检索结果-内蒙古大学图书馆

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Li, Lianghao He, Cheng Cheng, Ran Pan, Linqiang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9783030720612

Mating restriction strategies are capable of restricting the distribution of parent solutions for effective offspring generation in evolutionary algorithms (EAs). Studies have shown the importance of these strategies in improving the performance of EAs for multiobjective optimization. Our previous study proposed a specific manifold learning inspired mating restriction (MLMR) strategy. It has shown promising capability of solving multiobjective optimization problems (MOPs) with complicated Pareto set shapes. However, the effect of mating restriction strategies in solving constrained MOPs is yet to be well studied. Here, we investigate the effectiveness of MLMR for solving constrained MOPs. The MLMR strategy is embedded into some representative multiobjective EAs and tested on various benchmark constrained MOPs. Experimental results indicate the encouraging performance of MLMR in constrained multiobjective optimization. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Operator-Adapted Evolutionary Large-Scale Multiobjective Optimization for Voltage Transformer Ratio Error Estimation 11th

Operator-Adapted Evolutionary Large-Scale Multiobjective Opt...

引用

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Huang, Changwu Li, Lianghao He, Cheng Cheng, Ran Yao, Xin Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783030720612

Large-scale multiobjective optimization problems (LSMOPs) exist widely in real-world applications, and they are challenging for existing evolutionary algorithms due to their massive volume of search space. Despite that a number of large-scale multiobjective evolutionary algorithms (LSMOEAs) have been proposed in recent years, their effectiveness in solving LSMOPs remains unsatisfactory. One main reason is that most existing LSMOEAs may fail to balance convergence enhancement and diversity maintenance, especially for solving real-world problems. To address this issue, we propose to use a hybridized LSMOEA with adaptive operator selection (AOS) to handle real-world LSMOPs. Specifically, the proposed hybridized LSMOEA with AOS (AOS-LSMOEA) includes multiple different offspring generation and environmental selection strategies extracted from some existing LSMOEAs. Then it uses the AOS to adaptively determine the application rates of different offspring generation and environmental selection operators in an online manner. The proposed approach is capable of taking advantage of existing LSMOEAs, and the AOS enables the algorithm to choose suitable operators for solving different LSMOPs. In this study, the proposed algorithm is expected to solve the voltage transformer ratio error estimation (TREE) problems effectively. Experimental results show that AOS-LSMOEA achieves significant performance improvement due to the hybridization of different operators and the adoption of AOS method. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

DYO-SLAM: Visual Localization and Object Mapping in Dynamic Scenes

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Hu, Xinggang Wu, Yanmin Zhao, Mingyuan Cao, Zhenzhong Zhang, Xiangkui Ji, Xiangyang Dalian University of Technology School of Computer Science and Technology Dalian China Tsinghua University Department of Automation Beijing China Northeastern University School of Information Science and Engineering Shenyang China Peking University School of Electronic and Computer Engineering Shenzhen China University of Chinese Academy of Sciences National Astronomical Observatories Beijing China Nankai University School of Artificial Intelligence Tianjin China Dalian University of Technology School of Control Science and Engineering Dalian 116024 China

Addressing the impact of dynamic factors on localization accuracy and constructing a long-term consistent map containing only static elements are two crucial tasks in visual simultaneous localization and mapping (SLAM) for dynamic scenes. The introduction of dynamic elements can compromise the geometric constraints essential for visual SLAM, leading to a decrease in localization accuracy. Existing related research faces challenges in simultaneously ensuring localization accuracy in both low-dynamic and high-dynamic scenarios, while also maintaining the system's real-time performance. To address this issue, we propose a two-stage, coarse-to-fine static-probability-based localization scheme. The construction of object-level maps offers strong support for tasks involving higher-level intelligent agent manipulation as well as augmented reality (AR). However, current research is inadequate for dynamic scenes where the objects to be modeled are frequently and irregularly obscured by dynamic objects, and where there are significant challenges such as severe image and point cloud noise, semantic noise, and lack of observational perspectives. To overcome these challenges, we first propose an object parameter estimation algorithm that combines clustering, weighted Principal Component Analysis (PCA) based on an energy function, and a minimum bounding rectangle. Then, we design a multi-modal object data association strategy based on appearance, semantic, and spatial features. The proposed object parameter estimation algorithm and data association strategy demonstrate improved accuracy and robustness in dynamic scenes with the aforementioned challenges. Finally, based on the entire system, we further develop a dynamic object tracking algorithm and construct an AR system to demonstrate the system's application prospects. A series of public datasets and real-world scene results have been used to evaluate the effectiveness of the proposed system. © 1991-2012 IEEE.

