检索结果-内蒙古大学图书馆

Unsupervised face image deblurring via disentangled representation learning

PATTERN RECOGNITION LETTERS 2024年 183卷 9-16页

作者： Hu, Yufan Xia, Junyong Liu, Hongmin Wang, Xing Univ Sci & Technol Beijing Sch Intelligence Sci & Technol Beijing 100083 Peoples R China Beijing Electromech Engn Res Inst Natl Key Lab Complex Syst Control & Intelligent Ag Beijing 100074 Peoples R China

Unsupervised face image deblurring aims to restore latent clear face images with explicit structure and facial details without relying on labels. Despite the recent progress, most existing approaches ignore the domain shift issue between clear and blur domains, leading to color distortion and loss of detail in deblurred images. To tackle this issue, we propose a symmetrical unsupervised framework including a decoupling stage and a reconstruction stage. In the decoupling stage, we employ disentangled representation and adversarial domain translation to establish discriminative boundaries between content-invariant domains and feature-shift domains. Besides, a clear feature encoder for clear images is introduced to obtain a latent feature space containing more detailed clarity, providing reliable input for subsequent reconstruction. In the reconstruction stage, similar modules are adopted to ensure the integrity of the mutual mapping between clear and blurred images, while domain latent supervision loss is introduced to ensure that the decoupled features and content information from both stages belong to the same domain. Extensive experimental results on popular benchmarks validate the effectiveness of our method by surpassing existing works.

关键词： Facial image deblurring Unsupervised disentangled representations Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Decentralised hierarchical coordination of electric vehicles in multi-microgrid systems

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2019年第13期13卷 2899-2906页

作者： Zou, Suli Ma, Zhongjing Yang, Nan BIT Natl Key Lab Complex Syst Intelligent Control & D Sch Automat Beijing 100081 Peoples R China China Elect Power Res Inst Beijing 100192 Peoples R China

Here, the authors study the optimal coordination of electric vehicles (EVs) in a multi-microgrid (MMG) system with respect to a given time-of-use (TOU) price trajectory over a multi-time period. The authors firstly formulate a class of EV charging/discharging coordination problems for each individual microgrid (MG) to minimise the electricity cost of this MG, while the implemented strategy may result in high variations of the total demand and even build new peaky demands. To mitigate these negative effects, the authors build an aggregate optimisation problem with quadratic cost function under certain bounds on the electricity costs of each MG. The authors further propose a decentralised method for the underlying optimisation problem and verify the convergence of the system to the optimal strategy with a logarithmic convergence rate. Furthermore, the authors consider the power exchange capacity between the MMG system and the main grid, and present a decentralised algorithm to obtain an optimal strategy that minimises the system cost under this capacity constraint. Also, the convergence, the optimality, and the convergence rate of the proposed algorithm are shown.

关键词： distributed power generation minimisation electric vehicles pricing electricity cost MG total demand peaky demands aggregate optimisation problem quadratic cost function decentralised method logarithmic convergence rate MMG system decentralised algorithm optimality decentralised hierarchical coordination electric vehicles multimicrogrid system optimal coordination EVs multitime period coordination problems individual microgrid optimisation problem system cost minimization time-of-use price trajectory

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation Game Under Double-Sided Auction Mechanism: Efficiency and Convergence

引用

IEEE TRANSACTIONS ON AUTOMATIC control 2018年第5期63卷 1273-1287页

作者： Zou, Suli Ma, Zhongjing Liu, Xiangdong Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol Natl Key Lab Complex Syst Intelligent Control & D Beijing 100081 Peoples R China

With an effort to allocate divisible resources among suppliers and consumers, a double-sided auction model is designed to decide strategies for individual players. Under the auction mechanism with the Vickrey-Clarke-Groves-type payment, the incentive compatibility holds, and the efficient bid profile is a Nash equilibrium (NE). However, it brings difficulties for players to implement the efficient solution due to the fact that there exist infinite number of NEs in the underlying double-sided auction game. To overcome this challenge, we formulate the double-sided auction game as a pair of single-sided auction games which are coupled via a joint potential quantity of the resource. A decentralized iteration procedure is then designed to achieve the efficient solution, where a single player, a buyer, or a seller implements his best strategy with respect to a given potential quantity and a constraint on his bid strategy. Accordingly, the potential quantity is updated with respect to iteration steps as well. It is verified that the system converges to the efficient NE within finite iteration steps in the order of O(ln(1/epsilon)) with epsilon representing the termination criterion of the algorithm.

