检索结果-内蒙古大学图书馆

Surface-PMSM Sensorless Control Strategy Based on Reduced-Order Linear Kalman Filter Cooperating with Prediction Error Rolling Compensation

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 10804-10815页

作者： Xu, Sang Shen, Anwen Tang, Qipeng Wang, Miaomiao Luo, Pan Luo, Xin Xu, Jinbang National Key Laboratory of Science and Technology on Multispectral Information Processing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Wuhan430074 China Science and Technology on Reactor System Design Technology Laboratory Chengdu China

Kalman filter (KF) is increasingly attracted for sensorless control of surface permanent magnet synchronous motors (SPMSMs) due to its strong robustness against measurement and system noise. However, conventional method suffers from poor position and speed estimation accuracy under dynamic conditions, and high computational cost. In order to solve these problems, an enhanced sensorless control strategy based on reduced-order linear Kalman filter (RLKF) cooperating with prediction error rolling compensation is introduced in this paper. Differing from conventional method, a reduced-order linear state equation encompassing rotor position, speed and torque disturbance is constructed. Then, by obtaining the prediction error of system output using the motor current equation in the predictive reference frame, the optimal estimation of rotor position and speed in KF algorithm is achieved based on the reduced-order model. This not only simplifies the calculation process, but also enhances the position and speed estimation accuracy under dynamic conditions. Meanwhile, a prediction error rolling compensation algorithm is developed to minimize the estimation deviations caused by motor parameters variations. Additionally, the system's dynamic performance is further improved with an adopted speed controller based on torque disturbance feedforward and acceleration feedback. Finally, experimental results verify the effectiveness and feasibility of the proposed strategy.1 © 1986-2012 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

From First-Order to Second-Order Rationality: Advancing Game Convergence with Dynamic Weighted Fictitious Play 21st

From First-Order to Second-Order Rationality: Advancing Gam...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Ju, Qi Hei, Falin Liu, Yuxuan Fang, Zhemei Luo, Yunfeng Huazhong University of Science and Technology Wuhan China National Key Laboratory of Science and Technology on Multispectral Information Processing Wuhan China

ISBN: (纸本)9789819601271

Constructing effective algorithms to converge to Nash Equilibrium (NE) is a important problem in algorithmic game theory. Prior research generally posits that the upper bound on the convergence rate for games is OT-1/2. This paper introduces a novel perspective, positing that the key to accelerating convergence in game theory is "rationality". Based on this concept, we propose a Dynamic Weighted Fictitious Play (DW-FP) algorithm. We demonstrate that this algorithm can converge to a NE and exhibits a convergence rate of O(T-1) in experimental evaluations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Pixel-Level Multidirectional Image Sharpness Linear Assessment for Optical Image Stabilizer Performance Monitoring

引用

IEEE Sensors Journal 2025年第9期25卷 15204-15215页

作者： Zhou, Yuhang Zhang, Zhe Yang, Bokang Ma, Jie Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology China-EU Institute for Clean and Renewable Energy Wuhan430074 China

Linear quantification of blur intensity in different directions of an image and blur-type classification are crucial for the detection of anomalies and optimization calibration of widely used optical image stabilizer (OIS). However, previous image quality assessment methods mainly focused on isotropic blur, emphasizing the correlation with subjective ratings, making it difficult to provide multidirectional linear sharpness assessment. Moreover, they invariably offer a single evaluation score regardless of the kind of fuzziness. In this article, we propose a pixel-level multidirectional image sharpness (PMIS) linear assessment method that, to our knowledge, is the first to provide the capability to linearly quantify blur across multiple directions and distinguish blur types in an end-to-end manner while assessing the degree of image blur. We introduce a novel method for extracting edge information to characterize image blur, significantly enhancing correlation with the human visual system (HVS) in blur perception by filtering out high-frequency edge noise. Uniform edge block selection and data postprocessing are introduced to adapt to HVS characteristics and enhance robustness. Using blur results from four different directions and simply setting thresholds, we are able to achieve an 84.5% classification accuracy in distinguishing between defocus blur, motion blur, and clear images. In addition, we creatively make a motion blur image quality (MBIQ) database, accurately representing motion blur through the concrete physical quantity of rotational speed. Experimental results confirm that PMIS achieves significant improvements over the previous methods especially on databases with anisotropic motion blur. © 2025 IEEE.

