检索结果-内蒙古大学图书馆

Finite-time sliding-mode control for semi-Markov systems with delayed impulses

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Ren, Fangmin Wang, Xiaoping Li, Yangmin Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Hubei Key Laboratory of Braininspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China The Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong999077 Hong Kong

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Evolutionary Algorithm Based Graph Neural Network Architecture Search 11th

Multi-objective Evolutionary Algorithm Based Graph Neural Ne...

引用

11th International Symposium on Computational Intelligence and Industrial Applications, ISCIIA 2024

作者： He, Lianyi Liu, Xiaobo Xiang, Hongbo Wang, Guangjun School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of Geosciences Wuhan430074 China

ISBN: (纸本)9789819647521

Graph Neural Networks (GNN) has become a powerful graph data processing method, which has been widely used in node classification, link prediction, and other graph analysis tasks. Due to the diversity and complexity of graph structures and information propagation, as well as the handling of heterogeneous graphs, etc., the design of GNNs presents many challenges. The existing methods have high classification accuracy, but their structures are very complex. In this paper, a graph neural network architecture search framework named MO-GNN, which is based on multi-objective evolutionary algorithm is proposed. Furthermore, a weight sharing strategy MO-GNN-WS is proposed to reduce the resource consumption caused by weight training of different architectures. To verify the performance of the proposed algorithm, experiments on four popular graph datasets are used for transduction and induction tasks. The experimental results show that the MO-GNN-WS algorithm outperforms the most advanced neural network architecture search methods in terms of classification accuracy and resource consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data Sharing

来源：评论

学校读者我要写书评

暂无评论

A Facial Expression Emotion Recognition Based Human-robot Interaction System

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 668-676页

作者： Zhentao Liu Min Wu Weihua Cao Luefeng Chen Jianping Xu Ri Zhang Mengtian Zhou Junwei Mao School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems IEEE

A facial expression emotion recognition based human-robot interaction(FEER-HRI) system is proposed, for which a four-layer system framework is designed. The FEERHRI system enables the robots not only to recognize human emotions, but also to generate facial expression for adapting to human emotions. A facial emotion recognition method based on2D-Gabor, uniform local binary pattern(LBP) operator, and multiclass extreme learning machine(ELM) classifier is presented,which is applied to real-time facial expression recognition for robots. Facial expressions of robots are represented by simple cartoon symbols and displayed by a LED screen equipped in the robots, which can be easily understood by human. Four scenarios,i.e., guiding, entertainment, home service and scene simulation are performed in the human-robot interaction experiment, in which smooth communication is realized by facial expression recognition of humans and facial expression generation of robots within 2 seconds. As a few prospective applications, the FEERHRI system can be applied in home service, smart home, safe driving, and so on.

关键词： Emotion generation facial expression emotion recognition(FEER) human-robot interaction(HRI) system design

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning-based decoder calibration for intracortical brain-machine interfaces

引用

Computers in Biology and Medicine 2025年第Pt A期192卷 110231-110231页

作者： Li, Xiao Dong, Xianxin Wang, Jun Mao, Haodong Tu, Xikai Li, Wei He, Jiping Li, Qiang Zhang, Peng Hubei Key Laboratory of Modern Manufacturing Quantity Engineering School of Mechanical Engineering Hubei University of Technology Wuhan430068 China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Science and Technology Hubei Wuhan China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan China Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

Intracortical brain-machine interfaces (iBMIs) aim to establish a communication path between the brain and external devices. However, in the daily use of iBMIs, the non-stationarity of recorded neural signals necessitates frequent recalibration of the iBMI decoder to maintain decoding performance, which requires collecting and labeling a large amount of new data. To address this challenge and minimize the time needed for decoder recalibration, we proposed an active learning domain adversarial neural network (AL-DANN). This model leveraged a substantial volume of historical data alongside a small amount of current data (four samples per category) to calibrate the decoder. By incorporating domain adversarial and active learning strategies, the model effectively transferred knowledge from historical data to new data, reducing the demand for new samples. We validated the proposed method using neural signals recorded from three monkeys performing different movements in a classification task or a regression task. The results showed that the AL-DANN outperformed existing state-of-the-art methods. Impressively, it required only four new samples per category for decoder recalibration, leading to a recalibration time reduction of over 80 %. To our knowledge, this is the first study to incorporate deep transfer learning into iBMI decoder calibration, highlighting the significant potential of applying deep learning technologies in iBMIs. © 2025

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Extended Dissipativity Analysis and Synthesis for Discrete-Time Lur'e Delayed systems: Matrix-Separation-Based Lyapunov Functional Method