关键词： Convergence decentralized process double-sided auction efficiency Nash equilibrium (NE) resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Distributed Charging Coordination for Large-Scale Plug-In Electric Vehicles Considering Battery Degradation Cost

引用

IEEE TRANSACTIONS ON control systEMS TECHNOLOGY 2015年第5期23卷 2044-2052页

作者： Ma, Zhongjing Zou, Suli Liu, Xiangdong Beijing Inst Technol Sch Automat Beijing 100081 Peoples R China Beijing Inst Technol Natl Key Lab Complex Syst Intelligent Control & D Beijing 100081 Peoples R China

Much research has focused on the issue of how to effectively coordinate the charging behaviors of large-scale plug-in electric vehicles (PEVs), like the valley-fill strategy, to minimize their impacts on the power grid. However, high charging rates under the valley-fill strategy may result in a higher battery degradation cost. Consequently, in this brief, we formulate a class of PEV charging coordination problems that deal with the tradeoff between the total generation cost and the accumulated battery degradation cost of PEV populations. Due to the autonomy of individual PEVs and the computational complexity of the system with large-scale PEVs, it is impractical to implement the solution in a centralized way. Alternatively, in this brief, we propose a distributed method such that all of the individual PEVs simultaneously update their own best charging behaviors with respect to a common electricity price curve, which is updated as the generation marginal cost with respect to the aggregated charging behaviors of the PEV populations implemented at the last step. The iteration procedure terminates in case the price curve does not update any longer. We show that by applying the proposed distributed method and under certain mild conditions, the system can converge to a unique charging strategy, which is nearly socially optimal. Simulation examples are studied to illustrate the results developed in this brief.

关键词： Battery degradation cost convergence distributed coordination method generation marginal cost plug-in electric vehicles (PEVs) social optimality

来源：评论

学校读者我要写书评

暂无评论

Memoryless Dual-Observer-Based Output Feedback Stabilization of Linear systems With Input and Output Delays

引用

IEEE TRANSACTIONS ON CYBERNETICS 2024年第10期54卷 5806-5817页

作者： Zhou, Bin Peng, Zhengxiao Michiels, Wim Harbin Inst Technol Ctr Control Theory & Guidance Technol Harbin 150001 Peoples R China Natl Key Lab Complex Syst Control & Intelligent Ag Harbin 150001 Peoples R China Katholieke Univ Leuven Dept Comp Sci B-3001 Leuven Belgium

This article focuses on the dual-observer-based stabilization of linear systems with delays in both the inputs and outputs. By a model reduction approach the system can be converted to an equivalent linear system without delays, for which a dual-observer-based stabilizing controller can be designed. However, such a controller is infinite dimensional or memory-based. To solve such a problem, a modified memoryless dual-observer-based stabilizing controller is designed, and the closed-loop stability is proven under some additional conditions. Compared with the reduced-order observer-based controller, the dimension of the dual-observer-based controller is smaller if the system has more inputs than outputs. At the same time, the design approach is more challenging in proving closed-loop stability, as for example a more intricate Lyapunov-Krasovskii functional has to be constructed associated with the proposed approach. The proposed approach is applicable to both continuous-time and discrete-time systems. Numerical simulations validate the effectiveness of the proposed method.

关键词： Dual-observer memoryless controller output feedback stabilization time-delay systems

来源：评论

学校读者我要写书评

暂无评论

Fully distributed output regulation of linear discrete-time multiagent systems with time-varying topology and delays

引用

AUTOMATICA 2024年 167卷

作者： Zhang, Kai Li, Zhao-Yan Zhou, Bin Harbin Inst Technol Ctr Control Theory & Guidance Technol Harbin 150001 Peoples R China Harbin Inst Technol Sch Math Harbin 150001 Peoples R China Natl Key Lab Complex Syst Control & Intelligent Ag Harbin 100074 Peoples R China

This paper investigates the cooperative output regulation problem of linear discrete-time multiagent systems in the presence of time-varying input and communication delays, as well as time-varying topology. The problem is addressed in two phases. Firstly, a new distributed observer is designed for each follower that helps to get information about the state of the leader agent. Secondly, a class of state feedback protocols based on time-varying regulation equations are formulated to solve the cooperative output regulation problem. A key element in proving the main results is the establishment of a new stability criteria for a class of time-varying time-delay interconnected systems. The proposed protocols have several significant advantages, including the ability to achieve cooperative output regulation without requiring a prior global information of the time-varying network topology, and allowing for heterogeneous and arbitrarily large input and communication delays. Finally, an example about spacecraft formation flying is presented to verify the effectiveness of the proposed approach. (c) 2024 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

关键词： Distributed output regulation Discrete-time system Fully distributed control Communication delays

来源：评论

学校读者我要写书评

暂无评论

On exponential and L 2-exponential stability of continuous-time delay-difference systems

引用

APPLIED MATHEMATICS AND COMPUTATION 2024年 481卷

作者： Li, Zhao-Yan Zhang, Qianqian Zhou, Bin Harbin Inst Technol Sch Math Harbin 150001 Peoples R China Harbin Inst Technol Ctr Control Theory & Guidance Technol Harbin 150001 Peoples R China Natl Key Lab Complex Syst Control & Intelligent Ag Harbin 150001 Peoples R China

In this paper, the exponential stability (ES) and L 2-exponential stability (L 2-ES) of continuoustime delay-difference systems are studied. Firstly, the relationship between ES and L 2-ES of the studied system is systematically presented. Secondly, a novel Lyapunov stability theorem is proposed to test both the ES and L 2-ES with a guaranteed convergence rate of the system. Then, for a particular class of delay-difference systems with both point delays and distributed delays having exponential integral kernels, some stability criteria based on linear matrix inequalities (LMIs) are established by selecting suitable Lyapunov-Krasovskii functionals (LKFs) and using a delay decomposition technique. Finally, a numerical example is worked out to illustrate the effectiveness of the theoretical results.

