检索结果-内蒙古大学图书馆

International Conference on Optics Photonics and Energy Engineering (OPEE)

作者： Changhao Piao Xiaoyong Yang Cong Teng HuiQian Yang Ministry of Education Key Lab of Network Control Technology & Intelligent Instruments Chongqing University of Posts and Telecommunications Chongqing China Ministry of Education Key Lab of Network Control Tech. & Intelligent Instruments Chongqing University of Posts and Communications China Research Center of Energy Electronics Chongqing University of Posts and Telecommunications China Chongqing Changan New Energy Automobile Company Limited Chongqing China

ISBN: (纸本)9781424452347;9781424452354;9781424452361

Based on artificial neural networks and Thenvenin model, this paper uses an improved model predicting state of charge. We combine artificial neural networks model with Thevenin model, and predict state of charge in real time at the same time. When the difference between the predictive value of artificial neural networks model and the predictive value of Thevenin model is more than 10%, we revised the predictive value of artificial neural networks model by weighted average value. The results show that it can reduce the error of artificial neural networks model obvious and the average error is 4.72%. It is lower independence on initial state of charge than artificial neural networks model.

关键词： Artificial neural networks Nickel Batteries Predictive models Input variables Hybrid electric vehicles neural networks Artificial intelligence Neurons optical computing

来源：评论

学校读者我要写书评

暂无评论

The energy spectrum of atmospheric neutrinos between 2 and 200 TeV with the AMANDA-II detector

