检索结果-内蒙古大学图书馆

Multi-scale network for single image deblurring based on ensemble learning module

Multimedia Tools and Applications 2025年第11期84卷 9045-9064页

作者： Wu, WenBo Pan, Yun Su, Na Wang, JingTao Wu, ShaoChuan Xu, ZeKun Yu, YouJian Liu, YaPeng State Key Laboratory of Media Convergence and Communication Communication University of China Beijing100024 China School of Computer and Cyberspace Security Communication University of China Beijing100024 China School of Electronics and Information Engineering Harbin Institute of Technology Harbin150080 China College of Computer and Control Engineering Northeast Forestry University Harbin150040 China School of Computer and Information Engineering Tianjin Chengjian University Tianjin300384 China School of Computer Science and Technology Anhui University Hefei230601 China

In this paper, we have identified two primary issues with current multi-scale image deblurring methods. On the one hand, the blurring scale is ignored. On the other hand, the context information of images is not fully utilized, and the spatial detail information of images is lost. To better solve the above problems, on top of that, this paper proposes a multi-scale network for single image deblurring. The designed network contains two parts: 1) Ensemble Learning Model: The Weak Learning Model in this module connects multiple weak learners in series to increase network depth. Moreover, through multi-scale feature ensemble module, the output features and intermediate features of different weak learner are integrated, and finally strong learner is used to enhance the features with semantic information at different scales;2) Spatial Feature Enhancement Module: This module can preserve spatial detail information of images and compensate for the disadvantages of losing image spatial details due to continuous downsampling in the Ensemble Learning Model structure. Our proposed deblurring model has been extensively evaluated on several benchmark datasets, and the model achieves superior performance compared to the most advanced deblurring methods. In particular, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) values are 33.57 dB and 0.965 on the GoPro dataset, respectively, with PSNR and SSIM improving by 0.49 dB and 0.002 over NAFNet, and 0.65 dB and 0.004 over Restormer. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Path Fusion Transformer Network for Hyperspectral Remote Sensing Image Classification

Multi-Path Fusion Transformer Network for Hyperspectral Remo...

引用

2024 International Conference on measurement, communication, and Virtual Reality, MCVR 2024

作者： Li, Jiacheng Wang, Wei School of Measurement-Control Technology and Communication Engineering Harbin University of Science and Technology 52 Xuefu Road Heilongjiang Harbin150000 China

ISBN: (纸本)9781510691773

To address the challenges of insufficient spectral feature extraction and feature redundancy in hyperspectral image (HSI) classification, this paper proposes a Multi-Path Fusion Transformer Network (MPFT) that integrates Vision Transformer, hybrid residual convolution, and attention mechanisms. The proposed approach effectively utilizes both spatial and spectral information of pixels to overcome these limitations. The MPFT architecture comprises a Data Processing Module (DPM), a Dual-Stream Feature Extraction Module (DSFE), and a Vision Transformer (ViT) module. Specifically, the DPM performs dimensionality reduction and merges HSI information in three-dimensional space, while the DSFE extracts deeper features, which are subsequently processed by the ViT module for classification. Experiments conducted on three benchmark datasets—Indian Pines, University of Pavia, and Salinas—demonstrate that MPFT significantly outperforms mainstream models. Notably, MPFT achieved improvements in Overall Accuracy (OA) by up to 5.52%, Average Accuracy (AA) by up to 6.39%, and Kappa coefficient by up to 6.49% compared to state-of-the-art methods. These results highlight that MPFT not only efficiently extracts spatial-spectral features from HSI but also demonstrates superior effectiveness and robustness in various classification tasks. © 2025 SPIE.

