检索结果-内蒙古大学图书馆

NEUROCOMPUTING 2006年第16-18期69卷 2301-2308页

作者： Lin, Wei Chen, Tianping Fudan Univ Inst Math Inst Nonlinear Math Sci Shanghai 200433 Peoples R China

Since the backpropagation algorithm used for neural network training suffers from a slow convergence and often sticking in local minima, the restart mechanism has been introduced, whose strategy is to cut off the training process and restart it with a fresh initialization when it seems unlikely to converge in a relatively short time. In this paper, we give detailed mathematical analysis on two versions of the restart algorithms. By deriving analytic expressions of the expected convergence time and the success rate, we illustrate why the restart algorithms work well and gain insights into the proper use of restarting. Numerical simulations are performed on the XOR problem, symmetry detection, parity problem and Arabic numeral recognition. We show the effectiveness of the restart algorithms, and compare them with simulated annealing. The analysis can also be applied to many other fields. (c) 2005 Elsevier B.V. All rights reserved.

关键词： restart mechanism neural network training backpropagation algorithm gradient descent method

来源：评论

学校读者我要写书评

暂无评论

NN-LEAP:: A neural network-based model for controlling leachate flow-rate in a municipal solid waste landfill site

引用

ENVIRONMENTAL MODELLING & SOFTWARE 2006年第8期21卷 1190-1197页

作者： Karaca, Ferhat Ozkaya, Bestamin Yildiz Tech Univ Fac Civil Engn Dept Environm Engn TR-34349 Istanbul Turkey Fatih Univ Dept Environm Engn Istanbul Turkey

A method is proposed for modeling leachate flow-rate in a municipal solid waste (MSW) landfill site, based on a popular neural network - the backpropagation algorithm (neural network-based leachate prediction method;NN-LEAP). After backpropagation training, the neural network model predicts flow-rates based on meteorological data. Depending on output value, relevant control strategies and actions are activated. To illustrate and validate the proposed method, a case study was carried out, based on the data obtained from the Istanbul Odayeri landfill site. As a critical model parameter (neural network outputs), daily flow-rate of leachate from the landfill site was considered. The Levenberg-Marquardt algorithm was selected as the best of 13 backpropagation algorithms. The optimal neural network architecture has been determined, and the advantages, disadvantages and further developments are discussed. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： neural network backpropagation algorithm leachate flow-rate modeling

来源：评论

学校读者我要写书评

暂无评论

NN-AirPol: a neural-networks-based method for air pollution evaluation and control

引用

INTERNATIONAL JOURNAL OF ENVIRONMENT AND POLLUTION 2006年第3-4期28卷 310-325页

作者： Karaca, Ferhat Nikov, Alexander Alagha, Omar Fatih Univ Dept Environm Engn TR-34900 Istanbul Turkey Fatih Univ Dept Ind Engn TR-34900 Istanbul Turkey

A method for air pollution evaluation and control, based on one of the most popular neural networks - the backpropagation algorithm, is proposed. After the backpropagation training, the neural network, based on weather forecasting data, determines the future concentration of critical air pollution indicators. Depending on these concentrations, relevant episode warnings and actions are activated. A case study is carried out to illustrate and validate the method proposed, based on Istanbul air pollution data. Sulphur dioxide and inhalable particulate matter are selected as air pollution indicators (neural network outputs). Relevant episode measures are proposed. Among ten backpropagation algorithms, the BFGS algorithm (Quasi-Newton algorithms) is adopted since it showed the lowest training error. A comparison of NN-AirPol method against regression and perceptron models showed significantly better performance.

关键词： air pollution modelling backpropagation algorithm optimisation

来源：评论

学校读者我要写书评

暂无评论

Evolutionary training of hardware realizable multilayer perceptrons

引用

NEURAL COMPUTING & APPLICATIONS 2006年第1期15卷 33-40页

作者： Plagianakos, VP Magoulas, GD Vrahatis, MN Univ Patras Articicial Intelligence Res Ctr Computat Intelligence Lab Dept Math GR-26110 Patras Greece Univ London Sch Comp Sci & Informat Syst London WC1E 7HX England

The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks, provides tolerance to noise and improves the interpretation of the internal representations. In certain case, such as in learning stationary tasks, it may be sufficient to find appropriate weights for an MLP with threshold activation functions by software simulation and, then, transfer the weight values to the hardware implementation. Efficient training of these networks is a subject of considerable ongoing research. Methods available in the literature mainly focus on two-state (threshold) nodes and try to train the networks by approximating the gradient of the error function and modifying appropriately the gradient descent, or by progressively altering the shape of the activation functions. In this paper, we propose an evolution-motivated approach, which is eminently suitable for networks with threshold functions and compare its performance with four other methods. The proposed evolutionary strategy does not need gradient related information, it is applicable to a situation where threshold activations are used from the beginning of the training, as in "on-chip" training, and is able to train networks with integer weights.