引用

ASTROPARTICLE PHYSICS 2010年第1期34卷 48-58页

作者： Abbasi, R. Abdou, Y. Abu-Zayyad, T. Adams, J. Aguilar, J. A. Ahlers, M. Andeen, K. Auffenberg, J. Bai, X. Baker, M. Barwick, Sw Bay, R. Alba, J. L. Bazo Beattie, K. Beatty, J. J. Bechet, S. Becker, J. K. Becker, K. -H. Benabderrahmane, M. L. Berdermann, J. Berghaus, P. Berley, D. Bernardini, E. Bertrand, D. Besson, D. Z. Bissok, M. Blaufuss, E. Boersma, D. J. Bohm, C. Boeser, S. Botner, O. Bradley, L. Braun, J. Buitink, S. Carson, M. Chirkin, D. Christy, B. Clem, J. Clevermann, F. Cohen, S. Colnard, C. Cowen, D. F. D'Agostino, M. V. Danninger, M. De Clercq, C. Demiroers, L. Depaepe, O. Descamps, F. Desiati, P. de Vries-Uiterweerd, G. DeYoung, T. Diaz-Velez, J. C. Dreyer, J. Dumm, J. P. Duvoort, M. R. Ehrlich, R. Eisch, J. Ellsworth, R. W. Engdegard, O. Euler, S. Evenson, P. A. Fadiran, O. Fazely, A. R. Fedynitch, A. Feusels, T. Filimonov, K. Finley, C. Foerster, M. M. Fox, B. D. Franckowiak, A. Franke, R. Gaisser, T. K. Gallagher, J. Ganugapati, R. Geisler, M. Gerhardt, L. Gladstone, L. Gluesenkamp, T. Goldschmidt, A. Goodman, J. A. Grant, D. Griesel, T. Gross, A. Grullon, S. Gunasingha, R. M. Gurtner, M. Ha, C. Hallgren, A. Halzen, F. Han, K. Hanson, K. Helbing, K. Herquet, P. Hickford, S. Hill, G. C. Hoffman, K. D. Homeier, A. Hoshina, K. Hubert, D. Huelsnitz, W. Huelss, J. -P. Hulth, P. O. Hultqvist, K. Hussain, S. Imlay, R. L. Ishihara, A. Jacobsen, J. Japaridze, G. S. Johansson, H. Joseph, J. M. Kampert, K. -H. Kappes, A. Karg, T. Karle, A. Kelley, J. L. Kemming, N. Kenny, P. Kiryluk, J. Kislat, F. Klein, S. R. Knops, S. Koehne, J. -H. Kohnen, G. Kolanoski, H. Koepke, L. Koskinen, D. J. Kowalski, M. Kowarik, T. Krasberg, M. Krings, T. Kroll, G. Kuehn, K. Kuwabara, T. Labare, M. Lafebre, S. Laihem, K. Landsman, H. Lauer, R. Lehmann, R. Lennarz, D. Luenemann, J. Madsen, J. Majumdar, P. Maruyama, R. Mase, K. Matis, H. S. Matusik, M. Meagher, K. Merck, M. Meszaros, P. Meures, T. Middell, E. Milke, N. Montaruli, T. Morse, R. Movit, S. M. Muenich, K. Nahnhauer, R. Nam, J. W. Naumann, U. Niessen, P. Nygren, D. R. O Ruhr Univ Bochum Fak Phys & Astron D-44780 Bochum Germany Rhein Westfal TH Aachen Inst Phys 3 D-52056 Aachen Germany Univ Alabama Dept Phys & Astron Tuscaloosa AL 35487 USA Univ Alaska Dept Phys & Astron Anchorage AK 99508 USA Clark Atlanta Univ CTSPS Atlanta GA 30314 USA Georgia Inst Technol Sch Phys Atlanta GA 30332 USA Georgia Inst Technol Ctr Relativist Astrophys Atlanta GA 30332 USA Southern Univ Dept Phys Baton Rouge LA 70813 USA Univ Calif Berkeley Dept Phys Berkeley CA 94720 USA Univ Calif Berkeley Lawrence Berkeley Lab Berkeley CA 94720 USA Humboldt Univ Inst Phys D-12489 Berlin Germany Univ Bonn Inst Phys D-53115 Bonn Germany Univ W Indies Dept Phys BB-11000 Bridgetown Barbados Univ Libre Bruxelles Fac Sci B-1050 Brussels Belgium Vrije Univ Brussel B-1050 Brussels Belgium Chiba Univ Dept Phys Chiba 2638522 Japan Univ Canterbury Dept Phys & Astron Christchurch New Zealand Univ Maryland Dept Phys College Pk MD 20742 USA Ohio State Univ Dept Phys Columbus OH 43210 USA Ohio State Univ Ctr Cosmol & Astroparticle Phys Columbus OH 43210 USA Ohio State Univ Dept Astron Columbus OH 43210 USA TU Dortmund Univ Dept Phys D-44221 Dortmund Germany Univ Alberta Dept Phys Edmonton AB T6G 2G7 Canada Univ Ghent Dept Subatom & Radiat Phys B-9000 Ghent Belgium Max Planck Inst Kernphys D-69117 Heidelberg Germany Univ Calif Irvine Dept Phys & Astron Irvine CA 92697 USA Ecole Polytech Fed Lausanne High Energy Phys Lab CH-1015 Lausanne Switzerland Univ Kansas Dept Phys & Astron Lawrence KS 66045 USA Univ Wisconsin Dept Astron Madison WI 53706 USA Univ Wisconsin Dept Phys Madison WI 53706 USA Johannes Gutenberg Univ Mainz Inst Phys D-55099 Mainz Germany Univ Mons B-7000 Mons Belgium Univ Delaware Dept Phys & Astron Newark DE 19716 USA Univ Delaware Bartol Res Inst Newark DE 19716 USA Univ Oxford Dept Phys Oxford OX1 3NP England Univ Wisconsin Dept Phys River Falls WI 54022 USA Univ Wisconsin Dept Phys River Falls WI 5402

The muon and anti-muon neutrino energy spectrum is determined from 2000-2003 AMANDA telescope data using regularised unfolding. This is the first measurement of atmospheric neutrinos in the energy range 2-200 TeV. The result is compared to different atmospheric neutrino models and it is compatible with the atmospheric neutrinos from pion and kaon decays. No significant contribution from charm had-ron decays or extraterrestrial neutrinos is detected. The capabilities to improve the measurement of the neutrino spectrum with the successor experiment IceCube are discussed. (c) 2010 Elsevier B.V. All rights reserved.

关键词： Atmospheric neutrinos Unfolding neural net AMANDA Cherenkov radiation

来源：评论

学校读者我要写书评

暂无评论

Optimal Design for the Supporting Structure of the Deformable Mirror

Optimal Design for the Supporting Structure of the Deformabl...

引用

International Conference on Computational Intelligence and Natural computing, CINC

作者： Fu Zhao Yanjue Gong Li Zhang Huiyu Xiang Ping Wang College of Mechanical Engineering Beijing Technology and Business University Beijing China Department of Optical Engineering Beijing Institute of Technology Beijing China

This paper describes the optimization solution to improve the dynamic stiffness of the deformable mirror supporting structure. With the methods of Finite element analysis(FEA), Orthogonal experiment and BP neural network, the relationship between the structure parameters of the deformable mirror supporting structure and its resonate frequency is built. With this relationship and Genetic Algorithm(GA) optimal design, a group of reasonable structure parameters are found that can improve the dynamic stiffness of the deformable mirror supporting structure.

