检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yang, Yuheng Chen, Haipeng College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China

ISBN: (纸本)9798350368741

Skeleton-based action recognition has long been a fundamental and intriguing problem in machine intelligence. This task is challenging due to pose occlusion and rapid motion, which typically results in incomplete or noisy skeleton data. State-of-the-art methods tend to learn human motion directly from these corrupted skeletons as if they were reliable. Unfortunately, this might lead to unsatisfactory results when key regions of the skeleton are occluded or disturbed. To tackle the problem, we propose a novel framework that integrates auxiliary tasks into a motion modeling network. These auxiliary tasks corrupt partial human skeletons with masking or noise and then force the network to recover the corrupted data, explicitly facilitating robust feature representation learning. We further propose supervising the auxiliary tasks with mutual information losses, mathematically ensuring feature consistency and spatial alignment between the recovered and original skeleton data. Empirically, our approach sets the new state-of-the-art performance on three benchmark datasets. © 2025 IEEE.

关键词： auxiliary task mutual information skeleton-based action recognition

来源：评论

学校读者我要写书评

暂无评论

Convolution Neural Network-based Load Model Parameter Selection Considering Short-term Voltage Stability

引用

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1064-1074页

作者： Ying Wang Chao Lu Xinran Zhang School of Technology Beijing Forestry UniversityBeijing 100083China State Key Laboratory of Control and Simulation of Power System and Generation Equipment Tsinghua UniversityBeijing 100084China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100083China IEEE

The recently proposed ambient signal-based load modeling approach offers an important and effective idea to study the time-varying and distributed characteristics of power ***,it also brings new *** the load model parameters of power loads can be obtained in real-time for each load bus,the numerous identified parameters make parameter application *** order to obtain the parameters suitable for off-line applications,load model parameter selection(LMPS)is first introduced in this ***,the convolution neural network(CNN)is adopted to achieve the selection purpose from the perspective of short-term voltage *** begin with,the field phasor measurement unit(PMU)data from China Southern Power Grid are obtained for load model parameter identification,and the identification results of different substations during different times indicate the necessity of ***,the simulation case of Guangdong Power Grid shows the process of LMPS,and the results from the CNNbased LMPS confirm its effectiveness.

关键词： Ambient signal CNN field PMU data load model parameter selection short-term voltage stability

来源：评论

学校读者我要写书评

暂无评论

Stability analysis of Runge-Kutta methods for nonlinear Volterra delay-integro-differential-algebraic equations

arXiv

引用

arXiv 2025年

作者： Wang, Gehao Yu, Yuexin Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

This paper is devoted to examining the stability of Runge-Kutta methods for solving stiff nonlinear Volterra delay-integro-differential-algebraic equations (DIDAEs) with constant delay. Hybrid numerical schemes combining Runge-Kutta methods and compound quadrature rules are analyzed for nonlinear stiff DIDAEs. Criteria for ensuring the global and asymptotic stability of the proposed schemes are established. Several numerical examples are provided to validate the theoretical findings. Copyright © 2025, The Authors. All rights reserved.

关键词： Runge Kutta methods

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE RESIDUAL-DRIVEN NEWTON SOLVER FOR NONLINEAR SYSTEMS OF EQUATIONS

arXiv

引用

arXiv 2025年

作者： Ding, Renjie Wang, Dongling Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Xiangtan Hunan411105 China

Newton-type solvers have been extensively employed for solving a variety of nonlinear system of algebraic equations. However, for some complex nonlinear system of algebraic equations, efficiently solving these systems remains a challenging task. The primary reason for this challenge arises from the unbalanced nonlinearities within the nonlinear system. Therefore, accurately identifying and balancing the unbalanced nonlinearities in the system is essential. In this work, we propose a residual-driven adaptive strategy to identify and balance the nonlinearities in the system. The fundamental idea behind this strategy is to assign an adaptive weight multiplier to each component of the nonlinear system, with these weight multipliers increasing according to a specific update rule as the residual components increase, thereby enabling the Newton-type solver to select a more appropriate step length, ensuring that each component in the nonlinear system experiences sufficient reduction rather than competing against each other. More importantly, our strategy yields negligible additional computational overhead and can be seamlessly integrated with other Newton-type solvers, contributing to the improvement of their efficiency and robustness. We test our algorithm on a variety of benchmark problems, including a chemical equilibrium system, a convective diffusion problem, and a series of challenging nonlinear systems. The experimental results demonstrate that our algorithm not only outperforms existing Newton-type solvers in terms of computational efficiency but also exhibits superior robustness, particularly in handling systems with highly imbalanced nonlinearities. © 2025, CC BY.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Analysis of displacement damage effects on the charge-coupled device induced by neutrons at Back-n in the China Spallation Neutron Source

