检索结果-内蒙古大学图书馆

TechRxiv 2023年

作者： Liu, Chenyang Zhao, Rui Chen, Jianqi Qi, Zipeng Zou, Zhengxia Shi, Zhenwei Rhe Image Processing Center School of Astronautics The Beijing Key Laboratory of Digital Media The State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China The Shanghai Artificial Intelligence Laboratory Shanghai200232 China The Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China

Remote sensing image change captioning (RSICC) is a novel task that aims to describe the differences between bitemporal images by natural language. Previous methods ignore a significant specificity of the task: the difficulty of RSICC is different for unchanged and changed image pairs. They process the unchanged and changed image pairs in a coupled way, which usually causes confusion for change captioning. In this paper, we decouple the task into two issues to ease it: whether and what changes have occurred. An image-level classifier performs binary classification to address the first issue. A feature-level encoder contributes to extracting discriminative features to help the caption generation module address the second issue. Besides, for caption generation, we utilize prompt learning to introduce pre-trained large language models (LLMs) into the RSICC task. A multi-prompt learning strategy is proposed to generate a set of unified prompts and a class-specific prompt conditioned on the image-level classifier’s results. The strategy can prompt a pre-trained LLM to know whether changes exist and generate captions. Finally, the multiple prompts and the visual features of the feature-level encoder are fed into a frozen LLM for language generation. Compared with previous methods, our method can leverage the powerful abilities of the pre-trained LLM in language to generate plausible captions, which is free of training. Extensive experiments show that our method is effective and achieves state-of-the-art performance. Besides, an additional experiment demonstrates that our decoupling paradigm is more promising than the previous coupled paradigm for the RSICC task. We will make our codebase publicly available to facilitate future research at https://***/Chen-Yang-Liu/PromptCC © 2023, CC BY-NC-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Coalitional predictive control: Consensus-based coalition forming with robust regulation

arXiv

引用

arXiv 2020年

作者： Baldivieso-Monasterios, Pablo R. Trodden, Paul A. Department of Automatic Control and Systems Engineering University of Sheffield Mappin Street SheffieldS1 3JD United Kingdom

This paper is concerned with the problem of controlling a system of constrained dynamic subsystems in a way that balances the performance degradation of decentralized control with the practical cost of centralized control. We propose a coalitional control scheme in which controllers of subsystems may, as the need arises, group together into coalitions and operate as a single entity. The scheme employs a robust form of distributed model predictive control for which recursive feasibility and stability are guaranteed, yet-uniquely-the reliance on robust invariant sets is merely implicit, thus enabling applicability to higher-order systems. The robust control algorithm is combined with an algorithm for coalition forming based on consensus theory and potential games;we establish conditions under which controllers reach a consensus on the sets of coalitions. The recursive feasibility and closed-loop stability of the overall time-varying coalitional control scheme are established under a sufficient dwell time, the existence of which is guaranteed. Copyright © 2020, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Decentralized control barrier functions for coupled multi-agent systems under signal temporal logic tasks

arXiv

引用

arXiv 2020年

作者： Lindemann, Lars Dimarogonas, Dimos V. Department of Automatic Control School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

We study the problem of controlling multi-agent systems under a set of signal temporal logic tasks. Signal temporal logic is a formalism that is used to express time and space constraints for dynamical systems. Recent methods to solve the control synthesis problem for single-agent systems under signal temporal logic tasks are, however, subject to a high computational complexity. Methods for multi-agent systems scale at least linearly with the number of agents and induce even higher computational burdens. We propose a computationally-efficient control strategy to solve the multi-agent control synthesis problem that results in a robust satisfaction of a set of signal temporal logic tasks. In particular, a decentralized feedback control law is proposed that is based on time-varying control barrier functions. The obtained control law is discontinuous and formal guarantees are provided by nonsmooth analysis. Simulations show the efficacy of the presented method. Copyright © 2020, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Observer Design for Chemical Tubular Reactors Based on System Linearization 18

Observer Design for Chemical Tubular Reactors Based on Syste...

引用

18th European control Conference, ECC 2020

作者： Yupanqui Tello, Ivan Francisco Coutinho, Daniel Winkin, Joseph Vande Wouver, Alain Federal University of Santa Catarina Department of Automation and Systems R. Delfino Conti - Trindade Florianpolis-SC88040-900 Brazil University of Namur NaXys and Department of Mathematics 8 Rempart de la Vierge NamurB-5000 Belgium University of Mons Department of Automatic Control 31 Boulevard Dolez Mons7000 Belgium

ISBN: (纸本)9783907144015

This paper presents an observer design technique for a class or nonlinear coupled parabolic PDEs using the infinite dimensional approach in Hilbert spaces. In particular, the linear approximate model incorporating the spatially varying coefficients of the set of PDEs is used for designing a Luenberger-like observer in order to achieve exponential convergence of the estimation error dynamics. The proposed observer is applied to a chemical tubular reactor considering only boundary measurements. The observer performance is assessed via numerical simulations. © 2020 EUCA.

