检索结果-内蒙古大学图书馆

2nd International Conference on Information Technology and Management Innovation (ICITMI 2013)

作者： Ding Shuo Chang Xiao-heng Wu Qing-hui Bohai Univ Coll Engn Jinzhou 121013 Liaoning Provin Peoples R China

ISBN: (纸本)9783037858646

When approximating nonlinear functions, standard BP algorithms and traditional improved BP algorithms have low convergence rate and tend to be stuck in local minimums. In this paper, standard BP algorithm is improved by numerical optimization algorithm. Firstly, the principle of Levenberg-Marquardt algorithm is introduced. Secondly, to test its approximation performance, lmBP neural network is programmed via MATLAB7.0 taking specific nonlinear function as an example. Thirdly, its approximation result is compared with those of standard BP algorithm and adaptive learning rate algorithm. Simulation results indicate that compared with standard BP algorithm and adaptive learning rate algorithm, lmBP algorithm overcomes deficiencies ranging from poor convergence ability, prolonged convergence time, increasing iteration steps to nonconvergence. Thus with its good approximation ability, lmBP algorithm is the most suitable for medium-sized networks.

关键词： lm algorithm BP Neural network Approximation performance Simulation MATLAB

来源：评论

学校读者我要写书评

暂无评论

Application of BP neural network in PSD nonlinear correction 3

Application of BP neural network in PSD nonlinear correction

引用

3rd International Conference on Advanced Engineering Materials and Architecture Science (ICAEMAS)

作者： Yang Zhuojing Zhang Jianwei Hao Wenjie Yang Jinping MLR Ctr Hydrogeol & Environm Geol Survey China Geol S Key Lab Monitoring Technol Geol Environm Baoding Hebei Peoples R China

ISBN: (纸本)9783038352679

Because resistance of two-dimensional position sensitive detector's (PSD) photo surface is not absolute uniformity that its output is nonlinear. It is this feature enables the PSD difficult to measure small displacement. In order to solve this problem, BP neural network is proposed to solve the problem of PSD nonlinear correction after the study of traditional nonlinear correction method;BP neural network would have a strong ability of nonlinear mapping after training, and it can approach arbitrarily contact function by arbitrary precision, and MATLAB neural networking boxes can simulate BP neural network easily. Simulation and verification indicate that the method has a remarkable effect in solving nonlinear problems, and it can meet system requirements.

关键词： PSD BP neural Network Nonlinear MATLAB lm algorithm

来源：评论

学校读者我要写书评

暂无评论

Modeling Research on Ground-Coupled Heat Pump System Based on Artificial Neural Network

Modeling Research on Ground-Coupled Heat Pump System Based o...

引用

26th Chinese Control and Decision Conference (CCDC)

作者： Zhang, Yating Jiang, Weichang Wang, Ruihua Beijing Univ Technol Coll Elctron & Control Engn Beijing 100124 Peoples R China

ISBN: (纸本)9781479937066

As a new technology of renewable energy, ground-coupled heat pump system has been rising in our country in recently years. However because of the nonlinear and high degree of coupling, it is not clear to find out the relationship between control variables and total energy consumption of the system. This paper proposes a modeling way for ground-coupled heat pump system that uses artificial neural network, it builds the relationship between control variables and total energy consumption of the system directly. Through the comparison we can find a better way for building the Ground-coupled heat pump System.

关键词： ground-coupled heat pump system BP neural network lm algorithm RBF neural network

来源：评论

学校读者我要写书评

暂无评论

Optimisation Using Levenberg-Marquardt algorithm of Neural Networks for Iris

Optimisation Using Levenberg-Marquardt Algorithm of Neural N...

引用

2nd International Conference on Frontiers in Intelligent Computing - Theory and Applications (FICTA)

作者： Sayed, Asim Sardeshmukh, M. Limkar, Suresh SAOE Dept Elect & Telecommun Pune Maharashtra India AISSMS IOIT Dept Comp Engn Pune Maharashtra India

ISBN: (纸本)9783319029313;9783319029306

This paper explores the optimisation technique of Damped Least Square Method also known as the Levenberg-Marquardt (lm) algorithm for Iris recognition. The motive behind it is to show that even though there are many algorithms available which act as an alternative to the lm algorithm such as the simple gradient decent and other conjugate gradient methods be it the vanilla gradient decent or the Gauss Newton iteration, the lm algorithm outperforms these optimisation techniques due to the addressing of the problem by the algorithm as the Non-linear Least Square Minimisation. The results are promising and provide an insight into Iris recognition which are distinct pattern of individuals and are unique in case of every eye.

