检索结果-内蒙古大学图书馆

United We Fall: On the Nash Equilibria of Multiplex and Multilayer Network Games

IEEE Transactions on Control of Network Systems 2025年第2期12卷 1238-1250页

作者： Ebrahimi, Raman Naghizadeh, Parinaz University of California Electrical and Computer Engineering Department San Diego United States

Network games provide a framework to study strategic decision making processes that are governed by structured interdependencies among agents. However, existing models do not account for environments in which agents simultaneously interact over multiple networks, or when agents operate over multiple action dimensions. In this paper, we propose new models of multiplex network games to capture the different modalities of interactions among strategic agents, and multilayer network games to capture their interactions over multiple action dimensions. We explore how the properties of the constituent networks of a multiplex/multilayer network can undermine or support the existence, uniqueness, and stability of the game's Nash equilibria. Notably, we highlight that both the largest and smallest eigenvalues of the constituent networks (reflecting their connectivity and two-sidedness, respectively) are instrumental in determining the uniqueness of the multiplex/multilayer network game's equilibrium. Together, our findings shed light on the reasons for the fragility of equilibria when agents interact over networks of networks, and point out potential interventions to alleviate them. © 2014 IEEE.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Compensation of Actuation and Communication Delays for Heterogeneous Platoons via Predictor-Feedback CACC with Integral Action

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 1-13页

作者： Samii, Amirhossein Bekiaris-Liberis, Nikolaos Department of Electrical & Computer Engineering Technical University of Crete Chania Greece

We construct a predictor-feedback cooperative adaptive cruise control (CACC) design with integral action, which achieves simultaneous compensation of long, actuation and communication delays, for platoons of heterogeneous vehicles whose dynamics are described by a third-order linear system with input delay. The key ingredients in our design are an underlying predictor-feedback law that achieves actuation delay compensation and an integral term of the difference between the delayed (by an amount equal to the respective communication delay) and current speed of the preceding vehicle. The latter, essentially, creates a virtual spacing variable, which can be regulated utilizing only delayed position and speed measurements from the preceding vehicle. We establish individual vehicle stability, string stability, and regulation for vehicular platoons, under the control design developed. The proofs rely on combining an input-output approach (in the frequency domain), with derivation of explicit solutions for the closed-loop systems, and they are enabled by the actuation and communication delays-compensating property of the design. We demonstrate numerically the control and model parameters' conditions of string stability, while we also present simulation results, in realistic scenarios, including a scenario in which the leading vehicle's trajectory is obtained from NGSIM data. All case studies confirm the effectiveness of the design developed. IEEE

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Apple Leaf Disease Detection Using Transfer Learning

引用

Annals of Data science 2025年第1期12卷 213-222页

作者： Wani, Ozair Ahmad Zahoor, Umer Shah, Syed Zubair Ahmad Khan, Rijwan Department of Computer Science & Engineering Islamic University of Science and Technology Jammu & Kashmir Awantipora India Department of Computer Science and Engineering ABES Institute of Technology Uttar Pradesh Ghaziabad India

Automated detection of plant diseases is crucial as it simplifies the task of monitoring large farms and identifies diseases at their early stages to mitigate further plant degradation. Besides the decline in plant health, reduced production severely impacts the country’s economy. Traditional disease identification methods, relying on human experts, are slow, time-consuming, and impractical for large farms. Our proposed model utilizes a combination of pre-trained Resnet18, Alexnet, GoogLeNet, and VGG16 networks to classify apple tree leaves into categories such as healthy, black rot, apple cedar rust, and apple scab based on images. Various image enhancement techniques were employed to enhance the model’s accuracy. Ultimately, our model achieved an accuracy of 97.25% on the validation dataset, demonstrating excellent performance across various metrics. This suggests its potential for efficient and accurate plant health monitoring in the agricultural sector. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High Accurate PMSM Computation Model Based on Strongly Coupled Magnetic Field and Multi-Turn Electric Winding Circuits Using the Time-Stepping Finite Element

引用

Progress in Electromagnetics Research C 2025年 153卷 13-23页

作者： Merzouki, Tarik Rachek, M’Hemed Department of Electrotechnics Faculty of Electrical and Computer Engineering Mouloud Mammeri University Algeria

