检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Department of Electrical Engineering University of North Texas DentonTX76203 United States State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

In this paper, we consider a stochastic distributed nonconvex optimization problem with the cost function being distributed over n agents having access only to zeroth-order (ZO) information of the cost. This problem has various machine learning applications. As a solution, we propose two distributed ZO algorithms, in which at each iteration each agent samples the local stochastic ZO oracle at two points with a time-varying smoothing parameter. We show that the proposed algorithms achieve the linear speedup convergence rate O(√p=(nT)) for smooth cost functions under the state-dependent variance assumptions which are more general than the commonly used bounded variance and Lipschitz assumptions, and O(p=(nT)) convergence rate when the global cost function additionally satisfies the Polyak-Lojasiewicz (P-L) condition in addition, where p and T are the dimension of the decision variable and the total number of iterations, respectively. To the best of our knowledge, this is the first linear speedup result for distributed ZO algorithms, which enables systematic processing performance improvements by adding more agents. We also show that the proposed algorithms converge linearly under the relative bounded second moment assumptions and the P-L condition. We demonstrate through numerical experiments the efficiency of our algorithms on generating adversarial examples from deep neural networks in comparison with baseline and recently proposed centralized and distributed ZO algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Recursive Weighted Null-Space Fitting Method for Identification of Multivariate Systems ⁎

引用

IFAC-PapersOnLine 2021年第7期54卷 345-350页

作者： Mengyuan Fang Miguel Galrinho Håkan Hjalmarsson Zhejiang Engineering Laboratory of Industrial Internet Communication Technology Zhejiang Sci-Tech University Hangzhou China. State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China OHB Sweden AB Kista Sweden Centre for Advanced Bio Production and Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

Recursive identification of structured multivariate models is known to be difficult due to the general non-convexity of the likelihood function. In this work, we propose a recursive multivariate weighted null-space fitting method for identification of structured multivariate models. The proposed method first uses recursive least squares to estimate a high order non-parametric model, then a parametric model is obtained through weighted least squares from the non-parametric model. In this way, the method avoids directly optimizing a non-convex likelihood function and has guaranteed global convergency. Moreover, the proposed method is flexible in model structures and has the same finite sample performance as its off-line counterpart. We use simulation examples to illustrate the performance.

关键词： Recursive system identification multivariate systems weighted null-space fitting

来源：评论

学校读者我要写书评

暂无评论

Scalable robustness of interconnected systems subject to structural changes

arXiv

引用

arXiv 2020年

作者： Knorn, Steffi Besselink, Bart Institute of Automation Engineering Otto-von-Guericke University Magdeburg Germany Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Jan C. Willems Centre for Systems and Control University of Groningen Netherlands

This paper studies the robustness of large-scale interconnected systems with respect to external disturbances, focussing on their scalability properties. Specifically, a notion of scalability is introduced that asks for these robustness properties to remain unchanged under a structural change of the system, such as the addition/removal of a subsystem or a change in the interconnection structure. Both necessary and sufficient conditions, in terms of the interconnection structure and edge weights, are given under which elementary structural changes are scalable. The results are illustrated through a simple *** Codes 93A15 (Primary), Copyright © 2020, The Authors. All rights reserved.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Execution of smart electric vehicle charging station driven by RE technology using soft computing approach 3

Execution of smart electric vehicle charging station driven ...

引用

3rd IEEE International Virtual Conference on Innovations in Power and Advanced Computing Technologies, i-PACT 2021

作者： Kumar, K. Vinoth Sujitha, S. Stalin, B. Buvana, D. Josh, F.T. Vinodha, K. Ramya, K.C. Saravanakumar, R. Logeswaran, D. New Horizon College of Engineering Department of Electrical and Electronics Engineering Bengaluru India Dr. MGR Polytechnic College Department of Electrical and Electronics Engineering Arni India Dhanalakshmi College of Engineering Department of Electrical and Electronics Engineering Chennai India Karunya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Coimbatore India PES University Electronic City Campus Department of Computer Science Engineering Bengaluru India Sri Krishna College of Engineering and Technology Department of Electrical and Electronics Engineering Coimbatore India School of Electrical Engineering Vellore Institute of Technology Department of Control and Automation Vellore India Kongu Engineering College Department of Electrical and Electronics Engineering Perundurai India

ISBN: (纸本)9781665426916

This paper outlines potential demand for electric vehicles, charging station infrastructure and its challenges for the India scenario, as well as the increasing liberalization and expansion of production, transmission and distribution. Distributed and renewable electricity generation and distribution, as well as market processes related to energy allocation and energy mix. is the subject of evolutionary development with improved performance and reliability. Structural analysis of respective parameters was performed for the commercial scope of electric vehicles in the existing energy market and regulatory concerns are taken into account to describe a scenario in which a company global control of electric vehicle charging and service provision of ancillary networks. Experimental results show confirmatory results. © 2021 IEEE.

