检索结果-内蒙古大学图书馆

TRNet: Two-Tier Recursion Network for Co-Salient Object Detection

IEEE Transactions on Circuits and systems for Video Technology 2025年第6期35卷 5844-5857页

作者： Cong, Runmin Yang, Ning Liu, Hongyu Zhang, Dingwen Huang, Qingming Kwong, Sam Zhang, Wei Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Northwestern Polytechnical University Brain and Artificial Intelligence Laboratory School of Automation Xi'an710129 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China Lingnan University Hong Kong

Co-salient object detection (CoSOD) is to find the salient and recurring objects from a series of relevant images, where modeling inter-image relationships plays a crucial role. Different from the commonly used direct learning structure that inputs all the intra-image features into some well-designed modules to represent the inter-image relationship, we resort to adopting a recursive structure for inter-image modeling, and propose a two-tier recursion network (TRNet) to achieve CoSOD in this paper. The two-tier recursive structure of the proposed TRNet is embodied in two stages of inter-image extraction and distribution. On the one hand, considering the task adaptability and inter-image correlation, we design an inter-image exploration with recursive reinforcement module to learn the local and global inter-image correspondences, guaranteeing the validity and discriminativeness of the information in the step-by-step propagation. On the other hand, we design a dynamic recursion distribution module to fully exploit the role of inter-image correspondences in a recursive structure, adaptively assigning common attributes to each individual image through an improved semi-dynamic convolution. Experimental results on five prevailing CoSOD benchmarks demonstrate that our TRNet outperforms other competitors in terms of various evaluation metrics. The code and results of our method are available at https://***/rmcong/TRNetTCSVT2025. © 1991-2012 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Temperature Rising Model of Tubular Permanent Magnet Linear Synchronous Motor Based on Transfer Learning-Deep Neural Network

Temperature Rising Model of Tubular Permanent Magnet Linear ...

引用

第42届中国控制会议

作者： YiFei Wang Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

High temperature rise of permanent magnet linear synchronous motor can lead to irreversible demagnetization of the motor permanent magnet, which can negatively affect the motor performance. To address this problem, a thermal modeling analysis method based on Transfer learning-Deep neural network(TL-DNN) was proposed in this paper. Its specific implementation steps include(1) corresponding to different heat source inputs, the equivalent thermal circuit method and the finite element analysis was adopted based on the structure and main parameters of PMLSM including overall average temperature rise, coil temperature rise and permanent magnet temperature rise from the data sets of the motor;(2) TL-DNN was used to fit the functional relationship between the input source features and the output targets based on the characteristics of the sample data sets. In order to verify the accuracy of the prediction model with small sample data sets, this paper divided the proportion of the data set and compared the results with other classic nonparametric models(random forest, support vector machine, and deep neural network). The results show that the TL-DNN model outperforms other machine learning models and has better robustness and generalization ability when the training datasets are insufficient, and achieves an organic combination of physical field path model and data-driven model, which provides a feasible solution for PMLSM modeling in the case of small samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Weighting Factors Autotuning Strategy for Model Predictive Torque Control of Permanent Magnet Synchronous Motor Based on Adaptive Multi-objective Black Hole Algorithm

A Weighting Factors Autotuning Strategy for Model Predictive...

引用

第42届中国控制会议

作者： Zixiang Zhou Tao Wu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems System Integration and Industrial Robotics Laboratory

The rational design of weighting factors in the cost function for finite control set model predictive torque control(FCS-MPTC) has been a matter of great interest in power electronics and electrical drives. In order to solve this problem, a weighting factors autotuning strategy for FCS-MPTC of permanent magnet synchronous motor(PMSM) based on the adaptive multi-objective black hole algorithm(AMOBH) is proposed. In this paper, the design process of the FCS-MPTC algorithm is first analyzed in detail. Then, an AMOBH algorithm that can take into account both population convergence and population diversity is introduced, and based on this algorithm, the design problem of the weighting factors is successfully transformed into a multiobjective optimization problem by means of reconstructing the cost function and designing the motor operation information collected in real time as the objective functions of the multi-objective optimization algorithm. Simulation results show that the proposed method can find a set of weighting factor combinations suitable for different working condition requirements, and these weighting factors can effectively improve the operation performance of the PMSM system.

