检索结果-内蒙古大学图书馆

International Conference on Application Specific systems (ASAP), Architectures and Processors

作者： Wenlai Zhao Haohuan Fu Wayne Luk Teng Yu Shaojun Wang Bo Feng Yuchun Ma Guangwen Yang Ministry of Education Key Laboratory for Earth System Modeling and Center for Earth System Science Tsinghua University China Tsinghua National Laboratory for Information Science and Technology China Department of Computing Imperial college London UK Department of Automatic Test and Control Harbin Institute of Technology China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781509015047

This paper presents a novel reconfigurable framework for training Convolutional Neural Networks (CNNs). The proposed framework is based on reconfiguring a streaming datapath at runtime to cover the training cycle for the various layers in a CNN. The streaming datapath can support various parameterized modules which can be customized to produce implementations with different trade-offs in performance and resource usage. The modules follow the same input and output data layout, simplifying configuration scheduling. For different layers, instances of the modules contain different computation kernels in parallel, which can be customized with different layer configurations and data precision. The associated models on performance, resource and bandwidth can be used in deriving parameters for the datapath to guide the analysis of design trade-offs to meet application requirements or platform constraints. They enable estimation of the implementation specifications given different layer configurations, to maximize performance under the constraints on bandwidth and hardware resources. Experimental results indicate that the proposed module design targeting Maxeler technology can achieve a performance of 62.06 GFLOPS for 32-bit floating-point arithmetic, outperforming existing accelerators. Further evaluation based on training LeNet-5 shows that the proposed framework achieves about 4 times faster than CPU implementation of Caffe and about 7.5 times more energy efficient than the GPU implementation of Caffe.

关键词： Training Field programmable gate arrays Convolution Computational modeling Bandwidth Neural networks Runtime

来源：评论

学校读者我要写书评

暂无评论

A Data Driven Approach for Resting-state EEG signal Classificition of Schizophrenia with control Participants Using Random Matrix Theory

arXiv

引用

arXiv 2017年

作者： Liu, Haichun Zhang, TianHong Ye, Yumeng Pan, Changchun Yang, Genke Wang, JiJun Qiu, Robert C. Key Laboratory of System Control and Information Processing Shanghai Jiaotong University Ministry of Education of China Shanghai200240 China Department of Automation Shanghai Jiaotong University Shanghai200240 China Shanghai Key Laboratory of Psychotic Disorders Shanghai Mental Health Center Shanghai Jiaotong University School of Medicine Shanghai200030 China Brain Science and Technology Research Center Shanghai Jiao Tong University Shanghai200240 China Department of Electrical Engineering Shanghai Jiaotong University Shanghai200240 China Department of Electrical and Computer Engineering Tennessee Technological University CookevilleTN38505 United States

Resting state electroencephalogram (EEG) abnormalities in clinically high-risk individuals (CHR), clinically stable first-episode patients with schizophrenia (FES), healthy controls (HC) suggest alterations in neural oscillatory activity. However, few studies directly compare these anomalies among each types. Therefore, this study investigated whether these electrophysiological characteristics differentiate clinical populations from one another, and from non-psychiatric controls. To address this question, resting EEG power and coherence were assessed in 40 clinically high-risk individuals (CHR), 40 first-episode patients with schizophrenia (FES), and 40 healthy controls (HC). These findings suggest that resting EEG can be a sensitive measure for differentiating between clinical *** paper proposes a novel data-driven supervised learning method to obtain identification of the patients mental status in schizophrenia research. According to Marchenko-Pastur Law, the distribution of the eigenvalues of EEG data is divided into signal subspace and noise subspace. A test statistic named LES that embodies the characteristics of all eigenvalues is adopted. different classifier and different feature(LES test function) are selected for experiments, we have shown that using von Neumann Entropy as LES test function combine with SVM classifier could obtain the best average classification accuracy during three classification among HC, FES and CHR of Schizophrenia group with EEG signal. It is worth noting that the result of LES feature extraction with the highest classification accuracy is around 90% in two classification(HC compare with FES) and around 70% in three classification. Where the classification accuracy higher than 70% could be used to assist clinical diagnosis. Copyright © 2017, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Active voltage balancing control for multi HV-IGBTs in series connection

Active voltage balancing control for multi HV-IGBTs in serie...