引用

Chinese Physics B 2023年第7期32卷 435-442页

作者：薛院院王祖军陈伟郭晓强姚志斌何宝平聂栩赖善坤黄港盛江坤马武英缑石龙 State Key Laboratory of Artificial Microstructure and Mesoscopic Physics School of Physics Peking UniversityBeijing 100871China State Key Laboratory of Intense Pulsed Irradiation Simulation and Effect Northwest Institute of Nuclear TechnologyXi’an 710024China School of Materials Science and Engineering Xiangtan UniversityXiangtan 411105China

Displacement damage effects on the charge-coupled device(CCD)induced by neutrons at the back-streaming white neutron source(Back-n)in the China Spallation Neutron Source(CSNS)are analyzed according to an online irradiation *** hot pixels,random telegraph signal(RTS),mean dark signal,dark current and dark signal non-uniformity(DSNU)induced by Back-n are *** dark current is calculated according to the mean dark signal at various integration *** single-particle displacement damage and transient response are also observed based on the online measurement *** trends of hot pixels,mean dark signal,DSNU and RTS degradation are related to the integration time and irradiation *** mean dark signal,dark current and DSNU2 are nearly linear with neutron irradiation fluence when nearly all the pixels do not reach *** addition,the mechanisms of the displacement damage effects on the CCD are demonstrated by combining the experimental results and technology computer-aided design(TCAD)***-induced traps in the space charge region of the CCD will act as generation/recombination centers of electron-hole pairs,leading to an increase in the dark signal.

关键词： displacement damage effects charge-coupled device(CCD) China Spallation Neutron Source(CSNS) mechanisms technology computer-aided design(TCAD)

来源：评论

学校读者我要写书评

暂无评论

Applying Kumaraswamy distribution on stick-breaking process: a Dirichlet neural topic model approach

引用

Neural Computing and Applications 2024年第22期36卷 13731-13744页

作者： Ouyang, Jihong Wang, Teng Cao, Jingyue Wang, Yiming College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130015 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130015 China

In recent years, neural topic modeling has increasingly raised extensive attention due to its capacity on generating coherent topics and flexible deep neural structures. However, the widely used Dirichlet distribution in shallow topic models is difficult to reparameterize. Therefore, most existing neural topic models assume the Gaussian as the prior of topic proportions for reparameterization. Gaussian distribution does not have the sparsity like Dirichlet distribution, which limits the model’s topic extraction ability. To address this issue, we propose a novel neural topic model approximating the Dirichlet prior with the reparameterizable Kumaraswamy distribution, namely Kumaraswamy Neural Topic Model (KNTM). Specifically, we adopted the stick-breaking process for posterior inference with the Kumaraswamy distribution as the base distribution. Besides, to capture the dependencies among topics, we propose a Kumaraswamy Recurrent Neural Topic Model (KRNTM) based on the recurrent stick-breaking construction to ensure that the model can still generate coherent topical words in high-dimensional topic space. We examined our method on five prevalent benchmark datasets over six Dirichlet-approximating neural topic models, among which KNTM has the lowest perplexity and KRNTM performance best on topic coherence and topic uniqueness. Qualitative analysis of the top topical words verifies that our proposed models can extract more semantically coherent topics compared with state-of-the-art models, further demonstrating our method’s effectiveness. This work contributes to the broader application of VAEs with Dirichlet priors. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Applying machine-learning screening of single transition metal atoms anchored on N-dopedγ-graphyne for carbon monoxide electroreduction toward C_(1)products

引用

Nano Research 2023年第8期16卷 11511-11520页

作者： Dongxu Jiao Dantong Zhang Dewen Wang Jinchang Fan Xingcheng Ma Jingxiang Zhao Weitao Zheng Xiaoqiang Cui State Key Laboratory of Automotive Simulation and Control School of Materials Science and Engineeringand Key Laboratory of Automobile Materials of MOEJilin UniversityChangchun 130012China College of Chemistry and Chemical Engineering and Key Laboratory of Photonic and Electronic Bandgap MaterialsMinistry of EducationHarbin Normal UniversityHarbin 150025China Multiscale Crystal Materials Research Center Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Carbon monoxide electroreduction(COER)has been a key part of tandem electrolysis of carbon dioxide(CO_(2)),in which searching for high catalytic performance COER electrocatalysts remains a great ***,by means of density functional theory(DFT)computations,we explored the potential of a series of transition metal atoms anchored on N-dopedγ-graphyne(TM@N-GY,TM from Ti to Au)as the COER *** found that the final product selectivity of these single-atom catalysts depended on the position of the metal atom in the periodic table,with metals in the front and middle of each periodic period exhibiting high selectivity for CH_(4),while metals in the back producing CH_(3)*** learning(ML)found that metal atomic number was intrinsic to the difference in COER performance of these single-atom catalysts(SACs).The free energy changes showed that Mn@N-GY and Ni@N-GY exhibited outstanding COER catalytic performance for producing CH_(4)and CH_(3)OH,*** results provide theoretical and experimental guidance for designing efficient COER catalysts to generate C_(1)products.