关键词： Commercial vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-hop reasoning over sparse knowledge graphs with deep reinforcement learning

引用

Expert Systems with Applications 2025年 290卷

作者： Liu, Yiyang Fu, Lejun Fu, Yukai Wu, Tianxing Bai, Hongfei State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China College of Information Engineering Shenyang University of Chemical Technology Shenyang110142 China School of Computer Science and Engineering Southeast University Nanjing211189 China

In recent years, knowledge reasoning has demonstrated substantial progress in inferring missing information, effectively alleviating the limitations caused by the incompleteness of knowledge graphs (KGs). Dealing with entities that have sufficient paths between them, multi-hop reasoning methods have achieved notable success and demonstrated interpretability, but they still exhibit deficiencies when dealing with sparse KGs. To overcome the insufficiency of edges in sparse KGs and the absence of effective guidance in multi-hop reasoning methods, a hybrid multi-hop collaborative Multi-Agent Sparse Knowledge Graph Reasoning model (MASKGR) is proposed. Attention-based dynamic completion (ADC) and variable rule guidance(VRG) are used to enhance the reasoning capability of deep reinforcement learning (RL) in sparse KGs. ADC focuses on high-value relations based on attention weights and combines embedding-based methods to predict the tail entities of these relations, expanding the original action space and improving the exploration capability of agents. Moreover, VRG greatly improves the ability of MASKGR to use rule-guided agent learning by utilizing the variable rule ratio and the variable loss reshaping. ADC can be applied to both single-agent and multi-agent in other models, while VRG is specifically designed for multi-agent. Comprehensive experiments have been conducted on four datasets: FB15K-237-10 %, FB15K-237-50 %, NELL23K, and WD-singer. Specifically, MASKGR achieves relative improvements of 1.3 % in Mean Reciprocal Rank (MRR) and 1.1 % in the proportion of correct tail entity rankings in the top 3 (Hit@3) on the FB15K-237-10 %, 2.4 % in MRR and 1.3 % in Hit@3 on the NELL23K, and 2.7 % in MRR and 3.6 % in Hit@3 on the WD-singer. The results indicate that MASKGR outperforms state-of-the-art multi-hop reasoning models based on reinforcement learning. © 2025

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Sliding sequential CVAE with time variant socially-aware rethinking for trajectory prediction

arXiv

引用

arXiv 2021年

作者： Zhou, Hao Ren, Dongchun Yang, Xu Fan, Mingyu Huang, Hai National Key Laboratory of Science and Technology of Underwater Vehicle Harbin Engineering University Harbin China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences Beijing China Research Center for Autonomous Vehicles Meituan Beijing China College of Computer Science Wenzhou University Wenzhou China National Key Laboratory of Science and Technology of Underwater Vehicle Harbin Engineering University Harbin China

Pedestrian trajectory prediction is a key technology in many applications such as video surveillance, social robot navigation, and autonomous driving, and significant progress has been made in this research topic. However, there remain two limitations of previous studies. First, with the continuation of time, the prediction error at each time step increases significantly, causing the final displacement error to be impossible to ignore. Second, the prediction results of multiple pedestrians might be impractical in the prediction horizon, i.e., the predicted trajectories might collide with each other. To overcome these limitations, this work proposes a novel trajectory prediction method called CSR, which consists of a cascaded conditional variational autoencoder (CVAE) module and a socially-aware regression module. The cascaded CVAE module first estimates the future trajectories in a sequential pattern. Specifically, each CVAE concatenates the past trajectories and the predicted points so far as the input and predicts the location at the following time step. Then, the socially-aware regression module generates offsets from the estimated future trajectories to produce the socially compliant final predictions, which are more reasonable and accurate results than the estimated trajectories. Moreover, considering the large model parameters of the cascaded CVAE module, a slide CVAE module is further exploited to improve the model efficiency using one shared CVAE, in a slidable manner. Experiments results demonstrate that the proposed method exhibits improvements over state-of-the-art method on the Stanford Drone Dataset (SDD) and ETH/UCY of approximately 38.0% and 22.2%, respectively. © 2021, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Regret and Cumulative Constraint Violation Analysis for Distributed Online Constrained Convex Optimization

arXiv

引用

arXiv 2021年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden The Digital Futures Stockholm10044 Sweden The Department of Control Science and Engineering College of Electronics and Information Engineering The Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

This paper considers the distributed online convex optimization problem with time-varying constraints over a network of agents. This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and constraint functions. At each round, each agent selects a decision from the decision set, and then only a portion of the loss function and a coordinate block of the constraint function at this round are privately revealed to this agent. The goal of the network is to minimize the network-wide loss accumulated over time. Two distributed online algorithms with full-information and bandit feedback are proposed. Both dynamic and static network regret bounds are analyzed for the proposed algorithms, and network cumulative constraint violation is used to measure constraint violation, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. In particular, we show that the proposed algorithms achieve O(T max{κ,1-κ}) static network regret and O(T 1-κ/2) network cumulative constraint violation, where T is the time horizon and κ ∈ (0, 1) is a user-defined trade-off parameter. Moreover, if the loss functions are strongly convex, then the static network regret bound can be reduced to O(T κ). Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results. Copyright © 2021, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

