检索结果-内蒙古大学图书馆

42nd Chinese Control Conference, CCC 2023

作者： Wang, YiFei Wu, Tao School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China System Integration and Industrial Robotics Laboratory Wuhan430074 China

ISBN: (纸本)9789887581543

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. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Finite element method

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

HDD4DBP: A Large-Scale Multi-Modal Benchmark on Driving Behavior Prediction

HDD4DBP: A Large-Scale Multi-Modal Benchmark on Driving Beha...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Dong, Qinghui Zhang, Zhang Chang, Yubo Chen, Wentao Wang, Liang Institute of Automation Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665410205

Driving behavior prediction (DBP) plays an important role in autonomous driving. Accurately anticipating driving behaviors (e.g., left turn, right turn) of ego-vehicles 3-5 seconds before actual occurrences of maneuvers can help AI pilots planning safer trajectories or informing possible dangers to drivers. However, current DBP benchmark datasets, e.g., the Brain4Cars, are restricted by the limited amount of data samples and small number of behavior categories. Thus, there is an urgent need for creating a new larger-scale benchmark to help boost the studies of DBP. In this work, based on the annotations in the HRI Driving Dataset (HDD), we extract 5000+ clips from untrimmed multi-modal data sequences to form a new dataset, termed the HDD4DBP, as a convincing large-scale testbed for evaluating various DPB methods. Furthermore, inspired by the success of transformers on modeling long range dependence in sequences, we build a strong baseline with the vision transformer (ViT) backbone for predicting driving behaviors. Compared to previous representative baselines, a large margin performance gain can be achieved by our strong baseline on the HDD4DBP. Moreover, simply fine-tuning the pre-trained strong baseline can obtain the state-of-the-art performance on the Brain4Cars dataset, thereby futher confirming the benefits of the HDD4DBP. The dataset and source code will be released. Find data and code at https://***/HDD4DBP/MTL. © 2024 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Full Attention Tracker: A Good Combination of Pixel-Level and Region-Level Cross-Correlation 42

Full Attention Tracker: A Good Combination of Pixel-Level an...

引用

42nd Chinese Control Conference, CCC 2023

作者： Wang, Yuxuan Yan, Liping Feng, Zihang Xia, Yuanqing Xiao, Bo School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100081 China

ISBN: (纸本)9789887581543

The tracker based on Siamese neural network is currently a technical method with high accuracy in the tracking field. With the introduction of transformer in the visual tracking field, the attention mechanism has gradually emerged in tracking tasks. However, due to the characteristics of attention operation, Transformer usually has slow convergence speed, and its pixel-level correlation discrimination in tracking is more likely to lead to overfitting, which is not conducive to long-term tracking. A brand new framework FAT was designed, which is the improvement of MixFormer. The operation for simultaneous feature extraction and target information integration in MixFormer is retained, and the Mixing block is introduced to suppress the background as much as possible before the information interaction. In addition, a new operation is designed: the result of region-level cross-correlation is used as a guidance to help the learning of pixel-level cross-correlation in attention, thereby accelerating the model convergence speed and enhancing the model generalization. Finally, a joint loss function is designed to further improve the accuracy of the model. Experiments show that the presented tracker achieves excellent performance on five benchmark datasets. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Deep learning algorithm-oriented blended teaching in secondary school mathematics courses in ethnic areas

引用

Applied Mathematics and Nonlinear Sciences 2024年第1期9卷

作者： Xu, Shifang Pan, Chunyan School of Mathematics and Statistics Qiannan Normal University for Nationalities Guizhou558000 China Key Laboratory of Complex Systems and Intelligent Computing School of Mathematics and Statistics Qiannan Normal University for Nationalities Guizhou558000 China

To provide teaching assistance to secondary school mathematics teachers in ethnic areas and improve the teaching effectiveness of mathematics courses, a hybrid teaching model based on deep learning algorithms is proposed. Convolutional neural networks and joint probability matrix decomposition are fused to design teaching resource recommendation methods, and hybrid teaching is carried out according to three stages: before, during, and after class. The overall mean of the questionnaire for the experimental class improved from 2.39 to 3.01, and the pass rate, merit rate, and mean score of mathematics scores increased by 13.79%, 9.02%, and 15.17 points, respectively. This method enables educational technology to be effective in mathematics curriculum and improve the quality and information of mathematics education in ethnic areas. © 2023 Shifang Xu and Chunyan Pan, published by Sciendo.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning discriminative foreground-and-background features for few-shot segmentation