关键词： Distributed parameter control systems

来源：评论

学校读者我要写书评

暂无评论

Aircraft protection for complex threat platforms through integrated EWOS application 18

Aircraft protection for complex threat platforms through int...

引用

18th International Conference on Aerospace Sciences and Aviation technology, ASAT 2019

作者： Rudd-Orthner, R. Mihaylova, L.S. Department of Automatic Control and Systems Engineering University of Sheffield Mappin Street SheffieldS1 3JD United Kingdom

The advancement of threats is focusing commanders to consider how to combat these complex threats throughout the kill chain including prior to launch and Anti-Access Area Denial (A2AD). To match this technology race, modern platforms have been designed with integrated command and control systems and automated Defensive Aids Suites built on modular open system architectures incorporating less diverse but more complex software driven systems. The successful operation of these combat systems is reliant upon the availability of accurate, configured, harmonised and "time sensitive" mission data without which the systems may be ineffective. This paper explores the use of threat analysis diagramming techniques, and open architectures tightly integrated with a EWOS life-cycle;to develop countermeasures with a measured response beyond the traditional self-protection kill chain stages of self-protection. It introduces how threat analysis prepares understanding for simulation and how a countermeasure description language can be used to store and exchange countermeasures in a structured form. This level of intelligence data support and analysis coordinated and synchronised across multiple platforms thereby facilitating the complexities of force protection higher up the kill chain into an onion of protection mapped to a Venn diagram of countermeasure types (design intentions) with differing data needs. © 2019 Published under licence by IOP Publishing Ltd.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Development of soft tactile sensor for force measurement and position detection

arXiv

引用

arXiv 2021年

作者： Yang, Wu-Te Kuang, Zhian Wang, Changhao Tomizuka, Masayoshi Department of Mechanical Engineering University of California Berkeley 2103 Etcheverry Hall CA94720 United States Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150001 China

As more robots are implemented for contact-rich tasks, tactile sensors are in increasing demand. For many circumstances, the contact is required to be compliant, and soft sensors are in need. This paper introduces a novelly designed soft sensor that can simultaneously estimate the contact force and contact location. Inspired by humans' skin, which contains multi-layers of receptors, the designed tactile sensor has a dual-layer structure. The first layer is made of a conductive fabric that is responsible for sensing the contact force. The second layer is composed of four small conductive rubbers that can detect the contact location. Signals from the two layers are firstly processed by Wheatstone bridges and amplifier circuits so that the measurement noises are eliminated, and the sensitivity is improved. An Arduino chip is used for processing the signal and analyzing the data. The contact force can be obtained by a pre-trained model that maps from the voltage to force, and the contact location is estimated by the voltage signal from the conductive rubbers in the second layer. In addition, filtering methods are applied to eliminate the estimation noise. Finally, experiments are provided to show the accuracy and robustness of the sensor. Videos can be found in the link below3. Copyright © 2021, The Authors. All rights reserved.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Flight Phase Recognition with Flight Data Clustering based on GMM

Unsupervised Flight Phase Recognition with Flight Data Clust...

引用

IEEE Instrumentation and Measurement technology Conference

作者： Datong Liu Ning Xiao Yujie Zhang Xiyuan Peng School of Electronics and information Engineering Harbin Institute of Technology Harbin China Department of Automatic Test and Control Harbin Institute of Technology Harbin China

ISBN: (数字)9781728144603

ISBN: (纸本)9781728144610

Currently, with the rapid development of the aviation industry, researchers are paying more attention to the improvement of aviation safety. Aviation safety mainly includes flight safety, aviation ground safety, and air defense safety. In terms of flight safety, the analysis of large amounts of flight data has gradually become a useful tool for timely detection of potential dangers at various stages of flight. As a result, flight data analysis has been one of the hot topics in aviation. However, due to the complexity of the aircraft operating conditions throughout the aircraft, if the data is analyzed at the entire flight phase, it is very difficult and time consuming to identify the problematic fight phase. Therefore, flight phase recognition for civil aircraft is implemented in this study. A flight phase recognition method based on Gaussian Mixture Model (GMM) is proposed in this work, which is the important foundation for timely detecting the abnormal event and improving the system safety and reliability. Firstly, the FDR data are preprocessed by spline interpolation and normalization, and then a GMM-based flight phase clustering is realized. In addition, a set of evaluation method is developed to evaluate the quality of flight phase recognition result. Finally, the effectiveness of the method is verified by using real FDR data from NASA's open database.