引用

IEEE Energy Conversion Congress and Exposition

作者： Shiqi Ji Fred Wang Leon Tolbert Ting Lu Zhengming Zhao Hualong Yu Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA State Key Laboratory of Control and Simulation of Power System and Generation Equipment Department of Electrical Engineering Tsinghua University Beijing China

ISBN: (纸本)9781509007387

The series connection of insulated gate bipolar transistors (IGBTs) allows the operation at voltage levels higher than the rated voltage of one IGBT. However, the technology has not been widely applied due to transient voltage unbalance. Asynchronous gate drive signals, which cause series-connected IGBTs not to turn-on and turn-off at the same time, result in serious unbalanced voltage sharing. This paper presents an active voltage balancing control for multi series connected HV-IGBTs including the active voltage balancing control (AVBC) circuit integrated in the gate driver and the control for multi series connected IGBTs. The effectiveness of the control has been experimentally validated in a 10 kV dc-link voltage converter using four 4.5 kV HV-IGBTs in series connection.

关键词： active voltage balancing control multi HV-IGBTs series connection

来源：评论

学校读者我要写书评

暂无评论

Reliability and Security Issues for IoT-based Smart Business Center: Architecture and Markov Model

Reliability and Security Issues for IoT-based Smart Business...

引用

International Conference on Mathematics and computers in sciences and in Industry (MCSI)

作者： Vyacheslav Kharchenko Maryna Kolisnyk Iryna Piskachova Nikolaos Bardis Department of Computer Systems and Networks National Aerospace University “KhAI” Kharkiv Ukraine Department of Automation and Control in Technical Systems National Technical University “KPI” Kharkiv Ukraine Department of Computer Science and Control System Ukrainian State University of the Railway Transport Kharkiv Ukraine Department of Mathematics & Engineering Sciences Hellenic Military Academy Athens - Vari Greece

ISBN: (纸本)9781509009749

One of the key subsystems from point of view of security of the complex IoT system is the smart business center (SB?) system. Some problems the design and operation of the SBC system are analyzed. When analysis of safety of the IoT system must take into account the reliability and security of the system at several levels: the level of sensors, the level of communication (communication lines, router, switch), the server level as the control device of components of the network, the level of the entire SBC subsystem. General architecture of network of the SB? is described. Reliability and security of key SB? hardwareand software manufacturers are analysed. In particular, security issue for SB? routers is considered. Shown the Markov model, which takes into account the technical conditions of typical network components of the SBC with the presence of software vulnerabilities when exposed to hacker attacks. On this model's basis it is possible to conduct further researches directed for improving the reliability operation and safety of IoT.

关键词： reliability Internet of Things smart business center network security

来源：评论

学校读者我要写书评

暂无评论

A Self-adaptive Similarity-based Fitness Approximation for Evolutionary Optimization

A Self-adaptive Similarity-based Fitness Approximation for E...

引用

IEEE Symposium Series on Computational Intelligence

作者： Jie Tian Chaoli Sun Yaochu Jin Yin Tan Jianchao Zeng Division of Industrial and System Engineering Taiyuan University of Science and Technology Taiyuan 030024 China Department ofComputer Scienoe andTechnology Taiyuan University of Science and Technology Taiyuan 030024 China Department of Computer Science University of Surrey Guildford GU27XH UK Division of Industrial and System Engineering Taiyuan University of Science and Technology Taiyuan 030024 China School of Computer Science and Control Engineering North University of China Taiyuan 030024 China

ISBN: (纸本)9781509042418

Evolutionary algorithms used to solve complex optimization problems usually need to perform a large number of fitness function evaluations, which often requires huge computational overhead. This paper proposes a self-adaptive similarity-based surrogate model as a fitness inheritance strategy to reduce computationally expensive fitness evaluations. Gaussian similarity measurement, which considers the ruggedness of the landscape, is proposed to adaptively regulate the similarity in order to improve the accuracy of the inheritance fitness values. Empirical results on three traditional benchmark problems with 5, 10, 20, and 30 decision variables and on the CEC'13 test functions with 30 decision variables demonstrate the high efficiency and effectiveness of the proposed algorithm in that it can obtain better or competitive solutions compared to the state-of-the-art algorithms under a limited computational budget.

