检索结果-内蒙古大学图书馆

SA-U-Net++: SAR marine floating raft aquaculture identification based on semantic segmentation and ISAR augmentation

引用

Journal of Applied Remote Sensing 2021年第1期15卷

作者： Wang, Deyi Han, Min Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Ganjingzi District Dalian China Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Ganjingzi District Dalian China

Marine floating raft aquaculture (FRA) monitoring is vital for environment protection and mariculture management. Synthetic aperture radar (SAR) could provide high-quality remote sensing images under all weather conditions compared with the existing optical remote-sensing-based methods. Traditional SAR monitoring methods extract the pixel feature of marine FRA in single patches, which commonly leads to poor generalization. We propose a self-Attention semantic segmentation method based on modified U-Net++ (SA-U-Net++) for FRA segmentation, which could automatically extract semantic feature information, and provide superior performance under complicated scenes. The proposed self-Attention backbone could help to extract more precise features and enhance the overall accuracy. Furthermore, we propose a FRA-ISAR data generation method based on inverse SAR (ISAR) imaging to alleviate the sample shortage problem. We introduce the semantic segmentation method into FRA-SAR segmentation for the first time. The experiments verify the effectiveness and superiority of SAR FRA segmentation based on the proposed SA-U-Net++ model compared with the existed semantic segmentation approaches. © 2021 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Research Status of 6LoWPAN in the Field of Internet of Things 5

Research Status of 6LoWPAN in the Field of Internet of Thing...

引用

5th International Conference on Automation, control and Robotics engineering, CACRE 2020

作者： Zhao, Liang Wang, Guangwen School of Control Science and Engineering Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian China Dalian University of Technology School of Control Science and Engineering Dalian China

ISBN: (纸本)9781728198880

The increasing number of wireless sensor nodes brings more application markets and challenges to the Internet of things (IoT). The traditional IPv4 address resources cannot meet the needs of the development of the IoT, so we need a communication mechanism with better compatibility and scalab.lity. With the proposal of the 6LoWPAN protocol, the application of 6LoWPAN to the communication network of the IoT has become the focus of research. This paper studies the research status of 6LoWPAN in the field of Internet of things in the past four years, and analyzes the system architecture, system composition and monitoring parameters of 6LoWPAN through different application scenarios. Experiments in related literatures show that 6LoWPAN has stable network transmission performance and can be used for precise monitoring and management in combination with web applications. In addition, RPL routing protocol security algorithm can be one of the future research directions. © 2020 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Cross-layer optimization of correlated data gathering in wireless sensor networks

Cross-layer optimization of correlated data gathering in wir...

引用

7th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks, SECON 2010

作者： He, Shibo Chen, Jiming Yau, David K. Y. Sun, Youxian State Key Lab. of Industrial Control Technology Zhejiang University Hangzhou 310027 China Department of Computer Sciences Purdue University West Lafayette IN United States

ISBN: (纸本)9781424471515

We consider the problem of gathering correlated sensor data by a single sink node in a wireless sensor *** assume that the sensor nodes are energy-constrained and design efficient distributed protocols to maximize the network lifetime. Many existing approaches focus on optimizing the routing layer only, but in fact the routing strategy is often coupled with power control in the physical layer and link access in the MAC layer. This paper represents a first effort on network lifetime maximization that jointly considers the three layers. We first assume that link access probabilities are known and consider the joint optimal design of power control and routing. We show that the formulated optimization problem is convex and propose a distributed algorithm, JRPA, for the solution. We also discuss the convergence of JRPA. When the optimal link access probabilities are unknown, as in many practical networks, we generalize the problem formulation to encompass all the three layers of routing, power control, and link-layer random access. In this case, the problem cannot be converted into a convex optimization problem, but there exists a duality gap when the Lagrangian dual method is employed. We propose an efficient heuristic algorithm, JRPRA, to solve the general problem. Even without a priori knowledge of the best link access probabilities predetermined for JRPA, JRPRA achieves extremely competitive performance with JRPA. Numerical results are provided to show the convergence of the algorithms and their advantages over existing solutions. © 2010 IEEE.

