Approximation Performance of BP Neural Networks Improved by Heuristic Approach

2013 ◽  
Vol 411-414 ◽  
pp. 1952-1955 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Numerical Optimization ◽  
Heuristic Algorithms ◽  
Nonlinear Function ◽  
Heuristic Approach ◽  
Optimization Approach ◽  
Bp Neural Networks ◽  
The One

Among all improved BP neural network algorithms, the one improved by heuristic approach is studied in this paper. Firstly, three types of improved heuristic algorithms of BP neural network are programmed in the environment of MATLAB7.0. Then network training and simulation test are conducted taking a nonlinear function as an example. The approximation performances of BP neural networks improved by different numerical optimization approaches are compared to aid the selection of proper numerical optimization approach.

Structural Damage Detection Using Parameters Combined with Changes in Flexibility Based on BP Neural Networks

2011 ◽  
Vol 243-249 ◽  
pp. 5475-5480
Author(s):  
Zhang Jun
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Damage Detection ◽  
Bp Neural Network ◽  
Structural Damage ◽  
The State ◽  
Structural Damage Detection ◽  
Bp Neural Networks ◽  
Simply Supported ◽  
Modal Flexibility

Modals of BP neural networks with different inputs and outputs are presented for different damage detecting schemes. To identify locations of structural damages, the regular vectors of changes in modal flexibility are looked on as inputs of the networks, and the state of localized damage are as outputs. To identify extents of structural damage, parameters combined with changes in flexibility and the square changes in frequency are as inputs of the networks, and the state of damage extents are as outputs. Examples of a simply supported beam and a plate show that the BP neural network modal can detect damage of structures in quantitative terms.

Prediction of Yarn Unevenness Based on BP Neural Network

2012 ◽  
Vol 627 ◽  
pp. 329-332
Author(s):  
Hui Jun Li ◽  
Xin Hou Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Prediction Models ◽  
Test Results ◽  
Bp Neural Networks

The objective of this research is to predict yarn unevenness. The model of predicting yarn unevenness is built based on BP neural network. The BP neural networks are trained with HVI test results of cotton and USTER TENSOJET 5-S400 test results of yarn. The results show prediction models based on BP neural network are very precise and efficient.

The Application of BP Neural Network in Diagnosing the Short Circuit Fault of Winding

2014 ◽  
Vol 543-547 ◽  
pp. 1064-1067
Author(s):  
Jian Qun Zhang ◽  
De Jian Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Short Circuit ◽  
Evidence Theory ◽  
Accurate Diagnosis ◽  
Bp Neural Networks ◽  
Rotor Winding ◽  
Short Circuit Fault

As a common fault of motor, the short circuit of rotor winding is important for the accurate diagnosis. In this article, the author collected every status parameter of motor by different sensors, using two BP neural networks to partly diagnose the motor and fusing the results of partly diagnosis by D-S evidence theory. The author increases the creditability of diagnosis results by practices and decreases uncertainty, showing the efficiency of this method.

The Applications of GA-BP Neural Networks in Option Direction for Catalytic Agent

2014 ◽  
Vol 510 ◽  
pp. 45-50 ◽  
Author(s):  
Lai Jiang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Design Method ◽  
Neutral Network ◽  
Bp Neural Networks ◽  
Slow Convergence ◽  
Optimum Direction

Although the application of the BP neural network can assist researching on catalytic agent and methods of synthesizing material, but because of slow convergence, in some cases, it can not work efficiently. The paper presents a design method for the application of GA-BP Neutral Network in optimum direction for catalytic agent and material. The simulation result shows that the application of the GA-BP neural network can improve the accuracy and versatility of the catalyst compounding.

Prediction of the Forest Health Based on BP Neural Networks

2013 ◽  
Vol 726-731 ◽  
pp. 4303-4306 ◽  
Author(s):  
Yong Wang ◽  
Zhuang Xiong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Forest Health ◽  
Bp Neural Networks ◽  
Forest Disease ◽  
Bp Neural Network Model

This paper simple introduced back propagation (BP) neural networks, and constructed a dynamic predict model, based on it to predict forest disease and insect and rat pest. Then it analyzed and simulated with the BP neural network model with the data produced in the recent ten years. The result indicated that the BP neural network model is reliable for predicting the forest disease and insect and rat pest. The method provides scientific foundation for the forestry management of studied area.

Predicting Yarn Unevenness Using Improved BP Neural Network

2011 ◽  
Vol 331 ◽  
pp. 219-222
Author(s):  
Hui Jun Li ◽  
Xin Hou Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Prediction Models ◽  
Test Results ◽  
Bp Neural Networks

The objective of this research is to predict yarn unevenness. The model of predicting yarn unevenness is built based on improved BP neural network. The improved BP neural networks are trained with HVI test results of cotton and USTER TENSOJET 5-S400 test results of yarn. The results show prediction models based on improved BP neural network are very precise and efficient.

