检索结果-内蒙古大学图书馆

Global Spatial-Temporal Information-based Residual ConvLSTM for Video Space-Time Super-Resolution

IEEE Transactions on Multimedia 2025年

作者： Fu, Congrui Yuan, Hui Jiang, Shiqi Zhang, Guanghui Shen, Liquan Hamzaoui, Raouf Center of Experimental Teaching China Shandong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Machine Intelligence and System Control China Shandong University School of software Shandong Jinan China Shandong University School of Computer Science and Technology China Shanghai University School of Communication and Information Engineering Shanghai China De Montfort University School of Engineering and Sustainable Development LeicesterLE1 9BH United Kingdom

By converting low-frame-rate, low-resolution videos into high-frame-rate, high-resolution ones, space-time video super-resolution techniques can enhance visual experiences and facilitate more efficient information dissemination. We propose a convolutional neural network (CNN) for space-time video super-resolution, namely GIRNet. Our method combines long-term global information and short-term local information from the video to better extract complete and accurate spatial-temporal information. To generate highly accurate features and thus improve performance, the proposed network integrates a feature-level temporal interpolation module with deformable convolutions and a global spatial-temporal information-based residual convolutional long short-term memory (convLSTM) module. In the feature-level temporal interpolation module, we leverage deformable convolution, which adapts to deformations and scale variations of objects across different scene locations. This provides a more efficient solution than conventional convolution for extracting features from moving objects. Our network effectively uses forward and backward feature information to determine inter-frame offsets, leading to the direct generation of interpolated frame features. In the global spatial-temporal information-based residual convLSTM module, the first convLSTM is used to derive global spatial-temporal information from the input features, and the second convLSTM uses the previously computed global spatial-temporal information feature as its initial cell state. This second convLSTM adopts residual connections to preserve spatial information, thereby enhancing the output features. Experiments on the Vimeo90K dataset show that the proposed method outperforms open source state-of-the-art techniques in peak signal-to-noise-ratio (by 1.45 dB, 1.14 dB, and 0.2 dB over STARnet, TMNet, and 3DAttGAN, respectively), structural similarity index(by 0.027, 0.023, and 0.006 over STARnet, TMNet, and 3DAttGAN, respectiv

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Extensive Cancellation Algorithm and Harmonic Enhanced Heart Rate Estimation based on MMWave Radar

arXiv

引用

arXiv 2025年

作者： Tang, Hui Yang, Zhan Rong, Yu Chai, Li Engineering Research Center of Metallurgical Automation and Measurement Technology Wuhan University of Science and Technology Wuhan430081 China The School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85281 United States College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Heart rate (HR) monitoring is crucial for assessing physical fitness, cardiovascular health, and stress management. Millimeter-wave radar offers a promising non-contact solution for long-term monitoring. However, accurate HR estimation remains challenging in low signal-to-noise ratio (SNR) conditions. To deal with both respiration harmonics and intermodulation interference, this paper proposes a cancellation-before-estimation strategy. Firstly, we present the adaptive extensive cancellation algorithm (ECA) to suppress respiratory and its low-order harmonics. Then, we propose an adaptive harmonic enhanced trace (AHET) method to avoid intermodulation interference by refining the HR search region. Various experimental results validate the effectiveness of the proposed methods, demonstrating improvements in accuracy, robustness, and computational efficiency compared to conventional approaches based on the FMCW (Frequency Modulated Continuous Wave) system. © 2025, CC BY-NC-ND.

关键词： Intermodulation

来源：评论

学校读者我要写书评

暂无评论

Node-Decomposition Privacy-Preserving for Finite-Time Secondary control of DC Microgrids

引用

IEEE Transactions on Smart Grid 2025年

作者： Wu, Han Zhu, Si-Min Chai, Li Zhu, Zhen-Hua Tian, Yu-Chu Wuhan University of Science and Technology Engineering Research Center of Metallurgical Automation and Measurement Technology School of Artificial Intelligence and Automation Wuhan430081 China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou China Queensland University of Technology School of Computer Science BrisbaneQLD4001 Australia

