RBF Neural Network Arithmetic and Applications in Surface Interpolation Reconstruction

2011 ◽  
Vol 460-461 ◽  
pp. 575-580
Author(s):  
X.M. Wu ◽  
Gui Xian Li ◽  
De Bin Shan ◽  
G.B. Yu
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Rbf Neural Network ◽  
Nonlinear Function ◽  
Hole Filling ◽  
Cloud Data ◽  
Surface Interpolation ◽  
Learning Speed ◽  
Arbitrary Precision ◽  
Data Surface

Aiming at problems such as: surface interpolation reconstruction of points cloud data，surface hole filling and two simple surface connection, a neural network arithmetic was employed. Based on radial basis function neural network, simulated annealing was employed to adjust the network weights. The new arithmetic can approach any nonlinear function by arbitrary precision, and also keep the network from getting into local minimum for global optimization feature of simulated annealing. MATLAB program was compiled, experiments on points cloud data have been done employing this arithmetic, the result shows that this arithmetic can efficiently approach the surface with 10-4 mm error precision, and also the learning speed is quick and reconstruction surface is smooth.

Hole Filling Algorithm in Surface Reconstruction Based on Radial Basis Function Neural Network

2008 ◽  
Vol 392-394 ◽  
pp. 750-754
Author(s):  
X.M. Wu ◽  
Gui Xian Li ◽  
W.M. Zhao
Keyword(s):  
Neural Network ◽  
Simulated Annealing ◽  
Radial Basis Function ◽  
Surface Reconstruction ◽  
Basis Function ◽  
Hole Filling ◽  
Cloud Data ◽  
Learning Speed ◽  
Radial Basis ◽  
Data Surface

Aiming at hole filling in points cloud data reconstruction, a novel neural network arithmetic was employed in abridged points cloud data surface reconstruction. Radial basis function neural network and simulated annealing arithmetic was combined. Global optimization feature of simulated annealing was employed to adjust the network weights, the arithmetic can keep the network from getting into local minimum. MATLAB program was compiled, experiments on abridged points cloud data have been done employing this arithmetic, the result shows that this arithmetic can efficiently approach the surface with 10-4 mm error precision, and also the learning speed is quick and hole filling algorithm is successful and the reconstruction surface is smooth. Different methods have been employed to do surface reconstruction in comparison, the results illustrate the error employed algorithmic proposed in the paper is little and converge speed is quick.

The Application of RBF Neural Networks in Curve Fitting

2012 ◽  
Vol 490-495 ◽  
pp. 688-692
Author(s):  
Zhong Biao Sheng ◽  
Xiao Rong Tong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Rbf Neural Network ◽  
Engineering Application ◽  
Nonlinear Function ◽  
Rbf Neural Networks ◽  
Neural Network Approach ◽  
Rbf Network ◽  
Fast Learning ◽  
Nonlinear Processing

Three means to realize function approach such as the interpolation approach, fitting approach as well as the neural network approach are discussed based on Matlab to meet the demand of data processing in engineering application. Based on basic principle of introduction, realization methods to non-linear are researched using interpolation function and fitting function in Matlab with example. It mainly studies the RBF neural networks and the training method. RBF neural network to proximate nonlinear function is designed and the desired effect is achieved through the training and simulation of network. As is shown from the simulation results, RBF network has strong nonlinear processing and approximating features, and RBF network model has the characteristics of high precision, fast learning speed for the prediction.

scholarly journals Computational neuroscience applied in surface roughness fiber optic sensor

2019 ◽  
Vol 10 (1) ◽  
pp. 70-75 ◽  
Author(s):  
Wei He
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Computational Neuroscience ◽  
Fiber Optic ◽  
Rbf Neural Network ◽  
Fiber Optic Sensor ◽  
Bottom Surface ◽  
Optic Sensor ◽  
Arbitrary Precision ◽  
The Stability

Abstract Computational neuroscience has been widely used in fiber optic sensor signal output. This paper introduces a method for processing the Surface Roughness Fiber Optic Sensor output signals with a radial basis function neural network. The output signal of the sensor and the laser intensity signal as the light source are added to the input of the RBF neural network at the same time, and with the ability of the RBF neural network to approach the non-linear function with arbitrary precision, to achieve the nonlinear compensation of the sensor and reduction of the effect of changes in laser output light intensity at the same time. The Surface Roughness Fiber Optic Sensor adopting this method has low requirements on the stability of the output power of laser, featuring large measuring range, high accuracy, good repeatability, measuring of special surfaces such as minor area, and the bottom surface of holed etc. The measurements were given and various factors that affect the measurement were analyzed and discussed.