The work presented in this paper has great significance in improving electromagnetic models based on the strong coupling between the magnetic and electric fields transient equations while considering a realistic random multi-turn stranded winding where eddy currents, proximity and skin effects occur. The space-time partial differential equations of electromagnetic field expressed in terms of magnetic vector potential under nonlinear (B-H) magnetic materials curves handled by the iterative Newton-Raphson (NR) algorithm are simultaneously coupled with the voltage fed multi-turns electric circuits equations based on Kirchhoff’s voltage law for each turn coil current loop. The magnetic field-multi-turn electric circuit coupled model solved using the time-stepping finite element method (FEM) formulation is dedicated to highly accurate computation of electromagnetic-mechanical devices. The developed FEM tools implemented under Matlab software are used to the modeling of the permanent magnet synchronous motor (PMSM) behavior through the physical quantities such as magnetic flux density, electric current, electromagnetic torque, and angular velocity. © 2025, Electromagnetics Academy. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Investigating the influence of material composition and design parameters on optical loss in hollow core fibers at 9.5 µm

引用

Optical and Quantum Electronics 2025年第3期57卷 1-19页

作者： Hummam, Zahraa Vahed, Hamid Pourziad, Ali Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran

This study examines a novel design for hollow core metal fibers HCMF by systematically altering geometric factors. Various materials, such as gold, silver, aluminum, graphene, and silicon nitride Si3N4, were examined as substitutes for conventional metallic components to assess their influence on fiber performance at a wavelength of 9.5 µm. The optical losses of each material were studied using Lumerical Ansys 2023 and the finite-difference time-domain approach. Results demonstrated that Si₃N₄ had outstanding optical characteristics, with negligible optical loss approaching zero at the specified wavelength, rendering it suitable for low-attenuation applications;regarding the selection of Si₃N₄ as the material for the metal wires in the hollow-core fiber, subsequent modifications to the geometry, such as wire widths and the spacing between the wires and the core, enhanced fiber performance, achieving an optical confinement loss as minimal as 10−18 dB/m. This illustrates Si₃N₄ capability as an exceptional material for highly efficient hollow-core fiber configurations. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Silicon nitride

来源：评论

学校读者我要写书评

暂无评论

FACNet: Feature alignment fast point cloud completion network

引用

Computational Visual Media 2025年第1期11卷 141-157页

作者： Xinxing Yu Jianyi Li Chi-Chong Wong Chi-Man Vong Yanyan Liang School of Computer Science and Engineering Faculty of Innovation EngineeringMacao University of Science and TechnologyTaipaMacaoChina Faculty of Science and Technology University of MacaoTaipaMacaoChina

Point cloud completion aims to infer complete point clouds based on partial 3D point cloud *** previous methods apply coarseto-fine strategy networks for generating complete point ***,such methods are not only relatively time-consuming but also cannot provide representative complete shape features based on partial *** this paper,a novel feature alignment fast point cloud completion network(FACNet)is proposed to directly and efficiently generate the detailed shapes of *** aligns high-dimensional feature distributions of both partial and complete point clouds to maintain global information about the complete *** its decoding process,the local features from the partial point cloud are incorporated along with the maintained global information to ensure complete and time-saving generation of the complete point *** results show that FACNet outperforms the state-of-theart on PCN,Completion3D,and MVP datasets,and achieves competitive performance on ShapeNet-55 and KITTI ***,FACNet and a simplified version,FACNet-slight,achieve a significant speedup of 3–10 times over other state-of-the-art methods.

关键词： 3D point clouds shape completion geometry processing deep learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Scheduling for Oil Spill SAR Image Detection in Space-Air-Ground Integrated Networks

引用

IEEE Transactions on Vehicular Technology 2025年第6期74卷 9689-9703页

作者： Son, Seok Bin Park, Soohyun Korea University Department of Electrical and Computer Engineering Seoul02841 Korea Republic of Sookmyung Women's University Division of Computer Science Seoul04310 Korea Republic of

Oil spills represent significant environmental hazards in ocean ecosystems, requiring rapid and accurate detection and response mechanisms. Due to its efficacy, synthetic aperture radar (SAR) is an important tool for remote monitoring of ocean environments. However, operational constraints such as communication time between low Earth orbit (LEO) satellites and ground stations (GS), as well as finite buffers, pose challenges. To address these issues, this paper proposes a space-air-ground-integrated network (SAGIN) scenario comprising LEO satellites, high altitude platforms (HAPs), and ground stations (GSs), suitable for rapid and accurate oil spill detection using SAR images. In addition, a novel three-step algorithm is proposed to facilitate SAR image transmission effectively. The first step of the proposed algorithm focuses on maximizing the transmission of ocean SAR images from the LEO satellites to the HAPs. This optimization involves the neural Myerson auction (NMA)-based scheduler, a second-price auction mechanism with deep learning methodologies for truthfulness, distributed computation, and low computational complexity. In addition, the pathloss is also considered for effective communication system design. The second step algorithm aims to maximize data transmission efficiency from HAPs to GSs, employing scheduling strategies based on the Markov decision process (MDP). This algorithm enables optimal decision-making over time steps, considering the throughput of each GS and the age of the information (AoI) ratio. Finally, an image compression rate control algorithm based on Lyapunov optimization is employed at the GSs to enhance detection accuracy while ensuring queue stability. The performance of the proposed three-step algorithm is intensively evaluated against various benchmark algorithms, demonstrating its superiority in oil spill detection efficacy. © 1967-2012 IEEE.

