检索结果-内蒙古大学图书馆

Optimization of multilayer coatings for future high-energy focusing telescopes

Optimization of multilayer coatings for future high-energy f...

Conference on Space Telescopes and Instrumentation - Ultraviolet to Gamma Ray Part of SPIE Astronomical Telescopes and Instrumentation Conference

作者： Gellert, N. C. Massahi, S. Ferreira, D. D. M. Christensen, F. E. Svendsen, S. Jegers, A. S. Madsen, K. K. Tech Univ Denmark DTU Space Elektrovej 328 DK-2800 Lyngby Denmark NASA Goddard Space Flight Ctr CRESST Greenbelt MD 20771 USA NASA Goddard Space Flight Ctr Xray Astrophys Lab Greenbelt MD 20771 USA Univ Maryland Baltimore Cty Dept Phys Baltimore MD 21250 USA Univ Maryland Baltimore Cty Ctr Space Sci & Technol Baltimore MD 21250 USA

ISBN: (纸本)9781510653443;9781510653436

Nanometer-thin multilayer coatings can enable high performance of focusing X-ray telescopes to energies up to 200 keV and beyond. In this paper we discuss the multilayer parameters and their limitations necessary for the reflection of hard X-ray photons. We present several multilayer coating designs that are optimized with a differential evolution algorithm to perform a stochastic global search of the multi-parametric model space. The coating designs are based on the new specifications of the HEX-P mission geometry, optimizing within the energy range 60 keV - 200 keV. We compare the simulated reflectivity spectra of Si/Ni, Si/Pt and Si/W, at different incident angles. We find the effective upper limit of bilayers in the multilayer stack, beyond which reflectivity will not be increased. We discuss a hybrid multilayer coating design, consisting of either a Si/Pt or Si/W multilayer with a top Si/Ni multilayer.

关键词： Thin film Optimization Multilayer coating High-energy astrophysics Focusing optics X-ray telescopes Grazing incidence angle differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Examination of the ECG signal classification technique DEA-ELM using deep convolutional neural network features

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第16期80卷 24777-24800页

作者： Diker, Aykut Sonmez, Yasin Ozyurt, Fatih Avci, Engin Avci, Derya Bandirma Onyedi Eylul Univ Dept Software Engn TR-10200 Balikesir Turkey Batman Univ Tech Sci Vocat Sch TR-72000 Batman Turkey Firat Univ Technol Fac Software Engn TR-23000 Elazig Turkey Firat Univ Tech Sci Vocat Sch TR-23000 Elazig Turkey

The accurate separation of ECG signals has become crucial to identify heart diseases. Machine learning methods are widely used to separate ECG signals. The aim of this study was to obtain optimal number of hidden neurons of the Extreme Learning Machine (ELM) using the differential evolution algorithm (DEA) and increase the accuracy rate of ECG classification. In this study, a public database on PhysioNet was used for ECG signal classification. A deep feature method using convolutional neural network was used to extract the major features of the ECG samples. Then, a conventional ELM was applied to the ECG signals. Subsequently, the ECG signals with deep properties were shared with the MATLAB classifier toolbox (k-NN, SVM, Decision Trees). In addition, the ECG signals in the dataset were tested using the Genetic algorithm Wavelet Kernel-ELM (GAWK-ELM). Finally, the DEA-ELM was improved for the determination of the number of hidden neurons. This study optimized the hidden neuron numbers of traditional ELM with DEA using deep learning capabilities in the feature extraction. The aim of was to maximize the best cost of the DEA and achieve the optimal number of hidden neurons in ELM. Accuracy (Acc), sensitivity (Se), specificity (Spe) and F-measure were used as the performance metrics for the classifier performances. The classification results were 80.60%, 81.50%, and 83.12% with SVM, ELM and DEA-ELM, respectively. Thus, the best classification scores were accomplished with an accuracy of 83.12% with the algorithm supported by the DEA.