关键词： flight data flight phase recognition Gaussian mixture model flight safety aircraft flight data flight safety Aircraft flight Gm(m) Mixture models Civil Aircraft Phase safety system

来源：评论

学校读者我要写书评

暂无评论

A polynomial-time algorithm for unconstrained binary quadratic optimization

arXiv

引用

arXiv 2020年

作者： Mulero-Martínez, Juan Ignacio Department of Automatic Control Electrical Engineering and Electronic Technology Technical University of Cartagena Campus Muralla del Mar 30203 Spain

In this paper, an exact algorithm in polynomial time is developed to solve unrestricted binary quadratic programs. The computational complexity is O (n15/2), although very conservative, it is sufficient to prove that this minimization problem is in the complexity class P. The implementation aspects are also described in detail with a special emphasis on the transformation of the quadratic program into a linear program that can be solved in polynomial time. The algorithm was implemented in MATLAB and checked by generating five million matrices of arbitrary dimensions up to 30 with random entries in the range [−50, 50]. All the experiments carried out have revealed that the method works correctly. Copyright © 2020, The Authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning with quantum-inspired experience replay

arXiv

引用

arXiv 2021年

作者： Wei, Qing Ma, Hailan Chen, Chunlin Dong, Daoyi The Department of Control and Systems Engineering School of Management and Engineering Nanjing University Nanjing210093 China The School of Engineering and Information Technology University of New South Wales CanberraACT2600 Australia

In this paper, a novel training paradigm inspired by quantum computation is proposed for deep reinforcement learning (DRL) with experience replay. In contrast to traditional experience replay mechanism in DRL, the proposed deep reinforcement learning with quantum-inspired experience replay (DRL-QER) adaptively chooses experiences from the replay buffer according to the complexity and the replayed times of each experience (also called transition), to achieve a balance between exploration and exploitation. In DRL-QER, transitions are first formulated in quantum representations, and then the preparation operation and the depreciation operation are performed on the transitions. In this progress, the preparation operation reflects the relationship between the temporal difference errors (TD-errors) and the importance of the experiences, while the depreciation operation is taken into account to ensure the diversity of the transitions. The experimental results on Atari 2600 games show that DRL-QER outperforms state-of-the-art algorithms such as DRL-PER and DCRL on most of these games with improved training efficiency, and is also applicable to such memory-based DRL approaches as double network and dueling network. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

引用

China CDC weekly 2022年第40期4卷 885-889,I0002-I0005页

作者： Yuan Bai Mingda Xu Caifen Liu Mingwang Shen Lin Wang Linwei Tian Suoyi Tan Lei Zhang Petter Holme Xin Lu Eric H.Y.Lau Benjamin J.Cowling Zhanwei Du WHO Collaborating Centre for Infectious Disease Epidemiology and Control School of Public HealthLi Ka Shing Faculty of MedicineThe University of Hong KongHong Kong Special Administrative RegionChina Laboratory of Data Discovery for Health Limited(D24H) Hong Kong Science ParkHong Kong Special Administrative RegionChina China-Australia Joint Research Center for Infectious Diseases School of Public HealthXi’an Jiaotong University Health Science CenterXi’an CityShaanxi ProvinceChina Department of Genetics University of CambridgeCambridge CB23EHUK College of Systems Engineering National University of Defense TechnologyChangsha CityHunan ProvinceChina Department of Computer Science Aalto UniversityEspooFinland Center for Computational Social Science Kobe UniversityKobeJapan

Introduction:Minimizing the importation and exportation risks of coronavirus disease 2019(COVID-19)is a primary concern for sustaining the“Dynamic COVID-zero”strategy in *** estimation is essential for cities to conduct before relaxing border control ***:Informed by the daily number of passengers traveling between 367 prefectures(cities)in China,this study used a stochastic metapopulation model parameterized with COVID-19 epidemic characteristics to estimate the importation and exportation ***:Under the transmission scenario(R0=5.49),this study estimated the cumulative case incidence of Changchun City,Jilin Province as 3,233(95%confidence interval:1,480,4,986)before a lockdown on March 14,2022,which is close to the 3,168 cases reported in real life by March 16,*** a total of 367 prefectures(cities),127(35%)had high exportation risks according to the simulation and could transmit the disease to 50%of all other regions within a period from 17 to 94 *** average time until a new infection arrives in a location in 1 of the 367 prefectures(cities)ranged from 26 to 101 ***:Estimating COVID-19 importation and exportation risks is necessary for preparedness,prevention,and control measures of COVID-19—especially when new variants emerge.

关键词： Export Changchun prevention

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：