Research on Nonlinear Approximation Model of Radial Basis Function Neural Network Trained Using Artificial Fish Swarm Algorithm with Adaptive Adjustment

2015 ◽  
Vol 713-715 ◽  
pp. 1855-1858 ◽  
Author(s):  
Xu Sheng Gan ◽  
Xue Qin Tang ◽  
Hai Long Gao
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Nonlinear Approximation ◽  
Nonlinear Function ◽  
Training Algorithm ◽  
Step Size ◽  
Artificial Fish Swarm Algorithm ◽  
Artificial Fish Swarm ◽  
Adaptive Adjustment ◽  
Swarm Algorithm

In order to improve the modeling efficiency of RBF neural network, an Artificial Fish Swarm Algorithm (AFSA) training algorithm with an adaptive mechanism is proposed. In the training algorithm, the search step size and visible domain of AFSA algorithm can be adjusted dynamically according to the convergence characteristics of artificial fish swarm, and then the improved AFSA algorithm is used to optimize the parameters of RBF neural network. The example shows that, the proposed model is a better approximation performance for the nonlinear function.

Speech Recognition Algorithm Based on Empirical Mode Decomposition and RBF Neural Network

2013 ◽  
Vol 831 ◽  
pp. 465-469
Author(s):  
Wei Wei Shi ◽  
Wei Hua Xiong ◽  
Wei Chen
Keyword(s):  
Neural Network ◽  
Speech Recognition ◽  
Empirical Mode Decomposition ◽  
Rbf Neural Network ◽  
Recognition Rate ◽  
Good Method ◽  
Recognition Algorithm ◽  
Intrinsic Mode Functions ◽  
Mode Decomposition ◽  
Learning Speed

This paper presents a novel method of the speech recognition in combining the empirical mode decomposition with radical basis function neural network. Speech signals which pretreated are decomposed by empirical mode decomposition to get a set of intrinsic mode functions. It extracts mel frequency cepstrum coefficient from intrinsic mode function. Features parameters are made up of the coefficients. For BP Neural Network, RBF Neural Network has advantages on approximating ability and learning speed. So using RBF Neural Network as a recognition model is a good method. Experiments show that this new method has good robustness and adaptability. The speech recognition rate of this method reach ninety-one percents accurately under no noise environment. Speech signal recognition is feasible and effective in noisy environment.

The Research of Intrusion Detection System Based on ANN on Cloud Platform

2012 ◽  
Vol 263-266 ◽  
pp. 2962-2965
Author(s):  
Xue Song Jiang ◽  
Xiu Mei Wei ◽  
Yu Shui Geng
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Detection System ◽  
Rbf Neural Network ◽  
Back Propagation ◽  
Cloud Platform ◽  
Bp Network ◽  
Rbf Network ◽  
Learning Speed

Intrusion detection system (IDS) can find the intrusion information before the computer be attacked, and can hold up and response the intrusion in real time. Artificial neural network algorithms play a key role in IDS. The intrusion detection system (ANN) algorithms can analyze the captured data and judge whether the data is intrusion. In this paper we used Back Propagation (BP) network and Radical Basis Function (RBF) network to the IDS. The result of the experiment improve that The RBF neural network is better than BP neural network in the ability of approximation, classification and learning speed. During the procedure there is a large amount of computes. On cloud platform the calculation speed has been greatly increased. So that we can find the invasion more quickly and do the processing works accordingly.

A Novel Knowledge Diffusion Efficiency Prediction Arithmetic in Equipment Manufacturing Industry Based on Simulated Annealing Arithmetic

2013 ◽  
Vol 441 ◽  
pp. 768-771
Author(s):  
Xu Sheng Chen ◽  
Wen Jun Yue ◽  
Hong Qi Wang
Keyword(s):  
Simulated Annealing ◽  
Manufacturing Industry ◽  
Learning Algorithm ◽  
Back Propagation ◽  
Nonlinear Function ◽  
Knowledge Diffusion ◽  
Related Data ◽  
Equipment Manufacturing ◽  
Equipment Manufacturing Industry ◽  
Arbitrary Precision

A novel knowledge diffusion efficiency prediction arithmetic in equipment manufacturing industry in China was proposed, Radial basis function neural network (RBFNN) was designed, and simulated annealing arithmetic was adopted to adjust the network weights. MATLAB program was compiled; experiments on related data have been done employing the program. All experiments have shown that the arithmetic can efficiently approach the precision with 10-4 error, also the learning speed is quick and predictions are ideal. Trainings have been done with other networks in comparison. Back-propagation learning algorithm network does not converge until 2000 iterative procedure, and exactness design RBFNN is time-consuming and has big error. The arithmetic can approach nonlinear function by arbitrary precision, and also keep the network from getting into partial minimum.

Adaptive Control for NC Position Table Base on Radical Basis Function Neural Network

2013 ◽  
Vol 404 ◽  
pp. 699-703 ◽  
Author(s):  
Jing Ma ◽  
Hong Yu Wu ◽  
Xiao Ming Ji ◽  
Yan Lei
Keyword(s):  
Neural Network ◽  
Control Method ◽  
Rbf Neural Network ◽  
System Optimization ◽  
Learning Ability ◽  
Control Precision ◽  
Learning Speed ◽  
Speed Up ◽  
Good Learning ◽  
Non Linear System

Dynamic optimization control algorithm is put forward for X-Y position table. Firstly, dynamics model of X-Y position table is established, then, RBF neural network with good learning ability is used to approach non-linear system. Optimization algorithm of network weights is designed to speed up the learning speed and the adjustment velocity. The control method is more effective to improve the control precision and has a good application value.

Sign in / Sign up

Export Citation Format

Share Document