关键词： Convolutional neural network Deep features differential evolution algorithm Electrocardiogram Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Sufficient Structural Conditions for Diagnosability and Heuristic Diagnoser Design in Timed Continuous Petri Nets

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2021年第11期19卷 3588-3597页

作者： Casas Carrillo, Ricardo Begovich Mendoza, Ofelia Ramirez Trevino, Antonio Ruiz Leon, Javier IPN CINVESTAV Unidad Guadalajara Av Bosque 1145 Zapopan 45017 Jalisco Mexico Intel Corp Av Bosque 1101 Zapopan 45017 Jalisco Mexico

This work is concerned with a structural characterization of the diagnosability property in Timed Continuous Petri Nets (TCPNs) systems under infinite server semantics. Regarding this problem, three novel results are presented. The first one is the introduction of structural sufficient conditions for diagnosability in TCPNs, which are based on the concepts of relative degree, system distinguishability, and parameter identification. To this aim, the concept of a simple directed path from other works is extended to diagnosable directed paths. These new paths include attribution-places, pre-join-places and post-join-places, which allows to deal with multiple non-concurrent tokens-leak faults, and enlarging the class of systems that can be analyzed. Based on these structural conditions, a novel methodology to place a reduced number of sensors that guarantees the net diagnosability is proposed. Finally, a diagnoser based on a modified differential evolution algorithm is presented, which introduces individual searching sets in orthogonal spaces to diagnose (detect, locate, and identify) faults when an error is detected, avoiding the use of a bank of diagnosers of other approaches. The effectiveness and applicability of the main results are illustrated through an illustrative example.

关键词： Diagnosability differential evolution algorithm sensor placement structural analysis switched linear systems timed continuous Petri nets

来源：评论

学校读者我要写书评

暂无评论

An assembly deviation calculation method based on surface deviation modeling for circumferential grinding plane

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE 2021年第6-7期235卷 1050-1060页

作者： Qiao, Lihong Shao, Peilin Zhao, Hanqing Huang, Zhicheng Beihang Univ Beijing Peoples R China

Performance of mechanical product is highly influenced by assembly deviation. Due to manufacturing errors, the real part surface is machined with morphology deviations, which would cause mating surface deviating from ideal position in assembly behavior, consequently leading to assembly deviation. Meanwhile, the random variation of relative position and orientation between two non-ideal parts also affects the assembly deviation. To efficiently obtain the maximum assembly deviation considering the comprehensive influence of two factors above for circumferential grinding plane, an assembly deviation calculation method based on surface deviation modeling is proposed in this paper. In this method, morphology deviations models of part surfaces are firstly established from the deviation function. The randomness of two factors are represented by a multivariate group with randomness containing deviation function coefficients and three deflected parameters. Then based on surface deviation modeling method, differential evolution algorithm is applied to search the maximum assembly deviation, which involves the construction of fitness function by implementing optimized progressive contact method and iterative operations of mutation, crossover and selection. Finally, the effectiveness of this method is illustrated by an assembly in the end.

关键词： Non-ideal surface assembly deviation deviation modeling Euler angle differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Early Considerations for Unit's Induced Electric Behaviour Characterization in the Extreme Low Frequency Domain

Early Considerations for Unit's Induced Electric Behaviour C...

引用

International Symposium on Electromagnetic Compatibility (EMC Europe)

作者： Baklezos, Anargyros T. Nikolopoulos, Christos D. Papastamatis, Panagiotis K. Kapetanakis, Theodoros N. Vardiambasis, Ioannis O. Capsalis, Christos N. Hellen Mediterranean Univ Dept Elect Engn Sch Engn Khania Greece Natl Tech Univ Athens Sch Elect & Comp Engn Zografos Greece Natl Tech Univ Athens Sch Elect & Comp Engn Zografos Greece