关键词： Data streams

来源：评论

学校读者我要写书评

暂无评论

A strategy for accurate prediction of dielectric permittivity and dielectric strength in polyimide

引用

High Voltage 2024年第6期9卷 1393-1401页

作者： Yu Wang Changhai Zhang Jiaqi Lin Hongguo Sun Ying Yang Wenlong Yang School of Electrical and Electronic Engineering Harbin University of Science and TechnologyHarbinChina School of Science Harbin University of Science and TechnologyHarbinChina Polymer Composites Engineering Laboratory Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchunChina State Key Laboratory of Mechanics and Control of Mechanical Structures Nanjing University of Aeronautics and AstronauticsNanjingChina School of Measurement and Communication Engineering Harbin University of Science and TechnologyHarbinChina

A strategy was proposed to predict accurately the dielectric permittivity and dielectric strength based on the Onsager local field *** molecular dynamic simulation was utilised to analyse the dipole moment fluctuation in polyimide(PI)to reflect the polar-isation response of applied electric *** simulation results revealed that the optical dielectric permittivity and static dielectric permittivity were 2.62 and 3.34,showing that the electronic displacement polarisation of the PI acted as a major *** deviation between simulated and measured values of the frequency-dependent relative dielectric permittivity was no more than 5%,which exhibited high *** the polarisation response of the polar groups in the PI was at infrared frequencies,the conductive loss may be the dominant role in 102–106 Hz at room ***,the effect of Joule heat on the structure,dielectric permittivity and Young modulus was considered to accurately predict the dielectric strength of the PI(359 kV/mm),which was in agreement with experimental values in the *** results establish a clear correlation between structural characteristics and dielectric properties of the PI,which would be the theoretical insights into the design and synthesis of the PI with tailored dielectric properties.

关键词： dielectric strength permittivity

来源：评论

学校读者我要写书评

暂无评论

FPGA-Oriented Target Detection Accelerator Design 5

FPGA-Oriented Target Detection Accelerator Design

引用

5th International Conference on Frontiers technology of Information and Computer, ICFTIC 2023

作者： Huang, Weizhe Harbin University of Science and Technology School of Measurement and Control Technology and Communication Engineering Harbin China

ISBN: (纸本)9798350309034

Target detection is widely applied in fields such as face recognition, autonomous driving, and industrial automation. However, when deploying target detection models based on convolutional neural networks on resource-constrained embedded platforms, issues like high computational complexity, long execution times, and significant on-chip memory usage arise. To address these challenges, this paper presents a target detection accelerator design based on Field Programmable Gate Array (FPGA). Firstly, the computational workload of convolutional neural networks is reduced by merging convolutional layers with batch normalization layers. Secondly, to mitigate on-chip storage space concerns, on-chip data fixed-point quantization is employed to decrease on-chip memory consumption. Subsequently, to tackle the issue of long execution times, a convolution calculation module based on the Winograd algorithm is designed, which reduces computation latency. Finally, a dual-buffer pipeline architecture is devised to optimize memory bandwidth. Experimental results demonstrate that the proposed solution accelerates YOLOv4-tiny on the ZYNQ-7020, achieving a performance of 21.35 GOP/s. The energy efficiency is 32.56 times higher than CPU and 9.76 times higher than GPU. Additionally, the convolution calculation module in this paper reduces inference time by 15% compared to the sliding window convolution calculation method. © 2023 IEEE.

关键词： CNN FPGA target detection Winograd algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Charging and Path Planning for UAV-Powered Rechargeable WSNs Using Multi-Agent Deep Reinforcement Learning

