The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, the BP neural network method and software related are used to evaluate the influence of corporate culture, in order to provide decision-making basis for business management. The evaluation on the running culture system of enterprises facilitates managers to adjust strategies and tactics and maintain the effectiveness of the cultural development. In this paper, an evaluation system on...
In the practice of risk evaluation on real estate, there are many events' degree of risk can not be accurately described, the application of fuzzy comprehensive evaluation method can reflect the risk degree of every element in detail. In addition, the combination use of BP neural network (ANN) and expert system (Es) method can determine impact extent of the risk factors on the real estate risk and...
Using Delphi method to determine the indicators and their weights of performance evaluation of enterprise's marketing team members, this paper proposes a performance evaluation model of enterprise's marketing team members based on BP neural network. Then, it operates the empirical analysis in an enterprise. The empirical results show that the model is an effective evaluation method because its output...
Modern credit risk management aims at assess the default probability (DP) of a debtor according to his historical and current financial data. Due to its prominent importance in credit loan decisions, the DP assessment becomes a research focus in the filed of financial data mining. To tackle this problem, we propose a nonlinear multi-parameter model (NMM) based on domain knowledge. Additionally, the...
Based on the investigation of impact on products composition of alloy additions in converter smelting process, a neural network model is established for the influence in this paper. Using BP neural network theory, select the actual production data as training samples and the main elements of alloy additions as input data. There are 4 layers in this model, namely input layer, hidden layer and output...
A banknote orientation recognition method is introduced in the paper. In order to avoid dealing with large numbers of image pixels and reduce calculation, the banknote image is divided into several blocks. And then, neural network is applied to establish a universal recognition method. Different banknote can get corresponding model through BP network that is introduced in detail in the paper.
BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. The gradient descent momentum and adaptive learning...
The credit risk assessment is the most difficulty in the credit risk management in commercial banks, so the combination method of principal component analysis and BP neural network based on biology nerve cell was introduced in detail according to the idea of combination forecasting. The principle component analysis is used to handle on input variables in advance to solve the problem of the inefficiency...
This paper presents a BP neural network-based model of enterprise learning capacity evaluation methods. Design a learning capacity enterprises evaluation index system through the point of learning process of enterprises. And build a model of enterprises learning capacity neural network. Experimental result shows that a BP neural network method is feasible and effective for enterprise learning capacity...
Parameters control problem was crucial in rolling industrial, but the mechanical properties forecasting of strip steel was an information space incompletely and non-linear complex system which was hard for traditional method. Artificial neural networks was a non-linear system with strong non-linear modeling ability, but the traditional BP neural networks has many shortcomings like easily step into...
Based on the fact that the Elman model of neural network can well approach any nonlinear continuous function and has ability to reflect dynamic features of the systems, a method of width spread to medium plate mill prediction by Elman model was present. Through the width prediction by Elman model and BP model, the results show that the convergence and accuracy of prediction by the Elman model was...
Automatic alignment design is always one pursuing goal of highway geometric designers with the rapid development of modern technologies such as intellection, digitalization and automatization. Because of the fact that artificial neural network is widely used in the field of pattern recognition, an approach to fit some control points and then to determine the appropriate type of horizontal curves based...
Because of the importance of dust abatement by sprayer, this paper studies the characteristic of fogdrop generated by one kind of nozzle on basis of Back Propagation (BP) Neural Network, using Marvin-3000 type laser granularity instrument in lab. It is pointed that the maximum and minimum errors of widely used BP Neural Network are 2.18% and 0.61%, when we compute the fogdrop diameter computing repeatedly...
A fault diagnosis method of rolling bearing based on BP neural network and time domain parameters of vibration signal was proposed to realize fast fault diagnosis. The input vectors of the BP neural network were skewness, kurtosis, peak and margin of vibration signal. The structure of the neural network was determined with simulation research. Gradient descending method was used to train the parameters...
This paper analyzes the defects and reasons for using standard BP neural network algorithm in building quality prediction model of yarns and explores an improved BP neural network algorithm. By increasing the back-propagation error-feedback signals and applying sell-adaptive and adjusting learning rate, the research has reinforced the adjustment of network weights and prevented network entering saturated...
Because artificial neural networks discard the traditional modeling methods, it can extract domain knowledge from a large number of discrete experimental data via study and training, and express these knowledge as network connection weights, so as to establish the corresponding relation model. In this paper, based on neural network BP algorithm, we built a relation model that shows how various process...
In this paper, the authors established an evaluation model of university teaching quality based on back-propagation neural networks. Quantified indices of teaching quality were inputs of the model, while teaching effect was output. The empirical research by MATLAB showed that this evaluation approach was suitable for the university teaching quality assessment tasks, which not only overcomes subjective...
This paper proposed a hybrid training algorithm by combining the Ant Colony System and BP algorithm. The Ant Colony System is used optimize the initial of the BP neural networks structure, connection between neurons and connection weights. The yield structure has trained using BP algorithms. This method can cope with trapping local minimum problem of the BP algorithm. The proposed method and the standard...
In this paper, the principle of neural network blind equalization algorithm was depicted, the fault of traditional BP (back propagation) algorithm, which is slow convergence rate and easy to fall into a local minimum, was analyzed, the influence of momentum factor to equalization performance was researched, the convergence track of traditional BP algorithm and momentum factor BP algorithm was compared...
Aim at need of project logistics in practice, a parameter evaluating system about leaguer of virtual enterprise is presented, and then the BP neural network model of qualification layer and target layer of this system are build and modularized. Based this, a double layer and intelligent estimating model is built. The Modularized, double layer structure of this model is propitious to update and develop...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.