检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Mengxi Qin Xin Chen School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Calligraphy is an important humanistic symbol of Chinese civilization. However, most of the calligraphy is incomplete, which has only a small number of Chinese characters circulating in the world. How to use these samples to efficiently restore the remaining calligraphy characters has always been considered as a difficult task. In this work, we propose Densenetpix2 pix model based style transfer method to solve this problem. By training some samples to learn the rules of transferring the printed font images to the calligraphy characters images, Densenet-pix2 pix can predict the remaining calligraphy characters. Our method modify the generation network and optimization strategies of style transfer, which improves the generation quality of the calligraphy characters and the stability of the model. In addition, we use pre-trained feature extraction models to extract content information and style information, and scientifically evaluate the quality of our generated calligraphy characters from these two aspects. We compared our method with several other baseline methods. The experimental results show that our method can effectively restore the remaining calligraphy characters, and the generated Chinese characters are more delicate.

关键词： Calligraphy characters Style transfer Restore Generation

来源：评论

学校读者我要写书评

暂无评论

Identification of Protein complex Based on Multi-label Learning Algorithm

Identification of Protein Complex Based on Multi-label Learn...

引用

第三十八届中国控制会议

作者： Zhu Yuan Liu Song School of Automation China University of Geoscienc Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Protein complexes are key molecular entities that play an integral role in human life activities. Systematic identification of protein complexes is an important application of data mining in the biological sciences. Existing multi-label learning algorithms can effectively label nodes belonging to different complexes in protein-protein interaction network to identify overlapping complexes. However, the protein complexes formed by the stochastic strategy may have unstable results and insufficient community quality. To solve these problems, this paper proposes a novel protein complex identification method based on multisource fused data and the multi-label learning algorithm. The descending order of the potential influence of the nodes is used as the node selection order to solve the problem of unstable partitioning of the composite results. The comprehensive similarity obtained by the link correlation and the similarity of the gene annotations is used as the node label update strategy to improve the quality of the composite. The experimental results show that the new proposed method is much more effective and feasible,and has higher precision and biological significance.

关键词： Protein-protein interaction network protein complex label propagation link coherence gene annotation

来源：评论

学校读者我要写书评

暂无评论

Hidden-Markov-model-based finite-time fault detection for networked singularly perturbed systems

Hidden-Markov-model-based finite-time fault detection for ne...

引用

第三十八届中国控制会议

作者： Jiankang Li Xiongbo Wan School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In this paper, the problem of finite-time fault detection(FD) is investigated for networked discrete-time singularly perturbed systems under the stochastic communication protocol(SCP). To alleviate the undesired data collisions caused by largescale data transmissions via the bandwidth-limited communication network, the SCP modeled by a Markov chain is *** to practical factors such as observation error, the Markov modes of the SCP are assumed to be available to the fault detection filter(FDF) according to a hidden Markov process. Our aim is to design a hidden-Markov-model-based FDF as the residual generator such that the resulting augmented system is stochastically H∞ finite-time bounded. A sufficient condition in terms of linear matrix inequalities(LMIs) is derived which ensures the existence of such an FDF. The parameters of the desired FDF are explicitly given when there exist feasible solutions to these LMIs. Finally, the effectiveness of the FD method is demonstrated by a numerical example.

关键词： Finite-time fault detection Singularly perturbed systems Hidden Markov model Stochastic communication protocol

来源：评论

学校读者我要写书评

暂无评论

On Ground Penetrating Radar Imaging Method Based on Compressed Sensing in Multi-target Environment

On Ground Penetrating Radar Imaging Method Based on Compress...

引用

第三十八届中国控制会议

作者： Guangjun Wang Chengyong Ma Jianjin Jiang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Recently, compressed sensing(CS) has been widely used in ground penetrating radar(GPR) imaging due to its low sampling time, high quality performance and high quality imaging results in underground imaging. However, for densely distributed underground multi-target, the error of GPR imaging based on CS is large. So, this paper proposes a filter matrix,which can effectively reduce the energy of B-scan hyperbolic arms, increase the hyperbolic apex energy, and reduce the error of GPR imaging based on CS in densely distributed multi-target environment. The algorithm also takes into account the distance between the antenna and the ground. At first, a method of the normalized is used to calculate the echo data. Then the filter matrix designed in this paper is used. Experimental results present that the filter matrix can effectively reduce the imaging error in multi-target environment.

关键词： Compressed sensing(CS) underground imaging ground penetrating radar(GPR) multi-target

来源：评论

学校读者我要写书评

暂无评论

Target tracking algorithm based on convolutional neural network and particle filtering

Target tracking algorithm based on convolutional neural netw...

引用

第三十八届中国控制会议

作者： Lijun Zhang Peng Chen Hui Guo Shun Huang Wei Xia Cong Hu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Aiming at the phenomenon that the target particle tracking algorithm is affected by illumination changes and occlusion in the target tracking process, the goal is lost. A target tracking algorithm based on convolutional neural network and particle filtering is proposed. The algorithm uses the convolutional neural network to automatically learn the depth features of the target,and extracts the more abstract semantic information of the target. The semantic information makes the algorithm robust to the apparent changes of the target, which can alleviate the drift problem to some extent. The algorithm can effectively combine the target apparent model based on convolutional neural network with the particle filter framework. The experimental results show that compared with the other five algorithms in the particle filter framework, the algorithm can track the moving targets with partial occlusion and morphological changes more robustly.

