检索结果-内蒙古大学图书馆

2024 China automation Congress, CAC 2024

作者： Yuan, Jie Li, Yongfu Huang, Longwang Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of Automation Chongqing University of Posts and Telecommunications Chongqing400065 China

ISBN: (纸本)9798350368604

The diversity of target scales and the complex background interference present in UAV imagery pose significant challenges for UAV target detection. In response, this paper proposes a novel small object detection model built upon the YOLOv5s. We introduce a new layer, Head-P2, dedicated to detecting small targets within the YOLOv5s framework to enhance precision. Additionally, we incorporate a decoupled detection head to refine the model's target positioning capability. Further augmenting the model's capabilities, the SimAM attention mechanism is integrated into YOLOv5s' feature extraction and fusion network, amplifying feature attention on targets and improving overall feature extraction performance. To address the limitations of the CIOU loss function, particularly its inability to adapt to varying detection targets and challenges with learning difficult samples, we adopt the inner-CIOU loss function. This adaptation enhances both precision and training convergence speed of the YOLOv5s. The modified model is rigorously evaluated on the VisDrone2019 dataset, with ablation experiments confirming its efficacy. In comparative experiments, our enhanced model exhibits notable improvements over YOLOv5s, with a 6.7% increase in mAP@.5 and a 3.8% increase in mAP@.5:.95 values. Moreover, it outperforms YOLOv8s and other models, demonstrating its robustness in small target detection tasks. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 7597-7609页

作者： Wu, Wenjing Fu, Hanjing Cui, Kaixin Liu, Zhigang Yang, Dong Shi, Dawei Beijing Institute of Technology MIIT Key Laboratory of Servo Motion System Drive and Control School of Automation Beijing100081 China Beijing Institute of Spacecraft System Engineering Beijing100094 China

Data limitation caused by the difficulty of data acquisition, the high cost of data collection, and the changes of working conditions is a serious obstacle to the accurate lithium-ion battery SOH estimation for spacecrafts system. To achieve accurate few-shot lithium-ion battery state of health(SOH) estimation and enhance the adaptability of learning methods across varying working conditions, a domain similarity model agnostic meta-learning method (DS-MAML) is proposed. First, we design a dynamic-static feature extraction method to adequately exploit information from the limited battery data and link the obtained features by gray correlation coefficients to collect sufficient information. Then, by calculating the domain similarity between the training tasks through the maximum mean discrepancy algorithm, the training tasks are ranked to reduce the re-training time. Finally, an LSTM model is added to the meta-learning framework to capture the long-term dependency relationships between SOH and time series of the voltage, and the ranked tasks are embedded in the meta-training process to improve adaptability in different working conditions. The effectiveness of the proposed method is validated by NASA and MIT datasets, and comparative experimental results illustrate that the proposed method average error is reduced by 73%, and the running speed is increased by 20% compared with traditional MAML in few-shot scenarios. © 1965-2011 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

Observer-based robust control for a class of sampled-data systems with model uncertainty and external disturbance

引用

Journal of control and Decision 2023年第3期10卷 454-463页

作者： Junqi Yang Zechen Li Yantao Chen School of Engineering and Automation Henan Polytechnic UniversityJiaozuoPeople’s Republic of China Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment Henan Polytechnic UniversityJiaozuoPeople’s Republic of China

This paper studies the issue of observer-based feedback stabilisation for a class of linear sampleddatasystems with model uncertainty and external disturbance. First, for a sampled-data systemwith external disturbance, a sampled-data observer is designed to estimate the system ***, a robust H∞ controller based on the observer is developed. For a continuous samplinginterval, the gain matrices of both observer and controller change exponentially. Second,using the state coordinate transformations with an exponential rate, a unified dynamics is constructedby augmenting the state estimation error and the closed-loop system state as a newstate. Next, the sufficient conditions ensuring the asymptotical stability of the closed-loop systemare given by the Lyapunov–Krasovskii method and linear matrix inequality (LMI) ***, the effectiveness of the proposed method is verified by a helicopter model.