关键词： Mirrors neural networks Adaptive optics Finite element methods optical distortion Modal analysis Shape Neurons Design optimization Deformable models

来源：评论

学校读者我要写书评

暂无评论

A proposed life cycle forecasting model of complex recycling technical systems by implementing neural super network

A proposed life cycle forecasting model of complex recycling...

引用

International Conference on networked Digital Technologies, NDT

作者： Khalil A. Yaghi Waheeb A. Abu-Dawwas Department of Management Information Systems Science Private University Jordan Department of Information Systems Petra University Jordan

The purpose of this paper is to increase the efficiency of functionality and reliability of complex recycling technical systems (CRTS) community, through improving the control quality of their life cycle. Automated control system (ACS) on the basis of neural super-network learning for forecasting damages and ensuring its information representation for learning was proposed. In the paper it was suggested an architecture and a method of learning of a neural super-network for forecasting the progress of CRTS community life cycle.

关键词： Predictive models Recycling Cathode ray tubes neural networks Automatic control Control systems Artificial neural networks Management information systems Information representation optical computing

来源：评论

学校读者我要写书评

暂无评论

Statistical physics on cellular neural network computers

引用

PHYSICA D-NONLINEAR PHENOMENA 2008年第9期237卷 1226-1234页

作者： Ercsey-Ravasz, M. Roska, T. Neda, Z. Pazmany Peter Catholic Univ Dept Informat Technol HU-1083 Budapest Hungary Univ Babes Bolyai Dept Phys RO-400084 Cluj Napoca Romania

The computational paradigm represented by Cellular neural/nonlinear networks (CNN) and the CNN Universal Machine (CNN-UM) as a Cellular Wave Computer, gives new perspectives also for computational statistical physics. Thousands of locally interconnected cells working in parallel, analog signals giving the possibility of generating truly random numbers, continuity in time and the optical sensors included on the chip are just a few important advantages of such computers. Although CNN computers are mainly used and designed for image processing, here we argue that they are also suitable for solving complex problems in computational statistical physics. This study presents two examples of stochastic simulations on CNN: the site-percolation problem and the two-dimensional Ising model. Promising results are obtained using an ACE16K chip with 128 x 128 cells. In the second part of the work we discuss the possibility of using the CNN architecture in studying problems related to spin-glasses. A CNN with locally variant parameters is used for developing an optimization algorithm on spin-glass type models. Speed of the algorithms and further trends in developing the CNN chips are discussed. (c) 2008 Elsevier B.V. All rights reserved.

关键词： cellular neural network CNN universal machine unconventional computing cellular wave computers

来源：评论

学校读者我要写书评

暂无评论

neural network training: Using untransformed or log-transformed training data for the inversion of ocean colour spectra?

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2006年第9-10期27卷 2011-2016页

作者： Dransfeld, S Tatnall, AR Robinson, IS Mobley, CD Univ Hamburg Inst Meereskunde D-20253 Hamburg Germany Southampton Oceanog Ctr Southampton SO17 1BJ Hants England Sequoia Sci Inc Westpk Tech Ctr Redmond WA 98052 USA

A bio-optical model coupled with the radiative transfer model Hydrolight was used to create 18,000 synthetic ocean colour spectra corresponding to open ocean and coastal waters. The bio-optical model took into account the optical properties of the three oceanic constituents, chlorophyll-a, suspended non-chlorophyllous particles and coloured dissolved organic matter (CDOM) as well as of normal seawater. The resulting spectra were input into multilayer perceptron neural network algorithms with the aim of computing the original concentrations of chlorophyll-a, non-chlorophyllous particles and CDOM initially input into the bio-optical model. The process of training the neural networks is essential for the accuracy of the inversion the neural net performs on the coupled bio-optical and radiative transfer models. The objective of this paper is to investigate the performance difference of a neural network trained with untransformed as opposed to logarithmically transformed data.

关键词： REMOTE sensing neural networks (Computer science) OCEAN color optical oceanography CHLOROPHYLL

来源：评论

学校读者我要写书评

暂无评论

CITSA 2006 - 3rd International Conference on Cybernetics and Information Technologies, Systems and Applications, Jointly with the 4th International Conference on computing, Communications and Control Technologies, CCCT 2006 - Proceedings

CITSA 2006 - 3rd International Conference on Cybernetics and...

