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.
Based on the idea of nonlinear prediction of phase space reconstruction, this paper presented a time delay BP neural network model, whose generalization capability was improved by Bayesian regularization. Furthermore, the model is applied to forecast the imp&exp trades in one industry. The results showed that the improved model has excellent generalization capabilities, which not only learned...
In this paper, an algorithm of learning a simple type of Bayesian network-Bayesian spanning tree with maximum log-likelihood is presented. The log likelihood function is used to measure the Bayesian spanning tree with respect to given documents data. In a Bayesian spanning tree, besides the root node, each node has at most two parent nodes. The Bayesian spanning tree is an unsupervised classifier...
Generative learning and discriminative learning are two different classifier learning methods. Bayesian network classifiers belong to in nature generative classifiers because the learners always attempt to find the Bayesian network that maximizes likelihood rather than classification accuracy. In order to improve the classification performance, many researchers is trying to train the generative classifier...
Economic early warning (EEW) helps decision-making by judging the tendency of economic development. However, little research is considered about the noise problem commonly existing in the economic data. Traditional EEW method such as Bayesian model needs the feature independent assumption; artificial neural network suffers from the over-fitting problem. This paper proposes a new method of combining...
As more and more data are described, stored, exchanged and represented by XML, the abilities of information retrieval for XML documents become increasingly important. However, the retrieval results to users are quite large. To text-rich XML documents' retrieval, a structured index method is designed at first, which accounts for the structure and content of each document. Then each XML document is...
The ability to correctly detect the location and derive the contextual information where a concept begins to drift is essential in the study of domains with changing context. This paper proposes a top-down learning method with the incorporation of a learning accuracy mechanism to efficiently detect and manage context changes within a large dataset. With the utilisation of simple search operators to...
The retrieval performance of an information system usually increases when it uses the relationships among the terms in a given document collection. This paper presents an improved co-occurrences frequency method to mine relationship among document index terms, then gives an extended model by adding one term layer in belief network model, shows its topology, probability estimating and information retrieval...
This paper is based on the fault diagnosis analysis about electrical product of Bayesian network. We represent fault diagnosis as decision problem under ambiguity and immaturity of information. Bayesian network classifiers (BNC) is thus established which is based on the fault diagnosis of, and representing the ambiguity of information as probability description. Pre-process analysis is made to fault...
Based on the complicated relationships between the symptoms and the defects of hydro-generator units, An approach to diagnosing the faults in hydro-generator units via a neural networks combined with genetic algorithm (GA) and nonlinear principal analysis neural network (NLPCA NN) is presented in this paper. At first, GA optimizes both the structure and the connection of the NLPCA NN. The so-called...
A modified fuzzy Bayesian network (FBN) is proposed in this study, which integrates fuzzy theory into Bayesian networks (BN) by using Gaussian mixture models (GMM) to make a fuzzy procedure. This particular procedure transforms continuous variables into discrete ones, when dealing with continuous inputs with probabilistic and uncertain nature. Based on the FBN, the fuzzy reasoning model for prediction...
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.