检索结果-内蒙古大学图书馆

Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Qing Zhang YingMing Luo Guoliang Gong Lin Lin School of Software Dalian University of Technology Dalian China Alibaba Limited Hangzhou China Key Laboratory for Ubiquitous Network and ServicSoftware of Liaoning Province DUT-RU International School of Information Scienceand Engineering Dalian University of Technology Dalian China Fuzzy Logic Systems Institute Iizuka Japan

In this paper, we propose Evolutionary Algorithm-based Neural Architecture Search(EvoNAS), which use Evolutionary Algorithm to find the optimized Convolutional Neural Network(CNN) and combine with Distribution Estimation to improve efficiency during the search process to improve the classification performance. The optimized CNN reveal the process of classification. It can classify the features according to specified classes, improving the classification accuracy of similar features while achieving the desired classification accuracy. We conduct feature separation experiments On the publicly available CIFAR dataset, we use EvoNAS to conducte feature separation experimentson. EvoNAS is subjected to feature separation experiments on the publicly available CIFAR dataset. The classification accuracy has been improved by 0.55% and 0.56% respectively compare to the original network. In addition, the feature visualization and attribution visualization improve the classificatory interpretability of CNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Influence of Temperature and Noise on Subthreshold Signal Propagation in Feedforward Neural Network

Research Square

引用

Research Square 2021年

作者： Yi, Ming Dai, Shiqi Lu, Lulu Wei, Zhouchao Zhu, Yuan School of Mathematics and Physics China University of Geosciences Hubei Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Automation China University of Geosciences Hubei Wuhan430074 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Ministry of Education Fudan University Shanghai200433 China

Temperature is an important environmental factor that all creatures depend on. Under the appropriate temperature, the neural system shows good biological performance. Based on an improved Hodgkin-Huxley (HH) neuron model considering temperature and noise, the ten-layers pure excitatory feedforward neural network and the ten-layers excitatory-inhibitory (EI) neural network are constructed to study the subthreshold signal propagation. It’s found that increasing temperature can restrain the signal propagation, and raise the noises intensity threshold where the failed signal propagation can transform into succeed signal propagation. Under the large noise, the signal propagation in network in different temperatures exhibits different anti-noise capabilities. There exists the saturation value of interlayer connection probability, that is, the signal propagation maintains constant when interlayer connection probability beyond a certain value. Moreover, in EI network with large noise, the network’s intrinsic oscillation activity will completely cover subthreshold signal, and block the signal propagation. The jumping phenomenon in the value of fidelity, which measures the similarity between input signal and output signal, appears in both pure excitatory network and EI network. This paper provides potential value for understanding the regulation of both temperature and noise in information propagation in neural network. © 2021, CC BY.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Applications of Edge Computing in IoT-Driver Smart Manufacturing of Automobiles

Applications of Edge Computing in IoT-Driver Smart Manufactu...

引用

Chinese Automation Congress (CAC)

作者： Yingjie Yu Bo Xu Lin Liu Juncheng Wang Minghe Li Zhe Ma Jianfu Cao General Business Department CATARC Automotive Test Center (ChangZhou) Co. Ltd Changzhou China State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong university Xi'an China Software Business Department Automotive Data of China (Tianjin) Co. Ltd Tianjin China

The automobile manufacturing industry is evolving towards increased connectivity and intelligence, with Industrial Internet of Things (IIoT) being a pivotal technology for realizing smart automobile production. Edge computing, complementing cloud computing in IIoT framework, presents a topic of significant interest in industry and academia with regard to coordinating efforts between cloud and edge computing. This paper provides an in-depth investigation of the current status of research, both domestically and globally, in areas such as smart automobiles manufacturing, edge computing, and data storage. It outlines the comprehensive structure of Internet of Things (IoT) within automobile manufacturing and introduces the hardware and software structures and functionalities of edge computing devices. Finally, an edge computing device designed specifically for automobile manufacturing is proposed and implemented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of overpasses in the Biham-Middleton-Levine traffic flow model with random and parallel update rule

引用

Physical Review E 2013年第2期88卷 022809-022809页

作者： Zhong-Jun Ding Rui Jiang Zi-You Gao Bing-Hong Wang Jiancheng Long MOE Key Laboratory for Urban Transportation Complex Systems Theory and Technology Beijing Jiaotong University Beijing 100044 People's Republic of China School of Transportation Engineering Hefei University of Technology Hefei 230009 People's Republic of China School of Engineering Science University of Science and Technology of China Hefei 230026 People's Republic of China Department of Modern Physics University of Science and Technology of China Hefei 230026 People's Republic of China