关键词： information filtering

来源：评论

学校读者我要写书评

暂无评论

Self-distilled Dual-Network with Pixel Screening Loss for Blind Image Deblurring 27th

Self-distilled Dual-Network with Pixel Screening Loss for ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Tianyi Tian, Ming Gao, Changxin Sang, Nong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031781247

In the field of image processing, blind image deblurring aims to restore sharp details in images blurred by an unknown convolution kernel. Recent advancements have shown that deep networks can act as effective image generative priors (DIP) for restoring clear images without requiring external datasets. However, the inherent non-uniqueness of solutions in blind image deblurring often leads DIP-based methods to converge on local optima, resulting in over- or under-deblurred images. To overcome this limitation, we propose a novel deblurring framework featuring dual image generators. These generators mutually constrain each other during training, guiding the model towards the optimal solution. Building on our network structure, we employ a self-ensemble and self-distillation strategy to guide network training, further enhancing performance. Additionally, we introduce a novel loss function based on a pixel screening method, which focuses on the important pixels. This loss enables the network to model the blur kernel more accurately and facilitates the restoration of image details. Our experiments demonstrate that our deblurring approach outperforms most existing methods both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

引用

science China(information sciences) 2025年第1期68卷 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of Computer Science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of Computer Science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词： graph representation learning graph neural networks graph contrastive learning graph augmentations graph pooling

来源：评论

学校读者我要写书评

暂无评论

Complementary Dual-Branch Network for Space-Time Video Super-Resolution 27th

Complementary Dual-Branch Network for Space-Time Video Supe...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Tian, Ming Li, Tianyi Luo, RongSheng Gao, Changxin Sang, Nong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031781247

Space-time video super-resolution aims to simultaneously increase the space-time resolution of low-resolution and low frame-rate videos. Existing deep learning-based methods have made notable strides, predominantly achieving space-time video super-resolution through the relatively simple integration of modules for video super-resolution and video frame interpolation sub-tasks. However, these methods typically do not fully exploit the inherent relationships between the two sub-tasks. To address this limitation, we propose a Complementary Dual-Branch Network designed to better explore the interdependence of the two sub-tasks. Specifically, our dual-branch architecture facilitates mutual enhancement between video super-resolution and video frame interpolation sub-tasks within each branch and provides mutual guidance between the two branches. Additionally, we introduce a simple yet effective strategy for the rough estimation of optical flow, incorporating Flow-Guided Deformable Alignment into space-time video super-resolution to achieve precise motion estimation. In addition, we use an RNN-based Backward and Forward Recurrent module to ensure that all frames can utilize the information of the whole sequence. It is more efficient and memory saving compared to the currently popular bidirectional LSTM module. Experimental results on several datasets show that our method achieves superior accuracy and requires fewer parameters compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Label Semantic Dynamic Guidance Network for Remote Sensing Image Scene Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Chai, Borui Zhao, Tianming Yang, Runou Zhang, Nan Tian, Tian Tian, Jinwen Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Wuhan430074 China

The remote sensing image scene classification continues to face significant challenges due to high intraclass diversity and interclass similarity. Existing methods mainly use semantic associations between images to establish deep semantic associations between classes, ignoring the rich high-level semantic knowledge contained in the label text. This high-level information are especially valuable for distinguishing between confusing categories, as it enables the model to capture both similarity and distinctive features effectively. In this article, we introduce a novel approach that incorporates label semantic information and proposes a plug-and-play framework to guide classification model learning of intraclass and interclass relationships. Specifically, our framework includes a dynamic soft label module (DSLM), which uses textual semantics to facilitate classification model learning of interclass relationships via soft labels at the target level. In addition, we design a coarse-to-fine contrastive module (CFCM) to integrate textual semantics into contrastive learning, guiding the model in capturing intraclass and interclass relationships at the feature level. Our framework is compatible with both convolutional neural network (CNN)-based and vision transformer (ViT)-based classification architectures and is employed solely during training to minimize computational overhead. Experimental results on four datasets validate the effectiveness of our approach. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Federated Stochastic Primal-Dual Learning for Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 17034-17050页

作者： Li, Yiwei Wang, Shuai Chang, Tsung-Hui Xiamen University of Technology Fujian Key Laboratory of Communication Network and Information Processing Xiamen361024 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China The Chinese University of Hong Kong Shenzhen School of Science and Engineering Shenzhen Research Institute of Big Data Shenzhen518172 China

