检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Yu, Zhou Yu, Jun Xiang, Chenchao Fan, Jianping Tao, Dacheng Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and Technology Hangzhou Dianzi University China Department of Computer Science University of North Carolina Charlotte United States UBTECH Sydney Artificial Intelligence Centre School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney DarlingtonNSW2008 Australia

Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both visual content of images and textual content of questions. To support the VQA task, we need to find good solutions for the following three issues: 1) fine-grained feature representations for both the image and the question;2) multi-modal feature fusion that is able to capture the complex interactions between multi-modal features;3) automatic answer prediction that is able to consider the complex correlations between multiple diverse answers for the same question. For fine-grained image and question representations, a 'co-attention' mechanism is developed by using a deep neural network architecture to jointly learn the attentions for both the image and the question, which can allow us to reduce the irrelevant features effectively and obtain more discriminative features for image and question representations. For multi-modal feature fusion, a generalized Multi-modal Factorized High-order pooling approach (MFH) is developed to achieve more effective fusion of multi-modal features by exploiting their correlations sufficiently, which can further result in superior VQA performance as compared with the state-of-the-art approaches. For answer prediction, the KL (Kullback-Leibler) divergence is used as the loss function to achieve precise characterization of the complex correlations between multiple diverse answers with same or similar meaning, which can allow us to achieve faster convergence rate and obtain slightly better accuracy on answer prediction. A deep neural network architecture is designed to integrate all these aforementioned modules into a unified model for achieving superior VQA performance. With an ensemble of our MFH models, we achieve the state-of-the-art performance on the large-scale VQA datasets and win the runner-up in VQA Challenge 2017. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Dynamic State Estimation Using Event-Trigger Master-Slave Nonlinear Filter for WAMS Applications

Dynamic State Estimation Using Event-Trigger Master-Slave No...

引用

Data Driven Control and Learning systems (DDCLS)

作者： Qing Yuan Fengdi Zhang Hengheng Gong Luyu Li Sen Li Xiaozhong Liao Zhen Li Xiangdong Liu School of Automation and Key Laboratory for Intelligent Control & Decision on Complex Systems Beijing Institute of Technology Beijing P. R. China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing P. R. China Beijing Institute of Radio Measurement Beijing P. R. China

ISBN: (纸本)9781538626191

The real-time state estimation becomes greatly important with the wide application of phasor measurement unit (PMU) in distributed generation (DG) for wide-area measurement systems (WAMS). In view of estimation, particle filter (PF) is capable of providing the best performance but at the cost of heavy computation burden. Besides, the growing grid size sustainably boosts the amount of data communication from PMU, causing the congestion. An event-trigger master-slave nonlinear filter (ET-MSNF) is proposed to guarantee the estimation accuracy and get the communication bandwidth relieved. The local slave filter at the generator node carries out the local estimation and event-trigger strategy using unscented transformation, which is identical to the center slave. The master filter at the center is designed using Monte Carlo method to improve the center's estimation accuracy by the cooperation with the center slave. Such master-slave filtering structure can fully utilize the computation capability both at the center and node. simulation on the standard IEEE 39-bus system verify the performance of ET-MSNF.

关键词： Generators Monte Carlo methods Phasor measurement units Master-slave Wide area measurements State estimation

来源：评论

学校读者我要写书评

暂无评论

A distributed MIMO radar oriented barrage jamming strategy

A distributed MIMO radar oriented barrage jamming strategy

引用

Signal, Information and Data Processing (ICSIDP), IEEE International Conference on

作者： Guangyong Zheng Siqi Na Tianyao Huang Lulu Wang State Key Laboratory of Complex Electromagnetic Environment Effects on Electronic Information Systems (CEMEE) Luoyang China Tsinghua University Beijing China Artificial Intelligence Research Center National Innovation Institute of Defense Technology Academy of Military Science Beijing China

ISBN: (数字)9781728123455

ISBN: (纸本)9781728123462

Distributed multiple input multiple output (MIMO) radar has attracted much attention for its improved detection and estimation performance as well as enhanced Electronic Counter-Counter Measures (ECCM) ability. In order to protect the target from being detected and tracked by such radar, we consider a barrage jamming strategy orienting towards a distributed MIMO. We first derive the Cramer-Rao bound (CRB) of target parameters estimation using a distributed MIMO under barrage jamming environments. We then set maximizing the CRB as the criterion for jamming resource allocation, aiming at degrading the accuracy of target parameters estimation. Particle swarm optimization is utilized to solve the maximizing problem. simulation results demonstrate the advantages of the the proposed strategy over traditional jamming methods.

