concept and design a MINE-based FJ scheme that can achieve comparable security performance to the conventional FJ methods that require perfect CSI. Extensive simulations in a multiple-input-multiple-output (MIMO) system demonstrate that our proposed solution can effectively deal with eavesdropping attacks in various settings. Moreover, the proposed framework can seamlessly integrate MIMO security and detection tasks into a unified end-to-end learning process. This integrated approach can significantly maximize the throughput and minimize the BLER, offering a good solution for enhancing communication security in wireless communication systems. © 2014 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Modelling of Laminated Cores in electrical Machines using Homogenization and Neural Networks

Fast and Accurate Modelling of Laminated Cores in Electrical...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Purnode, Florent Henrotte, François Louppe, Gilles Geuzaine, Christophe University of Liège Department of Electrical Engineering and Computer Science Belgium

ISBN: (纸本)9798350338362

Eddy currents induced in the individual laminations of ferromagnetic laminated cores are usually disregarded in conventional electrical machine simulations, and magnetic losses are then only evaluated a posteriori, by means of Steinmetz-like formulas. This approach yields however seriously inaccurate computed fields and losses whenever the operating frequency increases, or in the presence of higher harmonics, which is an issue of growing importance in industrial R&D. In this contribution we introduce a significantly improved and effective approach based on homogenization and neural networks. The method can be easily implemented in standard finite element packages. © 2023 IEEE.

关键词： Laminating

来源：评论

学校读者我要写书评

暂无评论

DemoCraft: Using In-Context Learning to Improve Code Generation in Large Language Models 3

DemoCraft: Using In-Context Learning to Improve Code Generat...

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, electrical and Electronics, IITCEE 2025

作者： Joshua, Kapu Nirmal Sreejith, Mihit Indian Institute of Technology Department of Electrical Engineering Kanpur India Indian Institute of Technology Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798331515911

Producing executable code from natural-language directives via Large Language Models (LLMs) involves obstacles like semantic uncertainty and the requirement for task-focused context interpretation. To resolve these difficulties, we introduce DemoCraft, a framework that refines code generation through in-context learning and demonstration selection, in tandem with latent concept learning. Latent concept learning appends extra concept tokens, which act as trainable embeddings encapsulating task-oriented insights. We evaluate our approach on two promi- nent datasets: MBPP and Humaneval. Our experimental findings reveal that this method attains roughly a 2x boost in the pass@k metric compared to baseline models. Moreover, we propose two new evaluation measurements: correctness@k and similarity@k. Empirical analyses indicate that our system achieves nearly a 3x advancement in these measures as well. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Neurosymbolic Reinforcement Learning and Planning: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 1939-1953页

作者： Acharya, Kamal Raza, Waleed Dourado, Carlos Velasquez, Alvaro Song, Houbing Herbert University of Maryland Department of Information Systems Baltimore County BaltimoreMD21250 United States Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science Daytona BeachFL32114 United States University of Colorado Department of Computer Science BoulderCO80309 United States

The area of neurosymbolic artificial intelligence (Neurosymbolic AI) is rapidly developing and has become a popular research topic, encompassing subfields, such as neurosymbolic deep learning and neurosymbolic reinforcement learning (Neurosymbolic RL). Compared with traditional learning methods, Neurosymbolic AI offers significant advantages by simplifying complexity and providing transparency and explainability. Reinforcement learning (RL), a long-standing artificial intelligence (AI) concept that mimics human behavior using rewards and punishment, is a fundamental component of Neurosymbolic RL, a recent integration of the two fields that has yielded promising results. The aim of this article is to contribute to the emerging field of Neurosymbolic RL by conducting a literature survey. Our evaluation focuses on the three components that constitute Neurosymbolic RL: neural, symbolic, and RL. We categorize works based on the role played by the neural and symbolic parts in RL, into three taxonomies: learning for reasoning, reasoning for learning, and learning-reasoning. These categories are further divided into subcategories based on their applications. Furthermore, we analyze the RL components of each research work, including the state space, action space, policy module, and RL algorithm. In addition, we identify research opportunities and challenges in various applications within this dynamic field. © 2023 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Decentralized Data-driven Optimal Control for the Microgrid 14

Decentralized Data-driven Optimal Control for the Microgrid

引用

14th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2023

作者： Weerasinghe, Kasun Srikantha, Pirathayini York University Department of Electrical Engineering and Computer Science TorontoON Canada