关键词： Oil spills

来源：评论

学校读者我要写书评

暂无评论

Question classification task based on deep learning models with self-attention mechanism

引用

Multimedia Tools and Applications 2025年第10期84卷 7777-7806页

作者： Mondal, Subhash Barman, Manas Nag, Amitava Computer Science and Engineering Central Institute of Technology Kokrajhar Assam Kokrajhar India Computer Science and Engineering [AI & ML Dayananda Sagar University Karnataka Bengaluru India

Question classification (QC) is a process that involves classifying questions based on their type to enable systems to provide accurate responses by matching the question type with relevant information. To understand and respond to natural language questions posed by humans, machine learning models or systems must comprehend the type of information requested, which can often be inferred from the structure and wording of the question. The high dimensionality and sparse nature of text data lead to challenges for text classification. These tasks can be improved using deep learning (DL) approaches to process complex patterns and features within input data. By training on large amounts of labeled data, deep learning algorithms can automatically extract relevant features and representations from text, resulting in more accurate and robust classification. This study utilizes a dataset comprising 5452 instances of questions and six output labels and uses two different word embedding techniques, like GloVe and Word2Vec, tested on the dataset using three deep learning models, LSTM, BiLSTM, and GRU, followed by a convolution layer. Additionally, a self-attention layer is included, which helps the model to focus on more relevant information when making predictions. Finally, an analytical discussion of the proposed models and their performance results provide insight into how GloVe and Word2Vec perform on the above-mentioned models. The GloVe embedding outperforms by achieving 97.68% accuracy and a moderate loss of 16.98 with the GRU model. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Fast 3D Beam Training with True-Time-Delay Arrays in Wideband Millimeter-Wave Systems

引用

IEEE Transactions on Wireless Communications 2025年第6期24卷 5146-5162页

作者： Wadaskar, Aditya Boljanovic, Veljko Yan, Han Cabric, Danijela University of California Department of Electrical and Computer Engineering Los Angeles United States

True-time-delay (TTD) arrays can implement frequency-dependent rainbow beams and enable fast beam alignment in wideband millimeter-wave (mmWave) systems. In this paper, we consider 3D rainbow beam training with planar TTD arrays. We first design a planar TTD-array-based codebook that can realize a partial or complete scan of the entire 3D sphere using a single Orthogonal Frequency Division Multiplexing (OFDM) symbol. We demonstrate that a rainbow-beam codebook with a proper configuration of delays and phase shifts, and a sufficient number of subcarriers, can simultaneously probe all angular directions in the desired coverage sector with the required beamforming gain. Leveraging this full coverage codebook, we propose two frequency-domain power-based 3D beam training algorithms for fast estimation of the azimuth and elevation angles corresponding to the dominant propagation direction. The proposed algorithms take into account practical hardware-imposed delay range constraints. We numerically evaluate the performance of the proposed algorithms in mmWave channels as a function of the TTD codebook and system parameters. We show that the proposed 3D beam training offers considerable overhead reduction relative to the state-of-the-art methods with planar phased antenna arrays (PAA). © 2002-2012 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

CSI Robust Joint User Selection and Precoder Design in MIMO Downlink Systems

引用

IEEE Wireless Communications Letters 2025年第6期14卷 1796-1800页

作者： Vaezy, Hossein Blostein, Steven D. Queen’s University Department of Electrical and Computer Engineering KingstonON Canada

In multiuser multiple-input multiple-output (MU-MIMO) systems, the selection of a subset of users to achieve the maximum sum rate is critical when resources are limited. In addition, designing suitable precoder and decoder matrices at the base station (BS) and at the user side requires unattainable perfect channel state information. In this letter, the downlink of a cellular system with multiple antennas at user equipments (UEs) is considered. A framework is derived for joint user selection and precoder/decoder design in the presence of imperfect channel estimation with neither instantaneous nor statistical error matrices. A robust method is proposed that incorporates a bounded worst-case channel in the design of precoders, decoders, and user selection. The optimization problem is solved iteratively by decomposition into multiple convex sub-problems which are solved successively. Finally, it is illustrated that for the case of a set of predesigned precoders, the interference pattern remains fixed for each user, implying that the problem of user selection could be transformed to that of beam selection. © 2025 IEEE. All rights reserved.

关键词： Channel estimation

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：