关键词： Fitness inheritance Fitness estimation similarity Computationally expensive optimization Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

MoS2 heterostructure with tunable phase stability: Strain induced interlayer covalent bond formation

arXiv

引用

arXiv 2017年

作者： Ouyang, Bin Xiong, Shiyun Yang, Zhi Jing, Yuhang Wang, Yongjie National Center for Supercomputing Applications University of Illinois at Urbana-Champaign UrbanaIL61801 United States Collaborative Innovation Center of Suzhou Nano Science and Technology Soochow University Suzhou JiangSu215123 China College of Physics and Optoelectronics Taiyuan University of Technology Taiyuan ShanXi030024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education and Shanxi Province Taiyuan University of Technology Taiyuan ShanXi030024 China Department of Astronautical Science and Mechanics Harbin Institute of Technology Harbin Heilongjiang150001 China Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Electrical Engineering and Computer Engineering University of Michigan Ann ArborMI48109 United States

Due to the distinguished properties offered by different structural phases of monolayer MoS2, phase engineering design are urgently required for achieving switchable structural phase. Strain engineering is widely accepted as a clean and flexible method, however, can not be achieved in engineering monolayer MoS2 phase transition because the critical biaxial strain required (~15%) is much larger than measured elastic limit (~11%). In this study, employing density functional theoretical calculations, it has been found out that with the forming of heterostructure between MoS2 with buckled 2D materials such as silicence, germanene and stanene, only a small strain can trigger the phase transition. As being suggested by the constructed phase stability diagram, biaxial deformation as low as 3% in MoS2/silicene and MoS2/stanene sandwich structure, would be sufficient to induce the structural phase transition in MoS2 lattice. This strain falls well within experimental elastic limit, thus would be feasible to realize in experiment. The origin of such behavior can be understood as strain induced interlayer covalent bond formation, which finally make MoS2 lattice more sensitive to external strain. This theoretical work provides one realistic route for achieving flexible phase stabilities in experimental design. Copyright © 2017, The Authors. All rights reserved.

关键词： Molybdenum compounds

来源：评论

学校读者我要写书评

暂无评论

Attitude synchronization of multiple rigid bodies in SE(3) over proximity networks

Attitude synchronization of multiple rigid bodies in SE(3) o...

引用

第35届中国控制会议

作者： Juan Deng Zhixin Liu Lin Wang John S.Baras Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceCAS Department of Automation Shanghai Jiao Tong Universityand the Key Laboratory of System Control and Information ProcessingMinistry of Education Department of Electrical and Computer Engineering and the Institute for Systems Research University of MarylandCollege Park

ISBN: (纸本)9781509009107

This paper investigates the attitude synchronization of a group of moving rigid bodies whose states including positions and rotation matrices evolve in the Lie group SE(3).The commonly used circular neighborhood is adopted,and the neighbor graphs are described by proximity *** order to avoid introducing discussions on the abrupt changes of neighbor graphs,a dwell time is *** distributed sampled-data control law for the angular velocity is *** the assumptions on the initial states,we provide sufficient conditions for the attitude synchronization of multiple rigid body *** with the existing results,our condition depends only on the neighborhood radius,the moving velocity and the dwell time.

关键词： rigid body SE(3) attitude synchronization sampled-data control proximity network

来源：评论

学校读者我要写书评

暂无评论

Flexible polymer/multi-walled carbon nanotube composite sensor array equipped with microheater for gas sensing

Flexible polymer/multi-walled carbon nanotube composite sens...