The effect of overpasses in the Biham-Middleton-Levine traffic flow model with random and parallel update rules has been studied. An overpass is a site that can be occupied simultaneously by an eastbound car and a northbound one. Under periodic boundary conditions, both self-organized and random patterns are observed in the free-flowing phase of the parallel update model, while only the random pattern is observed in the random update model. We have developed mean-field analysis for the moving phase of the random update model, which agrees with the simulation results well. An intermediate phase is observed in which some cars could pass through the jamming cluster due to the existence of free paths in the random update model. Two intermediate states are observed in the parallel update model, which have been ignored in previous studies. The intermediate phases in which the jamming skeleton is only oriented along the diagonal line in both models have been analyzed, with the analyses agreeing well with the simulation results. With the increase of overpass ratio, the jamming phase and the intermediate phases disappear in succession for both models. Under open boundary conditions, the system exhibits only two phases when the ratio of overpasses is below a threshold in the random update model. When the ratio of the overpass is close to 1, three phases could be observed, similar to the totally asymmetric simple exclusion process model. The dependence of the average velocity, the density, and the flow rate on the injection probability in the moving phase has also been obtained through mean-field analysis. The results of the parallel model under open boundary conditions are similar to that of the random update model.

关键词： TRAFFIC flow MATHEMATICAL models BOUNDARY value problems SIMULATION methods & models MEAN field theory VELOCITY PHASE transformations (Physics)

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Model for Estimating the Maximum Energy Harvesting Efficiency from Vortex-Induced Vibration

SSRN

引用

SSRN 2023年

作者： Han, Peng Huang, Wei-Xi Qin, Denghui Wang, Junlei Zhao, Jisheng AML Department of Engineering Mechanics Tsinghua University Beijing100084 China State Key Laboratory of Turbulence and Complex Systems College of Engineering Peking University Beijing100871 China School of Mechanical and Power Engineering Zhengzhou University Zhengzhou450000 China Department of Mechanical and Aerospace Engineering Monash University Clayton3800 Australia School of Engineering and Information Technology University of New South Wales CanberraACT102600 Australia

The present work presents a mathematical model (MM) based on a nonlinear reduced-order model (ROM) for estimating the maximum efficiency (ηm) of energy harvesting from vortex-induced vibration (VIV) of a circular cylinder. The proposed MM was validated through comparisons against both the origin ROM and experiments over a wide range of parameters. Of interest, it provided a low-cost analytical approximation relating the maximum efficiency ηm to physical parameters. As inspired by the modified Griffin plot, the use of MM allowed the collapse of the maximum efficiency ηm as a function of the combined mass-damping parameter α. Furthermore, detailed analyses of the effects of α showed that the maximum efficiency ηm is a balanced result of the vibration amplitude, the magnitude of the driving fluid force coefficient, and the phase angle between the driving fluid force and the body movement velocity. Of significance, the presented MM should be not only effective for estimating the maximum efficiency ηm but also useful to shed light on VIV dynamics. © 2023, The Authors. All rights reserved.

关键词： Fluid structure interaction

来源：评论

学校读者我要写书评

暂无评论

Knowledge-routed visual question reasoning: Challenges for deep representation embedding

arXiv

引用

arXiv 2020年

作者： Cao, Qingxing Li, Bailin Liang, Xiaodan Wang, Keze Lin, Liang School of Intelligent Systems Engineering Sun Yat-sen University China DarkMatter AI Research China Department of statistics University of California Los AngelesCA90095 United States School of Computer Science and Engineering Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Engineering Research Center for Advanced Computing Engineering Software of Ministry of Education China

Though beneficial for encouraging the Visual Question Answering (VQA) models to discover the underlying knowledge by exploiting the input-output correlation beyond image and text contexts, the existing knowledge VQA datasets are mostly annotated in a crowdsource way, e.g., collecting questions and external reasons from different users via the internet. In addition to the challenge of knowledge reasoning, how to deal with the annotator bias also remains unsolved, which often leads to superficial over-fitted correlations between questions and answers. To address this issue, we propose a novel dataset named Knowledge-Routed Visual Question Reasoning for VQA model evaluation. Considering that a desirable VQA model should correctly perceive the image context, understand the question, and incorporate its learned knowledge, our proposed dataset aims to cutoff the shortcut learning exploited by the current deep embedding models and push the research boundary of the knowledge-based visual question reasoning. Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases. The programs can select one or two triplets from the scene graph or knowledge base to push multi-step reasoning, avoid answer ambiguity, and balanced the answer distribution. In contrast to the existing VQA datasets, we further imply the following two major constraints on the programs to incorporate knowledge reasoning: i) multiple knowledge triplets can be related to the question, but only one knowledge relates to the image object. This can enforce the VQA model to correctly perceive the image instead of guessing the knowledge based on the given question solely;ii) all questions are based on different knowledge, but the candidate answers are the same for both the training and test sets. We make the testing knowledge unused during training to evaluate whether a model can unde