关键词： Augmented Reality Data Association Dynamic Scenes Dynamic Tracking Parameter Estimation Static Probability Visual SLAM

来源：评论

学校读者我要写书评

暂无评论

Structural Robustness of Complex Networks: A Survey of A Posteriori Measures

arXiv

引用

arXiv 2023年

作者： Lou, Yang Wang, Lin Chen, Guanrong The Graduate School of Information Science and Technology Osaka University Osaka Suita565-0871 Japan The Department of Computer Science National Yang Ming Chiao Tung University Hsinchu300 Taiwan The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China The Department of Electrical Engineering City University of Hong Kong Hong Kong

Network robustness is critical for various industrial and social networks against malicious attacks, which has various meanings in different research contexts and here it refers to the ability of a network to sustain its functionality when a fraction of the network fail to work due to attacks. The rapid development of complex networks research indicates special interest and great concern about the network robustness, which is essential for further analyzing and optimizing network structures towards engineering applications. This comprehensive survey distills the important findings and developments of network robustness research, focusing on the a posteriori structural robustness measures for single-layer static networks. Specifically, the a posteriori robustness measures are reviewed from four perspectives: 1) network functionality, including connectivity, controllability and communication ability, as well as their extensions;2) malicious attacks, including conventional and computation-based attack strategies;3) robustness estimation methods using either analytical approximation or machine learning-based prediction;4) network robustness optimization. Based on the existing measures, a practical threshold of network destruction is introduced, with the suggestion that network robustness should be measured only before reaching the threshold of destruction. Then, a posteriori and a priori measures are compared experimentally, revealing the advantages of the a posteriori measures. Finally, prospective research directions with respect to a posteriori robustness measures are recommended. © 2023, CC BY.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Departure Counting Process in a Finite-Buffer Queue with Batch Arrivals and Multiple Vacation Policy

SSRN

引用

SSRN 2024年

作者： Marjasz, Rafal Kempa, Wojciech M. Kovtun, Viacheslav Institute of Theoretical and Applied Informatics Polish Academy of Sciences 5 Baltycka Str. Gliwice44-100 Poland Silesian University of Technology Faculty of Applied Mathematics 23 Kaszubska Str. Gliwice44-100 Poland Vinnytsia National Technical University Faculty of Intelligent Information Technologies and Automation Department of Computer Control Systems 95 Khmelnitske Shose Str. Vinnytsia21000 Ukraine

The study investigates the departure counting process in a finite-buffer queueing system with batch arrivals and multiple vacation policy. A representation for the mixed double transform of the number of departures up to the fixed time moment is obtained in the explicit form applying analytic approach based on integral equations and linear algebra. Numerical study is attached that focuses on understanding the impact of various system parameters on the behaviour of the mean number of packets processed within a fixed time frame. Utilizing numerical experiments, the study examines the influence of vacation duration, initial buffer state, arrival intensity, and processing rate on the departure process. Results reveal significant dependencies between these parameters and the transient behaviour of the queueing system. Notably, the service speed parameter demonstrates the most substantial influence on the mean number of processed packets, followed by the arrival rate. Conversely, variations in vacation duration and initial packet count exhibit comparatively minor effects on system behaviour. Overall, the findings provide valuable insights into the dynamics of departure processes in finite-buffer queue systems with batch arrivals and multiple vacation policies, offering implications for system optimization and performance enhancement strategies. © 2024, The Authors. All rights reserved.

关键词： Integral equations

来源：评论

学校读者我要写书评

暂无评论

Finite-time Consensus for Third-Order Multi-Agent Systems with Directed Communication Networks

Finite-time Consensus for Third-Order Multi-Agent Systems wi...

引用

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Xirui Zhang Zhi-Liang Zhao Tengfei Liu Zhong-Ping Jiang School of Mathematics and Statistics Shaanxi Normal University Xi’an P. R. China School of Electrical and Control Engineering North University of China Taiyuan P. R. China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang P. R. China Department of Electrical and Computer Engineering New York University Brooklyn NY USA

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This paper focuses on third-order multi-agent systems with directed communication networks. It is for the first time that the finite-time consensus problem is solved for third-order multi-agent systems under digraphs containing spanning trees. Two explicit-coefficient finite-time protocols, namely, edge-based and node-based, are proposed. First, we prove that asymptotic consensus is achievable with the reduced linear protocol. Then, we show that finite-time consensus is achievable with our explicit-coefficient finite-time protocols through homogeneous theory. Finally, numerical simulations are carried out to demonstrate the effectiveness of the proposed protocols.

