检索结果-内蒙古大学图书馆

2018 International Joint Conference on Neural Networks, IJCNN 2018

作者： Lima, Aron A. Martins Araujo, Rafael M. Santos, Fábio A. Guidotti Dos Yoshizumi, Victor H. De Barros, Fábio K. H. Spatti, Danilo H. Liboni, Luisa H. B. Dajer, Maria E. Department of Electrical Engineering Federal University of Technology Paraná Cornélio Procópio Brazil Department of Computational Engineering Federal University of Technology Paraná Cornélio Procópio Brazil Department of Computational Systems University of São Paulo São Carlos Brazil Dep. Of Electrical and Computer Engineering Federal Institute of Education Science and Technology of São Paulo Sertãozinho Brazil

ISBN: (纸本)9781509060146

The emergence of artificial neural networks (ANNs) caused a great revolution in the knowledge area of pattern-classification and contributed to the fast development of intelligent systems. For an ANN to be effective, its topology parameters must be set up, such as learning rate, number of layers, and number of neurons. Therefore, optimization algorithms can be used to produce more efficient ANNs. In this paper, we propose a genetic algorithm (GA) to better estimate parameters of an ANN applied to the classification of the type, strength, and orientation of different hand movements from electromyography signals. Acquired data signals were first processed with the Wavelet Transform (WT) to extract the most important features. These features were presented to the optimized hybrid intelligent system (HIS) composed of ANNs and the optimization GA. Classification results are promising, presenting accuracy rates above 90% and reliability rate of 98%. These results support the use of HIS in practical applications such as smart prostheses and automatic medical evaluations. © 2018 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Full Characterization of Magneto-Dielectric Materials Using a Novel CSRR Based Sensor

Full Characterization of Magneto-Dielectric Materials Using ...

引用

International Symposium on Telecommunications, IST

作者： Maryam Saadat-Safa Vahid Nayyeri Mostafa Khanjarian Mohammad Soleimani Omar M. Ramahi Antenna and Microwave Research Lab. Iran University of Science & Technology Tehran Iran Dep. Electrical & Computer Eng. University of Waterloo Waterloo Canada

ISBN: (纸本)9781538682753;9781538682746

A novel complementary split-ring resonator (CSRR) based sensor for full characterization of magneto-dielectric materials is proposed. The CSRR is etched on the ground plane of a microstrip line and is loaded with materials under test. The sensor operation is based on the shift in the resonance frequency and the change in the quality factor of the loaded structure. The main idea behind this work is to localize the electric and magnetic fields in two separate zones. In an area of the CSRR, the magnetic field is localized with a high intensity while the electric field has a very low strength; therefore this zone can be used for sensing of magnetic permeability. On the other hand, in another area of the CSRR namely permeability sensing zone, the electric field has a high intensity while the magnetic field has a low intensity. By analysis of the measured resonance frequency and quality factor, the real and imaginary parts of the electric permittivity and the magnetic permeability of the material under test can be determined. The work is validated by providing experimental results and comparison with reference data.

关键词： Permeability Permittivity Magnetic resonance Q-factor Magnetic separation Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Machine learning for QoT estimation of unseen optical network states

arXiv

引用

arXiv 2018年

作者： Panayiotou, Tania Savva, Giannis Shariati, Behnam Tomkos, Ioannis Ellinas, Georgios KIOS CoE Dep. of Electrical and Computer Engineering University of Cyprus Nicosia1678 Cyprus Barcelona08034 Spain Athens Information Technology MarousiAthens15125 Greece

We apply deep graph convolutional neural networks for Quality-of-Transmission estimation of unseen network states capturing, apart from other important impairments, the inter-core crosstalk that is prominent in optica... 详细信息

关键词： Fiber optic networks

来源：评论

学校读者我要写书评

暂无评论

FF-CMNET: A CNN-BASED MODEL FOR FINE-GRAINED CLASSIFICATION OF CAR MODELS BASED ON FEATURE FUSION

FF-CMNET: A CNN-BASED MODEL FOR FINE-GRAINED CLASSIFICATION ...