关键词： Barrage jamming Distributed MIMO radar Cramer-Rao bound Cramer-Rao bounds MIMO radar complementary return to bias multiple input multiple output systems Parameter estimation Distribute Targets radar jamming

来源：评论

学校读者我要写书评

暂无评论

Distributed circle formation control over directed networks with communication constraints ⁎

引用

IFAC-PapersOnLine 2019年第3期52卷 108-113页

作者： Peng Xu Jiayan Wen Chen Wang Guangming Xie College of Electrical and Information Engineering Guangxi University of Science and Technology Liuzhou 545006 China National Engineering Research Center for Software Engineering Peking University Beijing 100871 China The State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing100871 China

This paper investigates distributed circle formation problems of multi-agent systems (MAS) subject to limited information communication under a class of weight-unbalanced directed graphs, in which the communication topology contains a directed spanning tree and each agent can only perceive the distances from itself to the nearest neighbor in counterclockwise direction as well as the counterpart in the clockwise direction. Towards this end, a novel algorithm combined with an encoder-decoder framework has been proposed. We show that, under the proposed policy, the resulting network executions can drive the states of all mobile agents to converge to some expected equilibrium point. Numerical simulation results have been given to demonstrate the effectiveness of the proposed algorithm.

关键词： Multi-agent systems Communication Bandwidth Directed Network Circle Formation Control

来源：评论

学校读者我要写书评

暂无评论

Quasi-two-body decays B → ηc(1S, 2S) [ρ(770), ρ(1450), ρ(1700) →] ππ in the perturbative QCD approach

arXiv

引用

arXiv 2017年

作者： Li, Ya Ma, Ai-Jun Rui, Zhou Xiao, Zhen-Jun Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing Jiangsu210023 China College of Sciences North China University of Science and Technology Tangshan063009 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing Jiangsu210023 China

In this paper, we calculated the branching ratios of the quasi-two-body decays B → ηc(1S, 2S) [ρ(770), ρ(1450), ρ(1700) →]ππ by employing the perturbative QCD (PQCD) approach. The contributions from the P -wave resonances ρ(770), ρ(1450) and ρ(1700) were taken into account. The two-pion distribution amplitude ΦPππ is parameterized by the vector current time-like form factor Fπ to study the considered decay modes. We found that (a) the PQCD predictions for the branching ratios of the considered quasi-two-body decays are in the order of 10−7 ∼ 10−6, while the two-body decay rates B(B → ηc(1S, 2S)(ρ(1450), ρ(1700))) are extracted from those for the corresponding quasi-two-body decays;(b) the whole pattern of the pion form factor-squared |Fπ|2 measured by the BABAR Collaboration could be understood based on our theoretical results;(c) the general expectation based on the similarity between B → ηcππ and B → J/ψππ decays are confirmed: R2(ηc) ≈ 0.45 is consistent with the measured R2(J/ψ) ≈ 0.56 ± 0.09 within errors;and (d) new ratios R3(ηc(1S)) and R4(ηc(2S)) among the branching ratios of the considered decay modes are defined and could be tested by future experiments. Copyright © 2017, The Authors. All rights reserved.

关键词： Hadrons

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Mengchu Xu Yan Zeng Meiting Xue Ji-Lin Zhang Jian Wan Mingyao Zhou Yilin Wen Yukun Shi School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China School of Cyberspace Hangzhou Dianzi University Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An iterative space alternative tiling parallel algorithm for 3D finite difference stencil computations

International Journal of Database Theory and Application

引用

International Journal of Database Theory and Application 2014年第6期7卷 105-120页

作者： Shen, Jing Zhang, Jilin Wan, Jian Zhou, Li Jiang, Ming School of Computer Science and Technology Hangzhou Dianzi University Hangzhou Zhejiang China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education China Zhejiang Provincial Engineering Center on Media Data Cloud Processing and Analysis Hangzhou China School of Information Engineering Hangzhou Dianzi University Hangzhou Zhejiang China

Stencils are finite-difference algorithms for solving large-scale and high-dimension partial differential equations. Due to the data dependences among the iterative statements in Stencils, traditional Stencil computations are be executed serially, rather than in parallel. It's challenging to design an effective and scalable Stencil parallelized method. To address the issue of 3D data space computing, we present a serial execution model based on multi-layers symmetric Stencil method and time skewing techniques. Within this model, the iteration space is divided to multiple tiles based on time skewing, where the executive process is ordered by the sequence of tiles, and the nodes in each individual tile can be swept repeatedly to improve the data locality. In addition, we propose a novel 3D iterative space alternate tiling Stencil parallel method, which subdivides the iteration space along high dimension, and changes the execution sequence of tiles to reduce the data dependency and communication cost, where the partial order of tiles is still guaranteed. Experimental results demonstrate our proposed alternative tiling parallel method achieves better parallel efficiency and scalability compared with the domain-decomposition methods.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Synthesizing and controlling helical indirect exchange interactions at nonequilibrium

arXiv

引用

arXiv 2018年

作者： Liu, Tingting Ren, Jie Tong, Peiqing Department of Physics Institute of Theoretical Physics Nanjing Normal University Nanjing210023 China Center for Phononics and Thermal Energy Science China-EU Joint Center for Nanophononics Shanghai Key Laboratory of Special Artificial Microstructure Materials and Technology School of Physics Science and Engineering Tongji University Shanghai200092 China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China