关键词： Protocols Network topology Numerical simulation Topology Communication networks Closed loop systems Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

The applied principles of EEG analysis methods in neuroscience and clinical neurology

引用

Military Medical Research 2024年第6期11卷 907-941页

作者： Hao Zhang Qing-Qi Zhou He Chen Xiao-Qing Hu Wei-Guang Li Yang Bai Jun-Xia Han Yao Wang Zhen-Hu Liang Dan Chen Feng-Yu Cong Jia-Qing Yan Xiao-Li Li School of Systems Science Beijing Normal UniversityBeijing 100875China College of Electrical and Control Engineering North China University of TechnologyBeijing 100041China School of Automation Science and Engineering South China University of TechnologyGuangzhou 510641China Department of Psychology the State Key Laboratory of Brain and Cognitive Sciencesthe University of Hong KongHong Kong SAR 999077China HKU-Shenzhen Institute of Research and Innovation Shenzhen 518057GuangdongChina Department of Health Technology and Informatics the Hong Kong Polytechnic UniversityHong Kong SAR 999077China Department of Rehabilitation Medicine the First Afliated Hospital of Nanchang UniversityNanchang 330006China Rehabilitation Medicine Clinical Research Center of Jiangxi Province Nanchang 330006China Beijing Key Laboratory of Learning and Cognition School of PsychologyCapital Normal UniversityBeijing 100048China School of Communication Science Beijing Language and Culture UniversityBeijing 100083China Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004HebeiChina School of Computer Science Wuhan UniversityWuhan 430072China School of Biomedical Engineering Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalian 116081LiaoningChina Guangdong Artifcial Intelligence and Digital Economy Laboratory(Guangzhou) Guangzhou 510335China.

Electroencephalography(EEG)is a non-invasive measurement method for brain *** to its safety,high resolution,and hypersensitivity to dynamic changes in brain neural signals,EEG has aroused much interest in scientific research and medical *** article reviews the types of EEG signals,multiple EEG signal analysis methods,and the application of relevant methods in the neuroscience feld and for diagnosing neurological ***,3 types of EEG signals,including time-invariant EEG,accurate event-related EEG,and random event-related EEG,are ***,5 main directions for the methods of EEG analysis,including power spectrum analysis,time-frequency analysis,connectivity analysis,source localization methods,and machine learning methods,are described in the main section,along with diferent sub-methods and effect evaluations for solving the same ***,the application scenarios of different EEG analysis methods are emphasized,and the advantages and disadvantages of similar methods are *** article is expected to assist researchers in selecting suitable EEG analysis methods based on their research objectives,provide references for subsequent research,and summarize current issues and prospects for the future.

关键词： Electroencephalogram analysis methods Applied principles Neuroscience Diagnosis Neurological diseases

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

引用

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

Convergence rate of mean-square error of kernel estimators of non-homogeneous Poisson process intensity function 13

Convergence rate of mean-square error of kernel estimators o...

引用

13th International Conference on computer-Aided Technologies in Applied Mathematics, ICAM 2020

作者： Kitaeva, A.V. Kolupaev, M.V. Stepanova, N.V. Zhukovskiy, O.I. Department of Computer Science Tomsk State University Tomsk Russia Facebook Menlo ParkCA United States Institution of Control Sciences of Russian Academy of Sciences Moscow Russia Department of Data Processing Automation Tomsk State University of Control Systems and Radioelectronics Tomsk Russia

The estimator has been constructed similar to the Parzen-Rosenblatt window method using a single realization of a Poisson process at a fixed time interval. The intensity function of a non-homogeneous Poisson process is estimated up to a multiplicative constant. The convergence rate of the mean square error was found in the series of schemes with an unlimited increase of the intensity. © Published under licence by IOP Publishing Ltd.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Evaluating contextualized language models for Hungarian

arXiv

引用

arXiv 2021年

作者： Ács, Judit Lévai, Dániel Nemeskey, Dávid Márk Kornai, András Department of Automation and Applied Informatics Budapest University of Technology and Economics Hungary Institute for Computer Science and Control Hungary Alfréd Rényi Institute of Mathematics Hungary

We present an extended comparison of contextualized language models for Hungarian. We compare huBERT, a Hungarian model against 4 multilingual models including the multilingual BERT model. We evaluate these models through three tasks, morphological probing, POS tagging and NER. We find that huBERT works better than the other models, often by a large margin, particularly near the global optimum (typically at the middle layers). We also find that huBERT tends to generate fewer subwords for one word and that using the last subword for token-level tasks is generally a better choice than using the first one. Copyright © 2021, The Authors. All rights reserved.

关键词： Computational linguistics

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：