引用

International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS)

作者： Chin-Cheng Wu Jin-Chern Chiou Yu-Ping Wang Li-Chun Wang Department of Electrical and Computer Engineering Institute of Electrical and Control Engineering National Chiao Tung University Hsinchu Taiwan Chemical System Research Division National Chung-Shan Institute of Science and Technology Taoyuan Taiwan

ISBN: (纸本)9781509015115

A polymer/multi-walled carbon nanotube (MWCNT) composite sensor array based on a flexible polyimide substrate equipped with a thermostatic microheater to provide different working temperatures was developed for gas sensing. The thermostatic microheater provided nine working temperatures ranging from 20°C to 60°C. Each microheater element included a 3 × 3 polymer/MWCNT composite sensor array, which is composed of MWCNTs and polymer composite, as a sensing material. The device was developed to investigate the effect of device temperature on the response of polymer/MWCNT composite gas sensor arrays. The response to ethanol at different temperatures showed resistance variation but similar performance for the proposed gas sensor array.

关键词： Polymers Temperature sensors Sensor arrays Gas detectors Films Carbon nanotubes

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Model Selection Strategy for Surrogate-Assisted Particle Swarm Optimization Algorithm

An Adaptive Model Selection Strategy for Surrogate-Assisted ...

引用

IEEE Symposium Series on Computational Intelligence

作者： Haibo Yu Chaoli Sun Yin Tan Jianchao Zeng Yaochu Jin School of Mechanical Engineering Taiyuan University of Science and Technology Taiyuan 030024 China Department of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan 030024 China Division of Industrial and System Engineering Taiyuan University of Science and Technology Taiyuan 030024 China School of Computer Science and Control Engineering North University of China Taiyuan 030051 China Department of Computer Science University of Surrey Guildford GU2 7XH UK

ISBN: (纸本)9781509042418

Computationally expensive problems pose a serious challenge to the successful application of evolutionary algorithms to complex engineering optimization. To address this challenge, surrogate models, also known as metamodels, are commonly used in lieu of the expensive fitness function for the computational cost of optimization. However, it is nontrivial to choose an appropriate metamodel for properly replacing the expensive fitness function. In this paper, an adaptive model selection strategy based on fitness landscape analysis is proposed for a surrogate-assisted particle swarm optimization algorithm. The structure of the sampling space is learned, based on which the more suited surrogate model, either a polynomial regression model or a radial basis function network, will be chosen to estimate the fitness value. Simulation results on seven widely used benchmark functions demonstrate the efficacy of the proposed algorithm.

关键词： Surrogate models Particle swarm optimization Fitness landscape analysis Fitness distance correlation Model selection

来源：评论

学校读者我要写书评

暂无评论

control of Fuzzy Technological Objects Based on Mathematical Models

Control of Fuzzy Technological Objects Based on Mathematical...

引用

International Conference on control, Automation and systems

作者： Y. A. Ospanov B. B. Orazbayev K. N. Orazbayeva T. Gancarczyk A. K. Shaikhanova Department of System Analysis and Control L.N. Gumilyov Eurasian National University Astana Kazakhstan Department of Management Kazakh University of Economics Finance and International Trade Astana Kazakhstan Department of Computer Science and Automatics University of Bielsko-Biala Poland Department of Automatic Control Shakarim State University of Semey Semey Kazakhstan

ISBN: (纸本)9781467390583

This paper proposes methods for the development of mathematical models and for the control of operation modes of technological objects in oil refinery in face of uncertainty based on fuzzy information. The mathematical formulation of the problem of decision-making on controlling modes, which are solved on the basis of mathematical modeling, is formalized and obtained. By using the example of the problem of decision-making on optimal operation modes of technological complex for the benzene production and based on the methods of fuzzy mathematics an algorithm of its solution is developed. The initial problem is formalized as a problem of decision-making in the fuzzy environment, since the investigated object is characterized by multicriteriality and frequently functions in a fuzzy environment. The mathematical formulation of the problem of object's mode selection in the fuzzy environment and the heuristic algorithm of its solution is obtained by modifying various optimality principles based on methods of the fuzzy sets theory.

关键词： Mathematical modeling Fuzzy control Decision-making Fuzzy information Optimality principles Heuristic control algorithm

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：