引用

IEEE Transactions on Automation Science and engineering 2025年 22卷 15610-15626页

作者： Betalo, Mesfin Leranso Leng, Supeng Seid, Abegaz Mohammed Abishu, Hayla Nahom Erbad, Aiman Bai, Xiaoshan Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar Shenzhen University College of Mechatronics and Control Engineering National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Unmanned Aerial Vehicle (UAV)-powered 5G/6G networks integrated with rechargeable wireless sensor networks (RWSNs) offer promising solutions for extending system lifetime, collecting data, and providing computing services and power to sensor nodes (SNs). UAVs offer significant advantages, including exceptional mobility, cost-effective deployment, and the ability to be easily reprogrammed for a wide range of missions. However, the limited onboard power capacity of UAVs, coupled with the lack of dynamic and intelligent charging station (CS) management and inefficient path planning, can lead to SN failure in dynamic mobile environments. To address these challenges, we propose an energy-efficient laser-charged UAV (LCU)-enabled RWSN environment, wherein UAVs, powered by laser beams from ground-based stations, provide services, collect data, and transfer energy to SNs. We formulate a joint optimization problem involving power allocation, dynamic charging strategy (DCS), and path planning to minimize task completion time and sensor node death time. Given the NP-hard nature of the problem, we employ a stochastic game model based on a Markov decision process (MDP) for its solution. To solve this problem, we propose a deep reinforcement learning (DRL) based algorithm that enables real-time charging scheduling decisions while optimizing network performance. We introduce a multi-agent double deep Q-network (MA-DDQN) model to determine the optimal trajectories for all UAVs in large and complex environments. Simulation results demonstrate that the MA-DDQN approach outperforms state-of-the-art techniques, showing significant improvements in terms of average delay, energy consumption, and task completion time. © 2004-2012 IEEE.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Deterministic Event-Based Physical Watermarks Against Replay Attacks in Cyber-Physical Systems

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 61-69页

作者： Zhao, Xudong Xing, Wei Zhang, Junfeng Wang, Xinyu Zong, Guangdeng Zhao, Ning Hainan University School of Information and Communication Engineering Haikou570288 China Dalian University of Technology Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian116622 China Tiangong University School of Control Science and Engineering Tianjin300387 China Bohai University College of Control Science and Engineering Jinzhou121013 China

Cyber-physical systems (CPSs) are of great importance in various applications and have garnered significant attention. Ensuring their security is a crucial concern, while this paper focuses on the security of CPSs against replay attacks during the transmission of sensor measurements over a wireless network. It is widely recognized that incorporating physical watermark signals is an effective approach to mitigate replay attacks. However, traditional physical watermarks are time-based and result in a notable degradation in the performance of Linear Quadratic Gaussian systems. With this in mind, a novel event-based physical watermarking technique is devised to address the performance degradation and detect replay attacks. The approach involves a deterministic physical watermark schedule that utilizes the innovation sequence to determine whether to incorporate physical watermarks or not. We provide evidence that the probability of successfully embedding physical watermarks increases when the system is targeted by malicious attacks. Additionally, we demonstrate that the deterministic event-based watermarking approach is more effective than the traditional time-based watermarking method. Finally, simulation examples are included to validate and illustrate the theoretical results. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

SSO Suppression Strategy for Adaptive PV Power Generation System Based on Quasi-Resonant control

SSO Suppression Strategy for Adaptive PV Power Generation Sy...

引用

International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Sun, Dongyang Han, Chuang Liu, Jinfeng School of Electrical and Electronic Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China School of Measurement Control Technology and Communication Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China

ISBN: (纸本)9789819618514

Moving cloud shadows in the region where a large-scale PV power plant is located will cause the DC voltage output of some PV arrays to be perturbed, and the inter-harmonic component will be output to the grid, which will lead to sub-synchronous oscillations of PV power generation systems that are normally operated at the same grid. In this paper, firstly, the output characteristics of PV arrays under moving cloud shadows are investigated, and the generation mechanism of inter-harmonics in PV power generation system is analyzed through the small-signal perturbation model, which elucidates the reasons for the occurrence of sub-synchronous oscillations in PV power generation system triggered by the inter-harmonics;secondly, the influence of the change of the sub-synchronous oscillation frequency on the resonance suppression strategy is explored, and a sub-synchronous oscillation suppression strategy based on the proportional resonance control is designed for suppression of Finally, the effectiveness of the proposed suppression strategy is verified by simulation. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Adaptive SSO Suppressor Based on SVD-Prony Algorithm in PV Grid-Connected System

Adaptive SSO Suppressor Based on SVD-Prony Algorithm in PV G...