引用

IET control Theory and Applications 2025年第1期19卷

作者： Xie, Ke-You Lee, Sangmoon Zhang, Chuan-Ke Jin, Li Liu, Yajuan He, Yong School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Electronic and Electrical Engineering Kyungpook National University Daegu Korea Republic of School of Control and Computer Engineering North China Electric Power University Beijing China

This paper develops a matrix-separation-based Lyapunov functional method to study the extended dissipativity analysis and synthesis issue of discrete-time Lur'e-type delayed systems. The advanced idea of matrix-separation is reflected in Lyapunov functional candidates and estimates summation terms as precisely as feasible. First, we introduce a novel summation inequality based on the matrix-separation method to provide a bound for the augmented summation that involves common state variables. An improved delay-product-type Lyapunov functional is devised by extending non-positive definite summations as separate subblocks of the state-augmented summation. Then, by using the matrix injection method to handle the cubic delay term in the functional forward difference, a delay-variation-dependent stability criterion and an extended dissipativity criterion are developed under the matrix-separation-based method. Subsequently, sufficient conditions for the control design of Lur'e-type systems are derived. Finally, the effectiveness and superiority of the proposed method are verified through its application to Chua's circuits, neural networks, and a stochastic numerical example. © 2025 The Author(s). IET control Theory & Applications published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.

关键词： Stability criteria

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Distribution Network Robots with Adaptive Simulated Annealing-Enhanced Artificial Potential Field Method

Path Planning for Distribution Network Robots with Adaptive ...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Baichao Zhang Xin Chen Jinge Chen Jinbin Li Xiaokai Wang Xu Jian School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan P. R. China Hubei Fangyuan Dongli Electric Power Science Research Co. Ltd Wuhan P. R. China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

In this paper, we propose a hybrid algorithm that combines an improved Artificial Potential Field (APF) method with the Simulated Annealing (SA) algorithm for path planning of an electric power operation robot manipulator in complex distribution grid environments. To address the unreachable target issue inherent in traditional APF, we introduce a distance regulation factor to optimize the repulsive function. This modification allows the manipulator to smoothly approach the target point as it nears, while the repulsion from obstacles gradually decreases. Additionally, to overcome the limitations of the traditional SA algorithm, such as its tendency to get trapped in local minimum solutions and its inefficiency in complex environments, we propose an adaptive temperature rise strategy. This strategy increases the temperature, enhancing the probability of escaping local optimal solutions. When the APF algorithm becomes trapped in a local optimum, the improved SA algorithm is applied to escape the local minimum. Once the local optimum is avoided, the algorithm switches back to APF to continue the path planning process. Simulation results demonstrate that the proposed improved APF-SA algorithm adapts effectively to various complex environments, achieving shorter planning times and higher success rates compared to traditional APF and SA algorithms. It successfully resolves the unreachable target and local minimum problems associated with APF. Finally, the feasibility of the proposed APF-SA fusion algorithm is validated through experiments conducted on an electric power operation robot experimental platform for distribution grid applications.

关键词： Electric potential Adaptation models Force Distribution networks Simulated annealing Manipulators Path planning Planning Collision avoidance Robots

来源：评论

学校读者我要写书评

暂无评论

Geological Reservoir Modeling Method Based on Conditional Progressive Growing of GANs

Geological Reservoir Modeling Method Based on Conditional Pr...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Huaijin Huang Xiaobo Liu Yiting Zheng Dongsen Zhang Hongbo Xiang School of Automation China University of Geosciences Wuhan China Hubei Key Lab of Advanced Control and Intelligent Automation China University of Geosciences Wuhan China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of Geosciences Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

Accurately characterizing geological patterns in reservoir modeling remains a significant challenge due to their inherent spatial heterogeneity and complexity. This paper proposes a Conditional Progressive Growing of GANs (CPGAN), which improves progressive growing of GANs (PGGAN) and Conditional GAN (CGAN). In this approach, the generator architecture of PGGAN is revised to incorporate a conditioning data input pipeline, allowing the generator to learn the features of geological patterns and conditioning data across different scales. In addition, a loss function derived from the conditioning data is introduced. This function defines the distance between the generated reservoir model and the conditioning data, guiding the generator in learning how the conditioning data constrain geological patterns. Experimental results indicate that CPGAN can generate high-quality reservoir models that comply with geological patterns and meet the constraints of the conditioning data.