ISBN: (数字)9781665407885

ISBN: (纸本)9781665407885

The majority of space science missions aim to measure weak slow varying electromagnetic fields and in order to do so, need to meet strict cleanliness requirements. The accurate characterization of equipment in the extremely low-frequency domain (below several hundred kHz) should include the direct emitted electric field as well as the induced behavior of the device due to the unit-to-unit interaction. Following a detailed characterization at the unit level, the unit-to-unit interaction is attributed to the near field scattering effect, usually considering the scatterer as a small sphere. This way the induced behavior of the unit can be described by an oscillating dipole coherent to the incident field. This work highlights the importance of induced behavior of the units at the system level for accurate system predictions in the case that the scatterer can't be considered as a small sphere due to dielectric materials or complex unit geometry. The authors aim to characterize the induced behavior by solving the inverse electromagnetic scattering problem through a customized measurement procedure.

关键词： differential evolution algorithm Induced Dipole EM Simulation

来源：评论

学校读者我要写书评

暂无评论

Aircraft Fuel Consumption Prediction Method Based on Just-In-Time Learning and Enhanced Fifitness Adaptive-differential evolution-Relevance Vector Machine

Aircraft Fuel Consumption Prediction Method Based on Just-In...

引用

Chinese Automation Congress (CAC)

作者： Wang Xi Chen Jingjie Civil Aviat Univ China Coll Comp Sci & Technol Tianjin 300300 Peoples R China Civil Aviat Univ China Coll Elect Informat & Automat Tianjin 300300 Peoples R China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176871

In order to accurately predict the fuel consumption of fixed aircraft model and in view of the non-linearity of fuel consumption data, which affected by various external factors, a forecast model of aircraft fuel consumption based on just-in-time learning and enhanced fitness adaptive differential evolution relevance vector machine (EFADE-RVM) is proposed. By introducing the just-in-time learning algorithm of 'similar input produce similar output' to select the relevant sample set, and using the enhanced adaptive differential evolution (DE) algorithm to improve the parameters of the relevance vector machine kernel function. Thus, an aircraft fuel consumption prediction model is established. The experimental results show that the improvement method gets better prediction performance.

关键词： Aircraft fuel consumption prediction just-in-time learning algorithm enhanced fitness adaptive algorithm differential evolution algorithm relevance vector machine

来源：评论

学校读者我要写书评

暂无评论

Time series prediction based on fuzzy-membership cerebellar model neural network with differential evolution

Time series prediction based on fuzzy-membership cerebellar ...

引用

Chinese Automation Congress (CAC)

作者： Dong, Jingjiao Li, Wenjing Qiao, Junfei Beijing Univ Technol Fac Informat Technol Beijing Peoples R China

ISBN: (纸本)9781728176871

In this paper, a fuzzy-membership cerebellar model neural network with differential evolution (DEFM-CMNN) is proposed, which improves the prediction accuracy of the cerebellar model neural network based on fuzzy membership (FM-CMNN) for prediction of time series. Firstly, use the linear quantization function of FM-CMNN input space to quantize the time series into nonlinear state variables. Secondly, the mutation, crossover and selection operations of the differential evolution (DE) algorithm are used to learn the connection weight of the network. Meanwhile, the adaptive mutation operator is introduced to enhance the diversity of individuals in the early stages of evolution. Finally, the effectiveness of the proposed DEFM-CMNN is demonstrated in experiments for time series prediction. The results show that this model has better real-time performance and higher prediction accuracy.

关键词： fuzzy-membership cerebellar model neural network differential evolution algorithm time series prediction

来源：评论

学校读者我要写书评

暂无评论

differential evolution algorithm Aided Minimum Symbol Error Rate Multi-user Detection for Multi-user OFDM/SDMA Systems

Differential Evolution Algorithm Aided Minimum Symbol Error ...