引用

Multimedia Tools and Applications 2024年第18期83卷 55999-56019页

作者： Jiang, Cong Zhou, Yange Liu, Zhaoshuo Feng, Chaolu Li, Wei Yang, Jinzhu School of Computer Science and Engineering Northeastern University Liaoning Shenyang110819 China College of Science Northeastern University Liaoning Shenyang110819 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Liaoning Shenyang110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang110819 China

Few-shot Semantic Segmentation (FSS) endeavors to segment novel categories in a query image by referring to a support set comprising only a few annotated examples. Presently, many existing FSS methodologies primarily embrace the prototype learning paradigm and concentrate on optimizing the matching mechanism. However, these approaches tend to overlook the discrimination between the features of foreground background. Consequently, the segmentation results are often imprecise when it comes to capturing intricate structures, such as boundaries and small objects. In this study, we introduce the Discriminative Foreground-and-Background feature learning Network (DFBNet) to enhance the distinguishability of bilateral features. DFBNet comprises three major modules: a multi-level self-matching module (MSM), a feature separation module (FSM), and a semantic alignment module (SAM). The MSM generates prior masks separately for the foreground and background, employing a self-matching strategy across different feature levels. These prior masks are subsequently used as scaling factors within the FSM, where the features of the query’s foreground and background are independently scaled up and then concatenated along the channel dimension. Furthermore, we incorporate a two-layer Transformer encoder-based semantic alignment module (SAM) in DFBNet to refine the features, thereby creating a greater distinction between the foreground and background features. The performance of DFBNet is evaluated on the PASCAL-5i and COCO-20i benchmarks, demonstrating its superiority over existing solutions and establishing new state-of-the-art results in the field of few-shot semantic segmentation. The codes will be released if this paper is accepted. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis for the Vehicular Platoon System With Time- Varying Delay via A State Decomposition Method

Stability Analysis for the Vehicular Platoon System With Tim...

引用

Automation, Control and Robotics Engineering (CACRE), International Conference on

作者： Hang Xu Chuan-Ke Zhang Xing-Chen Shangguan Li Jin Yang Li Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences

ISBN: (数字)9798350350302

ISBN: (纸本)9798350350319

In this paper, the consideration of the stability problem for the vehicular platoon system (VPS) with communication delays under proportional differential (PD) control is studied by the Lyapunov- Krasovskii functional (LKF). Firstly, a VPS considering delay is modeled to analyze the influence of delays for the VPS in operation. Then, an error state-space system of the VPS is constructed and transformed into a singular system. As a result, the stability criterion is proposed based on the state decomposition method via the LKF. Finally, the tolerance for delay is calculated for a case of four vehicles with different controller gains. The result shows that the proportional gain is inversely proportional to the time delay and the differential gain is in direct proportion to the time delay meanwhile. Besides, the high-speed vehicular platoon is more affected by the time delay.

关键词： Automation Delay effects Roads Stability criteria Estimation Delays PD control

来源：评论

学校读者我要写书评

暂无评论

Dual-Layer Collaborative Hunting Algorithm Using Virtual Wolf Pack

Dual-Layer Collaborative Hunting Algorithm Using Virtual Wol...