关键词： CO electroreduction single atom catalysts γ-graphyne density functional theory machine learning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multilabel Adversarial Examples: An Effective Black-Box Attack

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 562-572页

作者： Kong, Linghao Luo, Wenjian Zhang, Hongwei Liu, Yang Shi, Yuhui Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Shenzhen518055 China Peng Cheng Laboratory Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation School of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attack. Minor malicious modifications of examples will lead to the DNN misclassification. Such maliciously modified examples are called adversarial examples. So far, the work on adversarial examples is mainly focused on multiclass classification tasks;there is less work in the field of multilabel classification. In this article, for the first time, a differential evolution (DE) algorithm that can effectively generate multilabel adversarial examples is proposed, which is called MLAE-DE. Different from traditional DE, we designed a complementary mutation operator for MLAE-DE, which can improve attack performance and reduce the number of fitness evaluations. As a black-box attack, MLAE-DE does not need to access model parameters and only uses model outputs to generate adversarial examples. Experiments on two typical multilabel classification models and three typical datasets under the black-box settings are conducted in this article. Experimental results demonstrate that, comparing with the existing black-box attack algorithms for multilabel classification models, the attack success rate of our proposed algorithm is much better. © 2020 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Ultrahigh-energy and-power aqueous rechargeable zinc-ion microbatteries based on highly cation-compatible vanadium oxides

引用

Journal of Materials science & Technology 2022年第25期120卷 159-166页

作者： Sheng-Bo Wang Qing Ran Wu-Bin Wan Hang Shi Shu-Pei Zeng Zi Wen Xing-You Lang Qing Jiang Key Laboratory of Automobile Materials(Jilin University) Ministry of Education and School of Materials Science and EngineeringJilin UniversityChangchun 130022China State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China

Aqueous multivalent-metal-ion intercalation chemistries hold genuine promise to develop safe and powerful microbatteries for potential use in many miniaturized ***,their development is beset by state-of-the-art electrode materials having practical capacities far below their theoretical *** we demonstrate that high compatibility between layered transition-metal oxide hosts and hydrated cation guests substantially boost their multi-electron-redox reactions to offer higher capacities and rate capability,based on typical bipolar vanadium oxides preintercalated with hydrated cations(M_(x)V_(2)O_(5)).When seamlessly integrated on Au current microcollectors with a three-dimensional bicontinuous nanoporous architecture that offers high pathways of electron transfer and ion transport,the constituent Zn_(x)V_(2)O_(5) exhibits specific capacity of as high as∼527 mAh g^(−1) at 5 mV s^(−1) and retains∼300 mAh g^(−1) at 200 mV s^(−1) in 1 M ZnSO_(4) aqueous electrolyte,outperforming the M_(x)V_(2)O_(5)(M=Li,Na,K,Mg).This allows aqueous rechargeable zinc-ion microbatteries constructed with symmetric nanoporous Zn_(x)V_(2)O_(5)/Au interdigital microelectrodes as anode and cathode to show high-density energy of∼358 mWh cm^(−3)(a value that is forty-fold higher than that of 4 V/500μAh Li thin film battery)at high levels of power delivery.

关键词： Multivalent metal ions Aqueous rechargeable batteries Microbatteries Nanoporous metals Metal/oxide composites

来源：评论

学校读者我要写书评

暂无评论

Local convergence analysis of L1/finite element scheme for a constant delay reaction-subdiffusion equation with uniform time mesh

arXiv

引用

arXiv 2024年

作者： Bu, Weiping Zheng, Xin School of Mathematics and Computational Science Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Hunan411105 China

The aim of this paper is to develop a refined error estimate of L1/finite element scheme for a reaction-subdiffusion equation with constant delay τ and uniform time mesh. Under the non-uniform multi-singularity assumption of exact solution in time, the local truncation errors of the L1 scheme with uniform mesh is investigated. Then we introduce a fully discrete finite element scheme of the considered problem. Next, a novel discrete fractional Grönwall inequality with constant delay term is proposed, which does not include the increasing Mittag-Leffler function comparing with some popular other cases. By applying this Grönwall inequality, we obtain the pointwisein-time and piecewise-in-time error estimates of the finite element scheme without the Mittag-Leffler function. In particular, the latter shows that, for the considered interval ((i-1)τ, iτ], although the convergence in time is low for i = 1, it will be improved as the increasing i, which is consistent with the factual assumption that the smoothness of the solution will be improved as the increasing i. Finally, we present some numerical tests to verify the developed theory. Copyright © 2024, The Authors. All rights reserved.

关键词： Finite element method

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：