关键词： Levenberg-Marquardt lm algorithm Iris Biometrics of the eye Optimisation of Iris Images Least square method for Iris Damped Least Square Non Linear Least Square Method

来源：评论

学校读者我要写书评

暂无评论

A Novel Method to Improve Dynamic Performance of GPS Carrier Tracking Loop with INS Aiding

A Novel Method to Improve Dynamic Performance of GPS Carrier...

引用

International Conference on Wireless Communication and Sensor Network (WCSN)

作者： Ren, Chun-hua Liu, Qin-qin Wang, Man-xi Yang, Li-ping State Key Lab Complex Electromagnet Environm Effe Luoyang 471003 Peoples R China Chongqing Univ Minist Educ Key Lab Optoelect Technol & Syst Chongqing 400044 Peoples R China

ISBN: (纸本)9781479970919

It is inclined to lose the tracking of a GPS receiver's carrier loop in noisy jamming or high dynamic environment, therefore, INS's velocity information is often used to expand the equivalent bandwidth of GPS receiver's tracking loop, reduce loop's bandwidth, improve high dynamic adaptability and Signal-noise ratio. However, because of the discretization of INS's velocity, the rapidly changing control quantity for NCO under high dynamic environment makes the loop tracking unstable. For this reason, tracking loop with INS's acceleration information aiding based on lm algorithm of BP neural network is proposed. Firstly, the effect of INS's update frequency on a typical second-order tracking loop is analyzed, then the model of BP neural network based on lm algorithm is built, and the INS instantaneous velocity and acceleration as input variables to obtain the estimate of the loop NCO through training the network and compensation the loop NCO, after training is completed, we can create the appropriate database, which the data can be called directly. The results show that this method enhances loop's tracking speed and stability, improves loop's adaptability to dynamic stress.

关键词： PLL high dynamic ultra-tight signal tracking INS BP neural network lm algorithm

来源：评论

学校读者我要写书评

暂无评论

A New algorithm for Solving Inverse Kinematics of Robot Based on BP and RBF Neural Network 4

A New Algorithm for Solving Inverse Kinematics of Robot Base...

引用

4th International Conference on Instrumentation and Measurement, Computer, Communication and Control (IMCCC)

作者： Yuan, Tianming Feng, Yi Dalian Univ Technol Inst Control Sci & Engn Dalian Peoples R China

ISBN: (纸本)9781479965755

A parallel neural network algorithm based on BP and RBF neural network for solving inverse kinematics of robot is proposed in this paper. Concrete steps of this method and related matters that should be noticed are presented. BP network is trained by lm algorithm and RBF network increases radial basis neurons automatically. The simulation results of PUMA560 show that this algorithm is simple and reliable, making the error of the whole system become smaller. In addition, the algorithm effectively solves the problem of inverse kinematics and overcomes the defects of traditional methods for solving inverse kinematics, such as large amount of calculation, slow convergence rate and low accuracy.

关键词： BP and RBF Neural Network Inverse Kinematics lm algorithm Puma560

来源：评论

学校读者我要写书评

暂无评论

Ultrasonic Parameter Estimation Using the Maximum Likelihood Estimation

Ultrasonic Parameter Estimation Using the Maximum Likelihood...

引用

International Conference on Electrical Engineering

作者： S. Laddada S. Lemlikchi H. Djelouah M. O. Si-Chaib Centre de Developpement des Technologies Avancees Laboratoire de Physique des Materiaux USTHB Laboratoire de Mecanique des Solides et Systemes UMB. Boumerdes

ISBN: (纸本)9781467366748

The estimation of the backscattered echo was performed using the Maximum Likelihood Estimation (MLE). The backscattered ultrasonic echo is modeled as a nonlinear function of a set of parameters using the Gaussian echo model corrupted with an additive noise. Because of the white Gaussian noise (WGN) assumption, the estimation problem reduces to a least squares estimation. Thus, the nonlinear least square curve fitting with the Levenberg-Marquardt (lm) optimization algorithm was tested in the estimation procedure. The results are compared with existing results from the literature. To improve the goodness of the fit, the multivariate denoising procedure were applied as a preprocessing operation. Then, the efficiency and robustness of the lm algorithm are evaluated for both denoised and noisy signals.

