Structural Reanalysis using a Neural Network-based Iterative Method

The properties of decays that take place during jet formation cannot be easily deduced from the final distribution of particles in a detector. In this work, we first simulate a system of particles with well-defined masses, decay channels, and decay probabilities. This presents the “true system” for which we want to reproduce the decay probability distributions. Assuming we only have the data that this system produces in the detector, we decided to employ an iterative method which uses a neural network as a classifier between events produced in the detector by the “true system” and some arbitrary “test system”. In the end, we compare the distributions obtained with the iterative method to the “true” distributions.

Download Full-text

Methods for Multi-Step Time Series Forecasting Neural Networks

Neural Networks in Business Forecasting ◽

10.4018/978-1-59140-176-6.ch012 ◽

2011 ◽

pp. 226-250 ◽

Cited By ~ 21

Author(s):

Douglas M. Kline

Keyword(s):

Neural Network ◽

Neural Networks ◽

Time Series ◽

Iterative Method ◽

Time Series Forecasting ◽

Independent Method ◽

Data Series ◽

Operating Characteristics ◽

Quarterly Data ◽

Joint Method

In this study, we examine two methods for Multi-Step forecasting with neural networks: the Joint Method and the Independent Method. A subset of the M-3 Competition quarterly data series is used for the study. The methods are compared to each other, to a neural network Iterative Method, and to a baseline de-trended de-seasonalized naïve forecast. The operating characteristics of the three methods are also examined. Our findings suggest that for longer forecast horizons the Joint Method performs better, while for short forecast horizons the Independent Method performs better. In addition, the Independent Method always performed at least as well as or better than the baseline naïve and neural network Iterative Methods.

Download Full-text

An Iterative Method for Deciding SVM and Single Layer Neural Network Structures

Neural Processing Letters ◽

10.1007/s11063-011-9171-3 ◽

2011 ◽

Vol 33 (2) ◽

pp. 171-186 ◽

Cited By ~ 9

Author(s):

Tarek M. Hamdani ◽

Adel M. Alimi ◽

Mohamed A. Khabou

Keyword(s):

Neural Network ◽

Iterative Method ◽

Single Layer ◽

Network Structures

Download Full-text

Structural Reanalysis by Neural Network

Advances in Engineering Computational Technology ◽

10.4203/ccp.53.4.10 ◽

2009 ◽

Author(s):

W.M. Jenkins

Keyword(s):

Neural Network ◽

Structural Reanalysis

Download Full-text

Hyper-Chaotic Neural Network Based on Newton Iterative Method and Its Application in Solving Load Flow Equations of Power System

2009 International Conference on Measuring Technology and Mechatronics Automation ◽

10.1109/icmtma.2009.531 ◽

2009 ◽

Cited By ~ 2

Author(s):

Mingshan Cai ◽

Rixin Chen ◽

Lingshuang Kong

Keyword(s):

Neural Network ◽

Iterative Method ◽

Power System ◽

Load Flow ◽

Chaotic Neural Network ◽

Flow Equations ◽

Newton Iterative Method

Download Full-text

Forward Kinematics of Parallel Robot Based on Neuro-Fuzzy System

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.470.636 ◽

2013 ◽

Vol 470 ◽

pp. 636-643 ◽

Cited By ~ 2

Author(s):

Xiang Wu ◽

Zu De Zhou ◽

Qing Song Ai ◽

Wei Meng

Keyword(s):

Neural Network ◽

Iterative Method ◽

Fuzzy System ◽

Fuzzy Theory ◽

Parallel Robot ◽

Learning Ability ◽

Forward Kinematics ◽

Kinematics Model ◽

Neuro Fuzzy ◽

Self Learning

As the structure of parallel robot is special in general mechanical and electrical systems, its forward kinematics needs to be solved by nonlinear equations. In this paper, for the issue that numerical iterative method requires complex mathematical derivation and programming, and is sensitive to the initial value, a Neuro-fuzzy system is proposed for solving forward kinematics model of parallel robot. Meanwhile, inverse kinematics is used for training database, knowledge representation ability of fuzzy theory and self-learning ability of neural network are combined to overcome the shortcomings that neural network cannot express human language and fuzzy system do not have self-learning ability. In addition, training and generation efficiency of the model can also be improved by reducing the input dimension reasonably. Simulation results have been showed that, in the premise of efficiency, accuracy of forward kinematics model using Neuro-fuzzy system is better than Newton-Raphson iterative method, and has better versatility.

Download Full-text