关键词： Model Predictive Torque Control Weighting Factors Multi-objective Optimization Algorithm Permanent Magnet Synchronous Motor

来源：评论

学校读者我要写书评

暂无评论

Design of a Novel Autonomous Docking system With a Supporting Robotic Fish

Design of a Novel Autonomous Docking System With a Supportin...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Dong, Huijie Zhao, Chunyang Qiao, Tiezhu Wang, Jian Chen, Di Meng, Yan Yu, Junzhi Taiyuan University of Technology Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan030024 China Chinese Academy of Sciences Laboratory of Cognitive and Decision Intelligence for Complex System Institute of Automation Beijing100190 China Peking University State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics College of Engineering Beijing100871 China Guangdong Ocean University College of Electronics and Information Engineering Zhanjiang524088 China

ISBN: (纸本)9798350327182

Underwater supporting robots serving as a relay of energy supplements and communication for other underwater equipment are promising for ocean exploration, development, and protection. This paper proposes a novel autonomous docking system centered on a designed supporting robotic fish named 'CourierFish'. Specifically, CourierFish is capable of docking with a surface dock station for supplying itself and docking with a seafloor platform for supporting equipment in the platform. A visual navigation scheme integrating LED and ArUco markers is presented for accurate localization. The control approach for docking motion is also illustrated. Simulations and aquatic experiments are performed to verify the feasibility of the proposed docking system. The obtained results lay a solid foundation for the construction of various underwater equipment and robot networks. © 2023 IEEE.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Simulation Study on Electrothermal and Mechanical Coupling of Bumps in 5×5 Micro-LED Array 20

Simulation Study on Electrothermal and Mechanical Coupling o...

引用

20th China International Forum on Solid State Lighting and 9th International Forum on Wide Bandgap Semiconductors, SSLCHINA: IFWS 2023

作者： Yang, Zhu Fu, Hao Wang, Kefeng Ji, Xiaoxiao Chen, Liang Yin, Luqiao Lu, Xiuzhen Zhang, Jianhua School of Microelectronics Shanghai University Shanghai201800 China Shanghai University Key Laboratory of Advanced Display and System Applications Ministry of Education Shanghai2000072 China School of Mechatronic Engineering and Automation Shanghai University Shanghai2000072 China

ISBN: (纸本)9798350385373

As a frontier research field of next-generation display technology, Micro-LED technology has the advantages of high brightness, high contrast and high energy efficiency. With the development trend of high-power, multi-array LEDs, the research on thermal stability of LEDs is gradually deepened. In order to explore the thermal stability of bumps during the working of Micro-LED, COMSOL Multiphysics simulation software and finite element method were used to analyze the electrothermal and mechanical coupling of bumps in 5×5 Micro-LED array in this paper. Flip-chip bonding was employed for interconnection of Micro-LED array and Si driver chip with the gap except Micro-LED devices between sapphire and silicon substrate filled with underfill to alleviate the stress concentration. The effects of different filling materials, applied current densities, and dimensions of In bumps (cylindrical) on thermal stress and displacement of the Micro-LED array were analyzed in detail. The results show the stress and displacement of the bumps with polyimide (PI) underfill were the smallest than that of bumps with benzocyclobutene (BCB) and epoxy resin (EP) underfill. Additionally, the temperature, thermal stress, and displacement of the bumps were also affected by the applied current density and the size of the bumps. © 2023 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Mechanical Properties of Flip-Chip Bonding Structures for Micro-Led Devices: Cu-Cu Bonding with Passivation Layer and Indium Bumps Bonding

Mechanical Properties of Flip-Chip Bonding Structures for Mi...