引用

3rd International Conference on Cybernetics and Information Technologies, Systems and Applications, CITSA 2006, Jointly with the 4th International Conference on computing, Communications and Control Technologies, CCCT 2006

ISBN: (纸本)9806560833

The proceedings contain 127 papers. The topics discussed include: encryption models for patient record databases;on the feasibility of a statewide patient record database;an algorithm for massive loading of raster geo-spatial data;patient flow optimization model;properties investigation of thin films photovoltaic hetero-structures;ultra-fast optical signal processing based on nonlinear optical effects in quantum dot semiconductor optical amplifiers (QD SOAs);visualization of nanoscale processes by image processing methods;nano indentation inspection of the mechanical properties of gold nitride thin films;computerized analysis of flowing conditions for use of chemical sticks in natural gas wells;implementation of a neural network controller on a real time system;type-2 fuzzy set based neuro-fuzzy model for identification and control of nonlinear systems;and intelligent control of blood glucose for diabetes mellitus patient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CITSA 2006 - 3rd International Conference on Cybernetics and...

引用

ISBN: (纸本)9806560841

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral aquatic radiative transfer modeling using cluster computing

Hyperspectral aquatic radiative transfer modeling using clus...

引用

Annual Conference of the American Society for Photogrammetry and Remote Sensing 2006: Prospecting for Geospatial Information Integration, ASPRS 2006

作者： Filippi, Anthony M. Bhaduri, Budhendra L. Naughton III, Thomas J. King, Amy L. Scott, Stephen L. Department of Geography College of Geosciences Texas A and M University College Station TX United States Oak Ridge National Laboratory One Bethel Valley Road Oak Ridge TN 37831 United States

ISBN: (纸本)9781604237290

Estimating aquatic biophysical quantities from remote sensor imagery is an inverse problem, which is still unsolved. In this research, forward-modeling was considered to ultimately address the inverse problem of hydrologic optics. Above-surface hyperspectral remote-sensing reflectance can be inverted to yield bottom depth and various inherent and bottom optical properties. Retrievals can be obtained by using an artificial neural network (ANN) or similar algorithm. However, due to the paucity of measured oceanic field/organic training and testing sets, synthetic data generation is usually necessary to train such an algorithm in this application domain. Such modeled data sets, which can be quite large, are typically computationally expensive and time-consuming to generate. To accomplish this efficiently, a cluster computing method was developed to produce a forward-modeled, hyperspectral bio-optical database, based on radiative transfer (RT) theory. This method enables multiple instances of the Hydrolight RT model to be run in parallel. The Hydrolight runs are independent of one another, making them good candidates for parallelization, thus reducing the time required to generate the synthetic training/testing data. The resultant inputoutput pairs in the forward-modeled database can be used to develop remote-sensing inverse algorithms. Bathymetry and water-column and bottom optical models can thus be developed while minimizing the need for in situ data, which is useful in an operational environment. Simulated remote-sensing reflectance pseudodata are of utility in hydrologic inversion since adequate field data for model development are often difficult or impractical to acquire.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

Natural image classification in non linear network model

Natural image classification in non linear network model

引用

SPIE - The International Society for optical Engineering

作者： Azhar, Hanif Iftekharuddin, Khan Kozma, Robert Admala, Abhinav Intelligent Systems and Image Processing Lab. Electrical and Computer Engineering Department University of Memphis TN 38152 United States Computer Science Department University of Memphis TN 38152 United States

We study the non-linear behavior of the KIII model for natural image classification. The KIII model is designed to be a dynamic computational model that simulates the sensory cortex. The KIII model has been explored for rudimentary pattern recognition and classification in noisy environment [1-3]. We extend the study of KIII models in understanding whether self-organized neural populations can be exploited into perceptual and memory producing systems such as in natural image classification. Our goal is to obtain a quantitative index on how well the KIII model behaves when it is assigned the task to identify and distinguish one class of natural image from the other based on color and texture features. For twenty training data, twenty validation data and eighty test data set for four image classes, we obtain 80% correct classification using the KIII. We compare a standard non linear neural network tools such as back propagation for the classification of the same set of natural images and obtain 65% correct classification. We conclude that dynamic neural computational models such as KIII may be suitable candidates for natural image classification.

关键词： Image segmentation

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：