检索结果-内蒙古大学图书馆

An Algebraic Method to Stabilize Large-Scale Boolean Networks via Pinning Control

IEEE Transactions on Network Science and engineering 2025年

作者： Liu, Jiayang Liu, Yang Jiang, Haijun Abdel-Aty, Mahmoud Zhejiang Normal University School of Mathematical Sciences Jinhua321004 China Zhejiang Normal University Hangzhou School of Automation Hangzhou311231 China Yili Normal University School of Mathematics and Statistics Yining835000 China Ahlia University Graduate Studies and Research Manama10878 Bahrain Abu Dhabi University Electrical and Computer Engineering Department Zayed City MZ39 United Arab Emirates Sohag University Mathematics Department Faculty of Science Sohag82524 Egypt

As a discrete-time system, the dynamics of each gene node of Boolean networks (BNs) is determined by logical functions. This article aims to stabilize BNs globally through distributed pinning control. According to the existing literature, the state transition matrix-based pinning control strategy always suffers from high time complexity. The proposed approach, while likewise matrix-based, replaces the state transition matrix in favor of structure matrices based on the logical functions of each node and develops four computationally effective phases to solve the minimum set of controlled nodes and the corresponding pinning controllers, reducing the time complexity to O(2ξ), where ξ is a value determined by the specific network and the target state. The primary contribution is to provide a new method that eliminates time complexity as a barrier to matrix-based pinning control strategy by determining the index set of key nodes, particularly for sparse biological networks while preserving the benefits of matrix-based strategies. Finally, to demonstrate the effectiveness of the control method, gene networks with different sizes are discussed as simulations. © 2013 IEEE.

关键词： Discrete time control systems

来源：评论

学校读者我要写书评

暂无评论

Stereo Matching for Face Images Based on Feature Points

引用

电子学报(英文版) 2010年第2期19卷 241-244页

作者： WANG Yinghui XIAO Bing WANG Qiongfang Faculty of Computer Science and Engineering Xi'an University of Technology Xi'an China Department of Computer Science Shaanxi Normal University Xi'an China Faculty of of Automation and Information Engineering Xi'an University of Technology Xi'an China

Stereo matching is the key of reconstructing 3D face model from 2D face images and Barnard's algorithm is one of the classical stereo matching algorithms based on feature points. In order to enhance the stability of extracting feature points, reduce computational complexity and minimize the effect of subjective factors, in this paper, Barnard's algorithm of edge point matching was improved from two aspects: edge point sets of left and right face images were extracted with dyadic wavelet transform, rather than comparing gray values of adjacent pixels;on the other hand, edge points in binocular stereo face images were matched under epipolar constraint in parallel binocular stereo matching. Experimental results demonstrate that stability and efficiency of stereo matching algorithm are both improved.

关键词：立体匹配算法人脸图像特征点点匹配算法配基二进小波变换计算复杂度人脸模型

来源：评论

学校读者我要写书评

暂无评论

Adaptive outer synchronization between two delayed oscillator networks with cross couplings

引用

Science China(Information Sciences) 2020年第10期63卷 267-269页

作者： Jianbao ZHANG Ancai ZHANG Jinde CAO Jianlong QIU Fuad E.ALSAADI School of Automation Southeast University School of Information Science and Engineering Linyi University Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz University

Dear editor,Chaos synchronization is a typical kind of collective behaviors induced by external control or mutual couplings between chaotic nodes [1].During the past decades,increasing interest has been devoted to study the interplay between network topology and chaos synchronization [1,2].Many types of synchronization phenomena have been proposed such as complete synchronization,cluster synchronization [3],and outer synchroni-

关键词： Adaptive control Complex networks Lyapunov method Outer synchronization Cross coupling

来源：评论

学校读者我要写书评

暂无评论

Dynamic Legged Ball Manipulation on Rugged Terrains with Hierarchical Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhu, Dongjie Yang, Zhuo Wu, Tianhang Ge, Luzhou Li, Xuesong Liu, Qi Li, Xiang Department of Automation Tsinghua University China School of Computer Science Beijing Institute of Technology China Faculty of Robot Science and Engineering Northeastern University United States

