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

Enhancing surrogate-assisted evolutionary optimization for medium-scale expensive problems: a two-stage approach with unsupervised feature learning and Q-learning

引用

Neural Computing and Applications 2024年第25期36卷 15545-15565页

作者： Gong, Yiyun Yu, Haibo Kang, Li Sun, Chaoli Zeng, Jianchao School of Electrical and Control Engineering North University of China Taiyuan030051 China School of Computer Science and Technology North University of China Taiyuan030051 China School of Environment and Safety Engineering North University of China Taiyuan030051 China School of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan030024 China

This paper presents a novel two-stage progressive search approach with unsupervised feature learning and Q-learning (TSLL) to enhance surrogate-assisted evolutionary optimization for medium-scale expensive problems. The method attempts to address the challenges posed by multi-polar and multi-variable coupling properties in such problems. During the iteration, TSLL splits the optimization process into two distinct stages. First, two unsupervised feature learning techniques: principal component analysis (PCA) and Autoencoder, are utilized to improve the representation of potential optimal samples in the solution space. PCA is used for feature reduction, extracting the most important features. On the other hand, Autoencoder focuses on reconstructing features within the medium-scale solution space. To ensure comprehensive exploration of the entire solution space, TSLL employs two distinct surrogate modeling approaches along with Q-learning in the second stage to dynamically select the mutation strategy for the differential evolution operator. Numerous experiments demonstrate the superiority of TSLL over five state-of-the-art surrogate-assisted approaches and two sophisticated evolutionary algorithms including the winner of CEC 2017 on medium-scale benchmark problems and a wind farm layout problem. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-time-synchronized control: a system-dimension-categorized approach

引用

Science China(Information Sciences) 2023年第7期66卷 177-194页

作者： Wanyue JIANG Shuzhi Sam GE Dongyu LI Institute for Future & Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Department of Electrical and Computer Engineering National University of Singapore School of Cyber Science and Technology Beihang University Shanghai Institute of Satellite Engineering

This study addresses the fixed-time-synchronized control problem of perturbed multi-input multioutput(MIMO) systems. In the task of fixed-time-synchronized control, different dimensions of the output signal in MIMO systems are required to reach the desired value simultaneously within a fixed time *** MIMO system is categorized into two cases: the input-dimension-dominant and the state-dimensiondominant cases. The classification is defined according to the dimension of system signals and, more importantly, the capability of converging at the same time. For each kind of MIMO system, sufficient Lyapunov conditions for fixed-time-synchronized convergence are explored, and the corresponding robust sliding mode controllers are designed. Moreover, perturbations are compensated using the super-twisting technique. The brake control of the vertical takeoff and landing aircraft is considered to verify the proposed method for the input-dimension-dominant case, which shows the essential advantages of decreasing the energy consumption and the output trajectory length. Furthermore, comparative numerical simulations are performed to show the semi-time-synchronized property for the state-dimension-dominant case.

关键词： fixed-time-synchronized convergence sliding mode control perturbed MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Advanced synaptic devices and their applications in biomimetic sensory neural system

引用

Chip 2023年第1期2卷 1-22页

作者： Yiqi Sun Jiean Li Sheng Li Yongchang Jiang Enze Wan Jiahan Zhang Yi Shi Lijia Pan School of Electronic Science and Engineering Nanjing University210093NanjingChina School of Microelectronics and Control Engineering Changzhou University213164ChangzhouChina School of Computer Sci-ence and Engineering Macao University of Science and Technology

Human nervous system,which is composed of neuron and synapse networks,is capable of processing information in a plastic,dataparallel,fault-tolerant,and energy-efficient *** by the ingenious working mechanism of this miraculous biological data processing system,scientists have been devoting great efforts to ar-tificial neural systems based on synaptic devices in recent *** continuous development of bioinspired sensors and synaptic devices in recent years have made it possible that artificial sensory neural systems are capable of capturing and processing stimuli informa-tion in real *** progress of biomimetic sensory neural systems could provide new methods for next-generation humanoid robotics,human-machine interfaces,and other frontier ***,this review summarized the recent progress of synaptic devices and biomimetic sensory neural ***,the opportunities and remaining challenges in the further development of biomimetic sensory neural systems were also outlined.

关键词： Artificial synapse Biomimetic sensory neural system Memristor Synaptic transistor

来源：评论

学校读者我要写书评

暂无评论

Autonomous WSNs node powered by a thermal energy harvester for temperature monitoring

引用

International Journal of Ambient Energy 2023年第1期44卷 1058-1066页

作者： Zhang, Zhijuan Ji, Xiaoming Zhang, Qunjun Hou, Liqun School of Electrical and Electronic Engineering North China Electric Power University Baoding China School of Control and Computer Engineering North China Electric Power University Baoding China

An autonomous wireless sensor networks (WSNs) node powered by a thermal energy harvester with MPPT is proposed in this paper for temperature monitoring. Two commercial TEG modules are used to build up the thermoelectric collector, while an energy management circuit with a DC/DC converter is employed to boost the TEG output voltage. The harvested energy is stored in a supercapacitor. The feasibility of the presented self-powered WSNs node is verified by a series of experiments with various node sleep periods and temperature differences across the thermoelectric generator (ΔT TEG). The results show that the proposed thermal energy harvester can work at its maximum power point and autonomously power a commercial WSN node when ΔT TEG is above 13.3°C and node sleep period is not less than 1.5 s. In addition, the designed self-powered WSNs node can monitor the temperature of industrial devices successfully. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Thermal energy

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data Fitting and Trust Assessment to Improve the Security of Industrial Networks 43

Leveraging Data Fitting and Trust Assessment to Improve the ...