Study of Bidding Decision-Making in Construction Project Based on LM-BP Neural Networks

2014 ◽  
Vol 584-586 ◽  
pp. 2339-2342 ◽  
Author(s):  
Tian Bao Wu ◽  
Xun Liu ◽  
Tai Quan Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Bp Neural Network ◽  
Construction Project ◽  
Bp Neural Networks ◽  
Slow Convergence ◽  
Bidding Process

There is a tendency that arbitrary and tendentiousness are brought by experts’ subjectivity during the bidding evaluation. A method for construction project bidding based on the BP neural network improved by LM is proposed. To overcome the disadvantage of slow convergence and being prone to converge to minimum, LM was used to be combined with the BP neural networks. It has been proved by an application an effective complement for the deficiency of BP neural network on the bidding decision of construction project. Through the application in reality, we found that the LM-BP neural network in resolving the problems during the bidding process is meaningful.

A Simulation and Prediction Method of the Height of Wheat Based on BP Neural Networks and the Ant Colony Algorithm

2013 ◽  
Vol 659 ◽  
pp. 113-117 ◽  
Author(s):  
Hong Yi Li ◽  
Xi Xin Wu ◽  
Tong Wang ◽  
Di Zhao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Ant Colony Algorithm ◽  
Prediction Method ◽  
Ant Colony ◽  
Local Optimum ◽  
Prediction Problem ◽  
Bp Neural Networks ◽  
Advantages And Disadvantages

This paper focuses on the simulation and prediction problem of height of the crops, particularly the wheat, which plays a significantly important role in its yield, in different growing stages. Our model bases on the BP neural network and the ant colony algorithm. Both of these two algorithms has their own advantages and disadvantages. However, through observations, we find that their advantages and disadvantages seem to be complementary, by which we propose the combination algorithm. This combination algorithm can conquer the local optimum problem of the BP Neural Network, and could overcome the shortcomings of the weak local optimum searching capability of the ant colony algorithm. The experiments show that the our proposed algorithm can hopefully yield good simulation and prediction results of the height of wheat in different growing stages.

A MATLAB-Based Study on Approximation Performances of Improved Algorithms of Typical BP Neural Networks

2013 ◽  
Vol 313-314 ◽  
pp. 1353-1356 ◽  
Author(s):  
Shuo Ding ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Adaptive Learning ◽  
Function Approximation ◽  
Nonlinear Function ◽  
Bp Neural Networks ◽  
Advantages And Disadvantages ◽  
The Best Approximation ◽  
Bp Networks ◽  
Quasi Newton

BP neural networks are widely used and the algorithms are various. This paper studies the advantages and disadvantages of improved algorithms of five typical BP networks, based on artificial neural network theories. First, the learning processes of improved algorithms of the five typical BP networks are elaborated on mathematically. Then a specific network is designed on the platform of MATLAB 7.0 to conduct approximation test for a given nonlinear function. At last, a comparison is made between the training speeds and memory consumption of the five BP networks. The simulation results indicate that for small scaled and medium scaled networks, LM optimization algorithm has the best approximation ability, followed by Quasi-Newton algorithm, conjugate gradient method, resilient BP algorithm, adaptive learning rate algorithm. Keywords: BP neural network; Improved algorithm; Function approximation; MATLAB

N. Belknap's Four-Valued Logic, Belknap Computer and New Proximity Functions for Comparing Discrete Objects

2021 ◽  
Vol 1 (2 (6)) ◽  
Author(s):  
Valerii Dmitrienko ◽  
Sergey Leonov ◽  
Mykola Mezentsev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
The Other ◽  
Proximity Function ◽  
Input Information ◽  
Proximity Measures ◽  
The One ◽  
True Values

The idea of ​​Belknap's four-valued logic is that modern computers should function normally not only with the true values ​​of the input information, but also under the conditions of inconsistency and incompleteness of true failures. Belknap's logic introduces four true values: T (true - true), F (false - false), N (none - nobody, nothing, none), B (both - the two, not only the one but also the other).  For ease of work with these true values, the following designations are introduced: (1, 0, n, b). Belknap's logic can be used to obtain estimates of proximity measures for discrete objects, for which the functions Jaccard and Needhem, Russel and Rao, Sokal and Michener, Hamming, etc. are used. In this case, it becomes possible to assess the proximity, recognition and classification of objects in conditions of uncertainty when the true values ​​are taken from the set (1, 0, n, b). Based on the architecture of the Hamming neural network, neural networks have been developed that allow calculating the distances between objects described using true values ​​(1, 0, n, b). Keywords: four-valued Belknap logic, Belknap computer, proximity assessment, recognition and classification, proximity function, neural network.

Sign in / Sign up

Export Citation Format

Share Document