关键词： Continuous-time delay-difference systems Exponential stability L2-exponential stability Lyapunov-Krasovskii functionals

来源：评论

学校读者我要写书评

暂无评论

A Review of the Current Status of Simulation Platforms for Unmanned Swarms 20th

A Review of the Current Status of Simulation Platforms for U...

引用

20th Chinese intelligent systems Conference

作者： Zhen, Zesong Zhou, Lili Shi, Hang Tong, Jiahui Jiang, Chuanlin Su, Yinke Beijing Electromech Engn Inst Beijing Peoples R China Natl Key Lab Complex Syst Control & Intelligent A Beijing Peoples R China

ISBN: (纸本)9789819786527;9789819786503;9789819786497

As a key support for accelerating the R&D of unmanned aerial vehicle products and reducing R&D costs, the simulation platform has increasingly become the core competitiveness of enterprises to improve their R&D level. Driven by the demand for unmanned cluster combat, perfect simulation support platforms have been established domestically and internationally to meet the design and validation needs of algorithms for unmanned drone flight control, cooperative control, cluster obstacle avoidance, and more, including but not limited to widely-used simulation support platforms like XTDrone, X-Plane, FlightGear, Gazebo, AirSim, and JMAVSim, as well as dedicated platforms built for specific requirements. This article introduces the functionality and application scenarios of simulation platforms for designing and validating functions related to unmanned aerial vehicle control both domestically and internationally. It analyzes the issues and solutions of some simulation platforms and summarizes the future development direction of simulation platforms, providing a reference for the development of domestic simulation platforms.

关键词： UAV Cluster simulation Simulation of virtual and real X-Plane FlightGear Gazebo AirSim JMAVSim

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Fusion Mapping and Localization Method for complex Geographical Environments 20th

Multi-sensor Fusion Mapping and Localization Method for Comp...

引用

20th Chinese intelligent systems Conference

作者： Wei, Yujia Li, Ping Han, Jian Tong, Jiahui Beijing Electromech Engn Inst Beijing Peoples R China Natl Key Lab Complex Syst Control & Intelligent A Beijing Peoples R China

ISBN: (纸本)9789819786565;9789819786541;9789819786534

In environments characterized by complex geographical features, the presence of vegetation with pronounced unstructured attributes challenges the efficacy of exclusive reliance on LiDAR for map construction, as it may result in localization inaccuracies due to imprecise matching of feature points. Furthermore, the impact of IMU's cumulative errors on localization is intensified by the vast scale of such environments, while GPS signals are prone to instability owing to vegetation obstructions. These observations underscore the potential pitfalls of singular sensor deployment in compromising localization precision, and consequently, map accuracy. In light of this, the present study advances a novel SLAM (Simultaneous Localization and Mapping) approach that amalgamates the capabilities of LiDAR, IMU, and GPS. Through comparative analyses with single-sensor paradigms, our findings demonstrate that this integrative multi-sensor fusion strategy substantially enhances localization accuracy and facilitates the creation of high-fidelity maps.

关键词： Multisensory integration SLAM Point cloud map

来源：评论

学校读者我要写书评

暂无评论

A Robust Method With Adaptive Inpainting for Edge Detection of Single Silicon Crystal

引用

IEEE SENSORS JOURNAL 2023年第5期23卷 4500-4507页

作者： Zhang, Xinyu Liu, Ding Lin, Pengyi Ji, Ruirui Xian Univ Technol Natl & Local Joint Engn Res Ctr Crystal Growth Equ Xian 710048 Peoples R China Shaanxi Key Lab Complex Syst Control & Intelligent Xian 710048 Peoples R China

The improvement of the edge detection accuracy and integrity of the single silicon crystal and bright halo is the key to measuring the crystal diameter. This paper proposes an edge detection method with adaptive image inpainting. Firstly, according to the image characteristics, an evaluation function is designed to obtain the optimal order of fractional differential operators for the Canny method. Then, the initial edges of the single silicon crystal and bright halo are obtained with the Canny method based on these operators, and many details of the edges can be obtained. Meanwhile, an improved curvature driven diffusions (CDD) model is proposed for repairing the initial edge, which introduces the gradient information of edge into the CDD model to repair the edge breaks in the initial edges and enhance the edge integrity. Finally, a series of experiments are conducted to validate the effectiveness and performance of the proposed method on the images of practical engineering applications. The experimental results show that the proposed method performs significantly better than the existing methods in the edge detection accuracy and integrity of the single silicon crystal and highlight halo.

关键词： Image edge detection Crystals Silicon Differential operators Temperature measurement Maintenance engineering Crystal growth Single silicon crystal growth edge detection fractional differential operators edge inpainting curvature driven diffusions

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：