关键词： Training Solid modeling Three-dimensional displays Geology Pipelines Reservoirs Generative adversarial networks Generators Data models Ice

来源：评论

学校读者我要写书评

暂无评论

A Low-Cost Enhanced Heterogeneous Barrier Construction Method for Multi-Target Intrusion Monitoring

引用

IEEE Sensors Journal 2025年

作者： Ye, Jing Xiong, Yonghua Dong, Haobin Yu, Anjun She, Jinhua China University of Geosciences School of Automation Wuhan 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan 430074 China Jiangxi Ganyue Expressway Company Ltd Nanchang 330200 China Tokyo University of Technology School of Engineering Tokyo 192-0982 Japan

In multi-target intrusion monitoring, heterogeneous nodes may overlap due to different sensing ranges. Additionally, excessively long barriers will increase the cost of barriers and reduce the number of barriers. To address these issues, this article proposes a distributed method for constructing weighted heterogeneous barriers using depth-first search and learning automata (WHBDLA). It designs a dynamically weighted coverage graph based on the non-overlap rate and horizontal displacement. The proposed method considers multiple heterogeneous properties. It uses several intrusion targets to identify the boundaries of local sub-regions while avoiding the cost increase and quantity decrease caused by long barriers. WHBDLA combines the advantages of depth-first search and the reinforcement learning mechanism to adaptively construct heterogeneous barriers in sub-regions with unknown faults. The algorithm initially searches for potential barrier path nodes and then activates nodes with sufficient energy and high weights. Finally, it monitors and repairs the barriers. Comparative experiments and analyses indicate that the proposed method increases the number of barriers, reduces node costs, and decreases running time. © 2001-2012 IEEE.

关键词： Barrier coverage heterogeneous probabilistic sensing model multi-target intrusion monitoring search and learning automata (LA) sub-region

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking for Directional Drilling in Underground Coal Mine Using Robust Model Predictive control

Trajectory Tracking for Directional Drilling in Underground ...

引用

IEEE International Conference on Industrial Technology (ICIT)

作者： Jiajun Wu Chengda Lu Hao Li Hongchao Wei Min Wu School of Future Technology China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan China School of Automation China University of Geosciences Wuhan China Xi'an Research Institute Co. Ltd. China Coal Technology and Engineering Group Xi'an China China Coal Research Institute Beijing China

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

This paper studies the problem of trajectory tracking control for directional drilling in underground coal mine by devising a robust model predictive control method. First, a directional drilling trajectory extension model is obtained by the linearization of a drilling tool kinematic model through the Taylor series expansion in the borehole depth domain. Then, in view of the influence of the uncertainty of the drilling tool slope and external interference, a robust model predictive control method is introduced in the form of an optimal control problem. A sufficient condition is obtained to calculate the corresponding controller gain matrix on the premise of satisfying the stability of the closedloop control system and the $H_{\infty}$ performance index. At last, the effectiveness of our method is illustrated through simulation analysis. Compared with model predictive control, robust model predictive control directly incorporates the uncertainty of the drilling tool slope and external interference into the control design, enabling it to better adapt to the complex and variable underground coal mine environment.

关键词： Drilling Uncertainty Trajectory tracking Stability criteria Predictive models Taylor series Coal mining Trajectory Thermal stability Predictive control

来源：评论

学校读者我要写书评

暂无评论

Adapting Human Mesh Recovery with Vision-Language Feedback

arXiv

引用

arXiv 2025年

作者： Xu, Chongyang Huang, Buzhen Zhang, Chengfang Feng, Ziliang Wang, Yangang College of Computer Science Sichuan University Chengdu610065 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education The School of Automation Southeast University Nanjing210096 China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou646000 China

Human mesh recovery can be approached using either regression-based or optimization-based methods. Regression models achieve high pose accuracy but struggle with model-to-image alignment due to the lack of explicit 2D-3D correspondences. In contrast, optimization-based methods align 3D models to 2D observations but are prone to local minima and depth ambiguity. In this work, we leverage large vision-language models (VLMs) to generate interactive body part descriptions, which serve as implicit constraints to enhance 3D perception and limit the optimization space. Specifically, we formulate monocular human mesh recovery as a distribution adaptation task by integrating both 2D observations and language descriptions. To bridge the gap between text and 3D pose signals, we first train a text encoder and a pose VQ-VAE, aligning texts to body poses in a shared latent space using contrastive learning. Subsequently, we employ a diffusion-based framework to refine the initial parameters guided by gradients derived from both 2D observations and text descriptions. Finally, the model can produce poses with accurate 3D perception and image consistency. Experimental results on multiple benchmarks validate its effectiveness. The code will be made publicly available. © 2025, CC BY.

关键词： Mesh generation

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：