In the distributed secondary control of DC microgrids, achieving both rapid convergence and robust information security is critical for enhancing control performance and maintaining power quality. However, current privacy-preserving approaches often compromise either control performance or privacy preservation performance. To address this challenge, this paper presents a node-decomposition privacy-preserving (NDPP) method for fully distributed, finite-time secondary control in DC microgrids. By splitting each node in the communication graph into multiple sub-nodes, the method enhances both convergence speed and privacy preservation without sacrificing control accuracy. Sub-nodes communicate within groups, and the topology of the generated graph is concealed from malicious nodes and eavesdroppers. Theoretical analysis is provided to prove finite-time voltage regulation and current sharing with privacy preservation against malicious nodes and external eavesdroppers. Simulations are conducted to verify the effectiveness of the method in maintaining control performance and power quality. © 2010-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

Training-free Ultra Small Model for Universal Sparse Reconstruction in Compressed Sensing

arXiv

引用

arXiv 2025年

作者： Tang, Chaoqing Zhuang, Huanze Tian, Guiyun Zeng, Zhenli Ding, Yi Liu, Wenzhong Bai, Xiang Lin, Lin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China China Belt and Road Joint Lab on Measurement and Control Technology Wuhan China School of Electric and Electrical Engineering Chongqing University of Technology Chongqing China Optics Valley Laboratory Wuhan China School of Water Conservancy and Transportation Zhengzhou University Zhengzhou China School of Software Engineering Huazhong University of Science and Technology Wuhan China

Pre-trained large models attract widespread attention in recent years, but they face challenges in applications that require high interpretability or have limited resources, such as physical sensing, medical imaging, and bioinformatics. Compressed Sensing (CS) is a well-proved theory that drives many recent breakthroughs in these applications. However, as a typical under-determined linear system, CS suffers from excessively long sparse reconstruction times when using traditional iterative methods, particularly with large-scale data. Current AI methods like deep unfolding fail to substitute them because pre-trained models exhibit poor generality beyond their training conditions and dataset distributions, or lack interpretability. Instead of following the big model fervor, this paper proposes ultra-small artificial neural models called coefficients learning (CL), enabling training-free and rapid sparse reconstruction while perfectly inheriting the generality and interpretability of traditional iterative methods, bringing new feature of incorporating prior knowledges. In CL, a signal of length n only needs a minimal of n trainable parameters. A case study model called CLOMP is implemented for evaluation. Experiments are conducted on both synthetic and real one-dimensional and two-dimensional signals, demonstrating significant improvements in efficiency and accuracy. Compared to representative iterative methods, CLOMP improves efficiency by 100 to 1000 folds for large-scale data. Test results on eight diverse image datasets indicate that CLOMP improves structural similarity index by 292%, 98%, 45% for sampling rates of 0.1, 0.3, 0.5, respectively. We believe this method can truly usher CS reconstruction into the AI era, benefiting countless under-determined linear systems that rely on sparse solution. The code and core data of this paper are available at https://***/BillTtzqgbt/***. Copyright © 2025, The Authors. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Evolving Multi-Access Edge Computing (MEC) for Diverse Ubiquitous Resources Utilization: A Survey

引用

Telecommunication Systems 2025年第2期88卷 1-41页

作者： Khattak, Muhammad Ilyas Yuan, Hui Khan, Ajmal Ahmad, Ayaz Ullah, Inam Ahmed, Manzoor School of Control Science and Engineering Shandong University Shandong Province Jinan China Communication and Information Research Center Sultan Qaboos University Muscat Oman Department of Electrical Engineering College of Engineering King Faisal University Al-Ahsa Saudi Arabia Jinan China School of Computer and Information Science and AI Industrial Technology Research Hubei Engineering University Xiaogan China