引用

IEEE International Conference on Multimedia and Expo

作者： Ye Yu Qiang Jin Chang Wen Chen Dep. of Computer Science and Engineering State University of New York at Buffalo Buffalo USA School of Computer and Information Hefei University of Technology Hefei China School of Science and Engineering Chinese University of Hong Kong at Shenzhen Shenzhen China

We present in this paper a novel scheme for fine-grained car model classification based on convolutional neural network and feature fusion. This scheme is called FF-CMNET (Feature Fusion based Car Model Classification Net) and is based on the principle that the car frontal images can be partitioned into upper and lower parts that exhibit distinct feature distributions but are still structurally correlated to allow feature fusion. The characteristics of FF-CMNET include: (1) the design of two separate branches, named UpNet and DownNet, for extracting the features of upper parts and lower parts of the car frontal images separately;(2) a two-step fusion of features at the output of UpNet and DownNet and then again in FusionNet;and (3) the adoption of small convolution kernels and global average pooling. Extensive experiments conducted on a benchmark dataset, CompCars, show favorable results which demonstrate that the proposed FF-CMNET is able to outperform the state-of-the-art models in the classification of large datasets.

关键词： Fine-grained car model classification CNNs Feature fusion Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design Monitoring Electrical Power Consumtion at computer Cluster

引用

Journal of Physics: Conference Series 2020年第1期1445卷

作者： Alfianto, Enggar Agustini, Siti Muharom, Syahri Rusydi, Febdian Puspitasari, Ira Department of Computer System Institut Teknologi Adhi Tama Surabaya Jl. Arief Rachman Hakim No 100 Surabaya Indonesia Electrical Engineering Department Institut Teknologi Adhi Tama Surabaya Jl. Arief Rachman Hakim No 100 Surabaya Indonesia Theoretical Physics Research Group Dep. of Physics Fac. of Science and Technology Airlangga University Jl. Mulyorejo Surabaya Indonesia 60115 Dep. of the information system Fac. of Science and Technology Airlangga University Jl. Mulyorejo Surabaya Indonesia 60115

Electricity is one of the basic needs in the era of technological development, where all equipment must use electricity to operate such as computer, so that it requires a system that can monitor power consumption at computer cluster. To monitoring power consumption using WCS1800 to current sensor and microcontroller Atmega32 to data sensor process, and serial communication to send data to display at personal computer. From test system having two result, first is power consumption at computer cluster starting, where current value range is 0 to 38A with power consumption is 0 to 8360 watt. And second is power consumtion at computer cluster execution progran, current value is 27 to 40 A, with power consumption 5940 to 8800 watt. From this system has been design, the power consumption at computer cluster can be monitored and known value of energy consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big data analytics of inpatients flow with diabetes mellitus type 1 : Rrrevealing new awareness with advanced visualization of medical information system data 9

Big data analytics of inpatients flow with diabetes mellitus...

引用

9th International Conference On Cloud Computing, Data Science and Engineering, Confluence 2019

作者： Kolesnichenko, Olga Marochkina, Elena Komarov, Roman Mazelis, Lev Mazelis, Andrey Soldatov, Daniel Minushkina, Larisa Chernoskutov, Mikhail Averbukh, Vladimir Mikhaylov, Igor Martynov, Alexander Pulit, Valeriy Amelkin, Sergey Grigorevsky, Ivan Kolesnichenko, Yuriy Institute of Social Sciences Clinic of Aortic Cardiovascular Surgery of I. M. Sechenov First Moscow State Medical University Moscow Russia Department of Mathematics and Modeling Vladivostok State University of Economics and Service Vladivostok Russia Department of Therapy Cardiology and Nephrology CS Medical Academy Dep. of Presidential Affairs Moscow Russia Department of N.N. Krasovskii Institute of Mathematics and Mechanics Institute of Natural Sciences Mathematics of Ural Federal University Computer Visualization Yekaterinburg Russia SP.ARM St.-Petersburg Russia A.K. Aylamazyan Program Systems Institute of RAS National Supercomputing Technology Platform Pereslavl Zalessky Russia Uzgraph Moscow Russia

