检索结果-内蒙古大学图书馆

13th International Conference on Information Science and Technology, ICIST 2023

作者： Yan, Yancheng Li, Tieshan Yang, Hanqing Li, Yaolun Zhang, Yunhao Long, Yue Chen, C.L. Philip School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering South China University of Technology Guangzhou510641 China

ISBN: (纸本)9798350313925

This paper proposes a neural adaptive fixed-time consensus control approach for the nonlinear multi-agent system (MAS) with prescribed performance. First, by employing an error transformation, a prescribed performance consensus control strategy is presented, which can steer the consensus errors to the predetermined range in a fixed time. Then, the unknown nonlinear functions are approximated by utilizing neural networks and the adaptive backstepping technique. Meanwhile, a first-order filter is adopted to avoid taking derivatives of the virtual controller. With the proposed strategy, all signals of the MAS remain bounded and the fixed-time leader-following consensus control performance is ensured. Finally, these results are illustrated by simulations. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

MULTISOURCE DUAL UNSUPERVISED DOMAIN ADAPTATION METHOD FOR REMAINING LIFE PREDICTION UNDER MULTIPLE OPERATING CONDITIONS 14

MULTISOURCE DUAL UNSUPERVISED DOMAIN ADAPTATION METHOD FOR R...

引用

14th International Conference on Quality, Reliability, Risk, Maintenance, and Safety engineering, QR2MSE 2024

作者： Zhou, Ningxu Lyu, Yi Shen, Zaichen Xiao, Xu Fan, Ruhui School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer University of Electronic Science and Technology of China Zhongshan Institutes Zhongshan China School of Automation Guangdong University of Technology Guangzhou China

ISBN: (纸本)9781837242672

Aero engines, with their complex structures and intricate gas paths, are a crucial component of the aviation system. Traditional machine learning-based methods for predicting the remaining useful life (RUL) of rolling bearings often struggle to provide adequate feature representation and adaptive extraction due to complex operating conditions and challenges in obtaining degradation data. Given that traditional machine learning methods require substantial amounts of labeled data, they frequently fail to yield satisfactory RUL prediction results. To overcome these limitations, domain adaptation methods have been employed, facilitating the transfer of knowledge from a well-labeled source domain to an unlabeled target domain. Additionally, to augment the available data, a multisource domain transfer approach is proposed, which transfers data from multiple source domains to the target domain intended for prediction. To enhance the effectiveness of this multisource domain transfer method, a dual alignment strategy is introduced for aligning features at both the feature and semantic levels, thereby improving predictive performance. The model incorporates a convolutional neural network (CNN) and long short-term memory (LSTM) as its backbone, leveraging CNN's robust feature extraction capabilities combined with LSTM’s proficiency in processing time-dependent data. Experiments conducted on the CMAPSS dataset, along with comparisons and ablation studies against current popular multisource domain adaptation methods, demonstrate the superiority of the proposed approach. © The Institution of engineering & Technology 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An adaptive multitasking optimization algorithm based on population distribution

引用

Mathematical Biosciences and engineering 2024年第2期21卷 2432-2457页

作者： Li, Xiaoyu Wang, Lei Jiang, Qiaoyong Xu, Qingzheng School of Computer Science and Engineering Xi'an University of Technology Xi'an710048 China School of Electronic and Information Engineering Ankang University Ankang725000 China The Key Laboratory of Industrial Automation of Shaanxi Province Shaanxi University of Technology Hanzhong723001 China College of Information and Communication National University of Defense Technology Wuhan430019 China

Evolutionary multitasking optimization (EMTO) handles multiple tasks simultaneously by transferring and sharing valuable knowledge from other relevant tasks. How to effectively identify transferred knowledge and reduce negative knowledge transfer are two key issues in EMTO. Many existing EMTO algorithms treat the elite solutions in tasks as transferred knowledge between tasks. However, these algorithms may not be effective enough when the global optimums of the tasks are far apart. In this paper, we study an adaptive evolutionary multitasking optimization algorithm based on population distribution information to find valuable transferred knowledge and weaken the negative transfer between tasks. In this paper, we first divide each task population into K sub-populations based on the fitness values of the individuals, and then the maximum mean discrepancy (MMD) is utilized to calculate the distribution difference between each sub-population in the source task and the subpopulation where the best solution of the target task is located. Among the sub-populations of the source task, the sub-population with the smallest MMD value is selected, and the individuals in it are used as transferred individuals. In this way, the solution chosen for the transfer may be an elite solution or some other solution. In addition, an improved randomized interaction probability is also included in the proposed algorithm to adjust the intensity of inter-task interactions. The experimental results on two multitasking test suites demonstrate that the proposed algorithm achieves high solution accuracy and fast convergence for most problems, especially for problems with low relevance. © 2024 the Author(s).

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

On Efficient Planning of Oil&Gas Investments and Characteristics of BMS-models Destabilization 16

On Efficient Planning of Oil&Gas Investments and Characteris...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Zholkov Jolkov, Sergei Shashev, A.M. National University of Oil and Gas 'Gubkin University' Faculty of Automation and Computer Engineering Moscow Russia Moscow Institute of Physics and Technology Department of Radio Engineering and Cybernetics Moscow Russia