引用

2023 China Semiconductor Technology International Conference, CSTIC 2023

作者： Wang, Kefeng Chen, Zehua Ji, Xiaoxiao Yin, Luqiao Lu, Xiuzhen Zhang, Jianhua School of Microelectronics Shanghai University Shanghai201800 China Shanghai University Ministry of Education Key Laboratory of Advanced Display and System Applications Shanghai200072 China School of Mechatronic Engineering and Automation Shanghai University Shanghai200072 China

ISBN: (纸本)9798350311006

A traditional bonding structure with indium bumps and a new bonding structure with passivation layer using Cu bumps were simulated to bond Micro-LED and substrate. Anand model and bilinear isotropic hardening model were used to characterize the viscoplastic behavior of In and the plastic behavior of composite structure simplified from the combination of Cu and Au, respectively. Mechanical properties of two kinds of micro-display devices with different bonding structures were analyzed by the ANSYS finite element method and the thermo-mechanical coupling field. The deformation and stress of the micro-display device using Cu-Cu bonding structure with passivation layer are reduced by 19.5% and 59.1% compared with the device bonded by In bumps. © 2023 IEEE.

关键词： Display devices

来源：评论

学校读者我要写书评

暂无评论

ViT-based Terrain Recognition system for wearable soft exosuit

引用

Biomimetic Intelligence & Robotics 2023年第1期3卷 57-64页

作者： Fangliang Yang Chunjie Chen Zhuo Wang Hui Chen Yao Liu Gang Li Xinyu Wua Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Shenzhen College of Advanced Technology University of Chinese Academy of SciencesShenzhen 518055China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Guangdong-Hong Kong-Macao Joint Laboratory of Human–Machine Intelligence-Synergy Systems Shenzhen 518055China SIASUN Robot and Automation CO. LtdShenyang 110169China

Terrain classification and force assistance strategies in complex environments have always piqued the interest of many *** wearable soft exosuits,inaccurate terrain recognition can easily introduce undesired assist forces that can easily injure the *** of these problems,we introduced a depth camera into the exosuit system,perform classification of terrain based on a Vision Transformer(ViT),and optimized the control algorithm,which is known as a ViT-Based Terrain Recognition system(TTRS).First,we used the Transformer algorithm to achieve a considerable classification effect in terrain *** also introduced terrain recognition as prior knowledge into the force assistance strategy of the exosuit,providing different force assistance to the exosuit in different ***,we performed human experiments with seven able-bodied people(six males and one female).The promising results demonstrate that our classification accuracy can reach 99.2%under six different terrains and that it can smoothly switch the force–assist curve in different terrains to better adapt to the complex terrain and improve the walking *** aforementioned terrain recognition algorithms and force–assist strategies may positively influence the study of soft exosuit,powered prostheses,and orthotics.

关键词： Vision Transformer(ViT) Depth camera Wearable soft exosuit Force assistance strategy Terrain recognition

来源：评论

学校读者我要写书评

暂无评论

Variational Autoencoder Based Network Embedding Algorithm for Protein Function Prediction 2022

Variational Autoencoder Based Network Embedding Algorithm fo...

引用

14th International Conference on Machine Learning and Computing, ICMLC 2022

作者： Cao, Guansong Zhu, Yuan Yi, Ming School of Automation China University of Geosciences China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System China University of Geosciences Wuhan China School of Mathematics and Physics China University of Geosciences Wuhan China