The surge in smart device usage and the demand for high-throughput, low-latency mobile networks have accelerated the adoption of distributed smart applications and Collaborative Resource Management (CRM) techniques such as Multi-Access Edge Computing (MEC). With its ability to handle large data volumes, computational demands, scalability, and high energy consumption, MEC represents the next generation of Mobile Cloud Computing (MCC), addressing key challenges in emerging smart applications. MEC supports real-time, high-throughput, and energy-efficient techniques like task offloading and ultra-reliable low-latency communication (URLLC). However, as these techniques become more widespread, their diversity increases, leading to complexities that make them harder to understand and validate in different applications. This includes their use in areas like assistance for unmanned vehicles (UVs), autonomous driving, unmanned aerial vehicles (UAVs), high altitude platforms (HAPs), underwater unmanned vehicles (UUVs), satellite air-ground communication (SAGC), and other emerging systems that rely on Collaborative Resource Management (CRM). Although a number of review articles pertaining to MEC systems exist, we analyzed techniques beyond task offloading that explore MEC system applicability in diverse domains, including UUVs, vehicular edge computing, Re-configurable Intelligent Surfaces (RIS), Massive MIMO, autonomous driving, HAPs, and SAGC. From the perspective of these optimization techniques, this article highlights their role in shaping MEC’s evolution, focusing on parameters such as real-time response, energy efficiency, and other critical factors in task offloading processes. We also explored the role of Standard Development Organizations (SDOs), such as ETSI and IEEE, in advancing MEC systems. This included an analysis of offloading techniques based on their principles, features, and trade-offs, using key performance indicators (KPIs) for fair comparison, while ident

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Secure Beamforming Design for IRS-ISAC Systems with a Hardware-Efficient Hybrid Beamforming Architecture

引用

IEEE Transactions on Vehicular technology 2025年

作者： Xiong, Weijie Zhao, Zhenglan Lin, Jingran Xiao, Zhiling Li, Qiang University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing100083 China Tianfu Jiangxi Laboratory Sichuan Chengdu641419 China

In this paper, we employ a hardware-efficient hybrid beamforming (HB) architecture to achieve balanced performance in an intelligent reflecting surface (IRS)-assisted integrated sensing and communication (ISAC) system. We consider a scenario where a multi-antenna, dual-function base station (BS) performs secure beamforming for a multi-antenna legitimate receiver while simultaneously detecting potential targets. Our objective is to maximize the communication secrecy gap by jointly optimizing the analog and digital beamformers, IRS reflection coefficients, and radar scaling factor, subject to constraints on beampattern similarity, total transmit power budget, and the constant modulus of both the analog beamformer and IRS reflection coefficients. This secrecy gap maximization problem is generally non-convex. To address this, we incorporate the exterior penalty method by adding the radar constraint as a penalty term in the objective function. We then propose an efficient approach based on the penalty dual decomposition (PDD) framework to solve the reformulated problem, featuring closed-form solutions at each step and guaranteeing convergence to a stationary point. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the superiority of the IRS-ISAC system with HB architecture in balancing performance and hardware costs. © 1967-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Sensing With Random communication Signals

arXiv

引用

arXiv 2025年

作者： Lu, Shihang Liu, Fan Xiong, Yifeng Du, Zhen Cui, Yuanhao Li, Shuangyang Yuan, Weijie Yang, Jie Jin, Shi National Mobile Communications Research Laboratory Southeast University Nanjing210096 China School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China Faculty of Electrical Engineering and Computer Science Technical University of Berlin Berlin10587 Germany Southern University of Science and Technology Shenzhen518055 China Frontiers Science Center for Mobile Information Communication and Security and also The Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing211189 China

communication-centric Integrated Sensing and communication (ISAC) has been recognized as a promising methodology to implement wireless sensing functionality over existing network architectures, due to its cost-effectiveness and backward compatibility to legacy cellular systems. However, the inherent randomness of the communication signal may incur huge fluctuations in sensing capabilities, leading to unfavorable detection and estimation performance. To address this issue, we elaborate on random ISAC signal processing methods in this article, aiming at improving the sensing performance without unduly deteriorating the communication functionality. Specifically, we commence by discussing the fundamentals of sensing with random communication signals, including the performance metrics and optimal ranging waveforms. Building on these concepts, we then present a general framework for random ISAC signal transmission, followed by an in-depth exploration of time-domain pulse shaping, frequency-domain constellation shaping, and spatial-domain precoding methods. We provide a comprehensive overview of each of these topics, including models, results, and design guidelines. Finally, we conclude this article by identifying several promising research directions for random ISAC signal transmission. © 2025, CC BY-SA.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Automatic location of surface-monitored microseismicity with deep learning

引用

Earthquake Research Advances 2025年第2期5卷

作者： Gan, Zhaolong Tian, Xiao Zhang, Xiong Dai, Mengxue Engineering Research Center for Seismic Disaster Prevention and Engineering Geological Disaster Detection of Jiangxi Province (East China University of Technology) Nanchang 330013 China School of Geophysics and Measurement-Control Technology East China University of Technology Nanchang 330013 China

