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.
An ensemble of Elman networks (EEN) is formed by bagging to enhance the performance of the individual networks. The combined density functional theory (DFT) with EEN correction approach has been applied to evaluate the electronic excitation energies of organic molecules. The EEN approach improved DFT calculation results and reduced the RMS deviations from 0.48 to 0.23 eV for the training set. For...
In order to deal with the defects of the poor convergences and easily immerging in partial minimum frequently, a new algorithm is proposed based on the combination of genetic algorithm and BP neural network, which is called GA- BP algorithm. This algorithm is applied to optimization of initial weights of BP Network, the structure and learn rule. It searches through the total solution space and can...
Aims at the complex and dynamic nature of traffic flow in mountain expressway tunnel, through the analysis of change characteristics of traffic flow, based on BP network improve the existing expressway traffic flow model, this thesis puts forward the Elman dynamic neural network model of traffic flow predicting in mountain expressway tunnel. In practice, this model has the strong operational, we adopt...
Least squares support vector machines (LSSVM) has been carried out in order to obtain a statistically meaningful analysis of the extended set of molecules. The combined HF with LSSVM correction approach (LSSVM/HF) has been applied to evaluate the transition energies of organic molecules. After LSSVM correction, the RMS deviations of the calculated transition energies reduce from 0.91 to 0.26 eV for...
The neural network ensemble approach (NNE) is proposed for improving the generalization ability of neural networks and to reduce the calculation errors of density functional theory (DFT). The simple averaging approach (NNEA) and weighted averaging approach (NNEW) for combining the predictions of component neural networks we adopted respectively. As a demonstration, this combined DFT and NNE correction...
In view of the defect of particle swarm optimization(PSO) which easily gets into partial extremum, the paper puts out an improved particle swarm optimization(IPSO), and applies the algorithm to the selecting of parameter of RBF neural network pit function. The algorithm searches the parameter vector which has the best fitness in the whole space, according to coding mode, iterative formula, fitness...
In order to overcome inherent bugs of basic hidden markov model (HMM), a method of speech recognition based on fuzzy clustering neural network is presented. Based on the fuzzy system model, every state (HMM) is regarded as a fuzzy system in this method. With continuous frames character vector of speech signal as the system's input, the model can forecast the probability density function of the system's...
Radial basis function (RBF) neural network is used to predict the blast furnace hot metal based on its characteristics such as fast convergence and global optimization. As hot metal silicon content had close relationship with furnace temperature, the change of temperature in furnace was reflected indirectly by hot metal silicon content. Newrbe function in Matlab was applied for function approximation...
This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined...
We introduce a method for modeling cancer diagnosis at the molecular level using a Chinese microarray gastric cancer dataset. The method combines an artificial neural network with a decision tree that is intended to precede standard techniques, such as classification, and enhance their performance and ability to detect cancer genes. First, we used the relief algorithm to select the featured genes...
Designing less intrusive intelligent environments requires a deep understanding of activities that a user is engaged in. This paper presents a novel one-pass neural network system that uses unobtrusive and relatively simple sensors and puts forward a constructive algorithm which is able to recognize different high level activities (such as ldquosleepingrdquo, ldquowashingrdquo, ldquoworking at computerrdquo)...
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.