ISBN: (纸本)9781665455541

Recent advances in climate change policies and sustainable energy systems are spurring the widespread deployment of microgrids. The main operational challenge of these systems is the lack of inertia (in islanded mode) that is typically present in the main grid. To preserve the stable operation of the system, efficient control algorithms are necessary. In this paper, we present a novel optimal control algorithm that leverages constructs from machine learning to decouple interactions between various actuating power components in the microgrid. This allows every actuating entity to make control decisions based only on local measurements. As no communication is necessary with our proposed control algorithm, vulnerabilities and delays that are typically associated with communication-based control algorithms are eliminated. Also, in contrast to traditional decentralized techniques (e.g. droop-based) that are myopic in nature, our algorithm allows for the tracking of the original setpoint without any offsets as the global interactions are accounted for by the machine learning component of the proposed algorithm. We demonstrate the performance, stability and scalability of our proposal via practical simulations conducted on a 15-bus microgrid system. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

HyperBrain: Anomaly Detection for Temporal Hypergraph Brain Networks 7th

HyperBrain: Anomaly Detection for Temporal Hypergraph Brain...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Sadeghian, Sadaf Li, Xiaoxiao Seltzer, Margo Department of Computer Science University of British Columbia Vancouver Canada Department of Electrical and Computer Engineering University of British Columbia Vancouver Canada Vector Institute Toronto Canada

ISBN: (纸本)9783031787607

Identifying unusual brain activity is a crucial task in neuroscience research, as it aids in the early detection of brain disorders. It is common to represent brain networks as graphs, and researchers have developed various graph-based machine learning methods for analyzing them. However, the majority of existing graph learning tools for the brain face a combination of the following three key limitations. First, they focus only on pairwise correlations between regions of the brain, limiting their ability to capture synchronized activity among larger groups of regions. Second, they model the brain network as a static network, overlooking the temporal changes in the brain. Third, most are designed only for classifying brain networks as healthy or disordered, lacking the ability to identify abnormal brain activity patterns linked to biomarkers associated with disorders. To address these issues, we present HyperBrain, an unsupervised anomaly detection framework for temporal hypergraph brain networks. HyperBrain models fMRI time series data as temporal hypergraphs capturing dynamic higher-order interactions. It then uses a novel customized temporal walk (BrainWalk) and neural encodings to detect abnormal co-activations among brain regions. We evaluate the performance of HyperBrain in both synthetic and real-world settings for Autism Spectrum Disorder and Attention Deficit Hyperactivity Disorder (ADHD). HyperBrain outperforms all other baselines on detecting abnormal co-activations in brain networks. Furthermore, results obtained from HyperBrain are consistent with clinical research on these brain disorders. Our findings suggest that learning temporal and higher-order connections in the brain provides a promising approach to uncover intricate connectivity patterns in brain networks, offering improved diagnosis. Our code is available at: https://***/ubc-systopia/HyperBrain. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Recovery Strategy of Wind Turbine for Frequency Regulation Considering Wind Condition 3

Recovery Strategy of Wind Turbine for Frequency Regulation C...

引用

3rd International Conference on Energy, Power and electrical Technology, ICEPET 2024

作者： Xin, Zhipeng Zhang, Feng Sun, Kexu Cornélusse, Bertrand Shandong University School of Electrical Engineering Jinan China University of Liege Department of Electrical Engineering and Computer Science Liège Belgium

ISBN: (纸本)9798350352658

The traditional recovery strategy of wind turbines after frequency regulation generally sets the wind speed unchanged during the frequency recovery period, during which while the wind speed has random volatility and has an impact on the overall wind power. For this reason, a staged frequency recovery strategy for wind turbines adapted to the random change of wind speed is proposed. Specifically, a high level of power support is provided by the wind power at the early stage to inhibit the rapid fall of frequency, and the wind speed is regarded as constant due to the relatively short control time. At the middle stage, wind power carries out continuous frequency support, continuously feeding back random wind speed information and iteratively updating control parameters, and then cooperates with synchronous machine frequency response for smooth action. The last stage is the wind turbine speed recovery phase, divided into several time intervals, and the speed recovery parameters are adjusted to adapt to the random wind speed changes, and weaken the frequency secondary drop caused by the wind power withdrawal. Finally, the effectiveness of the proposed strategy is verified in simulation part. © 2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

A Highly-Scalable Area-Efficient ADC-Direct Neural Recording Front-End with Proportional-Integral Single-Bit Feedback

A Highly-Scalable Area-Efficient ADC-Direct Neural Recording...