ISBN: (纸本)9798350337907

With an unconventional approach, we regard the problem of building a precise adaptive model of oil price dynamics in the context of investment projects. I. Newton formulated the principle of analysis. We list the Principles of applying the stochastic theory of asset management to building the optimal investment projects in oil and gas field development. We also analyze all the data of daily oil exchange from 1988 to 2019 (spot prices, Platts (Platt's) McGraw Hill Financial). We use methods and quantitative evaluations of adaptive BMS models with stochastic switches. We outline precise (normalized quadratic deviation within 9%) adaptive BMS models, plot extrapolation (quasi-forecast) on a stability period;make a stability period quasi-forecast and list essential quantitative evaluations and graphs. We discuss the possibility of quick profiting using BMS models. We also discuss the approaches to solving the problem of building optimal midterm oil and gas field development projects and operations, as well as the results we acquire. Analysis of incomes and expenses of an optimal investment project would allow for a substantiated decision on whether the development should be started or forgone. © 2023 IEEE.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

An overview on the distributed internal model approach and its applications

引用

Control Theory and Technology 2024年第3期22卷 345-359页

作者： Youfeng Su He Cai Jie Huang College of Computer and Data Science Fuzhou UniversityFuzhou 350116China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Mechanical and Automation Engineering The Chinese University of Hong KongShatinHong KongChina

The cooperative output regulation problem has been studied by two approaches:the distributed observer(DO)approach and the distributed internal model(DIM)approach,*** of these two approaches has its own merits and ***,we presented an overview on the cooperative output regulation problem by the DO *** paper further surveys the cooperative output regulation problem by the DIM *** first summarize the constructions and the roles of two different versions of the internal models:the distributed p-copy internal model and the distributed canonical internal ***,we describe an integrated framework that combines the DO approach and the DIM *** and variants of the DIM and their applications will also be highlighted.

关键词： Cooperative output regulation Distributed p-copy internal model Distributed canonical internal model Integrated approach

来源：评论

学校读者我要写书评

暂无评论

Comparative Study Between CNN and LSTM Approaches for Sign Language Recognition 6

Comparative Study Between CNN and LSTM Approaches for Sign L...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Edward, Phoebe Sameeh, Bola Alexan, Wassim Universities of Canada in Egypt Computer Science Dept. Egypt German International University Robotics and Automation Engineering Germany The German University in Cairo Communications Dept. Egypt

ISBN: (纸本)9798350378511

Image recognition technology has advanced to the point where it can help address challenges such as communication barriers faced by individuals with hearing impairments. Due to the societal rarity of learning and practicing Sign Languages (SLs), Machine Learning (ML) techniques have come to light to ease and automate this process through Sign Language Recognition (SLR) systems. This paper compares two SLR approaches;namely: Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). These two ML approaches are used to accurately identify the English alphabet, numbers, and specific words in American Sign Language (ASL). Results show that both techniques achieve very good accuracy values using test dataset, however in real-time tests CNN has outperformed LSTM. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models 38

Text-Guided Attention is All You Need for Zero-Shot Robustne...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yu, Lu Zhang, Haiyang Xu, Changsheng School of Computer Science and Engineering Tianjin University of Technology China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation University of Chinese Academy of Sciences China

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: the Attention Refinement module and the Attention-based Model Constraint module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness: The Attention Refinement module aligns the text-guided attention obtained from the target model via adversarial examples with the text-guided attention acquired from the original model via clean examples. This alignment enhances the model's robustness. Additionally, the Attention-based Model Constraint module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. The experiments validate that our method yields a 9.58% enhancement in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets. Our code is available at https://***/zhyblue424/TGA-ZSR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Backstepping-Based Interception Control for an underactuated ASV with Experimental Validation

Backstepping-Based Interception Control for an underactuated...

引用

2024 China automation Congress, CAC 2024

作者： Lin, Bin Hu, Zhihuan Duan, Kairong Sun, Zhijian Xie, Wei Zhang, Weidong Wu, Defeng Zhong, Shangkun Department of Automation Shanghai Jiao Tong University Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Department of Automation Shanghai Jiao Tong University Crossocean of Suzhou Technology Co. Ltd. Shanghai China School of Information and Communication Engineering Hainan University Department of Automation Shanghai Jiao Tong University Haikou China School of Marine Engineering Jimei University Xiamen China

ISBN: (纸本)9798350368604

This article puts forward an interception control system designed specifically for an Autonomous Surface Vehicle (ASV). The prime goal of this system is to capture a moving target whose speed may vary, even when there are unknown external disturbances such as waves, wind, and stream currents. By applying the sophisticated backstepping method, it can guarantee that the relative speed between the interceptor ASV and the target globally gets close to a neighborhood of the desired value. The effectiveness of this interception control approach has been thoroughly verified through simulations as well as practical experimental tests. © 2024 IEEE.

关键词： Backstepping

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

Equitable Client Selection in Federated Learning via Truncated Submodular Maximization 63

Equitable Client Selection in Federated Learning via Truncat...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Castillo J, Andres C. Kaya, Ege C. Ye, Lintao Hashemi, Abolfazl Purdue University Elmore Family School of Electrical and Computer Engineering West LafayetteIN United States Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan China

ISBN: (纸本)9798350316339

In a typical Federated Learning paradigm, a random subset of clients is selected at every round for training. This randomly chosen subset often does not perform well when evaluated in terms of fairness as the final model's performance often varies greatly between clients. This lack of a balanced and fair performance can be detrimental in sensitive applications, such as disease diagnosis in healthcare settings. Such issues may be exacerbated by emerging performance-centric client sampling procedures. This paper proposes a new equitable client selection method, SubTrunc, that addresses the shortcomings of random selection via a modification of the well-known facility location problem through submodular function maximization. This new approach entailing submodular functions incorporates using the information of loss values of each client to ensure a more balanced and thus more fair performance of the final model. Additionally, strong theoretical guarantees on the convergence of the resulting FL algorithm are established under mild assumptions. The algorithm's performance is evaluated on heterogeneous scenarios with a clear improvement in fairness when being observed under the scope of a client dissimilarity metric. © 2024 IEEE.

关键词： Federated learning

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：