关键词： Convolutional Neural Network Particle Filter Target Tracking

来源：评论

学校读者我要写书评

暂无评论

Modeling and Optimization of the Activated Sludge Process

Modeling and Optimization of the Activated Sludge Process

引用

第三十八届中国控制会议

作者： Shun Huang Lijun Zhang Hui Guo Peng Chen Wei Xia Cong Hu School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

In the process of urban sewage treating, reducing the energy consumption and improving the quality of the effluent are significantly meaningful. According to the activated sludge method, the key factors affecting the energy consumption and water quality of wastewater treatment are determined. In order to minimize the energy consumption of the activated sludge process and maximize the quality of the effluent, four different objective functions are modeled [i.e., the airflow rate, the carbonaceous biochemical oxygen demand(CBOD) of the effluent, the total phosphorus(TP) of the effluent, and the ammonia nitrogen of the effluent(NH4-N)]. These models are developed using a back propagation(BP) neural network based on industrial data, and dissolved oxygen(DO) is the controlled variable. A multi-objective model was evaluated by six evaluation indicators. Based on the analysis of the model and the mechanism of activated sludge process, the multi-objective particle swarm optimization(MOPSO)algorithm was used to optimize the energy consumption and water quality of the activated sludge process. The experimental results show that eventually reduce aeration energy consumption by 17%.

关键词： Activated sludge Wastewater treatment Energy consumption Back propagation neural network Multi-objective particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal Trajectory Planning Based on Improved Adaptive Genetic Algorithm for a 6 DOF Manipulator

Optimal Trajectory Planning Based on Improved Adaptive Genet...

引用

第三十八届中国控制会议

作者： Haoyang Zhang Yan Yuan Xin Chen School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

This paper is concerned with the optimal trajectory planning for a 6 degree-of-freedom(DOF) manipulator, where the energy minimization is considered under the constraint of power. Firstly, based on the establishment of kinematics model, the influence of main factors on power is analyzed by using Jacobian matrix and Lagrange equation. Then the energy consumption is calculated as the objective function by the power consumption of each joint, and in order to obtain the desired trajectory for the arm, each joint locus is approximated by a 3-5-3 spline interpolation curve. To this end, in order to obtain the most reliable solutions for trajectory planning, the improved adaptive genetic algorithm(IAGA) is used to optimize the energy under the constraint of power, speed and acceleration, and the crossover rate and mutation rate are effectively adjusted with ***, we conduct the simulation by using the dynamics analysis software-ADAMS. The results demonstrate the effectiveness of minimizing the optimized energy in the case of constrained power mainly.

关键词： Energy optimization trajectory planning improved adaptive genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic event-triggered communication based fault detection for networked singularly perturbed systems

Dynamic event-triggered communication based fault detection ...

引用

第三十八届中国控制会议

作者： Tizhuang Han Xiongbo Wan Jianqi An School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

This paper investigates the problem of fault detection(FD) for networked singularly perturbed systems under the dynamic event-triggered communication. To save the network resources, a dynamic event-triggered communication mechanism(DETCM) is proposed, which contains some existing triggering mechanisms as special cases. Our aim is to design a fault detection filter(FDF) under such a DETCM, which ensures that the resulting filtering error dynamics of FD is asymptotically stable and satisfies an H∞ performance requirement. By constructing a Lyapunov function dependent on both the singular perturbation parameter(SPP) and flexible variable of the DETCM, a sufficient condition is obtained in terms of linear matrix inequalities(LMIs), which ensures the existence of the desired FDF. When these LMIs have feasible solutions, the parameters of the FDF are explicitly given and the admissible upper and lower bounds of the SPP are evaluated. A numerical example is provided to demonstrate the effectiveness of the design method of the FDF.

关键词： Fault detection Dynamic event-triggered communication Singularly perturbed systems Networked systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Planning:A New Motion Planning Framework for Autonomous Driving

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 236-246页

作者： Long Chen Xuemin Hu Wei Tian Hong Wang Dongpu Cao Fei-Yue Wang IEEE School of Data and Computer Science Sun Yat-sen University the School of Computer Science and Information Engineering Hubei University Institute of Measurement and Control Systems Karlsruhe Institute of Technology Department of Mechanical and Mechatronics Engineering University of Waterloo the State Key Laboratory of Management and Control for Complex Systems.Institute of Automation Chinese Academy of Sciences the Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology

Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human ***, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.

关键词： Autonomous driving artificial traffic scene deep learning emergencies motion planning parallel planning

来源：评论

学校读者我要写书评

暂无评论

Distributed synchronous and asynchronous algorithms for semi-definite programming with diagonal constraints

arXiv

引用

arXiv 2021年

作者： Jiang, Xia Zeng, Xianlin Sun, Jian Chen, Jie Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Ministry of Education Beijing100081 China School of Electronic and Information Engineering Tongji University Shanghai200082 China

This paper develops distributed synchronous and asynchronous algorithms for the large-scale semi-definite programming with diagonal constraints, which has wide applications in combination optimization, image processing and community detection. The information of the semi-definite programming is allocated to multiple interconnected agents such that each agent aims to find a solution by communicating to its neighbors. Based on low-rank property of solutions and the Burer-Monteiro factorization, we transform the original problem into a distributed optimization problem over unit spheres to reduce variable dimensions and ensure positive semi-definiteness without involving semi-definite projections, which are computationally expensive. For the distributed optimization problem, we propose distributed synchronous and asynchronous algorithms, both of which reduce computational burden and storage space compared with existing centralized algorithms. Specifically, the distributed synchronous algorithm almost surely escapes strict saddle points and converges to the set of optimal solutions to the optimization problem. In addition, the proposed distributed asynchronous algorithm allows communication delays and converges to the set of critical points to the optimization problem under mild conditions. By applying proposed algorithms to image segmentation applications, we illustrate the efficiency and convergence performance of the two proposed algorithms. © 2021, CC BY.

关键词： Optimization

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：