引用

43rd Chinese control Conference, CCC 2024

作者： Zhang, Heng Wang, Yinchu Xue, Yawen Deng, Ruilong Li, Hongran Zhang, Jian Jiangsu Ocean University School of Computer Engineering China Zhejiang University College of Control Science and Engineering China

ISBN: (纸本)9789887581581

Industrial network control systems (INCSs) are easy to be targeted by attackers due to their high economic value. Most of the existing defense methods are deployed at the network boundary, which causes high-security risks to INCS once an attacker enters the system. In addition, many existing intrusion detection systems (IDSs) build detection models based on historical data. When INCS lacks sufficient historical data, it is difficult to build detection models with high accuracy. In this paper, we propose a trust assessment model for INCS based on Fourier series fitting employing concept of zero trust to assess the real-time trust of INCS. The model alerts when INCS has low trust. We test two data injection attacks in the experiment to prove the effectiveness of our approach. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

SEFormer:A Lightweight CNN-Transformer Based on Separable Multiscale Depthwise Convolution and Efficient Self-Attention for Rotating Machinery Fault Diagnosis

引用

computers, Materials & Continua 2025年第1期82卷 1417-1437页

作者： Hongxing Wang Xilai Ju Hua Zhu Huafeng Li State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and AstronauticsNanjing210016China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain ***,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis ***,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault ***,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative *** complexity results in high computational costs and limited industrial *** tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault ***,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration ***,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global ***,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and *** study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.

关键词： CNN-Transformer separable multiscale depthwise convolution efficient self-attention fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Corwdsourced Task Recommendation via Link Prediction 18th

Corwdsourced Task Recommendation via Link Prediction

引用

18th CCF Conference on computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Yu, Song Pan, Qingxian Li, Li School of Computer and Information Science Southwest University Chongqing400715 China School of Computer and Control Engineering Yantai University Shandong264005 China

ISBN: (纸本)9789819996391

Mobile crowdsourcing (MCS) can solve problems that are difficult for computers to solve accurately or efficiently. Current crowdsourcing workers face the challenges of overload, task recommendation is presented to deal with the above issue. The existing MCS task recommendation methods only consider the workers themselves, without taking the potential relationships between workers and workers and tasks, which may fail to grasp the long-term behavioral preferences of workers and cannot solve the cold start problem efficiently. To solve the above problems, this paper proposes a task recommendation method based on heterogeneous graph link prediction. First, we try to obtain the connection relationships between crowdsourcing tasks and workers and build a worker-task heterogeneous graph accordingly. Then, majority voting and DeepWalk are used to generate initial node features of workers. Second, we design two efficient message passing mechanisms to aggregate and update node features between task and worker nodes to explore the potential relationships between nodes. Finally, we obtain attention weights among nodes and use Bi-GRU to capture the long-term behavioral preferences of workers and recommend appropriate tasks to workers based on the similarity between workers and tasks to improve perceptual quality. Evaluations are conducted on seven real datasets. Experimental results show that our method is superior to the state-of-the-art baselines. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Investigations into the flow dynamics of mixed biomass particles in a fluidized bed through Hilbert-Huang transformation and data-driven modelling

引用

Particuology 2024年第12期95卷 115-123页

作者： Bojian Qi Yong Yan Wenbiao Zhang School of Computer and Artificial Intelligence Beijing Technology and Business UniversityBeijing100048China International Research Center for Carbon Neutralization Hangzhou Beihang International Innovation InstituteBeihang UniversityHangzhou311115China School of Control and Computer Engineering North China Electric Power UniversityBeijing102206China

Flow dynamics of binary particles are investigated to realize the monitoring and optimization of fluidized *** is a challenge to accurately classify the mass fraction of mixed biomass,considering the limitations of existing *** data collected from an electrostatic sensor array is *** correlation,empirical mode decomposition(EMD),Hilbert-Huang transform(HHT)are applied to process the *** a higher mass fraction of the wood sawdust,the segregation behavior occurs,and the high energy region of HHT spectrum ***,two data-driven models are trained based on a hybrid wavelet scattering transform and bidirectional long short-term memory(ST-BiLSTM)network and a EMD and BiLSTM(EMD-BiLSTM)network to identify the mass fractions of the mixed biomass,with accuracies of 92%and 99%.The electrostatic sensing combined with the EMD-BiLSTM model is effective to classify the mass fraction of the mixed biomass.

关键词： Fluidized beds Biomass Hilbert-Huang transformation Bidirectional long short-term memory network Electrostatic sensors

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：