检索结果-内蒙古大学图书馆

Learning to Branch in Combinatorial Optimization With Graph Pointer Networks

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 157-169页

作者： Rui Wang Zhiming Zhou Kaiwen Li Tao Zhang Ling Wang Xin Xu Xiangke Liao IEEE the Xiangjiang Laboratory and the College of Systems Engineering National University of Defense TechnologyChangsha 410073China the Institute of Automation Chinese Academy of SciencesBeijing 100190China the College of Systems Engineering National University of Defense TechnologyChangsha 410073 the Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology Changsha 410073China the Department of Automation Tsinghua UniversityBeijing 100084China the College of Intelligence Science and Technology National University of Defense TechnologyChangsha 410073China the College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China

Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex *** the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.

关键词： Branch-and-bound(B&B) combinatorial optimization deep learning graph neural network imitation learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Privacy-Preserving Approach to Incorporate Distributed Generators in AC Optimal Power Flow

A Machine Learning-Based Privacy-Preserving Approach to Inco...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Dindar, Burak Saner, Can Berk Polat, Dogukan Yigit Çakmak, Huseyin Kemâl Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany National University of Singapore Department of Electrical and Computer Engineering Singapore National University of Singapore School of Computing Singapore

ISBN: (纸本)9789531842976

In order to achieve the goal of a carbon-neutral power system, significant changes to the power grid are underway, necessitating enhanced interoperability between Transmission System Operators (TSOs) and Distribution System Operators (DSOs) for effective grid operation, particularly in light of the growing number of distributed generators (DGs). Data privacy concerns, however, complicate decision-making processes, particularly when integrating DGs into system-wide dispatch decisions. In this paper, we propose a machine-learning (ML)-based method to incorporate DGs located within the distribution system (DS) into dispatch decisions, adhering to data privacy by mitigating the exchange of sensitive data, such as system topology and demand profiles, between TSOs and DSOs. The methodology involves training three ML models to represent the behavior of the DS, thereby replacing the standard power flow model that contains sensitive information. Notably, we utilize a novel tailored neural network (NN) architecture to enhance computational efficiency in mapping the feasible region of the DS. Additionally, we employ open-source data to construct the Baden-Wü rttemberg (Germany) electricity grid, allowing to test our method not only on standard systems but also on a model that more accurately represents real-world power systems. The numerical case studies verify that the proposed method achieves results comparable to standard AC optimal power flow (AC-OPF) in both cost-optimality and computational time. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Modelling information warfare dynamics to counter propaganda using a nonlinear differential equation with a PINN-based learning approach

引用

International Journal of Information Technology (Singapore) 2024年第3期16卷 1527-1538页

作者： Pandey, Rashmikiran Pandey, Mrinal Nazarov, Alexey Nikolaevich Department of Radio Engineering and Cybernetics Moscow Institute of Physics and Technology Moscow Russian Federation Federal Research Center Computer Science and Control Russian Academy of Science Moscow Russian Federation

The widespread dissemination of misinformation and propaganda has become a crucial issue in societal conversations. This study presents an innovative framework to counter propaganda within information warfare using a modified logistic differential equation integrated with a Physics-Informed Neural Network (PINN). Employing the LIAR dataset, which reflects real-world political discourse, our model captures the intricate dynamics of propaganda. The novel approach effectively estimates underlying dynamics and unknown parameters, yielding superior accuracy (97.32%) compared to benchmark models. A parameter sensitivity analysis reveals the significant impact of the spread rate parameter, shedding light on aggressive propaganda dissemination. This research paves the way for robust methods in combating propaganda, demonstrating the effectiveness and superiority of the proposed PINN-based model over established benchmark models. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Information warfare Nonlinear differential equations PINN Propaganda Random forest classifier TF-IDF

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Online Dispatching Policy in Real-Time Train Timetable Rescheduling

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第1期25卷 478-490页

作者： Yue, Peng Jin, Yaochu Dai, Xuewu Feng, Zhenhua Cui, Dongliang Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China University of Bielefeld Nature Inspired Computing and Engineering Group Bielefeld33619 Germany University of Surrey Department of Computer Science GuildfordGU2 7XH United Kingdom University of Surrey School of Computer Science and Electronic Engineering GuildfordGU2 7XH United Kingdom

Train Timetable Rescheduling (TTR) is a crucial task in the daily operation of high-speed railways to maintain punctuality and efficiency in the presence of unexpected disturbances. However, it is challenging to promptly create a rescheduled timetable in real time. In this study, we propose a reinforcement-learning-based method for real-time rescheduling of high-speed trains. The key innovation of the proposed method is to learn a well-generalized dispatching policy from a large amount of samples, which can be applied to the TTR task directly. At first, the problem is transformed into a multi-stage decision process, and the decision agent is designed to predict dispatching rules. To enhance the training efficiency, we generate a small yet good-quality action set to reduce invalid explorations. Besides, we propose an action sampling strategy for action selection, which implements forward planning with consideration of evaluation uncertainty, thus improving search efficiency. Extensive experimental results demonstrate the effectiveness and competitiveness of the proposed method. It has been proven that the local policies trained by the proposed method can be applied to numerous problem instances directly, rendering it unnecessary to use human-designed rules. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Achieving Fine-Grained and Flexible Access control on Blockchain-Based Data Sharing for the Internet of Things