引用

International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Liang, Liyuan Sun, Dongyang Liu, Jinfeng School of Electrical and Electronic Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China School of Measurement Control Technology and Communication Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China

ISBN: (纸本)9789819618514

The risk of sub-synchronous oscillation of PV grid-connected system is increased by the decrease of power grid strength or the disturbance of DC voltage. It is theoretically necessary and engineering urgent to study the mechanism of sub-synchronous oscillation of PV grid-connected system and put forward corresponding suppression strategies. In this paper, a dq synchronous rotating coordinate system control model of PV grid-connected system with subsynchronous oscillation is established, and the influence of subsynchronous oscillation on PV grid-connected system is analyzed according to the model. An adaptive SSO suppressor based on SVD-Prony algorithm is designed to track and suppress sub-synchronous oscillations that vary in each frequency band. This algorithm can extract the effective mode information of the subsynchronous oscillation in PV grid-connected system, and then update it to the central resonant frequency of the suppressor, and generate the output which can compensate the subsynchronous oscillation component in the closed-loop control system. Finally, a simulation experiment platform is set up to verify the effectiveness of the suppression strategy proposed in this paper. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Sub-Synchronous Oscillation Suppression Strategy Research for Grid-Forming Direct-Drive Permanent Magnet Synchronous Generator Based on Adaptive Notch Filter

Sub-Synchronous Oscillation Suppression Strategy Research fo...

引用

International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Sun, Dongyang Jiao, Yingzi Liu, Jinfeng School of Electrical and Electronic Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China School of Measurement Control Technology and Communication Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China

ISBN: (纸本)9789819620791

When sub-synchronous oscillations (SSO) occur in power grid, they can affect control performance of grid-side converter (GSC) for direct-drive permanent magnet synchronous generators (D-PMSG), thereby impacting overall stability of system. To address this issue, this paper proposes a suppression strategy for SSO based on adaptive notch filter (ANF). Firstly, the mechanism by which grid SSO affects GSC control of D-PMSG based on virtual synchronous generator (VSG) is analyzed, and disturbance propagation path of SSO component is delineated. Secondly, to overcome problem that fixed-parameter notch filters are unsuitable for time varying characteristics of SSO frequencies, an improved fast Fourier transform-based algorithm for identifying SSO parameters is proposed. Based on identification results, a strategy for updating center frequency of ANF is designed. Optimal intervention point of ANF in control system is determined. Finally, by constructing a simulation model, the effectiveness of proposed control strategy for suppressing SSO is verified. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Research on Integrated Inertia control Strategy of Hydrogen Production System with Wind Power Permeability

Research on Integrated Inertia Control Strategy of Hydrogen ...

引用

International Conference of Electrical, Electronic and Networked Energy Systems, EENES 2024

作者： Sun, Dongyang Zhou, Yanbing Liu, Jinfeng School of Electrical and Electronic Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China School of Measurement Control Technology and Communication Engineering Harbin University of Science and Technology Heilongjiang Harbin150080 China

ISBN: (纸本)9789819620791

High proportion of new energy and high proportion of power electronic equipment in the power system, the problem of frequency safety is becoming increasingly prominent. It is the key of high permeability grid connection of wind power to realize virtual inertia support by rational use of energy reserve of wind storage hydrogen production system. In this paper, based on the improved system frequency response model considering wind power permeability, the dynamic response equation of system frequency is derived to analyze the influence of wind power permeability on the system frequency stability. Secondly, according to the definition of inertia time constant of synchronous unit, the virtual inertia time constant of electric hydrogen production and supercapacitor is established, the required inertia of the system is evaluated with the system frequency change rate as the safety constraint condition, and the inertia distribution strategy of the air storage hydrogen production system is proposed. Finally, a simulation model of hydrogen production system from wind storage is built to verify that the frequency stability of the system can be significantly improved under the proposed control strategy. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Frequency stability

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：