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Energy cascade and its locality in compressible magnetohydrodynamic turbulence

引用

Physical Review E 2016年第6期93卷 061102(R)-061102(R)页

作者： Yan Yang Yipeng Shi Minping Wan William H. Matthaeus Shiyi Chen State Key Laboratory for Turbulence and Complex Systems Center for Applied Physics and Technology College of Engineering Peking University Beijing 100871 People's Republic of China Department of Physics and Astronomy University of Delaware Newark Delaware 19716 USA Department of Mechanics and Aerospace Engineering South University of Science and Technology of China Shenzhen Guangdong 518055 People's Republic of China Collaborative Innovation Center of Advanced Aero-Engine Beijing 100191 People's Republic of China

We investigate energy transfer across scales in three-dimensional compressible magnetohydrodynamic (MHD) turbulence, a model often used to study space and astrophysical plasmas. Analysis shows that kinetic and magnetic energies cascade conservatively from large to small scales in cases with varying degrees of compression. With more compression, energy fluxes due to pressure dilation and subscale mass flux are greater, but conversion between kinetic and magnetic energy by magnetic line stretching is less efficient. Energy transfer between the same fields is dominated by local contributions regardless of compressive effects. In contrast, the conversion between kinetic and internal energy by pressure dilation is dominated by the largest scale contributions. Energy conversion between the velocity and magnetic fields is weakly local.

关键词： Magnetohydrodynamic turbulence Plasma turbulence Heliosphere Interstellar medium Space & astrophysical plasma Magnetohydrodynamic techniques

来源：评论

学校读者我要写书评

暂无评论

TEVA: Training-Efficient and Verifiable Aggregation for Federated Learning for Consumer Electronics in Industry 5.0

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xia, Yuanjun Liu, Yining Chen, Jingxue Liang, Yangfan Khan, Fazlullah Alturki, Ryan Wang, Xiaopei Guilin University of Electronic Technology Guangxi Key Laboratory of Trusted Software School of Computer and Information Security Guilin541004 China Wenzhou University of Technology School of Data Science and Artificial Intelligence Wenzhou325027 China University of Technology School of Mathematical and Physical Sciences SydneyNSW2007 Australia Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems The Key Laboratory of Medical Electronics and Digital Health of Zhejiang Province The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing314001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China Umm AI-Qura University Makkah Department of Software Engineering College of Computing Saudi Arabia Riverside Department of Computer Science and Engineering University of California CA92521 United States

Federated learning (FL) has been widely used for privacy-preserving model updates in Industry 5.0, facilitated by 6G networks. Despite FL's privacy-preserving advantages, it remains vulnerable to attacks where adversaries can infer private data from local models or manipulate the central server (CS) to deliver falsified global models. Current privacy-preserving approaches, primarily based on the FedAvg algorithm, fail to optimize training efficiency for non-independent and identically distributed (non-IID) data. This article proposes training-efficient and verifiable aggregation (TEVA) for FL to resolve these issues. This scheme combines threshold Paillier homomorphic encryption (TPHE), verifiable aggregation, and an optimized double momentum update mechanism (OdMum). TEVA not only leverages TPHE to protect the privacy of local models but also ensures the integrity of the global model through a verifiable aggregation mechanism. Additionally, TEVA integrates the OdMum algorithm to effectively address the challenges posed by non-IID data, promoting rapid model convergence and significantly enhancing overall training efficiency. Security analysis indicates that TEVA meets the requirements for privacy protection. Extensive experimental results demonstrate that TEVA can accelerate model convergence while incurring lower computational and communication overheads. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Ultra-Fast and Ultra-Efficient Removal of Cr (Vi) by the Aqueous Solutions of Monolayer Mxene (Ti3C2Tx)