关键词： Sampled-data system observer linear matrix inequality robust controller

来源：评论

学校读者我要写书评

暂无评论

High-speed train positioning based on a combination of Beidou navigation, inertial navigation and an electronic map

引用

Science China(Information Sciences) 2023年第7期66卷 237-252页

作者： Hui YANG Shuai-Qiang DONG Chun-Hua XIE School of Electrical and Automation Engineering East China Jiaotong University Key Laboratory of Advanced Control & Optimization of Jiangxi Province East China Jiaotong University State Key Laboratory of Performance Monitoring Protecting of Rail Transit Infrastructure East China Jiaotong University

To date, the studies on the combination positioning of high-speed trains have made great progress, but the positioning accuracy of these methods is relatively low. Map-matching positioning can improve positioning accuracy, but information transmission is time-consuming. Few studies incorporate it into combination positioning. To solve the problem, this paper proposes a high-speed train positioning method based on combining a Beidou navigation system, an inertial navigation system, and an electronic map. First, the combination positioning problem is transformed into a multi-objective optimization problem, which weights the direction similarity and distance error to form a fitness function and converts the railway line and the maximum error range of each positioning system into constraints. Second, an improved differential evolution algorithm is proposed to solve this problem. By referencing the gray wolf algorithm,the differential evolution algorithm updates individuals by varying toward the direction of multiple optimal values. Then, a new combination positioning algorithm for high-speed trains is proposed. In the simulation,the increase in positioning speed and accuracy is analyzed and validated. Compared to the current algorithms, the proposed algorithm performs better. The proposed method has practical value for improving the reliability and safety of train operations.

关键词： electronic map multi-objective optimization differential evolution algorithm Beidou navigation system high-speed train positioning

来源：评论

学校读者我要写书评

暂无评论

Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism

引用

Computers, Materials & Continua 2024年第7期80卷 1543-1561页

作者： Bing Li Liangyu Wang Xia Liu Hongbin Fan Bo Wang Shoudi Tong School of Automation Harbin University of Science and TechnologyHarbin150080China Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin150080China School of Computer Engineering Technology Guangdong Institute of Science and TechnologyZhuhai519090China

Nuclearmagnetic resonance imaging of breasts often presents complex *** tumors exhibit varying sizes,uneven intensity,and indistinct *** characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor ***,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention ***,the breast region of interest is extracted to isolate the breast area from surrounding tissues and ***,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor *** incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion ***,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel ***,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional *** was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the *** results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.

关键词： Dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI) breast tumor segmentation multi-scale dilated convolution boundary attention the hybrid loss function with boundary weight

来源：评论

学校读者我要写书评

暂无评论

control Policy Learning Design for Vehicle Urban Positioning via BeiDou Navigation

引用

Journal of Systems Science & Complexity 2024年第1期37卷 114-135页

作者： QIN Yahang ZHANG Chengye CHEN Ci XIE Shengli LEWIS Frank L School of Automation Guangdong University of TechnologyGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China. Center for Intelligent Batch Manufacturing Based on IoT Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China. UTA Research Institute The University of Texas at ArlingtonFort WorthTX 76019USA

This paper presents a learning-based control policy design for point-to-point vehicle positioning in the urban environment via BeiDou *** navigating in urban canyons,the multipath effect is a kind of interference that causes the navigation signal to drift and thus imposes severe impacts on vehicle localization due to the reflection and diffraction of the BeiDou ***,the authors formulated the navigation control system with unknown vehicle dynamics into an optimal control-seeking problem through a linear discrete-time system,and the point-to-point localization control is modeled and handled by leveraging off-policy reinforcement learning for feedback *** proposed learning-based design guarantees optimality with prescribed performance and also stabilizes the closed-loop navigation system,without the full knowledge of the vehicle *** is seen that the proposed method can withstand the impact of the multipath effect while satisfying the prescribed convergence rate.A case study demonstrates that the proposed algorithms effectively drive the vehicle to a desired setpoint under the multipath effect introduced by actual experiments of BeiDou navigation in the urban environment.

关键词： BeiDou navigation multipath effect prescribed convergence rate reinforcement learning urban localization.

来源：评论

学校读者我要写书评

暂无评论

Multi-UAV Cooperative Formation control Considering Finite Time and Collision Avoidance

Multi-UAV Cooperative Formation Control Considering Finite T...