We study the nonequilibrium effects of spin and/or electric currents on the helical indirect exchange interactions of local spins that embedded in general open electronic systems. Especially, besides the synthesized anisotropic Heisenberg interactions, we find that the synthetic helical indirect exchange interactions possess two parts: antisymmetric (Dzyaloshinskii-Moriya interaction) and symmetric (Kaplan-Shekhtman-Entin-WohlmanAharony interaction), which are all formulated in terms of Keldysh nonequilibrium Green's functions. The presence of either spin-orbit coupling or spin polarized currents alone is able to synthesize and control the antisymmetric Dzyaloshinskii-Moriya exchange interactions, as the same direction as spin splitting. However, the appearance of symmetric Kaplan-Shekhtman-Entin-Wohlman-Aharony interactions requires both, i.e., the spin-orbit coupling and spin polarized currents with different splitting directions. Our results show the detailed scheme of controlling the sign, magnitude, and direction of indirect Dzyaloshinskii-Moriya vectors and Kaplan-Shekhtman-Entin-Wohlman-Aharony interactions at nonequilibrium in open quantum devices. Copyright © 2018, The Authors. All rights reserved.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative Filtering with Range Measurements: A Distributed Constrained Zonotopic Method

arXiv

引用

arXiv 2023年

作者： Ding, Yu Cong, Yirui Wang, Xiangke Cheng, Long College of Intelligence Science and Technology National University of Defense Technology Changsha410073 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

This article studies the distributed estimation problem of a multi-agent system with bounded absolute and relative range measurements. Parts of the agents are with high-accuracy absolute measurements, which are considered as anchors;the other agents utilize low-accuracy absolute and relative range measurements, each derives an uncertain range that contains its true state in a distributed manner. Different from previous studies, we design a distributed algorithm to handle the range measurements based on extended constrained zonotopes, which has low computational complexity and high precision. With our proposed algorithm, agents can derive their uncertain range sequentially along the chain topology, such that agents with low-accuracy sensors can benefit from the high-accuracy absolute measurements of anchors and improve the estimation performance. simulation results corroborate the effectiveness of our proposed algorithm and verify our method can significantly improve the estimation accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Roles of four feedback loops in mitochondrial permeability transition pore opening induced by Ca2+ and reactive oxygen species

引用

Physical Review E 2020年第6期102卷 062422-062422页

作者： Hong Qi Guoping Xu Xiao-Long Peng Xiang Li Jianwei Shuai Rui Xu Complex Systems Research Center Shanxi University Taiyuan 030006 China Shanxi Key Laboratory of Mathematical Techniques and Big Data Analysis on Disease Control and Prevention Shanxi University Taiyuan 030006 China Department of Physics College of Physical Science and Technology Xiamen University Xiamen 361005 China State Key Laboratory of Cellular Stress Biology Innovation Center for Cell Signaling Network Xiamen University Xiamen 361102 China National Institute for Data Science in Health and Medicine Xiamen University Xiamen 361102 China

Transient or sustained permeability transition pore (PTP) opening is important in normal physiology or cell death, respectively. These are closely linked to Ca2+ and reactive oxygen species (ROS). The entry of Ca2+ into mitochondria regulates ROS production, and both Ca2+ and ROS trigger PTP opening. In addition to this feedforward loop, there exist four feedback loops in the Ca2+-ROS-PTP system. ROS promotes Ca2+ entering (F1) and induces further ROS generation (F2), forming two positive feedback loops. PTP opening results in the efflux of Ca2+ (F3) and ROS (F4) from the mitochondria, forming two negative feedback loops. Owing to these complexities, we construct a mathematical model to dissect the roles of these feedback loops in the dynamics of PTP opening. The qualitative agreement between simulation results and recent experimental observations supports our hypothesis that under physiological conditions the PTP opens in an oscillatory state, while under pathological conditions it opens in a high steady state. We clarify that the negative feedback loops are responsible for producing oscillations, wherein F3 plays a more prominent role than F4; whereas the positive feedback loops are beneficial for maintaining oscillation robustness, wherein F1 has a more dominant role than F2. Furthermore, we manifest that the proper increase in negative feedback strength or decrease in positive feedback strength not only facilitates the occurrence of oscillations and thus protects the system against a high steady state, but also assists in lowering the oscillation peak. This study may provide potential therapeutic strategies in treating neurodegenerative diseases due to PTP dysfunction.

关键词： Bifurcations Calcium signaling Dynamical 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：