关键词： Power control

来源：评论

学校读者我要写书评

暂无评论

Fuzzy control of clutch engagement with engine running at local constant speed

引用

Journal of Computational Information Systems 2013年第9期9卷 3423-3430页

作者： Zang, Huaiquan Fan, Jinlong Key Lab. of Industrial Computer Control Engineering of Heibei Province Yanshan University Qinhuangdao 066004 China

Aiming at the starting process of automated mechanical transmission, control algorithm of engaging process of clutch is studied. Firstly, the simplified dynamic model of clutch engagement is established. Secondly, the starting process of automobile is analyzed and the relationship between clutch engagement speed and jerk is obtained. Finally, fuzzy control algorithm of clutch engagement with engine running at local constant speed is proposed by combining engine constant speed control with fuzzy control of engaging process of clutch. Simulation results show that the algorithm can not only embody the driver's operation intention, but also ensure clutch engagement quickly and smoothly. © 2013 by Binary Information Press.

关键词： Clutches

来源：评论

学校读者我要写书评

暂无评论

control Method for Desorption Tower Liquid Level in Fluidized Catalytic Cracking Based on LESO-DMC

Control Method for Desorption Tower Liquid Level in Fluidize...

引用

2023 China Automation Congress, CAC 2023

作者： Xiao, Jinkun Zhu, Haibo Zhou, Fan Sun, Kaibiao Zhao, Jun Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment Ministry of Education China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (纸本)9798350303759

Fluidized catalytic cracking (FCC) units are crucial equipment in the petroleum refining process, and the level of control directly impacts product quality and yield. To improve the control level of the desorption tower in FCC, this paper proposes a dynamic matrix control (DMC) approach based on the active disturbance rejection strategy. Based on DMC, a linear extended state observer (LESO) is constructed to compensate for model plant mismatch (MPM) and unknown disturbances. The observer bandwidth parameters are determined to optimize robustness, enabling the implementation of active disturbance rejection model predictive control in FCC units. A comparative experimental study is conducted, comparing the proposed method with the traditional DMC approach that does not account for uncertainties and disturbances. The impact of different disturbances on the control strategy is discussed. Experimental results demonstrate that the proposed method exhibits superior control performance and stronger disturbance rejection capability for the liquid level in the desorption tower of the FCC unit. © 2023 IEEE.

关键词： Fluidization

来源：评论

学校读者我要写书评

暂无评论

Distributed edge control for multi-agent based on binocular vision system

引用

Journal of Computational Information Systems 2014年第7期10卷 2907-2915页

作者： Shao, Nuan Li, Huiguang Zou, Liying Liu, Le Key Lab. of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao 066004 China

For multiple Lagrange systems, the objective of distributed edge control problem is to drive all the followers converge to the edge of the convex hull spanned by the leaders. In this approach, we choose binocular vision system as sensing devices. Firstly, a pseudo-stereo visual model is proposed based on the concept of depth information sensitivity which can be used to provide the generalized coordinates of the leaders for all followers in the image coordinate system. Then, based on this new model, a distributed adaptive control algorithm is designed to compensate for the parametric uncertainties under a directed graph. Finally, the proposed control algorithm is applied to the multi-manipulators grasping control, simulation examples are provided to show the effectiveness of the controller. © 2014 Binary Information Press.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Weighted support vector machine for classification with uneven training class sizes

Weighted support vector machine for classification with unev...