关键词： feedforward neural networks backpropagation algorithm neural networks with threshold activations integer weight neural networks integer programming steepest descent unconstrained optimization differential evolution

来源：评论

学校读者我要写书评

暂无评论

Estimation of chemical oxygen demand by ultraviolet spectroscopic profiling and artificial neural networks

引用

NEURAL COMPUTING & APPLICATIONS 2006年第3-4期15卷 197-203页

作者： Fogelman, S Blumenstein, M Zhao, HJ Griffith Univ Ctr Aquat Proc & Pollut Sch Environm & Appl Sci Fac Environm SciGold Coast Mail Ctr Gold Coast Qld 9726 Australia Griffith Univ Sch Informat & Commun Technol Fac Engn & Informat Technol Gold Coast Mail Ctr Gold Coast Qld 9726 Australia

A simple method based on the mathematical treatment of spectral absorbance profiles in conjunction with artificial neural networks (ANNs) is demonstrated for rapidly estimating chemical oxygen demand (COD) values of wastewater samples. In order to improve spectroscopic analysis and ANN training time as well as to reduce the storage space of the trained ANN algorithm, it is necessary to decrease the ANN input vector size by extracting unique characteristics from the raw input pattern. Key features from the spectral absorbance pattern were therefore selected to obtain the spectral absorbance profile, reducing the ANN input vector from 160 to 10 selected inputs. The results indicate that the COD values obtained from the selected absorbance profiles agreed well with those obtained from the entire absorbance pattern. The spectral absorbance profile technique was also compared to COD values estimated by a multiple linear regression (MLR) model to validate whether ANNs were better and more robust models for rapid COD analysis. It was found that the ANN model predicted COD values closer to standard COD values than the MLR model.

关键词： chemical oxygen demand UV-vis spectroscopy artificial neural networks backpropagation algorithm multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

RBF neural network based model as an optimal classifier for the classification of radar returns from the ionosphere

RBF neural network based model as an optimal classifier for ...

引用

IEEE International Conference on Industrial Technology

作者： Salankar, Suresh S. Patre, Balasaheb M. BD Coll Engn Dept Elect & Telecommun Sevagram 442102 India SGGS Inst Engn & Technol Dept Instrumentat Nanded 431606 Maharashtra India

ISBN: (纸本)9781424407255

Research into the problem of classification of radar returns from the ionosphere has been taken up as a challenging task for the neural networks (NNs). It appears from the literature review that for the Multi layer Perceptron (MLP) NN trained with backpropagation, reported average classification accuracy was about 96% on the test instances. This paper investigates and designs an optimal classifier using a Radial Basis Function (RBF) NN. Authors compare the performance of two NN configurations, namely a well-known MLP NN model and the proposed RBF NN model on the radar dataset collected from the published studies. It is shown that the proposed RBF NN, consistently, has 100% accuracy on "bad" instances and 99.1935% accuracy on "good" instances. The results show that the proposed RBF NN classifier clearly outperforms the MP NN one in various performance measures such as MSE, NMSE, correlation coefficients, area under the ROC curve and classification accuracy on the testing datasets even after attempting different data partitions.

关键词： classification Multi-layer Perceptron Neural Network backpropagation algorithm Radial Basis Function Neural Network Receiver Operating Characteristics

来源：评论

学校读者我要写书评

暂无评论

LEARNING OF MULTILAYER NEURAL NETWORKS WITH THRESHOLD ACTIVATION FUNCTIONS FOR PATTERN CLASSIFICATION

引用

IFAC Proceedings Volumes 2006年第3期39卷 523-528页

作者： M.P. Batura V.A. Ptitchkin Belarusian State University of Informatics and Radioelectronics 6 P. Brovky Str. 220027 Minsk Belarus

Application of multi-layer neural networks with threshold activation functions is proposed for classification of patterns. For networks learning, using of back-propagation algorithm is proposed. Modification of this algorithm is considered for choosing of initial values of parameters and for learning of neural networks of before-mentioned type.

