Approximation Analysis for a New Kind of Neural Network Using Rational Spline Weight Functions

2014 ◽  
Vol 644-650 ◽  
pp. 1654-1657
Author(s):  
Dai Yuan Zhang ◽  
Shan Jiang Hou
Keyword(s):  
Neural Network ◽  
Weight Function ◽  
Rational Functions ◽  
Weight Functions ◽  
Rational Spline ◽  
The Neural Network ◽  
Approximation Analysis ◽  
Very High

To describe the performance for a new kind of neural network, This paper discusses the approximation of the neural network using a kind of rational spline weight function. The rational spline consists of piecewise rational functions with cubic numerators and linear denominators. The theoretic formula of approximation is proposed and an example is also given. It can be concluded that this new neural network can get very high training accuracy.

Environmental Quality Assessment Based on a New Kind of Neural Network Using Rational Spline Weight Functions

2015 ◽  
Vol 713-715 ◽  
pp. 1708-1711
Author(s):  
Dai Yuan Zhang ◽  
Shan Jiang Hou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Quality Assessment ◽  
Environmental Quality ◽  
Weight Functions ◽  
Spline Functions ◽  
Environmental Quality Assessment ◽  
Rational Spline ◽  
The Neural Network ◽  
Very High

As we all known, artificial neural network can be used in the process of environmental quality assessment. To improve the accuracy and science of assessment, a method of environmental quality assessment is presented in this paper, which is based on spline weight function (SWF) neural networks. The weigh functions of the neural network are composed of rational spline functions with cubic numerator and linear denominator (3/1 rational SWF). The simulation results show that, compared with the conventional BP neural networks, this method can get very high precision and accuracy. This case demonstrates that SWF neural networks can offer a very prospective tool for environmental quality assessment.

Complexity Analysis of Neural Network Based on Rational Spline Weight Functions

2014 ◽  
Vol 644-650 ◽  
pp. 1658-1661
Author(s):  
Dai Yuan Zhang ◽  
Hai Nan Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Theoretical Analysis ◽  
Time Complexity ◽  
Complexity Analysis ◽  
Weight Functions ◽  
Rational Spline ◽  
The Neural Network ◽  
The Neural Networks

This paper aims to obtain the time complexity for a new kind of neural network using rational spline weight functions. In this paper, we introduce the architecture of the neural network, and analyze the time complexity in detail. Finally, some examples are also given to verify the theoretical analysis. The results show that the time complexity depends on the number of patterns, the input and out dimensions of the neural networks.

Passenger Flow Analysis in Subway Using a Kind of Neural Network

2015 ◽  
Vol 713-715 ◽  
pp. 2284-2287 ◽  
Author(s):  
Dai Yuan Zhang ◽  
Hai Nan Yang
Keyword(s):  
Neural Network ◽  
Weight Function ◽  
Flow Analysis ◽  
Influential Factors ◽  
Matlab Simulation ◽  
Factors Affecting ◽  
Passenger Flow ◽  
Rational Spline ◽  
The Neural Network ◽  
Cubic Polynomial

This paper aims to analyze passenger flow in subway based on a kind of rational spline weight function neural network, in which the numerator of the spline is a cubic polynomial and the denominator of the spline is a quadratic polynomial, and this kind spline is denoted by 3/2 rational splines. There are many factors affecting the passenger flow. Combined the main influential factors with the self-learning method of neural network, we establish the neural network model of passenger flow in subway. This paper introduces the spline weight function neural network and the passenger flow model based on this neural network. Finally MATLAB simulation verifies that the 3/2 rational spline weight function neural network can be applied to analyze the passenger flow in subway with high accuracy.

Population Analysis Based on Neural Network of Rational Spline Weight Functions with Cubic Numerator and Quadratic Denominator

2015 ◽  
Vol 713-715 ◽  
pp. 1813-1816
Author(s):  
Dai Yuan Zhang ◽  
Jia Kai Wang
Keyword(s):  
Neural Network ◽  
Birth Rate ◽  
Population Analysis ◽  
Natural Increase ◽  
Weight Functions ◽  
Matlab Simulation ◽  
Rational Spline ◽  
Steady Growth ◽  
The Neural Network ◽  
Increase Rate

With the steady growth of the population in our country, the analysis of population is essential to the distribution of social resources and the improvement of the population quality. In this paper, we use the neural network of rational spline weight functions with cubic numerator and quadratic denominator to establish the model of Chinese population by four indicators, gender ratio, birth rate, elderly dependency ratio and natural increase rate. Finally we come to the conclusion through MATLAB simulation that the training speed is fast and the error is small. This kind of neural network can be applied to population analysis and it could be used in various fields.

Complexity Research on Second Class Orthogonal Weight Function Neural Networks

2014 ◽  
Vol 989-994 ◽  
pp. 2659-2662
Author(s):  
Dai Yuan Zhang ◽  
Ran Zhao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Weight Function ◽  
Linear Relationship ◽  
Time Complexity ◽  
Weight Functions ◽  
Simulation Experiments ◽  
Output Layer ◽  
The Neural Network ◽  
Input Layer

Weight function neural network is a new kind of neural network developed in recent years, which has many advantages, such as finding globe minima directly, good performance of generalization, extracting some useful information inherent in the problems and so on. Time complexity is an important measure of algorithm. This paper studies the complexity of neural network using second class orthogonal weight functions. The results indicate that the neural network has a linear relationship with the dimensions of input layer and output layer, an O (n3) relationship with the number of samples. Finally gives some simulation experiments for time complexity.