引用

2024 China automation Congress, CAC 2024

作者： Tang, Rui Li, Yongfu Huang, Longwang Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing College of Automation Chongqing University of Posts and Telecommunications Chongqing400065 China

ISBN: (纸本)9798350368604

In this paper, the formation control problem for UAVs subject to model uncertainty and external disturbance is studied. To realize the control goals, the formation control problem of UAVs is decomposed into position consensus control and attitude consensus control. Firstly, a finite-time position consensus controller is developed for UAVs such that the desired formation can be formed in a finite time. In the position controller, a collision avoidance mechanism is designed on the basis of a novel artificial potential field function. Secondly, to handle dynamic model uncertainties and realize attitude tracking control, a robust filter based finite-time attitude tracking controller is developed. Finally, stability of the position control subsystem and the attitude control subsystem is analyzed using Lyapunov method. And simulation results on MATLAB and RflySim show that the proposed algorithm enables UAVs to form stable formation while avoiding collisions within a finite time. © 2024 IEEE.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Competitive Meta-Learning

引用

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1902-1904页

作者： Boxi Weng Jian Sun Gao Huang Fang Deng Gang Wang Jie Chen National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081 Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China School of Automation Tsinghua UniversityBeijing 100084China Department of Control Science and Engineering Tongji UniversityShanghai 201804 National Key Laboratory of Autonomous Intelligent Unmanned Systems Beijing Institute of TechnologyBeijing 100081China IEEE

Dear Editor,This letter is concerned with developing meta-learning models for fast,stable,and effective few-shot learning across tasks over a few training ***,deep and reinforcement learning(RL)is widely used in auton... 详细信息

关键词： robot autonomous concerned

来源：评论

学校读者我要写书评

暂无评论

Establishment of a humanized ST6GAL1 mouse model for influenza research

引用

Animal Models and Experimental Medicine 2024年第3期7卷 337-346页

作者： Lyu Chao Han Feng Gao Qian Lv Limin Lu Ziwei Lu Shuangshuang Li Xiaoyan Hu Yuechao Yang Mengjie Zhao Yingze Liu Jun Lu Xuancheng Duo Shuguang National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases Chinese Center for Disease Control and PreventionBeijingChina Institute of Zoology Chinese Academy of SciencesBeijingChina NHC Key Laboratory of Biosafety National Key Laboratory of Intelligent Tracking and Forecasting for Infectious DiseasesNational Institute for Viral Disease Control and PreventionChinese Center for Disease Control and PreventionBeijingChina Zhejiang Provincial Key Laboratory of Medical Genetics Key Laboratory of Laboratory MedicineMinistry of EducationSchool of Laboratory Medicine and Life SciencesWenzhou Medical UniversityWenzhouChina

Background:This study aimed to construct and characterize a humanized influenza mouse model expressing ***:Humanized fragments,consisting of the endothelial cell-specific K18 promoter,human ST6GAL1-encoding gene,and luciferase gene,were microinjected into the fertilized eggs of *** manipulated embryos were transferred into the oviducts of pseudopregnant female *** offspring were identified using *** exhibiting elevated expression of the hST6GAL1 gene were selectively bred for propagation,and in vivo analysis was performed for *** of the humanized gene was tested by performing immunohistochemical(IHC)*** and biochemical analyses using the whole blood and serum of humanized hST6GAL1 mice were ***:Successful integration of the human ST6GAL1 gene into the mouse genome led to the overexpression of human SiaT *** mice were identified as carrying copies of the humanized gene,and the in vivo analysis indicated that hST6GAL1gene expression in positive mice mirrored influenza virus infection *** IHC results revealed that hST6GAL1 was expressed in the lungs of humanized ***,the hematologic and biochemical parameters of the positive mice were within the normal ***:A humanized influenza mouse model expressing the hST6GAL1 gene was successfully established and characterized.

关键词： hST6GAL1 humanized mice influenza animal model

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter Adaptive Speed Tracking control for High-speed Trains with Noise Interference 7

Kalman Filter Adaptive Speed Tracking Control for High-speed...

引用

7th International Conference on intelligent Robotics and control Engineering, IRCE 2024

作者： Zhang, Chunli Xie, Yuwei Yan, Lei Qian, Fucai Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing College of Automation and Information Engineering Xi'an China

ISBN: (纸本)9798350352399

In this paper, high-speed train is regarded as a single prime point, a new tracking control method combining adaptive control and Kalman filtering is proposed. This paper solves the noise interference problem in the tracking control process of high-speed train. The method first linearises the original system, then uses Kalman filtering to do model estimation, and the controller is designed for the predictive model through adaptive control. Finally, MATLAB is used to simulate and verify the effectiveness of this method. This proposed method successfully solves the problems of nonlinearity, noise interference and unknown parameters in system. The error caused by resistance in the high-speed train tracking control process can be dealt with effectively. © 2024 IEEE.

关键词： Kalman filters

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：