SSRN

引用

SSRN 2022年

作者： Wang, Hongwei Wu, Fang Wang, Zhiheng Ruan, Haibo Wang, Yang Zhang, Shufang Luo, Haijun Zheng, Zhiqin Zhou, Miao Fang, Liang State Key Laboratory of Power Transmission Equipment & System Safety and New Technology Chongqing Key Laboratory of Soft Condensed Matter Physics and Smart Materials College of Physics Chongqing University Chongqing 400044 China Research Center for Materials Interdisciplinary Sciences Chongqing University of Arts and Sciences Chongqing 402160 China Key Laboratory of Optoelectronic Technology and Systems Education Ministry of China College of Optoelectronic Engineering Chongqing University Chongqing 400044 China College of Software Chongqing College of Electronic Engineering Chongqing 401331 China Key Laboratory on Optoelectronic Functional Materials College of Physics and Electronic Engineering Chongqing Normal University Chongqing 401331 China Fundamental Science on Nuclear Wastes and Environmental Safety Laboratory Southwest University of Science and Technology Sichuan Mianyang621010 China

Chromium (VI) removal is crucial to the safety of water resources, but there is still a lack of effective fast dislodge methods, especially the on-site rapid remediation and emergency removal technology. Herein, the monolayer (ML) Ti3C2Tx nanosheets (NSs) were prepared to remove Cr (VI) from water. The solution sample of the two-dimensional (2D) Ti3C2Tx NSs demonstrate ultrafast desorption kinetics (the concentration decreasing from 300 to 3 mg L-1 in 10 min) and impressively high capacity (1483 mg g-1), which is several times higher than that of the most of the previous reported Cr (VI) adsorption by Ti3C2Tx. The analysis of the adsorption kinetics and isotherm models indicates that the adsorption reaction is endothermic, coexists with physical and chemical adsorption, but mainly ML chemical adsorption. The removal efficiency decreases gradually with pH increasing from 2 to 12, while the maximum adsorption capacity increases with increasing temperature. The joint study of the experimental analysis and theoretical calculation based on the density functional theory (DFT) demonstrates that the extraordinary outstanding removal performance of Cr (VI) is due to the synergetic effect of reduction reaction removal and electrostatic adsorption. It is found that the Cr (VI) is mainly reduced by the OH- terminals on Ti3C2, and the detoxified Cr (III) is anchored on the surface of Ti3C2Tx through complexation reaction with O terminal. The advantages of ultrafast desorption kinetics, extra-high adsorption capacity, and broad working pH range of the single-layered Ti3C2Tx for Cr (VI) removal make it a remarkable candidate for rapid and urgent removal of Cr (VI) wastewater. © 2022, The Authors. All rights reserved.

关键词： Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Van der Waals force modulation towards liquid processable covalent organic frameworks

Next Materials

引用

Next Materials 2023年第1期1卷

作者： Mi, Chunxai peng, Peng Yu, Haifeng Huo, Feng He, Hongyan Jiang, Naisheng Wang, Yifei Xiang, Hengyang Zhang, Shengli Zeng, Haibo Zhang, Suojiang Xiang, Zhonghua State Key Laboratory of Organic-Inorganic Composites Beijing University of Chemical Technology Beijing 100029 China Green Catalysis Centre and College of Chemistry Zhengzhou University Zhengzhou 450001 China Beijing Key Laboratory of Ionic Liquids Clean Process State Key Laboratory of Multiphase Complex Systems Institute of Process Engineering Chinese Academy of Sciences Beijing 100190 China School of Materials Science and Engineering University of Science and Technology Beijing Beijing 100083 China MIIT Key Laboratory of Advanced Display Materials and Devices School of Materials Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China

Covalent Organic Frameworks (COFs) have been widely developed in the fields of catalysis, energy storage, and transformation due to their excellent controllability, stability, and porosity, but the un-processable powder nature imposes limitations. Here, we report the designed synthesis of a liquid processable COF material (termed as COF_NTC-Fe) in a variety of organic solvents and alkaline solutions via modulating the van der Waals force approach. Through increasing conjugate structure by extending the number of benzene rings in the reaction monomer, the newly developed COF_NTC-Fe obtains lower inter-layer interactions and dissolves faster in the same solution compared with small conjugated materials, i.e., COF_BTC-Fe. Our experiments along with molecular dynamics simulations reveal that the COF_NTC-Fe can be more easily exfoliated to dissolve due to the smaller van der Waals force in the same solvent. Benefitting from the excellent liquid processability, the newly developed COFs can be directly added into Poly(9-vinylcarbazole) solution to form a uniform transport layer to obtain enhanced hole transport rate and more efficient blue light perovskite light-emitting diodes (perovskite LED) devices. This work, therefore, provides a new preparation approach toward liquid processable COF materials to broaden their applications. © 2023 The Authors

关键词： Covalent organic frameworks Exfoliation Liquid processing Perovskite LED Van der Waals interaction

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：