引用

2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023

作者： Sayedi, Mina Kassiri, Hossein York University Department of Electrical Engineering and Computer Science Toronto Canada

ISBN: (纸本)9798350300260

This paper presents the design and implementation of a DC-coupled continuous-time-input ADC-direct neural recording front-end architecture. The architecture incorporates a single-bit variable-step DAC to create a proportional-integral feedback path. This makes the design needless of conventionally-used area-inefficient nonlinear high-resolution multi-bit DACs for realizing 2nd-order noise shaping, significantly improving its area efficiency, linearity, and scalability. Additionally, thanks to employing a differential-difference gm stage, the feedback is subtracted from the inputs without the need for connection to the same node, allowing for the realization of a high-ZIN DC-coupled chopping-friendly input structure. The front-end achieves a maximum SNDR of 58dB and tolerates input differential DC offsets/artifacts up to ±350mV. The design is realized using a 130nm standard CMOS technology, occupies 0.021mm2, and consumes 5.6μW. It is verified through system and circuit-level simulations, and boasts a >800MΩ differential input impedance over frequency band up to 500Hz, and an IRN-PSD of 161nV Hz, all while maintaining a minimum use of passives in its structure. © 2023 IEEE.

关键词： ADC-Direct area efficient artifact tolerant brain-implantable devices DC offset tolerant DC-coupled input low-power Neural Recording Proportional-Integral Feedback scalable Variable Step DAC

来源：评论

学校读者我要写书评

暂无评论

Efficient Cluster Selection for Personalized Federated Learning: A Multi-Armed Bandit Approach

Efficient Cluster Selection for Personalized Federated Learn...

引用

2023 IEEE Virtual Conference on Communications, VCC 2023

作者： Ni, Zhou Hashemi, Morteza University of Kansas Department of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350318807

Federated learning (FL) offers a decentralized training approach for machine learning models, prioritizing data privacy. However, the inherent heterogeneity in FL networks, arising from variations in data distribution, size, and device capabilities, poses challenges in user federation. Recognizing this, Personalized Federated Learning (PFL) emphasizes tailoring learning processes to individual data profiles. In this paper, we address the complexity of clustering users in PFL, especially in dynamic networks, by introducing a dynamic Upper Confidence Bound (dUCB) algorithm inspired by the multi-armed bandit (MAB) approach. The dUCB algorithm ensures that new users can effectively find the best cluster for their data distribution by balancing exploration and exploitation. The performance of our algorithm is evaluated in various cases, showing its effectiveness in handling dynamic federated learning scenarios. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A fire management intelligent system for the Brazilian cerrado biome based on a deep learning two phase detection method

引用

Journal of Reliable Intelligent Environments 2025年第1期11卷 1-18页

作者： Borges, Natalia Fonseca, Lívia Barreto, Priscila Solis Alchieri, Eduardo Caetano, Marcos Fagundes Resende, Paulo Brandão, Leonardo Vieira, Lucas Department of Electrical Engineering University of Brasilia DF Brasília Brazil Department of Computer Science University of Brasilia DF Brasília Brazil GigaCandanga Association DF Brasília Brazil

The implementation of smoke and fire detection systems based on image processing and machine learning still present research challenges for certain biomes, such as the cerrado where video-based fire smoke detection using cameras could be more efficient than sensor-based systems. This work presents the SEMFOGO-DF fire monitoring system, a solution composed of a distributed processing architecture and a deep-learning computer vision algorithm for smoke detection and emergency alert generation. The solution performs smoke detection on image sequences using a two-phase algorithm. The first phase analyzes image sequences and classifies regions of the image with a high probability of fire and in the second phase, a smoke classification is conducted on a zoomed image. Experimental results show that the two-phase algorithm can consistently reduce the number of false alerts generated by the first phase alone, with a relatively low reduction in the detection rate. The development of the solution also allowed the creation of two novel datasets. The first dataset consists of image sequences of the cerrado biome, annotated with smoke contours. The second dataset includes zoomed images of the cerrado landscape, annotated with labels indicating smoke and non-smoke occurrences. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Intelligent systems

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：