关键词： Neural networks backpropagation algorithm system analysis threshold functions linearization approximate analysis

来源：评论

学校读者我要写书评

暂无评论

Investigating the enhancement of three-dimensional diffraction tomography by using multiple illumination planes

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION 2005年第7期22卷 1251-1262页

作者： Vouldis, AT Kechribaris, CN Maniatis, TA Nikita, KS Uzunoglu, NK Natl Tech Univ Athens Dept Elect & Comp Engn Biomed Simulat & Imaging Lab GR-15773 Athens Greece

The three dimensional (3-D) extension of the two well-known diffraction tomography algorithms, namely, direct Fourier interpolation (DFI) and filtered backpropagation. (FBP), are presented and the problem of the data needed for a full 3-D reconstruction is investigated. These algorithms can be used efficiently to solve the inverse scattering problem for weak scatterers in the frequency domain under the first-order Born and Rytov approximations. Previous attempts of 3-D reconstruction with plane-wave illumination have used data obtained with the incident direction restricted at the xy plane. However, we show that this restriction results in the omission of the contribution of certain spatial frequencies near the omega(z). axis for the final reconstruction. The effect of this omission is studied by comparing the results of reconstruction with and without data obtained from other incident directions that fill the spatial frequency domain. We conclude that the use of data obtained for incident direction in only the xy plane is sufficient to achieve a satisfactory quality of reconstruction for a class of objects presenting smooth variation along the z axis, while abrupt variations along the z axis cannot be imaged. This result should be taken into account in the process of designing the acquisition geometry of a tomography scanner. (C) 2005 Optical Society of America.

关键词： backpropagation algorithm NONLINEAR OPTIMIZATION ULTRASONIC TOMOGRAPHY MICROWAVE TOMOGRAPHY INVERSE SCATTERING RECONSTRUCTION OBJECTS APPROXIMATION

来源：评论

学校读者我要写书评

暂无评论

On the use of neural networks to evaluate groundwater levels in fractured media

引用

JOURNAL OF HYDROLOGY 2005年第1-4期307卷 92-111页

作者： Lallahem, S Mania, J Hani, A Najjar, Y Univ Lille Ecole Polytech Dept Geotech & Genie Civil CNRSUMR 8107LML F-59655 Villeneuve Dascq France Kansas State Univ Dept Civil Engn Manhattan KS 66506 USA

This paper evaluates the feasibility of using artificial neural network (ANN) methodology for estimating the groundwater level in some piezometers implanted in unconfined chalky aquifer of Northern France. These aquifers are the most susceptible to depletion and contamination, with the recharge rate and dominant processes determining their level of vulnerability. Groundwater level simulation in a chalky media is regarded as a difficult subject in hydrogeology due to the complexity of the physical processes involved, the variability of piezometry in space and time and the aquifer response in fissured and matrix blocks. In the present project, after a detailed geologic and hydrogeologic study of the sector, we simulated the groundwater level by Neural Network. The first objective was to determine the most influential parameters which impact groundwater level in fissured chalky media. The second objective was to investigate the effect of temporal and spatial information by considering current and past data sets along with the use of a variety of piezometer readings. The third objective was to simulate the groundwater level in a selected piezometer. The reasonably good ANN-based simulations revealed the merit of using ANNs and specifically Multi Layer Perceptron (MLP) models. The proposed ANN methodology using minimal lag and number of hidden nodes, along with the optimal number of spatial and temporal variables consistently produced the best performing network-based simulation models. (c) 2004 Elsevier B.V. All rights reserved.

关键词： ANN chalk groundwater fractured media backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Modelling combined open channel flow by artificial neural networks

引用

HYDROLOGICAL PROCESSES 2005年第18期19卷 3747-3762页

作者： Yang, HC Chang, FJ Natl Taiwan Univ Dept Bioenvironm Syst Engn Taipei 10764 Taiwan

Combined open channel flow is encountered in many hydraulic engineering structures and processes, such as irrigation ditches and wastewater treatment facilities. Extensive experimental studies have conducted to investigate combined flow characteristics. Nevertheless, there is no simple relationship that can fully describe the velocity profiles in a turbulent flow. The artificial neural network (ANN) has great computational capability for solving various complex problems, such as function approximation. The main objective of this study is to evaluate the applicability of the ANN for simulating velocity profiles, velocity contours and estimating the discharges accordingly. The velocity profiles measured by an acoustic doppler velocimeter in the open channel of the Chihtan purification plant, Taipei, with different discharges at fixed measuring section and different depths are presented. The total number of data sets is 640 and the data sets are split into two subsets, i.e. training and validation sets. The backpropagation algorithm is used to construct the neural network. The results demonstrate that the velocity profiles can be modelled by the ANN, and the ANN constructed can nicely fit the velocity profiles and can precisely predict the discharges for the conditions investigated. Copyright (c) 2005 John Wiley & Sons, Ltd.

关键词： velocity profile acoustic Doppler velocimeter (ADV) artificial neural network (ANN) backpropagation 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：