Advancing the dynamic loco-manipulation capabilities of quadruped robots in complex terrains is crucial for performing diverse tasks. Specifically, dynamic ball manipulation in rugged environments presents two key challenges. The first is coordinating distinct motion modalities to integrate terrain traversal and ball control seamlessly. The second is overcoming sparse rewards in end-to-end deep reinforcement learning, which impedes efficient policy convergence. To address these challenges, we propose a hierarchical reinforcement learning framework. A high-level policy, informed by proprioceptive data and ball position, adaptively switches between pretrained low-level skills such as ball dribbling and rough terrain navigation. We further propose Dynamic Skill-Focused Policy Optimization to suppress gradients from inactive skills and enhance critical skill learning. Both simulation and real-world experiments validate that our methods outperform baseline approaches in dynamic ball manipulation across rugged terrains, highlighting its effectiveness in challenging environments. Videos are on our website: ***. Copyright © 2025, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Using neural networks for time series prediction 6

Using neural networks for time series prediction

引用

6th International Conference on Optimization of Electrical and Electronic Equipments, OPTIM 1998

作者： Cimpeanu, Toma-Dorin Faculty of Automation Computer Engineering and Electronics University of Craiova Romania

ISBN: (纸本)9739851126

In this paper we show a method of time series prediction with neural networks. In the first section we present the main elements of the problem and two standard methods that can be used for predictions. In the second section we expose a summary of the back-propagation algorithm. This method is used to train a multi-layer perceptron as it is shown in that section. In the last part we present a way to improve the quality of the prediction. © 1998 Institute of Electrical and Electronics Engineers Inc. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Decomposition of a fuzzy controller based on the inference break-up method

引用

Intelligent Data Analysis 1999年第2期3卷 127-137页

作者： Golob, Marjan Laboratory for Process Automation University of Maribor Faculty of Electrical Engineering and Computer Science Smetanova 17 2000 Maribor Slovenia

A concept called the decomposition of multivariable control rules is presented. Fuzzy control is the application of the compositional rule of inference and it is shown how the inference of the rule base with complex rules can be reduced to the inference of a number of rule bases with simple rules. A fuzzy logic based controller is applied to a simple magnetic suspension system. The controller has proportional, integral and derivative separate parts which are tuned independently. This means that all parts have their own rule bases. By testing it was found that the fuzzy PID controller gives better performance over a typical operational range then a traditional linear PID controller. The magnetic suspension system and the contact-less optical position measurement system have been developed and applied for the comparative analysis of the real-time conventional PID control and the fuzzy control. © 1999 Elsevier Science B.V. All rights reserved.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

SVD-KD: SVD-based hidden layer feature extraction for Knowledge distillation

引用

Pattern Recognition 2025年 167卷

作者： Zhang, Jianhua Gao, Yi Zhou, Mian Liu, Ruyu Cheng, Xu Nikolić, Saša V. Chen, Shengyong School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China College of Artificial Intelligence and Automation Hohai University Changzhou213000 China Xi'an JiaoTong-Livepool University Suzhou China School of Information Science and Technology Hangzhou Normal University Hangzhou311121 China Department of Technology Management and Economics Technical University of Denmark Lyngby2800 Denmark Department of Electronics Faculty of Electronic Engineering University of Nis Nis Serbia

Recent advancement of Knowledge distillation (KD) is to extract and transfer middle-layer knowledge of teacher models to student models, which is better than original KDs which only transfer the last layer of knowledge. However, the middle-layer knowledge commonly appears as a high-dimensional tensor, which is more difficult to transfer than the one-dimensional knowledge in the last layer. Moreover, when there are significant differences between the teachers and students in terms of model parameter capabilities and model structures, the middle layers of teacher and student models differ in dimensionality and structure, which further increase the learning difficulty for student models. To solve these problems, we propose a novel knowledge extraction module to transform the high-dimensional tensor tensor-based knowledge in middle layers to one-dimensional knowledge based on singular value decomposition. Thus, the knowledge at the middle layers of teacher models can be effectively extracted and simplified, and extremely facilitate the learning of student models, even though the structure and parameter capacity between the teacher network and the student network are very different. To help the students learn the knowledge from the middle layers of teachers as accurately as possible, we also propose a novel loss function that can constrain values of the one-dimension knowledge learned by the student model to be as close as possible to that extracted from the teacher model, thus improving the learning efficiency of the student model. We have conducted extensive experiments on three major datasets (CIFAR-10, CIFAR-100, and ImageNet 1K), and the results of our method demonstrate superior performance by comparing with the state-of-the-art methods. © 2025