引用

China Communications 2022年第6期19卷 22-34页

作者： Ruimiao Wang Xiaodong Wang Wenti Yang Shuai Yuan Zhitao Guan School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China Department of Finance Operationsand Information SystemsBrock UniversityCanada

The traditional centralized data sharing systems have potential risks such as single point of failures and excessive working load on the central *** a distributed and collaborative alternative,approaches based upon blockchain have been explored recently for Internet of Things(IoTs).However,the access from a legitimate user may be denied without the pre-defined policy and data update on the blockchain could be costly to the *** this paper,we first address these issues by incorporating the Accountable Subgroup Multi-Signature(ASM)algorithm into the Attribute-based Access control(ABAC)method with Policy Smart Contract,to provide a finegrained and flexible ***,we propose a policy-based Chameleon Hash algorithm that allows the data to be updated in a reliable and convenient way by the authorized ***,we evaluate our work by comparing its performance with the *** results demonstrate significant improvement on the effectiveness and efficiency.

关键词： blockchain access control smart contract multi-signature chameleon-hash data sharing Internet of Things

来源：评论

学校读者我要写书评

暂无评论

BOOSTED CURRICULUM REINFORCEMENT LEARNING 10

BOOSTED CURRICULUM REINFORCEMENT LEARNING

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Klink, Pascal D'Eramo, Carlo Peters, Jan Pajarinen, Joni Department of Computer Science TU Darmstadt Germany Department of Electrical Engineering and Automation Aalto University Finland

Curriculum value-based reinforcement learning (RL) solves a complex target task by reusing action-values across a tailored sequence of related tasks of increasing difficulty. However, finding an exact way of reusing action-values in this setting is still a poorly understood problem. In this paper, we introduce the concept of boosting to curriculum value-based RL, by approximating the action-value function as a sum of residuals trained on each task. This approach, which we refer to as boosted curriculum reinforcement learning (BCRL), has the benefit of naturally increasing the representativeness of the functional space by adding a new residual each time a new task is presented. This procedure allows reusing previous action-values while promoting expressiveness of the action-value function. We theoretically study BCRL as an approximate value iteration algorithm, discussing advantages over regular curriculum RL in terms of approximation accuracy and convergence to the optimal action-value function. Finally, we provide detailed empirical evidence of the benefits of BCRL in problems requiring curricula for accurate action-value estimation and targeted exploration. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. 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

Design of Image-Based Autonomous Landing Instrumentation and control System for Unmanned Quadrotor Vehicles 10

Design of Image-Based Autonomous Landing Instrumentation and...

引用

10th IEEE Information Technology International Seminar, ITIS 2024

作者： Fauzan, Ihsan M. Mukhlish, Faqihza Prayoga, Aditya Ahmad, Robby Azhari Institut Teknologi Bandung Instrumentation and Control Master Program Faculty of Industrial Technology Indonesia Institut Teknologi Bandung Engineering Physics Research Group Center for Instrumentation Technology and Automation Indonesia PT. Sas Aero Sishan Engineering Department Indonesia

ISBN: (纸本)9798331521295

The study designs an instrumentation and control system for autonomous quadrotor landing using a visual marker as the landing target. For landing process, the marker used as a landing target is an embedded ArUco marker, capable for detection for both long range and close-range detection. Position of the quadrotor relative from the ArUco marker is estimated using Perspective-N-Point pose estimation. The estimation errors compared to actual measurements are under 20 cm, which is less than the distance between ArUco border and its center. To keep camera for facing downward during the flight, the 2 axis inertially stabilization platform (ISP). The designed ISP can maintain the camera orientation even when quadrotor angle has changed. The landing control system is made for two different scenarios. First scenario is for landing with Global Positioning System (GPS) support, and the second scenario is without GPS support. The landing control system in GPS support scenario uses velocity setpoint to control the quadrotor while in without GPS support scenario, control system uses angle-thrust setpoint to control quadrotor. Quadrotor landing control system can attempt landing on top of the ArUco marker in both scenarios. The trajectory Mean Average Error (MAE) of x and y coordinates and radius of the landing process is (0.108, 0.326, 0.359) m for GPS support scenario and (0.301, 0.251, 0.436) m for without GPS support scenario. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Estimating the AGV load and a battery lifetime based on the current measurement and random forest application