关键词： Ultrasonic echo Parameter estimation MLE lm algorithm Multivariate Wavelet Denoising

来源：评论

学校读者我要写书评

暂无评论

Optimization of the weights and asymmetric activation function family of neural network for time series forecasting

引用

EXPERT SYSTEMS WITH APPLICATIONS 2013年第16期40卷 6438-6446页

作者： Gomes, Gecynalda S. da S. Ludermir, Teresa B. Univ Fed Bahia Dept Estat Salvador BA Brazil Univ Fed Pernambuco Ctr Informat Recife PE Brazil

The use of neural network models for time series forecasting has been motivated by experimental results that indicate high capacity for function approximation with good accuracy. Generally, these models use activation functions with fixed parameters. However, it is known that the choice of activation function strongly influences the complexity and neural network performance and that a limited number of activation functions has been used in general. We describe the use of an asymmetric activation functions family with free parameter for neural networks. We prove that the activation functions family defined, satisfies the requirements of the universal approximation theorem We present a methodology for global optimization of the activation functions family with free parameter and the connections between the processing units of the neural network. The main idea is to optimize, simultaneously, the weights and activation function used in a Multilayer Perceptron (MLP), through an approach that combines the advantages of simulated annealing, tabu search and a local learning algorithm. We have chosen two local learning algorithms: the backpropagation with momentum (BPM) and Levenberg-Marquardt (lm). The overall purpose is to improve performance in time series forecasting. (c) 2013 Elsevier Ltd. All rights reserved.

关键词： Neural networks Asymmetric activation function Free parameter Simulated annealing Tabu search BPM algorithm lm algorithm Time series

来源：评论

学校读者我要写书评

暂无评论

Hybrid algorithm Based On Levenberg-Marquardt Bayesian Regularization algorithm and Genetic algorithm

Hybrid Algorithm Based On Levenberg-Marquardt Bayesian Regul...

引用

International Conference on Advanced Mechatronic Systems (ICAMechS)

作者： Song, Feng Wang, Hongchun Chongqing Normal Univ Dept Math Chongqing Peoples R China

ISBN: (纸本)9781479925186;9781479925193

In order to overcome the insufficiencies of the convergence of the low speed, a low precision of the forecast and easy convergence to a local minimum point of error function on BP Neural Networks (BPNN), a new hybrid algorithm-lmBRGA, which uses both the Levenberg-Marquardt(lm) Bayesian Regularization algorithm(lmBRA) and Genetic algorithm(GA) to optimize BPNN, is proposed. The specific process was as follows. Firstly, the GA optimized the best weights and thresholds as the training initial values of BPNN. Then, the BPNN after initialization was trained by the lmBRA until the network has converged. Finally, the network model, which met the requirements after being examined by the test samples, was applied to predict the resident consumption level of Chengdu. By Simulation Experiments analysis, the lmBRGA hybrid algorithm has faster convergence rate than the lmBRA. From the average relative forecasting error (ARFE)'s comparison of the predictive results, it clearly indicates that the forecast precision of the lmBRGA hybrid algorithm is higher than another five optimization algorithms.

关键词： BPNN lm algorithm Bayesian regularization algorithm GA

来源：评论

学校读者我要写书评

暂无评论

The technology of circular parts precise measurement based on binocular calibration

The technology of circular parts precise measurement based o...

引用

2nd International Conference on Measurement, Instrumentation and Automation (ICMIA 2013)

作者： Wang, Chuan Yang, Jie Zhou, Yanwei Wuhan Univ Technol Key Lab Fiber Opt Sensing Technol & Informat Proc Wuhan Peoples R China

ISBN: (纸本)9783037857502

A method of measuring the radius of circular parts by binocular stereo vision technology is proposed. First of all the interior and exterior parameters of cameras are acquired by the camera calibration technology. Then the epipolar constraint can be calculated which contains the calibrated information. The image matching which uses the epipolar constraint is done to find the matching points. The three dimensional (3D) coordinates of edges points are reconstructed through trigonometry reconstruction. At last the analytic expression of the plane in which the circle lies and the circle's radius are calculated in two steps by Levenberg-Marquardt (lm) algorithm. The proposed method does not require the prior knowledge of position between the measuring plane and the calibration plane which monocular measurement needs. Experimental results show that the measurement has high precision.

关键词： binocular calibration epipolar constraint image matching lm 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：