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 order to improve the calculation accuracy of structural system failure probability, RBF neural networks which is based on the failure probability data calculated accurately can simulate into the four-dimensional space neural network of a single output neuron and three input neurons because system failure probability is related to reliability index, failure mode number and the correlation coefficient...
It's a focus for researchers to forecast the nonlinear data got from the reality world system. Many methods based on nonlinear models are proposed. In this paper, a forecast model based on the wavelet analysis and the neural network is proposed. Firstly, the wavelet decomposing and reconstruction should be made on the time series studied, and then neural network forecast method is applied on all the...
As an essential step of 3D reconstruction, research on the camera calibration methods has great important significance of theoretical study and practical value. In this paper, a new simply, flexible and more accurate coplanar camera calibration method is proposed based on neural network. This method only requires a coplanar target and without camera motion. The neural network is used to learn the...
The construction and algorithm of a self-organizing feature map neural network is researched. It is the first time to present the method of classifying and diagnosing IVC fault based on clustering principle of the SOM network .The diagnosis results given in this article prove that the fault diagnosis approach is effective.
This paper, enlightened by the optic nerve of human, presents a method -- Group of Neural Network (GNN) to solve the problems when there are some problems in the information fusion of intelligent traffic road traffic information based on the Neural Network, and apply it to the road traffic information characteristic fusion to recognize the target. Compared with the neural network, the converge rate,...
2D barcode region detection is a non trivial problem for barcode revognition and decoding especially in complex backgrounds. Currently, morphological processing has been widely applied to extract potential regions of Data Matrix barcodes due to its low computation complexity. However, this method leads to two problems, adaptive selection of morphological structuring element and high false accept rate...
As accurate identification of weeds from crops is the prerequisite for precise herbicides spraying, this paper proposes a multi-feature fusion method based on neutral network and D-S evidential theory to improve the accuracy of weed recognition. Firstly, three kinds of single features such as color, shape and texture are extracted from the weed and crop leaves after a series of image processing. Secondly,...
Combining the characteristics of drilling rig fault, a solution of fault diagnosis expert system based on artificial neural network is proposeed. The fault diagnosis system is designed for HT-60 drilling rig, which acquires knowledge by neural network and diagnoses by expert system. The system with characteristics of self-learning and self-adaptive can acquire knowledge from existing data in order...
Neural networks are increasingly used in the study of deformation control dam based on its self-organization, adaptive, self-learning, associative memory, a high degree of fault-tolerant, parallel processing abilities, a high degree of non-linear mapping capability, as well as linear dynamic characteristics. In this paper combines former research achievements, summarize and analyze the application...
In this thesis, we will introduce the concepts of data mining technology and customer relationship management to analyze the advantages and disadvantages of decision tree and neural network. With the decision tree and neural network fusion algorithm, we shall find its necessity in bank-customers management system application in the banking sector development and will explain the detailed applications...
First arrival detecting of seismic waves plays an important role in research of mineral resource and petroleum resource. Many methods and theories have been put forward so far, such as ratio of energy method, maximal amplitude method, fractal dimension method and neural network. However, these methods have their own disadvantages. Therefore, mutual information in information theory is introduced to...
Sizing yarn hairiness is an important yarn property like yarn evenness and strength. This property is affected by many factors such as fiber properties, sizing instruction, sizing device condition, sizing process and processing parameters etc., which makes its prediction difficult also. In this paper, in order to predict the sizing yarn hairiness of sizing process, an ANN model is developed. By analyzing...
Analyzing and summarizing the advantages of the traditional decoupling algorithms, a new intelligent decoupling controller based on BP neural network PID with predictive compensation is designed to reduce the influence between the variables in multivariable, nonlinear and strong-coupling system. This kind of algorithm gains a decoupling performance by improving the structure of the traditional neural...
Deaf-mutes have the stronger advantage of visual identification ability and visual memory ability for color, a new speech visualization method for deaf-mute was proposed,it created readable patterns by integrating different speech features into a single picture. Firstly, series preprocessing of speech signals were done. Secondly, extracting features were done, among them, using three formant features...
Based on the qualitative analysis and research of implementing Reduce Vertical Separation Minimum (RVSM) to enhance the flight capacity in RVSM airspace all over the world, using systemic approaches that combine the qualitative analysis with ration analysis, this paper introduced mathematic description and neural network model of the air traffic issue in RVSM airspace. The mathematic description is...
Firstly, an air passenger capacity investigation at the capital international airport is made, and a composite forecasting model based on total air passenger capacity is established, in which multiple regression and ARIMA model are parallel connection and their forecast results are series connection with BP neural network. Secondly, according to the average growth rate of air passenger capacity, all...
A new neural network architecture, call a higher order multi-layer neural networks(HOMLNN) is presented. The architecture of an HOMLNN is a modified model of the Evolved functional neural network(EFNN)with a hidden layer which is composed of self-evolve neurons and additional multiplication inputs between conventional inputs and self-evolve neurons. The authors drive a generalized dynamic backpropagation...
This paper puts forward a new method of Rough Sets (RS) and Neural Network (NN) which is used to detect fine faults and coal seam thickness by analyzing 3D seismic data. This method uses RS to reduce seismic data containing noise, and after reduction, low noise seismic data can be hold. Then input those reduced data to NN, a predicting model which can detect fine faults and predict coal seam's thickness...
In this paper we design a Chaos Bidirectional Associative Memory (CBAM) network model based on Aihara chaos neuron for its sensitivity to noise. It includes an inside associative memory construct on its every layer. The simulation shows that the model improves the anti-noise ability of the BAM effectively.
Two artificial neural networks (ANN), backpropagation neural network (BPNN) and the radial basis function neural network (RBFNN), are proposed to predict the carbonation depth of stressed concrete. In order to generate the training and testing data for the ANNs, an accelerated carbonation experiment was carried out for stressed concrete specimens. Based on the experimental results, the BPNN and RBFNN...
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.