Error Analysis of Neural Network with Rational Spline Weight Function

2014 ◽  
Vol 644-650 ◽  
pp. 2407-2410
Author(s):  
Dai Yuan Zhang ◽  
Jia Kai Wang
Keyword(s):  
Neural Network ◽  
Weight Function ◽  
Topological Structure ◽  
High Accuracy ◽  
Local Minima ◽  
Slow Convergence ◽  
Rational Spline ◽  
Fast Learning ◽  
Learning Speed ◽  
Training Neural Network

Training neural network by spline weight function (SWF) has overcomed many defects of traditional neural networks (such as local minima, slow convergence and so on). It becomes more important because of its simply topological structure, fast learning speed and high accuracy. To generalize the SWF algorithm, this paper introduces a kind of rational spline weight function neural network and analyzes the performance of approximation for this neural network.

Error Analysis of Neural Network with Multiply Neurons Using Rational Spline Weight Functions

2015 ◽  
Vol 713-715 ◽  
pp. 1716-1720
Author(s):  
Dai Yuan Zhang ◽  
Lei Lei Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Error Analysis ◽  
Weight Functions ◽  
Generalization Ability ◽  
Rational Spline ◽  
Error Formula ◽  
Denominator Polynomial

In order to describe the generalization ability, this paper discusses the error analysis of neural network with multiply neurons using rational spline weight functions. We use the cubic numerator polynomial and linear denominator polynomial as the rational splines for weight functions. We derive the error formula for approximation, the results can be used to algorithms for training neural networks.

Time Complexity Research on the Second Type Neural Networks of Padé Weight Functions

2014 ◽  
Vol 989-994 ◽  
pp. 2667-2670
Author(s):  
Dai Yuan Zhang ◽  
Lei Yang
Keyword(s):  
Neural Network ◽  
Weight Function ◽  
Time Complexity ◽  
Weight Functions ◽  
Matlab Simulation ◽  
Training Samples ◽  
Neural Network Algorithm ◽  
Output Dimension ◽  
Key Steps ◽  
Second Category

Time complexity is an important measure of algorithm. The main purpose of this paper is to research the time complexity of the second category of Padé weight function neural network and find out the factors which affect its time complexity. In this paper, firstly, the second category of Padé weight function neural network algorithm is introduced. Then through the analysis of the key steps of the algorithm, the time complexity is given. After MATLAB simulation, the experimental results verify the theoretical analysis of the results. Therefore, its time complexity is related to input dimension, output dimension and the number of training samples.

Pressure Prediction Technology of the Deep Strata Based on BP Neural Network

2010 ◽  
Vol 143-144 ◽  
pp. 28-31 ◽  
Author(s):  
Wei Li ◽  
Tie Yan ◽  
Ying Jie Liang
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Gamma Ray ◽  
Forecast Model ◽  
Oil Field ◽  
The Neural Network ◽  
Natural Gamma ◽  
Gamma Ray Log ◽  
Deep Strata ◽  
Very High

. The accurate prediction of strata pressure is the base for safely, quality and efficiently drilling, decreasing hole problems and reasonable development of the reservoir. Because of the high cost, long cycle of the formation pressure measured method, which may influence the safety of drilling operation, thus a new method for predicting strata pressure, based on the BP neural network, is presented in this paper, and establishing process of the neural network forecast model are discussed in detail. This method takes the acoustic time, natural potential, natural gamma ray log data and pipe pressure test data as study sample, which has a very high accuracy. The paper predicts strata pressure of the Saertu oil field and Xingshugang oil field in Daqing, and the results show that relative error between the predicted data and experimental data is less than ±8.9%.

scholarly journals Improving flood forecasting in Bangladesh using an artificial neural network

2009 ◽  
Vol 12 (3) ◽  
pp. 351-364 ◽  
Author(s):  
A. S. Islam
Keyword(s):  
Neural Network ◽  
Absolute Error ◽  
Flood Forecasting ◽  
Computational Time ◽  
Output Node ◽  
River Stage ◽  
The Neural Network ◽  
Field Data Collection ◽  
The Ganges ◽  
Very High

A river stage neural network model has been developed to study and predict the water level of Dhaka city. A total of five stations located at the border area of Bangladesh on the Ganges, Brahmaputra and Meghna rivers are selected as input nodes and Dhaka on the Buriganga river is the output node for the neural network. This model is trained with river stage data for a period of 1998 to 2004 and validated with data from 2005 to 2007. The river stage of Dhaka has been predicted for up to ten days with very high accuracy. Values of R2, root mean square and mean absolute error are found ranging from 0.537 to 0.968, 0.607 m to 0.206 m and 0.475 m to 0.154 m, respectively, during training and validation of the model. The results of this study can be useful for real-time flood forecasting by reducing computational time, improving water resources management and reducing the unnecessary cost of field data collection.

Sign in / Sign up

Export Citation Format

Share Document