检索结果-内蒙古大学图书馆

State space representation and phase analysis of gradient descent optimizers

science China(Information sciences) 2023年第4期66卷 140-154页

作者： Biyuan YAO Guiqing LI Wei WU School of Computer Science and Engineering South China University of Technology School of Computer Wuhan University

Deep learning has achieved good results in the field of image recognition due to the key role of the optimizer in a deep learning network. In this work, the optimizers of dynamical system models are established,and the influence of parameter adjustments on the dynamic performance of the system is proposed. This is a useful supplement to the theoretical control models of optimizers. First, the system control model is derived based on the iterative formula of the optimizer, the optimizer model is expressed by differential equations, and the control equation of the optimizer is established. Second, based on the system control model of the optimizer, the phase trajectory process of the optimizer model and the influence of different hyperparameters on the system performance of the learning model are analyzed. Finally, controllers with different optimizers and different hyperparameters are used to classify the MNIST and CIFAR-10 datasets to verify the effects of different optimizers on the model learning performance and compare them with related methods. Experimental results show that selecting appropriate optimizers can accelerate the convergence speed of the model and improve the accuracy of model recognition. Furthermore, the convergence speed and performance of the stochastic gradient descent(SGD) optimizer are better than those of the stochastic gradient descent-momentum(SGD-M) and Nesterov accelerated gradient(NAG) optimizers.

关键词： optimizer control model phase trajectory parameter adjustment classification dynamic performance

来源：评论

学校读者我要写书评

暂无评论

A crowd simulation model based on emotional cognition and contagion for emergency evacuation

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10187-10200页

作者： Zong, Xinlu Li, Hejing Liu, Aiping Xu, Hui School of Computer Science Hubei University of Technology Wuhan China

Emotion is a crucial factor which influences evacuation effects. However, the studies and quantitative analysis of evacuation emotions, including the emotion generated by external factors and internal personality or cognition levels, emotional contagion evolution, and the regulation mechanism of pedestrians to negative emotion, are still rare. In this paper, an evacuation model based on emotional cognition and contagion (EMECC) is presented. Firstly, individual’s emotion is generated and quantified based on Lazarus’s cognitive theory. Secondly, the emotional contagion between individuals is simulated by SIS (Susceptible Infected Susceptible) infectious disease model. Combining with cellular automata model, an emotion-driven moving rule is proposed to guide pedestrians move towards the directions with more positive individuals so that positive emotions can be spread effectively. Various experiments on model parameters, obstacles, and emotional contagion process are implemented to verify the effectiveness of the EMECC model. The simulation and experimental results show that emotional regulation mechanism can improve pedestrian’s decision-making ability and contagion of positive emotion can accelerate evacuation process. The EMECC model can simulate emotional changes dynamically and guide pedestrians efficiently and reasonably in emergency evacuation. © 2024 – IOS Press. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Optimizing local search-based partial MaxSAT solving via initial assignment prediction

引用

science China(Information sciences) 2025年第2期68卷 59-73页

作者： Chanjuan LIU Guangyuan LIU Chuan LUO Shaowei CAI Zhendong LEI Wenjie ZHANG Yi CHU Guojing ZHANG School of Computer Science and Technology Dalian University of Technology School of Software Beihang University Institute of Software Chinese Academy of Sciences School of Computer Science Peking University

Partial maximum satisfiability(PMS) is a significant generalization of Boolean satisfiability(SAT) and maximum satisfiability(MaxSAT), by introducing hard clauses and soft clauses. Compared with SAT and MaxSAT, the PMS problem has more real-world applications where both hard and soft constraints are involved. Local search is an effective incomplete method for solving PMS and is useful for important domains where good-quality solutions are desired within reasonable *** local search PMS solvers, the approach for initial assignment generation is crucial because its effectiveness significantly affects practical performance. In this study, we propose a novel initial assignment prediction approach, called InitPMS. When predicting an assignment for PMS, InitPMS considers the specific structure of PMS instances, i.e., distinguishing hard and soft clauses. Our experiments on extensive PMS instances from MaxSAT evaluations(MSEs) 2020 and 2021 show that InitPMS significantly boosts the performance of five state-of-the-art local search PMS solvers, demonstrating its generality. In addition,our results indicate that incorporating InitPMS could improve the performance of one of the best incomplete PMS solvers in MaxSAT Evaluation 2021, indicating that InitPMS might help advance the state of the art in PMS solving.