引用

IEEE 75th Vehicular Technology Conference (VTC Spring)

作者： Zhang, Jiankang Chen, Sheng Mu, Xiaomin Hanzo, Lajos Zhengzhou Univ Sch Informat Engn Zhengzhou Peoples R China Univ Southampton Sch ECS Southampton SO9 5NH Hants England

ISBN: (纸本)9781467309905;9781467309882

A differential evolution (DE) algorithm assisted Minimum Symbol Error Ratio (MSER) Multi-User Detection (MUD) scheme is proposed for multi-user Multiple-Input Multiple-Output (MIMO) aided Orthogonal Frequency-Division Multiplexing / Space Division Multiple Access (OFDM/SDMA) systems. Quadrature Amplitude Modulation (QAM) is employed in most wireless standards by virtue of providing a high throughput. The MSER Cost Function (CF) may be deemed to be the most relevant one for QAM, but finding its minimum is challenging. Hence we propose a sophisticated DE assisted MSER-MUD scheme, which directly minimizes the SER CF of multi-user OFDM/SDMA systems employing QAM. Furthermore, the effects of the DE assisted MSER-MUD's algorithmic parameters, namely those of the population size P-s, of the scaling factor lambda and of the crossover probability C-r on the number of DE generations required for attaining convergence were investigated in our simulations. This allowed us to directly quantify their complexity. The simulation results also demonstrate that the proposed DE assisted MSER-MUD scheme significantly outperforms the conventional MMSE-MUD in term of the system's overall BER and it is capable of narrowing its BER performance discrepancy with respect to the optimal Maximum Likelihood (ML) MUD to about 4dB, while requiring about 200 times less CF evaluations compared to the optimal ML-MUD scheme.

关键词： Orthogonal frequency division multiplexing (OFDM) space division multiple access (SDMA) minimum symbol error rate multi-user detection differential evolution algorithm

来源：评论

学校读者我要写书评

暂无评论

Conductance estimation of a conductance-based neuron model by the differential evolution algorithm

引用

BMC Neuroscience 2013年第1期14卷 1-2页

作者： Mao Suzuka Ryota Kobayashi Katsunori Kitano Graduate School of Science and Engineering Ritsumeikan University Kusatsu Shiga 5258577 Japan Department of Human and Computer Intelligence Ritsumeikan University Kusatsu Shiga 5258577 Japan

来源：评论

学校读者我要写书评

暂无评论

Modeling of a real industrial wastewater treatment plant based on aerated lagoon using a neuro-evolutive technique

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2021年 148卷 114-124页

作者： Godini, Kazem Azarian, Ghasem Kimiaei, Alireza Dragoi, Elena Niculina Curteanu, Silvia Kurdistan Univ Med Sci Environm Hlth Res Ctr Res Inst Hlth Dev Sanandaj Iran Hamadan Univ Med Sci Dept Environm Hlth Engn Fac Hlth Hamadan Hamadan Iran Hamadan Univ Med Sci Res Ctr Hlth Sci Hamadan Hamadan Iran Hamadan Ind Estate Co Hamadan Hamadan Iran Gheorghe Asachi Tech Univ Iasi Dept Chem Engn & Environm Protect Bd Dimitrie Mangeron 71A Iasi 700050 Romania

Aerated lagoons are biological systems used for the treatment of different types of wastewaters and many operating parameters influence the performance of these systems. Thus, in the current study, an industrial aerated lagoon system was modeled in terms of the operating parameters with the goal of predicting its performances under different operating conditions in order to highlight possible bottlenecks or potential improvements. For this purpose, a neuro-evolutive approach, combining differential evolution (DE) algorithm and artificial neural networks (ANN), was employed. Two DE variants based on opposition-based learning and of chaos theory were used to determine the optimal models and to perform a process optimization. Multiple models in various configurations (simple or organized in stacks, with single or multiple outputs) were determined. The mean squared error of the best solutions were in the order of 10(-4), illustrating a good agreement between the model predictions and experimental data and demonstrating the effectiveness and reliability of the developed models. (C) 2020 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.

关键词： Aerated lagoons Wastewater treatment Artificial neural networks differential evolution algorithm Modeling Optimization

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：