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial for Special Issue on Human-centered Intelligent Robots:Issues and Challenges

引用

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 599-601页

作者： Zhijun Li C.L.Philip Chen Wei He IEEE College of Automation Science and Engineering South China University of Technology Department of Computer and Information Science Faculty of Science and Technology University of Macao School of Automation and Electrical Engineering University of Science and Technology Beijing

The special issue aims to address a broad spectrum of topics ranging from human-centered intelligent robots acting as a servant,secretary,or companion to intelligent robotic *** special issue publishes original papers of innovative ideas and concepts,new discoveries,and novel applications and business models relevant to the field of human-centered intelligent *** this special issue,modeling,intelligent control,

关键词： In Guest Editorial for Special Issue on Human-centered Intelligent Robots:Issues and Challenges

来源：评论

学校读者我要写书评

暂无评论

A Single-legged Robot Inspired by the Jumping Mechanism of Click Beetles and Its Hopping Dynamics Analysis

引用

Journal of Bionic engineering 2020年第6期17卷 1109-1125页

作者： Gang Chen Jiajun Tu Xiaocong Ti Huosheng Hu Faculty of Mechanical Engineering and Automation Zhejiang Sci-Tech UniversityHangzhou 310018China School of Computer Science and Electronic Engineering University of EssexColchester C043SQUK

The click beetle can jump up with a hinge when it is on the dorsal *** jumping mechanism is simple and suitable as an inspiration for designing a simple,small,and reliable hopping *** report a single-legged robot inspired by the jumping mechanism of click *** is 85 mm high,60 mm long,and 41 mm wide,and weighs about 49 *** robot has good hopping performance that the hopping height is about 4 times-4.3 times of its body *** is capable for rescue missions that require to enter enclosed spaces through cracks and narrow *** addition,hopping dynamics of the robot is important to understand its jumping mechanism and improve the robot’s hopping *** existing dynamic study does not complete the analysis including all stages in the hopping which are pre-hopping,take-off,and *** propose the decomposition method to study dynamics of the three stages separately,and synthesize them with related *** dynamic synthesis of multi-motion states in a hopping cycle of the single-legged hopping robot is *** hopping performance and dynamic synthesis theory of the robot are verified by simulations and *** study helps lay the foundation for design and hopping control of simple hopping robot systems.

关键词： single-legged hopping robots hopping cycle dynamics synthesis multi-motion states jumping mechanism imitaion of click beetles

来源：评论

学校读者我要写书评

暂无评论

Swaying Tree Simulation by Slicing Partition

引用

Chinese Journal of Electronics 2020年第5期29卷 826-832页

作者： TANG Jing WANG Yinghui WANG Ningna NING Xiaojuan LYU Ke SUI Liansheng SHI Zhenghao Faculty of Automation and Information Engineering Xi'an University of Technology School of Artificial Intelligence and Computer Science Jiangnan University The University of Texas at Dallas School of Engineering Sciences University of Chinese Academy of Sciences

The key of swaying tree simulation is to capture the essence of the interaction between wind and tree, which has not received much attention from scholars. In this paper, we present a method for simulating swaying tree based on slicing partition. The tree is divided into multiple "slices", and then jointly moved to simulate the tree swaying in wind. By slicing partition,the motion of any slice is independent of the others concurrently, which provides a parallel spatial topology for real-time calculation. Moreover, based on the fact that the wind will blow to a tree partly rather than the whole, partial swayings of the tree are also simulated. The experimental results show the correctness and effectiveness of our method.

关键词： Slicing Damping slicing partition geophysics computing swaying tree simulation Tree swaying wind vegetation

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：