ISBN: (纸本)9781538659335

Big Data Analytics with Advanced Data Visualization of Medical information system qMS records is presented. The inpatients with Diabetes Mellitus type 1 were chosen for analysis. The various methods of analysis and visualization were implemented: Gray reflected binary code (Java), Cluster analysis (iPython), Graph analysis (iPython, Gephi), 3D Visualization (Java), as well as supercomputer "Uran" was used. The connected pathogenetic Continuum of Diabetes Mellitus type 1 was built. The Continuum of Diabetes Mellitus type 1 progression allows assume that Parathyroid hormone-related protein (PTHrP) plays the critical role in multi-organ pathogenetic cascade in this disease, including the development of Lung cancer. Based on our study we suggest considering PTHrP in terms of pharmacological treatment. Big Data Analytics including Cluster and Graph Analysis of Medical information system's data flow can be used to study pathogenesis of the disease and for new drugs creation proposal. © 2019 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

A Compact 9 GHz Microwave Imaging System

A Compact 9 GHz Microwave Imaging System

引用

IEEE International Workshop on Electromagnetics, Applications and Student Innovation (iWEM)

作者： Kang-Chun Peng Chiu-Chin Lin Cyuan-Fong Li Cheng-Yuan Hung Yu-Sung Hsieh Dep. of Computer and Communication Engineering National Kaohsiung Univ. of Science and Technology Kaohsiung Taiwan Opto-electronics Equipment Department Metal Industries Research & Development Center Kaohsiung Taiwan

This work develops a compact 9 GHz microwave imaging system. The core of the system is a vector network analyzer (VNA) which utilizes range-correlation architecture to suppress the phase noise of the received signal. To overcome the bottleneck that conventional mixer-based phase detectors have limited phase detection range, a novel quadrature phase detection algorithm is proposed. The experimental results show that the microwave imaging system can well detect the bone image of a chicken wing.

关键词： Microwave imaging Microwave oscillators Microwave antennas Microwave communication

来源：评论

学校读者我要写书评

暂无评论

Energy management of a single grid-connected home microgrid for determining optimal supply/demand bids 5

Energy management of a single grid-connected home microgrid ...

引用

5th International Symposium on Environment-Friendly Energies and Applications, EFEA 2018

作者： Fouladfar, Mohammad Hossein Sumaiti, Ameena Al Fenik, Mohammed Seddik Marzband, Mousa Busawon, Krishna Pouresmaeil, Edris Science and Research of Bushehr Branch Islamic Azad University Bushehr Iran Electrical and Computer Engineering Khalifa University of Science and Technology Masdar Institute Abu Dhabi United Arab Emirates Faculty of Engineering and Environment Dep. of Maths Physics and Electrical Engineering Northumbria University Newcastle Newcastle United Kingdom Department of Electrical Engineering and Automation Aalto University Espoo Finland

ISBN: (纸本)9781538655177

As a result of socio-economic growth and paying attention to environmental aspects requirement in order to improve the reliability and achieve higher service, better power quality and increasing energy efficiency are taken more into consideration. Thus, home micro-grids (H-MG) with non-dispatchable Source and interruptible loads can be used as the primary tool to achieve the stated objectives. In order to implement the energy management system (EMS) an algorithm is presented in this paper. EMS which is based on harmony search method for multi-purpose extrapolation of a sample H-MG with renewable energy sources (RES) as well as compound resources of backup power such as micro-turbine and battery for levelling the mismatch of power or for additional power saving in case of necessary. In this paper, the harmony search (HS) for an algorithm to minimize the costs associated with sources, RLD and reduce the price of the electricity (i.e. market clearing price) with respect to the proposed price of production and supply, the price of non-interruptible loads, the optimal production of each of the existing resources in the micro grid is determined. For reliability enhancement the uncertainty is considered in using wind turbines (WT), photovoltaic (PV), load demand and market clearing price in the algorithm. The recommended algorithm system is tested on a H-MG sample. These results show the capability of the HS approach in supplying the load requested. © 2018 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

A Load Balancing Algorithm for Resource Allocation in IEEE 802.15.4e Networks

A Load Balancing Algorithm for Resource Allocation in IEEE 8...