Estimating the AGV load and a battery lifetime based on the ...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Hanzel, Krzysztof Grzechca, Damian Ziebinski, Adam Chruszczyk, Lukas Janus, Artur Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Telecommunications and Teleinformatics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Electronics Electrical Engineering and Microelectronics Gliwice Poland Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Department of Distributed Systems and Informatics Devices Gliwice Poland Silesian University of Technology Student of Electrical EngineeringFaculty of Electrical Engineering Gliwice Poland

ISBN: (纸本)9798350324457

The paper describes the energy consumption from the battery based on the current measurements for various cases, i.e., speed (PWL adjustment) and loads. The main purpose of the research is to have additional and reliable information about power consumption and battery life estimation for autonomous guided vehicles (AGV). The authors propose a two-step algorithm. In the first step, a linear classifier was proposed. Then, the KNN classifier was tested;however, it did not give satisfactory results, so it was finally decided to use the random forest to estimate the load and PWL. The time domain current measurement is evaluated, and the beforementioned algorithms process the selected statistical measures. It has been proven that a two-step algorithm allows for achieving high accuracy. Based on the current observation, the paper is a good starting point for further investigation of the AGV because it is usually implemented in the AGV - so it does not require additional hardware. Moreover, it can lead to better energy management and increase battery lifetime. © 2023 IEEE.

关键词： AGV load estimation machine learning Prediction of energy consumption random forest

来源：评论

学校读者我要写书评

暂无评论

Composing Like an Ancient Chinese Poet:Learn to Generate Rhythmic Chinese Poetry

引用

Journal of computer Science & Technology 2023年第6期38卷 1272-1287页

作者：何明陈艳赵洪科刘淇吴乐崔羽曾贵华刘贵全 Department of Electronic Engineering Shanghai Jiao Tong UniversityShanghai 200240China AI Laboratory Lenovo ResearchBeijing 100193China Baidu Incorporated Beijing 100193China College of Management and Economics Tianjin UniversityTianjin 300072China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230027China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China Risk Control Department OPayBeijing 100010China

Automatic generation of Chinese classical poetry is still a challenging problem in artificial ***-cently,Encoder-Decoder models have provided a few viable methods for poetry ***,by reviewing the pri-or methods,two major issues still need to be settled:1)most of them are one-stage generation methods without further polishing;2)they rarely take into consideration the restrictions of poetry,such as tone and ***,some an-cient Chinese poets tended first to write a coarse poem underlying aesthetics and then deliberated its semantics;while oth-ers first create a semantic poem and then refine its *** this basis,in order to better imitate the human creation procedure of poems,we propose a two-stage method(i.e.,restricted polishing generation method)of which each stage fo-cuses on the different aspects of poems(i.e.,semantics and aesthetics),which can produce a higher quality of generated *** this way,the two-stage method develops into two symmetrical generation methods,the aesthetics-to-semantics method and the semantics-to-aesthetics *** particular,we design a sampling method and a gate to formulate the tone and rhyme restrictions,which can further improve the rhythm of the generated *** results demon-strate the superiority of our proposed two-stage method in both automatic evaluation metrics and human evaluation met-rics compared with baselines,especially in yielding consistent improvements in tone and rhyme.

关键词： aesthetics poetry generation polishing semantics two-stage method

来源：评论

学校读者我要写书评

暂无评论

Investigation on Synchronization of Two Identical Class of Chaotic Systems Using Back-Stepping control Technique in the Presence of Time Delays 9

Investigation on Synchronization of Two Identical Class of C...

引用

9th International Conference on control, Decision and Information Technologies, CoDIT 2023

作者： Bora, Riddhi Mohan Sharma, Bharat Bhushan Dey, Bhabani Shankar Kar, Indra Narayan Indian Institute of Technology Delhi Control and Automation Group Electrical Engineering Department Hauz Khas New Delhi110016 India National Institute of Technology Hamirpur Department of Electrical Engineering Himachal Pradesh Hamirpur177005 India

ISBN: (纸本)9798350311402

Time delay analysis is very crucial when it comes to the synchronization of chaotic systems. All practical dynamical systems are described by differential equations, hence the presence of time delay in dynamics becomes a pivotal part of the system analysis. So, in this article, an attempt has been made to study the synchronization problem of two identical same-ordered time-delayed chaotic systems, in strict-feedback form as described in (2) and (3) in master and slave configuration. Unlike other conventional nonlinear control techniques, the back-stepping control design strategy is used to serve the purpose of synchronization. The main advantage of using the back-stepping control technique is that it utilizes only a single scalar controller to attain synchronization among different chaotic systems. A generalized control function u∈ R is designed for the same. For verification of the theoretical results, the 3D time-delayed Genesio-Tesi chaotic system is considered both a master and slave system. Simulation results are provided to support the proposition. © 2023 IEEE.

关键词： Chaotic systems

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：