Federated learning (FL) has the potential to empower Internet-of-Vehicles (IoV) networks by enabling smart vehicles (SVs) to participate in the learning process under the orchestration of a vehicular service provider while keeping data locally. In this paper, we propose a novel federated stochastic primal-dual algorithm with differential privacy (FedSPD-DP) to ensure robust privacy protection for FL based IoV (FL-IoV) systems. The FedSPD-DP algorithm leverages multiple steps of local stochastic gradient descent (SGD) and partial client participation (PCP) to improve communication efficiency while incorporating differential privacy (DP) to ensure privacy protection. Our theoretical analysis explores the impact of these strategies on learning performance. Specifically, we demonstrate that the data sampling strategy and PCP enhance data privacy, while a larger number of local SGD steps may increase privacy leakage, revealing a non-trivial tradeoff between communication efficiency and privacy protection. Extensive experiments on real-world data validate the effectiveness of the proposed algorithm, showing superior performance compared to state-of-the-art FL algorithms, and confirming the analytical results and properties. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Valuable and Low-Budget Process Scheme of Equivalized 1 nm technology Node Based on 2D Materials

引用

Nano-Micro Letters 2025年第8期17卷 294-305页

作者： Yang Shen Zhejia Zhang Zhujun Yao Mengge Jin Jintian Gao Yuhan Zhao Wenzhong Bao Yabin Sun He Tian College of Integrated Circuit Science and Engineering Shanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241People’s Republic of China Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijing 100084People’s Republic of China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433People’s Republic of China Shaoxin Laboratory Shaoxing 312000People’s Republic of China

Emerging two-dimensional(2D)semiconductors are among the most promising materials for ultra-scaled transistors due to their intrinsic atomic-level *** the stacking process advances,the complexity and cost of nanosheet field-effect transistors(NSFETs)and complementary FET(CFET)continue to *** 1 nm technology node is going to be based on Si-CFET process according to international roadmap for devices and systems(IRDS)(2022,https://***/),but not publicly confirmed,indicating that more possibilities still *** miniaturization advantage of 2D semiconductors motivates us to explore their potential for reducing process costs while matching the performance of next-generation nodes in terms of area,power consumption and *** this study,a comprehensive framework is built.A set of MoS2 NSFETs were designed and fabricated to extract the key parameters and *** then for benchmarking,the sizes of 2D-NSFET are scaled to a extent that both of the Si-CFET and 2D-NSFET have the same average device *** these conditions,the frequency of ultra-scaled 2D-NSFET is found to improve by 36%at a fixed power *** work verifies the feasibility of replacing silicon-based CFETs of 1 nm node with 2D-NSFETs and proposes a 2D technology solution for 1 nm nodes,i.e.,“2D eq 1 nm”*** the same time,thanks to the lower characteristic length of 2D semiconductors,the miniaturized 2D-NSFET achieves a 28%frequency increase at a fixed power ***,developing a standard cell library,these devices obtain a similar trend in 16-bit RISC-V *** work quantifies and highlights the advantages of 2D semiconductors in advanced nodes,offering new possibilities for the application of 2D semiconductors in high-speed and low-power integrated circuits.

关键词： Two-dimensional semiconductors 1 nm technology node Nanosheet field-effect transistors Complementary field-effect transistors Horizontal scaling

来源：评论

学校读者我要写书评

暂无评论

Infrared Dim Small Target Detection Algorithm Based on Adaptive Attention Transformer Network

引用

Journal of Shanghai Jiaotong University (science) 2025年 1-13页

作者： Ding, Leqi Xia, Yilin Wang, Biyun Cai, Yunze Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China National Key Laboratory of Air-based Information Perception and Fusion Henan Luoyang471009 China Shanghai Institute of Aerospace Control Technology Infrared Detection Technology R & D Center of China Aerospace Science and Technology Corporation Shanghai201109 China

This paper presents a novel algorithm for detecting infrared dim small targets in complex backgrounds by integrating both global and local feature information. The proposed method employs an adaptive attention transformer network which addresses challenges associated with computational complexity and information redundancy in traditional self-attention mechanisms. A global context aggregation module is designed to address the loss of small target features in high-level feature maps. This module compensates for spatial distribution information during the multi-scale feature fusion process, ensuring the preservation of target features. Comparison experiments were conducted on two datasets, NUAA-SIRST and IRSTD-1k. The proposed algorithm achieved 0.784 for mIoU and 0.878 for F-measure on NUAA-SIRST, 0.632 for mIoU and 0.807 for F-measure on IRST-1k, all of which are the highest values. The proposed algorithm shows a significant improvement over other existing detection algorithms, demonstrating its capability to accurately extract both local and global features of targets with high recall rates and low false alarm rates across various scenarios. The ablation study results highlight the significant improvements contributed by the key modules to the proposed algorithm. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： A adaptive attention global context aggregation module infrared dim small target detection TP391.4 Transformer network

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：