引用

IEEE International Conference on Pervasive Computing and Communications

作者： Katina Kralevska Dimitrios J. Vergados Yuming Jiang Angelos Michalas Dep. of Information Security and Communication Technology NTNU Norwegian University of Science and Technology School of Electrical and Computer Engineering National Technical University of Athens Department of Informatics Engineering Technological Education Institute of Western Macedonia Kastoria Greece

ISBN: (纸本)9781538632284

The recently created IETF 6TiSCH working group combines the high reliability and low-energy consumption of IEEE 802.15.4e Time Slotted Channel Hopping with IPv6 for industrial Internet of Things. We propose a distributed link scheduling algorithm, called Local Voting, for 6TiSCH networks that adapts the schedule to the network conditions. The algorithm tries to equalize the link load (defined as the ratio of the queue length over the number of allocated cells) through cell reallocation. Local Voting calculates the number of cells to be added or released by the 6TiSCH Operation Sublayer (6top). Compared to a representative algorithm from the literature, Local Voting provides simultaneously high reliability and low end-to-end latency while consuming significantly less energy. Its performance has been examined and compared to On-the-fly algorithm in 6TiSCH simulator by modeling an industrial environment with 50 sensors.

关键词： Schedules IEEE 802.15 Standard Scheduling algorithms Reliability Resource management Scheduling Computational modeling management of resources Scheduling algorithms Computational modeling Link Load Resource utilization Vote INSTITUTE OF ELECTRICAL AND ELECTRONIC ENGINEERS Internet of things IPv6 Load balancing

来源：评论

学校读者我要写书评

暂无评论

CFD analysis on MHD flow of two-fluid model for blood rheology in constricted arteries 7

CFD analysis on MHD flow of two-fluid model for blood rheolo...

引用

7th Brunei International Conference on Engineering and technology 2018, BICET 2018

作者： Sankar, D.S. Nagar, Atulya K. Viswanathan, K.K. Vanav Kumar, A. School of Applied Sciences and Mathematics Universiti Teknologi Brunei GadongBE1410 Brunei Department of Mathematics and Computer Science Liverpool Hope University Hope Park LiverpoolL16 9JD United Kingdom Dep. of Mathematics Kuwait College of Science and Technology Doha District P.O. Box No. 27135 Safat13133 Kuwait Department of Mathematics National Institute of Technology Yupia Arunachal Pradesh791112 India

ISBN: (纸本)9781785617911

This computational study analyses the pulsatile flow of blood in a narrow artery with mild asymmetric stenosis, treating the blood flow as two-layered model with the suspension of all the erythrocytes in the core layer region as Casson fluid and the cell dep.eted plasma in the peripheral layer region as Newtonian fluid. Finite difference method is employed to solve the resulting system of non-linear partial differential equations along with a set of initial and boundary conditions. Explicit finite difference scheme is derived for velocity profile, flow rate, wall shear stress and longitudinal impedance to flow. It is noted that skin friction and longitudinal impedance to flow increase with the increase of yield stress, Hartmann number and stenosis dep.h. The aforementioned fluid behaviour is reversed to the velocity profile and flow rate when these parameters increase. It is found that the longitudinal impedance to flow for the two-fluid Casson model is considerably lower than that of the single-fluid Casson model. © 2018 Institution of Engineering and technology. All rights reserved.

关键词： Finite difference 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：