关键词： MaxSAT local search initial assignment incomplete method assignment prediction

来源：评论

学校读者我要写书评

暂无评论

Low-frequency chatter suppression in robotic milling using Magnetorheological Joint Damper(MRJD)

引用

Chinese Journal of Aeronautics 2025年第3期38卷 521-543页

作者： Shihao XIN Xiaowei TANG Jiawei WU Fangyu PENG Rong YAN Kai SUN School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China

Low-frequency structural vibrations caused by poor rigidity are one of the main obstacles limiting the machining efficiency of robotic *** vibration suppression strategies primarily focus on passive vibration absorption at the robotic end and feedback control at the joint *** these strategies have a certain vibration suppression effect,the limitations of robotic flexibility and the extremely limited applicable speed range remain to be *** this study,a Magnetorheological Joint Damper(MRJD)is *** joint-mounted feature ensures machining flexibility of the robot,and the millisecond response time of the Magnetorheological Fluid(MRF)ensures a large effective spindle speed *** importantly,the evolution law of the damping performance of MRJD was revealed based on a low-frequency chatter mechanism,which guarantees the application of MRJD in robotic milling *** analyze the influence of the robotic joint angle on the suppression effect of the MRJD,the joint braking coefficient and end braking coefficient were *** coordinate plots were used to visualize the joint range with the optimal vibration suppression ***,a combination of different postures and cutting parameters was used to verify the vibration suppression effect and feasibility of the joint angle *** experimental results show that the MRJD,which directly improves the joint vibration resistance,can effectively suppress the low-frequency vibration of robotic milling under a variety of cutting conditions.

关键词： Magnetorheological fluids Joint damper Vibration suppressioni Low-frequency chatter Robotic milling

来源：评论

学校读者我要写书评

暂无评论

A new centrality measure based on neighbor loop structure for network dismantling

引用

Digital Communications and Networks 2024年第2期10卷 472-480页

作者： Qingxia Liu Bang Wang Jiming Qi Xianjun Deng School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhan430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430074China

Nearly all real-world networks are complex networks and usually are in danger of ***,it is crucial to exploit and understand the mechanisms of network attacks and provide better protection for network *** dismantling aims to find the smallest set of nodes such that after their removal the network is broken into connected components of sub-extensive *** overcome the limitations and drawbacks of existing network dismantling methods,this paper focuses on network dismantling problem and proposes a neighbor-loop structure based centrality metric,NL,which achieves a balance between computational efficiency and evaluation *** addition,we design a novel method combining NL-based nodes-removing,greedy tree-breaking and ***,we compare five baseline methods with our algorithm on ten widely used real-world networks and three types of model networks including Erd€os-Renyi random networks,Watts-Strogatz smallworld networks and Barabasi-Albert scale-free networks with different network generation *** results demonstrate that our proposed method outperforms most peer methods by obtaining a minimal set of targeted attack ***,the insights gained from this study may be of assistance to future practical research into real-world networks.