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Huang, Yi-Min Du, Shu-Xin Zhejiang Gongshang University Computer and Information Engineering Academy National Key Lab of Industrial Control Technology Institute of Intelligent Systems and Decision Making

ISBN: (纸本)078039092X

In the standard support vector machines for classification, training sets with uneven class sizes results in classification biases towards the class with the large training size. That is to say, the larger the training sample size for one class is, the smaller its corresponding classification error rate is, while the smaller the sample size, the larger the classification error rate. The main causes lie in that the penalty of misclassification for each training sample is considered equally. Weighted support vector machines for classification are proposed in this paper where penalty of misclassification for each training sample is different. By setting the equal penalty for the training samples belonging to same class, and setting the ratio of penalties for different classes to the inverse ratio of the training class sizes, the obtained weighted support vector machines compensate for the undesirable effects caused by the uneven training class size, and the classification accuracy for the class with small training size is improved. Experimental simulations on breast cancer diagnosis show the effectiveness of the proposed methods. © 2005 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Rapid ILC with variable index gain for manipulator trajectory tracking

引用

Journal of Computational Information Systems 2013年第12期9卷 4739-4746页

作者： Wang, Hongrui Wang, Na Wang, Yueling Wang, Chao Key Lab. of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao 066004 China

A non-causal iterative learning control (ILC) with variable index gain is presented to solve the trajectory tracking problem of rigid robot manipulator with non-zero initial error. This scheme eliminates the restriction that the initial state must be fixed or be consistent with the desired state. Compared with fixed learning gain, ILC with variable index gain not only avoids choosing gain aimlessly but also significantly enhances the convergent speed. In this paper, the proposed non-causal algorithm uses error information of future time in previous iteration, then the controller can offset future disturbances in advance. From the perspective of execution, the proposed scheme is easy to implement. Moreover, we analyze the convergence of the new algorithm. Finally, applying the proposed algorithm in manipulator trajectory tracking system, we present simulation results to illustrate the effectiveness of the control scheme. © 2013 by Binary Information Press.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of object tracking algorithm

Performance analysis of object tracking algorithm

引用

3rd International Conference on Image Analysis and Signal Processing, IASP 2011

作者： Cai, Rongtai Wu, Qingxiang Wang, Ping Zhang, Xuguang Hu, Shuo School of Physics Optics Electronic Science and Technology Fujian Normal University Fuzhou 350108 China Key Lab. of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao 066000 China

ISBN: (纸本)9781612848808

This paper analyzes the performance of object tracking algorithms. The issues that affect precision in object tracking are analyzed first and how the parameters in tracking algorithms affect the precision in object tracking are introduced. Then, the time complexity of those object-tracking algorithms is discussed. At last, the holistic analysis and evaluation of these object-tacking algorithms are parsed from application range, tracking precision and time complexity. © 2011 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Extended State Observer Based Nonsingular Terminal Sliding-mode control for Non-sinusoidal Oscillation of Continuous Casting Mold Driven by Servo Motor

Extended State Observer Based Nonsingular Terminal Sliding-m...

引用

第三十四届中国控制会议

作者： LI Qiang FANG Yiming KANG Kesong ZHENG Huicheng Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Department of Mechanical & Electronics Engineering Shijiazhuang Institute of Technology

ISBN: (纸本)9781467374439

A new driving mode that using servo motor to drive continuous casting mold oscillated following the expected non-sinusoidal(include sinusoidal) is introduced. For this system, the integral nonlinear mathematical model is built, which contains the nonlinear model of servo motor and the mechanical transmission parts of the mold. Because the servo motor rotates continuously in single direction while the oscillation waveform of the mold is nonlinear periodic function, firstly, establish the mapping between them to solve the irreversible of this system, and use a third-order tracking differentiator(TD) which has high-speed tracking ability and good tracking precision to track the result of the mapping function and obtain its derivative signal simultaneously. Then a new type of control scheme combined the extended state observer(ESO) with nonsingular terminal sliding-mode control is adopted in investigation. The controller is designed for the integral system by adopting a non-singular terminal sliding mode manifold and can make the singularity avoided by preventing differentiating terms deriving the control laws and applying a continuous control strategy to resolve the chattering. Meanwhile, the ESO is designed to estimate the states and the lumped uncertain disturbances accurately without requiring exact mathematical model and the sensors. The proposed controller can guarantee stabilization of the tracing system. Simulated results are provided to demonstrate the effectiveness of the proposed control scheme.

关键词： Sliding mode control,Extended state observer,Third order TD,Non-sinusoidal oscillation,Continuous casting mold

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：