检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zheng, Kaikai Shi, Dawei Shi, Ling State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Kowloon Hong Kong

This work attempts to approximate a linear Gaussian system with a finite-state hidden Markov model (HMM), which is found useful in solving sophisticated event-based state estimation problems. An indirect modeling approach is developed, wherein a state space model (SSM) is firstly identified for a Gaussian system and the SSM is then used as an emulator for learning an HMM. In the proposed method, the training data for the HMM are obtained from the data generated by the SSM through building a quantization mapping. Parameter learning algorithms are designed to learn the parameters of the HMM, through exploiting the periodical structural characteristics of the HMM. The convergence and asymptotic properties of the proposed algorithms are analyzed. The HMM learned using the proposed algorithms is applied to event-triggered state estimation, and numerical results on model learning and state estimation demonstrate the validity of the proposed algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Towards the Future Data Market: Reward Optimization in Mobile Data Subsidization 3rd

Towards the Future Data Market: Reward Optimization in Mobil...

引用

3rd EAI International Conference on 6G for Future Wireless Networks, 6GN 2020

作者： Xiong, Zehui Zhao, Jun Kang, Jiawen Niyato, Dusit Deng, Ruilong Xie, Shengli Alibaba-NTU Joint Research Institute NTU Singapore Singapore School of Computer Science and Engineering NTU Singapore Singapore Energy Research Institute NTU Singapore Singapore College of Control Science and Engineering School of Cyber Science and Technology Zhejiang University Hangzhou China Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou China Joint International Research Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou China

ISBN: (纸本)9783030639402

Mobile data subsidization launched by network operators is a promising business model to provide some economic insights on the evolving direction of the 4G/5G and beyond mobile data market. The scheme allows content providers to partly subsidize mobile data consumption of mobile users in exchange for displaying a certain amount of advertisements. The users are motivated to access and consume more content without being concerned about overage charges, yielding higher revenue to the data subsidization ecosystem. For each content provider, how to provide appropriate data subsidization (reward) competing with others to earn more revenue and gain higher profit naturally becomes the key concern in such a ecosystem. In this paper, we adopt a hierarchical game approach to model the reward optimization process for the content providers. We formulate an Equilibrium Programs with Equilibrium Constraints (EPEC) problem to characterize the many-to-many interactions among multiple providers and multiple users. Considering the inherent high complexities of the EPEC problem, we propose to utilize the distributed Alternating Direction Method of Multipliers (ADMM) algorithm to obtain the optimum solutions with fast-convergence and decomposition properties of ADMM. © 2020, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Algorithm for Solving Resource Constrained Project Scheduling Problem with Transfer Time under Resource Bundle

A Heuristic Algorithm for Solving Resource Constrained Proje...

引用

第三十八届中国控制会议

作者： Junqi Cai Zhihong Peng School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

In this paper we investigate an extension of Resource Constrained Projected Scheduling Problem(RCPSP): the Resource Constrained Project Scheduling Problem with Transfer Time under Resource Bundle. For this complex problem, the use of a parallel scheduling scheme is proposed. Such scheme has been successfully applied to the RCPSP. Introducing transfer time and resource bundle into RCPSP causes two problems, one is the possibility of resources significantly exceed the need of a task, the other is cooperation among unfamiliar members from different team may increase the makespan of the project. In order to deal with the problem, two new concepts are developed: task-related resource weight and collaboration coefficient. Some discussion of such concepts is given of and use them for new heuristic framework we proposed. A computational test is performed and the results show that the new heuristic is very effective in finding better solutions within a very short time.

关键词： RCPSP heuristic algorithm resource bundle transfer time

来源：评论

学校读者我要写书评

暂无评论

Research on path planning of robot based on deep reinforcement learning

Research on path planning of robot based on deep reinforceme...

引用

第三十九届中国控制会议

作者： Feng Liu Chang Chen Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In this paper, to avoid the problem of local optimization and slow convergence in complex environment, a reinforcement learning algorithm is proposed to solve the problem. A robot path planning model is built and its feasibility is verified by simulation. In addition, this paper proposes a deep environment to neural network for robot camera to establish a deep reinforcement learning path planning model, and establishes a deep recursive Q-network（DRQN） and Deep Dueling Q-network（DDQN）respectively. In the comparison of the final simulation results, DRQN needs to consume more computation time, but can achieve better results with higher accuracy.

关键词： Reinforcement learning path planning robots deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved potential field method path planning based on genetic algorithm

Improved potential field method path planning based on genet...

引用

第三十九届中国控制会议

作者： Feng Liu Hualing He Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In order to overcome the problem of path planning failure in traditional potential field method, an improved potential field path planning method based on genetic algorithm is proposed in this paper. Firstly, for the problem of inaccessibility of the target, a factor method is added to the traditional gravity function to solve it;then the local minimum point problem of the traditional artificial potential field method is solved to ensure that the robot can reach the target point. At the same time, in order to get the optimal path, genetic algorithm is used to optimize the combined potential field function of gravity and repulsion, to find the lowest point of potential energy directly, so as to determine the step size and moving direction of the robot. Simulation is carried out to verify the effectiveness of the method.