关键词： Complex networks Network dismantling Centrality measure

来源：评论

学校读者我要写书评

暂无评论

Swarming Magnetic Fe_(3)O_(4)@Polydopamine-Tannic Acid Nanorobots:Integrating Antibiotic-Free Superficial Photothermal and Deep Chemical Strategies for Targeted Bacterial Elimination

引用

Research 2025年第1期2024卷 840-853页

作者： Luying Si Shuming Zhang Huiru Guo Wei Luo Yuqin Feng Xinkang Du Fangzhi Mou Huiru Ma Jianguo Guan State Key Laboratory of Advanced Technology for Materials Synthesis and Processing International School of Materials Science and EngineeringWuhan University of TechnologyWuhanChina Wuhan Institute of Photochemistry and Technology WuhanChina School of Chemistry Chemical Engineering and Life ScienceWuhan University of TechnologyWuhanChina

Micro/nanorobots(MNRs)are envisioned to provide revolutionary changes to therapies for infectious diseases as they can deliver various antibacterial agents or energies to many hard-to-reach infection ***,existing MNRs face substantial challenges in addressing complex infections that progress from superficial to deep ***,we develop swarming magnetic Fe3O4@polydopamine-tannic acid nanorobots(Fe3O4@PDA-TA NRs)capable of performing targeted bacteria elimination in complicated bacterial infections by integrating superficial photothermal and deep chemical *** Fe3O4@PDA-TA nanoparticles(NPs),serving as building blocks of the nanorobots,are fabricated by in situ polymerization of dopamine followed by TA *** driven by alternating magnetic fields,Fe3O4@PDA-TA NPs can assemble into large energetic microswarms continuously flowing forward with tunable ***,the swarming Fe3O4@PDA-TA NRs can be navigated to achieve rapid broad coverage of a targeted superficial area from a distance and rapidly eradicate bacteria residing there upon exposure to near-infrared(NIR)light due to their efficient photothermal ***,they can concentrate at deep infection sites by traversing through confined,narrow,and tortuous passages,exerting sustained antibacterial action through their surface TA-induced easy cell adhesion and subsequent membrane ***,the swarming Fe3O4@PDA-TA NRs show great potential for addressing complex superficial-to-deep *** study may inspire the development of future therapeutic microsystems for various diseases with multifunction synergies,task flexibility,and high efficiency.

关键词： therapies infectious diseases complex infections chemical therapy magnetic nanoparticles polydopamine photothermal therapy targeted bacteria elimination tannic acid

来源：评论

学校读者我要写书评

暂无评论

Dynamics of three ferrofluid droplets in a rotating magnetic field

引用

Applied Mathematics and Mechanics(English Edition) 2025年第3期46卷 591-600页

作者： Xinping ZHOU Wencai XIAO Qi ZHANG Chunyue LIANG Wanqiu ZHANG Fei ZHANG School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China

Two-dimensional(2D)direct numerical simulations on the dynamics of three identical ferrofluid droplets suspended in a non-magnetic ambient fluid under a rotating uniform magnetic field are conducted,and the motion and deformation of the three ferrofluid droplets are studied in this *** show that there are four modes(i.e.,the three droplets'direct coalescence(TC),the coalescence of two droplets and the subsequent planetary motion with the third droplet(CAP),the three droplets'planetary motion(TP),and the independent spin(IS))for the three ferrofluid droplets,dependent on the magnetic Bond number(Bom)and the initial distance(d0)between two of the *** is found that the decrease in d0and the increase in Bomcan make the droplets'mode change from the IS to the planetary motion,and then turn to the ***,reducing Bomor d0is helpful for the droplets to become merged.

关键词： ferrofluid droplet rotating magnetic field capillary force

来源：评论

学校读者我要写书评

暂无评论

DGECN++: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation via Attention Mechanism

引用

IEEE Transactions on Circuits and Systems for Video technology 2024年第6期34卷 4214-4228页

作者： Cao, Tuo Zhang, Wenxiao Fu, Yanping Zheng, Shengjie Luo, Fei Xiao, Chunxia Wuhan University School of Computer Science Wuhan430072 China Anhui University School of Computer Science and Technology Hefei230039 China