An Efficient Evolutionary Algorithm for High-Speed Train Rescheduling Under a Partial Station Blockage

SSRN

引用

SSRN 2023年

作者： Wang, Rongsheng Zhang, Qi Dai, Xuewu Yuan, Zhiming Zhang, Tao Ding, Shuxin Jin, Yaochu China Academy of Railway Sciences Corporation Limited Beijing100081 China Signal and Communication Research Institute China Academy of Railway Sciences Corporation Limited Beijing100081 China Train Operation Control Laboratory for High-Speed Railway National Engineering Research Center of System Technology for High-Speed Railway and Urban Rail Transit Beijing100081 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Faculty of Technology Bielefeld University BielefeldD-33615 Germany Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

This paper investigates the high-speed train rescheduling (HSTR) problem under a partial station blockage and proposes an efficient problem-specific strengthen elitist genetic algorithm (PS-SEGA) for HSTR. An HSTR model that is subject to train operation constraints is established to minimize the total train delay. The PS-SEGA framework consists of the following main steps. Firstly, a permutation-based encoding method is developed to define an efficient search space based on a train departure sequence. A decoding method is employed to output the rescheduled timetable and objective value based on the departure sequence. Moreover, a hybrid initialization method involving an efficient heuristic strategy (EHS) is put forward to accelerate the convergence speed of Evolutionary algorithms (EAs). Using problem-specific knowledge, EHS generates an efficient and feasible solution for the initial population. Finally, a restart strategy is presented to maintain genetic diversity. Compared with other advanced EAs and their improved variants also using the PS-SEGA framework, experimental results demonstrate the effectiveness of the proposed PS-SEGA for addressing HSTR scenarios under the partial station blockage. As for the scenarios that CPLEX can not obtain optimal solutions within 10 minutes, PS-SEGA can all provide quasi-optimal solutions in real-time. Furthermore, compared with the other two strategies (i.e., First-Scheduled-First-Served and EHS), PS-SEGA can find the best departure sequence that can output the timetable with a quasi-optimal solution. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Structure parameter optimized kernel based online prediction with a generalized optimization strategy for nonstationary time series

arXiv

引用

arXiv 2021年

作者： Guo, Jinhua Chen, Hao Zhang, Jingxin Chen, Sheng Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic Systems Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fuzhou350002 China Department of Automation Tsinghua University Beijing100084 China School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

In this paper, sparsification techniques aided online prediction algorithms in a reproducing kernel Hilbert space are studied for nonstationary time series. The online prediction algorithms as usual consist of the selection of kernel structure parameters and the kernel weight vector updating. For structure parameters, the kernel dictionary is selected by some sparsification techniques with online selective modeling criteria, and moreover the kernel covariance matrix is intermittently optimized in the light of the covariance matrix adaptation evolution strategy (CMA-ES). Optimizing the real symmetric covariance matrix can not only improve the kernel structure's flexibility by the cross relatedness of the input variables, but also partly alleviate the prediction uncertainty caused by the kernel dictionary selection for nonstationary time series. In order to sufficiently capture the underlying dynamic characteristics in prediction-error time series, a generalized optimization strategy is designed to construct the kernel dictionary sequentially in multiple kernel connection modes. The generalized optimization strategy provides a more self-contained way to construct the entire kernel connections, which enhances the ability to adaptively track the changing dynamic characteristics. Numerical simulations have demonstrated that the proposed approach has superior prediction performance for nonstationary time series. Copyright © 2021, The Authors. All rights reserved.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Reputation-based Distributed Filtering Over Sensor Networks Subject to Stochastic Nonlinearity and Network-Induced Quantization

引用

IEEE Transactions on Network science and Engineering 2025年

作者： Jia, Chaoqing Wang, Zidong Hu, Jun Dong, Hongli Harbin University of Science and Technology School of Automation Harbin150080 China Harbin University of Science and Technology Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin150080 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Harbin University of Science and Technology Department of Applied Mathematics Harbin150080 China Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China

In sensor networks, due to inevitable sensor faults, malfunctions, or deliberate attacks, sensors may transmit erroneous, inaccurate, or misleading data, thereby degrading overall system performance. To address this issue, an effective approach is to assign reputation scores to sensors based on their trustworthiness, historical performance, or reliability. In this paper, the reputation-based distributed filtering (RBDF) problem is considered for a class of stochastic nonlinear systems over sensor networks with network-induced quantization. A reputation mechanism is employed to mitigate the adverse effects caused by noisy, faulty, or malicious sensors. Specifically, reputations are allocated by each sensor to the data received from its neighbors, ensuring that abnormal data are assigned smaller reputation values and may even be discarded. For the first time, a recursive RBDF algorithm is proposed, wherein an upper bound of the filtering error covariance (UBFEC) is derived by solving two matrix equations. Subsequently, the filter gain is determined by minimizing the trace of UBFEC at each step. Furthermore, a sufficient condition is presented to ensure the uniform boundedness of the filtering error dynamics. Finally, a simulation example is provided to verify the feasibility and validity of the developed RBDF algorithm. © 2013 IEEE.

关键词： Digital arithmetic

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：