Accurate and rapid determination of source locations is of great significance for surface microseismic monitoring. Traditional methods, such as diffraction stacking, are time-consuming and challenging for real-time monitoring. In this study, we propose an approach to locate microseismic events using a deep learning algorithm with surface data. A fully convolutional network is designed to predict source locations. The input data is the waveform of a microseismic event, and the output consists of three 1D Gaussian distributions representing the probability distribution of the source location in the x, y, and z dimensions. The theoretical dataset is generated to train the model, and several data augmentation methods are applied to reduce discrepancies between the theoretical and field data. After applying the trained model to field data, the results demonstrate that our method is fast and achieves comparable location accuracy to the traditional diffraction stacking location method, making it promising for real-time microseismic monitoring. © 2024 China Earthquake Networks Center.

关键词： Deep learning Microseismic monitoring Source location

来源：评论

学校读者我要写书评

暂无评论

A Cross-Task Transfer SAR Target Recognition Method Based on AMFFNet and IACGAN

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年

作者： Wan, Xunyang Du, Xiaolin Cui, Guolong Chen, Xiaolong Zheng, Jibin Yantai University School of Computer and Control Engineering Yantai264005 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Naval Aviation University Yantai264001 China Xidian University National Key Laboratory of Radar Signal Processing Xi'an710071 China

Convolutional neural networks (CNN) have shown excellent capability in synthetic aperture radar (SAR) target recognition. However, obtaining sufficient training samples for improving network recognition is difficult due to the deficiency of labeled SAR image data. To tackle the problem, a cross-task transfer method for SAR target recognition is proposed in this paper, which is based on a designed attention multi-scale feature fusion network (AMFFNet) and an improved auxiliary classifier generative adversarial network (IACGAN). In this method, firstly, a data augmentation method based on you only cut twice (YOCT) is devised for expanding the training samples. Secondly, the partial weight parameters of AMFFNet are initialized by the pre-trained IACGAN discriminator. Finally, AMFFNet is fine-tuned using the training samples. Additionally, on the network structure of AMFFNet, multi-scale features are extracted by adopting a multi-scale depth separable convolution module, which allows the model to acquire more informative features. Attention mechanisms are employed in this network to enhance its ability to capture important features while reducing the effects of noise. A multi-level feature fusion structure is used to further raise the representational capability of the model. Experimental results on multiple open-source real SAR datasets show that the proposed method can achieve better recognition performance under different percentages of training data, and the effectiveness and superiority of the method are confirmed by its robustness to noise. © 1965-2011 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Breather dynamics in an optomechanical array with staggered coupling

引用

Physical Review A 2025年第3期111卷 033502-033502页

作者： Yuan Zhao Yiheng Hou Yu Wang Zhuo Fan Wei Peng Qin Zhou Siliu Xu Shihua Chen Key Laboratory of Optoelectronic Sensing and Intelligent Control Hubei University of Science and Technology Xianning 437100 China School of Biomedical Engineering and Imaging Xianning Medical College Hubei University of Science and Technology Xianning 437100 China School of Electronic and Information Engineering Hubei University of Science and Technology Xianning 437100 China Research Center of Nonlinear Science School of Mathematics and Physical Sciences Wuhan Textile University Wuhan 430200 China School of Physics and Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing 211189 China

We present an approach toward generating highly controllable breathers, using an array of staggered optomechanical cavities that feature alternating coupling strengths. Four different types of breather states as well as stable two-soliton states are demonstrated to form in such an optomechanical array, thanks to the interplay between the photon-hopping induced tunneling effect and the photon-phonon coupling in the optomechanical cell. It is seen that both their photonic and phononic wave components manifest quasi-periodic oscillatory patterns and coherent localization. We unveil that such breather dynamics can be well controlled by adjusting the coupling strength, the cavity field decay, and the number of array cells. As a result, we observe an unusual odd-even lattice effect in that stable breathers are only available when the cell number is even. We anticipate that these findings from the staggered optomechanical configuration may expand the realm of cavity optomechanics, yielding promising applications such as on-chip manipulation of light propagation.

关键词： Solitons

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：