引用

第43届中国控制会议

作者： Zhiqiang Miao Jianlei Zhang Chunyan Zhang Chen Wang Guangming Xie State Key Laboratory for Turbulence and Complex Systems Intelligent Biomimetic Design LabCollege of EngineeringPeking University

Collaborative hunting,also known as Multi-Agent Pursuit Evasion(MAPE),is a crucial aspect of swarm *** main obstacles in MAPE research involve making real-time decisions in dynamic environments,efficient task allocation,collision avoidance among multiple agents,planning and tracking prey in unknown environments,and information sharing under communication *** paper presents the Dual-Layer Collaborative Hunting Algorithm Using Virtual Wolf Pack(DLCH-VWP),which utilizes biomimetic principles,specifically leveraging the advantages and hunting strategies of wolf packs,to enhance collaborative efficiency and adaptability in complex environments within *** algorithm employs a two-tier strategy,with the strategy planning center using biomimetic wolf pack algorithm to manage environment perception,state assessment,prey movement prediction,and inter-robot *** local response center treats each wolf as an independently operating sub-pack,utilizing a combination of Grey Wolf Optimizer(GWO) and the local A-star algorithm to provide each wolf with individual *** allows for efficient dynamic path planning by determining the path for each wolf based on joint decision-making of the group and *** experiments have confirmed the effectiveness and feasibility of this algorithm for collaborative hunting in multi-agent systems,presenting a novel strategy for addressing MAPE challenges.

关键词： Virtual wolf pack Swarm intelligence Collaborative hunting

来源：评论

学校读者我要写书评

暂无评论

Multi-Blockchain Based Data Trading Markets With Novel Pricing Mechanisms

引用

IEEE/CAA Journal of Automatica Sinica 2023年第12期10卷 2222-2232页

作者： Juanjuan Li Junqing Li Xiao Wang Rui Qin Yong Yuan Fei-Yue Wang IEEE the State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China the School of Artificial Intelligence Anhui UniversityHefei 266114 the Qingdao Academy of Intelligent Industries Qingdao 230031China the School of Mathematics Renmin University of ChinaBeijing 100872China the State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 the Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China

In the era of big data,there is an urgent need to establish data trading markets for effectively releasing the tremendous value of the drastically explosive *** security and data pricing,however,are still widely regarded as major challenges in this respect,which motivate this research on the novel multi-blockchain based framework for data trading markets and their associated pricing *** this context,data recording and trading are conducted separately within two separate blockchains:the data blockchain(DChain) and the value blockchain(VChain).This enables the establishment of two-layer data trading markets to manage initial data trading in the primary market and subsequent data resales in the secondary ***,pricing mechanisms are then proposed to protect these markets against strategic trading behaviors and balance the payoffs of both suppliers and ***,in regular data trading on VChain-S2D,two auction models are employed according to the demand scale,for dealing with users’ strategic *** incentive-compatible Vickrey-Clarke-Groves(VCG)model is deployed to the low-demand trading scenario,while the nearly incentive-compatible monopolistic price(MP) model is utilized for the high-demand trading *** temporary data trading on VChain-D2S,a reverse auction mechanism namely two-stage obscure selection(TSOS) is designed to regulate both suppliers’ quoting and users’ valuation ***,experiments are carried out to demonstrate the strength of this research in enhancing data security and trading efficiency.

关键词： Auction data trading markets multi-blockchain pricing mechanisms

来源：评论

学校读者我要写书评

暂无评论

Data Exchange and Sharing Framework for Intermodal Transport Based on Blockchain and Edge computing 1

引用

2nd International Conference on Cognitive Computation and systems, ICCCS 2023

作者： Wang, Li Zhang, Xue Xu, Lianzheng Fu, Deqian Qiu, Jianlong School of Information Science and Engineering Linyi University Shandong Linyi China Key Laboratory of Complex Systems and Intelligent Computing in Universities of Shandong Linyi University Shandong Linyi China

ISBN: (数字)9789819708857

ISBN: (纸本)9789819708840

As an intensive and efficient way of cargo transportation, intermodal transport can take full advantage of various modes of transport through effective combinations. However, there is a problem of lacking effective data connection between collaborators leading to broken business processes, reduced collaborative efficiency, and hindering the development of the intermodal transport industry. In this paper, we propose a data exchange and sharing framework by integrating blockchain technology and edge computing technology to realize efficient, convenient, safe, and credible data exchange, which also conveniently connects different partners of various modes of transport and then promotes cross-sector and cross-system data exchange and sharing in the intermodal transport environment. Furthermore, the ecosystem of intermodal transport data exchange and sharing based on the proposed framework can effectively meet the requirements of scalability, security, believability, and privacy protection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain

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：