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.
Forecasting method using neural networks has been advocated as an alternative to traditional statistical forecasting in recent years. The paper built a feed-forward neural network model to forecast the values of governmentpsilas financial educational fund (GFEF) in year 2010. On the basis of data processing, the structure of neural networks was given. The algorithm that adopted as a learning phase...
By integrating the global searching advantage of Genetic Algorithm (GA) and the local searching ability of BP Artificial Neural Network (BP ANN), this paper proposes a new model of BP ANN based on GA (called GA-BP ANN). Firstly, it applies GA to optimize the initial interconnecting weights and thresholds of BP ANN. Then, it utilizes the BP algorithm to train the neural network more accurately. This...
A prediction model of compression ratio for extruded oilseeds was developed based on improved BP neural networks. As an applied example, the predicted curves were successfully used to predict critical pressing pressures. Results indicated that the predicted values of compression ratios conformed to the measured values well for extruded cottonseed and castor been. There was a limiting compression for...
The particle swarm optimization was applied in BP neural network training. It reasonably confirms threshold and connection weight of neural network, and improves capability of solving problems in realities. Meanwhile, PSO-BP neural network is applied into classification of fabric defect. The method of orthogonal wavelet transform was used to decompose monolayer from fabric image. And the sub-images...
Neural networks (NNs) have been widely used to financial risk management because of their excellent performances of treating non-linear data with self-learning capability. However, the shortcoming of neural networks is also significant due to a "black box" syndrome and the difficulty in dealing with qualitative information, which limited its applications in practice. To overcome these drawbacks...
At present, the multivariate linear regression analysis was adopted in the biological toxicity forecast through establishment equation of the QSAR mostly, but the error forecasted was big in many situations because of the complexity and nonlinearity of structure-activity relationship, and it has a high request to the sample selection. In this paper forecast model of the nitrobenzene compound biological...
A fuzzy BP neural network model based on particle swarm optimization (PSO) is proposed in this paper. The basic idea of this model is, firstly, the relative membership degrees of fuzzy mathematics are used for deal with the input sample, and then use the algorithm optimizing. Secondly, PSO is used to optimize the BP neural network's initialized weights, an optimized result is got. Then based on the...
Word sense tagging is one of the difficult points in the field of natural language processing. This paper has studied Chinese word sense tagging with the hidden Markov model (HMM) based on semantic case amelioration in order to make use of statistical methods. Firstly,word sense tagging to the real text for application was carried on the HowNet, which is a kind of repository and regards the concept,...
In order to truly realize the personalized learning in which learners are looked as the main characters, we should focus on the characteristics of learners. In order to obtain the characteristics of learners, we should mine the characteristics of learners. In this paper we put forward a kind of data mining algorithm based on improved decision tree, and combined with the characteristics data of personalized...
Facial attribute-specific subspace-based PCA (FASS-based PCA) considers the information of class labels, and the discriminant power can be improved. However, it doesn't consider the outliers which are .common in realistic training sets. To address this problem, we propose robust facial attribute-specific subspace-based PCA (robust FASS-based PCA) algorithm in this paper, which gives a new weighted...
With the rapid developing of the network information, it seems to be quite important to provide a more reasonable text classification algorithm for learners. In this paper,we adopt a sensitivity method to modify the characteristic weight in the distance formula and put up with a cutting method of training sample database based on CURE algorithm and Tabu algorithm; then adopt CURE cluster algorithm...
Sunspot number time series, as a multivariable, strong coupling and nonlinear time series, has encountered troubles to describe its changes rules with modeling method owing to great complexity of sunspot number change. The main aim of this study is to develop a novel prediction method, based on the Quantum Neural Networks, which is composed of some quantum neurons and traditional neurons based on...
Radial basis function neural network (RBFNN) is widely applied in pattern recognition. Comparing with the Gaussian function of RBFNN, the ellipsoidal basis function (EBF) can make the partition of input space more specific. Ellipsoidal basis function neural network (EBFNN) is a forward-feedback neural network of which hidden-layer function is EBF, which can make the partition of input space limitary...
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.