ISBN: (纸本)9781450395700

The development of high-throughput technology has produced a large number of protein-protein interaction datasets, which provide an effective way to infer the functional annotation of proteins. However, how to make proper use of these datasets to extract effective low-dimensional feature representation of proteins for functional prediction is a challenge. Most existing network integration methods for protein function prediction have some limitations to capture complex and highly non-linear network structure information due to their design architecture. Therefore, we propose a novel multi-network embedding method deepVAE based on deep variational autoencoder (VAE), which uses the variational autoencoder to extract low-dimensional features of proteins from multiple various interactive network datasets and then trains a SVM classifier to predict protein function. Particularly, we denoise the original networks before network embedding, thus the new proposed method is called deepVAE-NE. The experiments are conducted on the yeast and human protein-protein interaction datasets and the experimental performance shows that our methods perform better than the other four compared advanced approaches, which greatly improves the accuracy of functional prediction. © 2022 ACM.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Multitarget gas alarm system for high-performance and anti-interference chemical warfare agents simulants detection

引用

Science China(Technological Sciences) 2025年第3期68卷 349-358页

作者： Yubin YUAN Qiang WU Menglong JIAO Haiyang WU Weihua LIU Xuming WANG Xiangrui BU Gong LI Chuanyu HAN Long HU Xin LI Xiaoli WANG Shool of Microelectronics School of Electronics and Information EngineeringXi’an Jiaotong UniversityXi’an710049China The Key Lab of Micro-nano Electronics and System Integration of Xi’an City Xi’an710049China Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhou310024China School of Automation and Information Engineering Xi’an University of TechnologyXi’an710048China Key Laboratory for Physical Electronics and Devices of the Ministry of Education Xi’an Jiaotong UniversityXi’an710049China School of Science Xi’an Jiaotong UniversityXi’an710049China

Chemical warfare agents(CWAs)can cause significant harm to health and even death in a very short time even when inhaled in small amounts(~100 mg min/m^(3)).Detection equipment based on conventional techniques,including gas chromatography-mass spectrometry,Raman spectroscopy,fluorescence spectroscopy,and ion mobility spectrometry,have the disadvantages of high cost,long detection time,and high power ***,portable,and convenient equipment for target CWAs detection under interference is a *** this study,we propose an alarm system comprising a multitype micro sensor array and a field-programmable gate array-based readout circuit for CWAs simulants *** common volatile organic compound,temperature,and water vapor interference,the proposed multitype sensor-based detection system realizes an alarm function in less than 20 s with thresholds of 1 ppm dimethyl methylphosphonate(DMMP),4.6 ppm 2,2'-dichlorodiethyl ether(DCE),and 20 ppm SO_(2).Furthermore,the proposed detection system was evaluated outside the laboratory and passed the wilderness test,demonstrating its reliability in the *** believe that the proposed alarm system will contribute to the development of intelligent,portable,low-cost,and anti-interference CWAs detection technology.

关键词： alarm system CWAs simulants surface acoustic wave sensor mixed gas anti-interference

来源：评论

学校读者我要写书评

暂无评论

Tracking performance limitations of networked control systems with packet dropouts and logarithmic quantization 41

Tracking performance limitations of networked control system...

引用

第41届中国控制会议

作者： Jianhao Li Xiaowei Jiang Hao Chen Shaoying Wang Xianhe Zhang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System College of Science Binzhou University School of Electrical Engineering and Automation Hubei Normal University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,we focus on the tracking performance(TP) limitations of networked control systems(NCS s).The control system considered is a multi-input and multi-output(MIMO) discrete-time network control system with time delay,channel noise,packet dropouts,and logarithmic quantization communication *** modeling the channel,we assumed the channel noise to be additive white Gaussian noise(AWGN) and used a binary random process to model packet dropouts and a logarithmic quantizer to model the quantization *** explicit expression of the TP limitations of NCSs utilizing the two-degree-of-freedom(TDOF) controller is then derived using the frequency-domain approach,coprime decomposition,and Youla parameterization *** results show that the essential characteristics of the plant(locations and directions of nonminimum phase zeros and unstable poles) and network constraints(time delay,packet dropouts,quantization,and noise power spectral density) are closely related to the TP limitations.

关键词： Networked control systems tracking performance limitations packet dropouts logarithmic quantization

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：