Monocular object 6D pose estimation is a fundamental yet challenging task in computer vision. Recently, deep learning has been proven to be capable of predicting remarkable results in this task. Existing works often adopt a two-stage pipeline with establishing 2D-3D correspondences and utilizing a PnP/RANSAC or differentiable PnP algorithm to recover 6 degrees-of-freedom (6DoF) pose parameters. However, most of them hardly consider the geometric features in 3D space, and ignore the topological cues when performing differentiable PnP algorithms. To this end, we present an improved end-to-end monocular 6D pose estimation method (DGECN++) that incorporates depth estimation and a geometric-aware learnable PnP network. Our method is based on keypoints. First we detect the 2D keypoints that correspond to the 3D model. We then integrate differentiable PnP/RANSAC algorithm to create an end-to-end pipeline for 6D pose estimation. We focuses on the following three key aspects: 1) We utilize the estimated depth information to guide the process of extracting 2D-3D correspondences and refine the results using a cascaded differentiable PnP/RANSAC algorithm that incorporates geometric information. 2) We leverage the uncertainty of the estimated depth map to enhance the accuracy and robustness of the predicted 6D pose. 3) We propose a differentiable Perspective-n-Point (PnP) algorithm based on edge convolution and self-attention to explore the topological relationships between 2D-3D correspondences. Experimental results demonstrate that our proposed network surpasses existing methods in terms of both effectiveness and efficiency. © 1991-2012 IEEE.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Perception-entropy-driven temporal reusing for real-time ray tracing

引用

Optoelectronics Letters 2025年第6期21卷 378-384页

作者： SHEN Zhongye CHEN Chunyi YAO Weixun YU Haiyang PENG Jun School of Computer Science and Technology Changchun University of Science and Technology

Although ray tracing produces high-fidelity, realistic images, it is considered computationally burdensome when implemented on a high rendering rate system. Perception-driven rendering techniques generate images with minimal noise and distortion that are generally acceptable to the human visual system, thereby reducing rendering costs. In this paper, we introduce a perception-entropy-driven temporal reusing method to accelerate real-time ray tracing. We first build a just noticeable difference(JND) model to represent the uncertainty of ray samples and image space masking effects. Then, we expand the shading gradient through gradient max-pooling and gradient filtering to enlarge the visual receipt field. Finally, we dynamically optimize reusable time segments to improve the accuracy of temporal reusing. Compared with Monte Carlo ray tracing, our algorithm enhances frames per second(fps) by 1.93× to 2.96× at 8 to 16 samples per pixel, significantly accelerating the Monte Carlo ray tracing process while maintaining visual quality.

关键词： A

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of visible infrared person re-identification from an application perspective

引用

Multimedia Tools and Applications 2024年第42期83卷 90243-90270页

作者： Chang, Hua Xu, Xin Liu, Wei Lu, Lingyi Li, Weigang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

Person re-identification (ReID) is a significant issue in computer vision, aiming to match the same pedestrian across various cameras. Recent research on this issue has successfully reached a satisfactory performance level in the daytime scenario. However, the performance of ReID in low illumination scenarios suffers a dramatic degradation due to the insufficient personal information captured by visible cameras in low or no light scenarios. To address this challenge, the adoption of novel camera technologies for more effective pedestrian data is imperative. Owing to the constraints of distance and usage scenarios in deploying depth cameras, practical infrared cameras are frequently utilized, spurring research in visible infrared person re-identification (VI-ReID). Significant progress has been made in the field of VI-ReID in recent years, but only a few reviews have categorized this problem based on methodology. This article offers a novel perspective by classifying VI-ReID according to application scenarios. Following our categorization scheme, the main advancements in deep learning for VI-ReID over the past five years have been grouped into three categories as follows: retrieval of infrared images using visible images (V→IR), retrieval of visible images using infrared images (IR→V), and joint retrieval of infrared and visible images (V→IR and IR→V). Next, this survey outlines the available datasets and evaluation metrics. After that, we categorize diverse methodologies under the proposed classification and assess their performance metrics across common datasets. Finally, we present two prospective avenues for future research in this domain, informed by the current state of advancement. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

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：