关键词： Path planning artificial potential field gravitation function genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

arXiv

引用

arXiv 2021年

作者： Zhang, Yang Yu, Xin Lu, Xiaobo Liu, Ping The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Australian Institute of Artificial Intelligence University of Technology Sydney UltimoNSW2007 Australia The School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Singapore138634 Singapore

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8×) the occluded and tiny faces (16×16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network upsamples and inpaints occluded LR faces via a coarse-to-fine fashion, significantly reducing undesirable artifacts and blurriness. Specifically, we design a novel cross-modal attention module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutually beneficial manner. Extensive experiments show that our Pro-UIGAN attains visually pleasing completed HR faces, thus facilitating downstream tasks, i.e., face alignment, face parsing, face recognition as well as expression classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ESND: An embedding-based framework for signed network dismantling

引用

Expert systems with Applications 2025年 289卷

作者： Xie, Chenwei Liu, Chuang Li, Cong Zhan, Xiu-Xiu Li, Xiang Research Center for Complexity Sciences Hangzhou Normal University Hangzhou311121 China Department of Electronic Engineering School of Information Science and Technology Adaptive Networks and Control Lab Fudan University Shanghai200433 China College of Media and International Culture Zhejiang University Hangzhou310058 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China

Network dismantling aims to maximize the disintegration of a network by removing a specific set of nodes or edges and is applied to various tasks in various domains, such as cracking down on crime organizations, delaying the propagation of rumors, and blocking the transmission of viruses. Most of the current network dismantling methods are tailored for unsigned networks, which only consider the connection between nodes without evaluating the nature of the relationships, such as friendship/hostility, enhancing/repressing, and trust/distrust. We here propose an embedding-based algorithm, namely ESND, to solve the signed network dismantling problem. The algorithm generally iterates the following four steps, i.e., giant component detection, network embedding, node clustering, and removal node selection. To illustrate the efficacy and stability of ESND, we conduct extensive experiments on six signed network datasets as well as null models, and compare the performance of our method with baselines. Experimental results consistently show that the proposed ESND is superior to the baselines and displays stable performance with the change in the network structure. Additionally, we examine the impact of sign proportions on network robustness via ESND, observing that networks with a high ratio of negative edges are generally easier to dismantle than networks with high positive edges. © 2025 Elsevier Ltd

关键词： Network dismantling Node clustering Node embedding Signed network

来源：评论

学校读者我要写书评

暂无评论

Compound nonlinear energy sink with multiple motion types for absorbing energy from wide excitation ranges

引用

Journal of Sound and Vibration 2025年 617卷

作者： Jianen Chen Jiaqi Zhao Wei Zhang Min Sun Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin 300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin 300384 China School of Civil Engineering and Architecture Guangxi University Nanning 530004 China School of Science Tianjin Chengjian University Tianjin 300384 China

Nonlinear energy sink (NES) has garnered significant attention since its inception due to its notable broadband vibration reduction capability. However, the introduction of strong nonlinear characteristics by NESs complicates system responses, leading to a loss of effectiveness when the excitation force exceeds a specific threshold. Consequently, NESs have limited applicability in engineering because they are effective only within a constrained range of excitation amplitude. In this study, a compound NES (CNES) with multiple motion types is designed to extend the effective force range while maintaining broadband vibration reduction capability. The CNES is distinguished by its piecewise stiffness, collision mechanisms, and unique design of two-degree-of-freedom oscillators. The wide effective range of the CNES is demonstrated through slow linear sweep and fixed-frequency tests. The results indicate that the CNES effectively reduces vibrations in the primary oscillator (PO) with various resonant frequencies. Notably, the CNES achieves significant vibration reduction over a particularly wide range of excitation amplitude when controlling the PO with relatively high resonance frequencies (approximately 10.5 Hz and 19 Hz). However, a nonnegligible limitation of the CNES is its restricted effective range of excitation amplitude when the PO resonates at lower frequency (approximately 7 Hz). Moreover, five motion types of the CNES are identified and analyzed, with one motion type autonomously emerging in response to changes in excitation parameters, ensuring excellent vibration reduction performance across a wide excitation range. Finally, the performance of the CNES and a degraded single-degree-of-freedom CNES are compared to further demonstrate the extension effect of the multiple motion types on the effective range. The CNES can be used in scenarios where the parameters of protected systems and excitations vary widely, providing a thought to improve the NESs.

关键词： Compound nonlinearity Compound features Vibration reduction Vibration test Multiple motion types Effective range

来源：评论

学校读者我要写书评

暂无评论

A Fast Image/Video Dehazing Algorithm Based on Modified Atmospheric Veil

A Fast Image/Video Dehazing Algorithm Based on Modified Atmo...

引用

第三十八届中国控制会议

作者： Kang Liu Yongqiang Bai Zhenwei Gao School of Automation Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology

In this paper, we propose a fast image/video dehazing algorithm based on modified atmospheric veil. For a single image, the coarse atmospheric veil is quickly estimated by the minimum and maximum channels. We take the depth image estimated by the color attenuation prior as the guided image to refine the coarse atmospheric veil and use down sampling technique to speed up the process. In addition, a fast Fourier enhancement method is used to improve the high frequency details. Based on the image dehazing, we design an atmospheric light adjustment strategy and a transmission optimized framework for video dehazing, which can effectively reduce flickering artifacts. Experimental results demonstrate that the proposed algorithm can achieve a very good dehazing effect while keeping a comparable processing speed with state-of-the-art algorithms.

关键词： image/video dehazing atmospheric veil flickering artifacts optimized framework

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：