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.
Recently, the minimum mean squared error (MMSE) has been a benchmark of optimization criterion for deep neural network (DNN) based speech enhancement. In this study, a probabilistic learning framework to estimate the DNN parameters for single-channel speech enhancement is proposed. First, the statistical analysis shows that the prediction error vector at the DNN output well follows a unimodal density...
A temperature prediction model based on Self-adaption Particle Swarm Optimization (SAPSO) and Extreme Learning Machine (ELM) is proposed in this paper. The nano-iron powder decomposing furnace temperature prediction model is established based on ELM. ELM, a neural network, is developed rapidly in recent years, but it requires a lot of hidden layer neurons to achieve ideal prediction accuracy. In order...
Abundant field experiments have showed that the super low frequency (SLF) electromagnetic detector is sensitive to Coalbed Methane(CBM). The signal curves collected by the SLF electromagnetic detector show high amplitude anomalies in the CBM enrichment areas. Based on this finding, we choose the Qinshui basin as study area, and take advantage of the field SLF electromagnetic data to make quantitative...
A new method based on neural network and genetic algorithm to optimizate the Multiphase Rotodynamic pump is given. Using cubic B-spline surface to parametric the blade profile. Based on the ability of highly nonlinear fitting of BP neural network, the nonlinear relation between the blade parameter and the pump performance parameters is build. Let the trained neural network as a fitness function of...
Based on the third generation YQH-100 multiphase rotodynamic pump independently developed as the research object, The models of BP and RBF neural network were established respectively to predict the Multiphase Rotodynamic pump energy characteristics. The 27 groups of sample data of neural networks were created by FLUENT numerical calculated. The performance data of 20 multiphase rotodynamic pumps...
The utilization of information and communication technology (ICT) to enhance teaching and learning is the emphasis of the education reform in China. The purpose of this study was to construct an effective online learning model for the online learning. Through the analysis of the web learning problem, the article brings forward the important function of the online tutor in web learning and defines...
Medical Informatics is the scientific field that deals with the storage, retrieval and optimal use of information and data in medicine. It is often called healthcare informatics or biomedicai informatics, and forms part of the wider domain of eHealth. The end objective of biomedicai informatics is the coalescing of data, knowledge, and the tools necessary to apply that data and knowledge in the decision-making...
Bus travel time prediction is a vital part for both bus operation optimizing system and information service system. This paper reviews existing bus travel time prediction models and analyzes the strengths and weaknesses of each model. A bus travel time prediction model based on nu - Support Vector Regression is proposed, which uses the departure time of bus from origin stop that can reflect traffic...
Vibration detection system of turbine generator can obtain large amounts of data resources; however, there are no effective methods to excavate useful knowledge from these massive data. In this paper, a new approach for fault diagnosis of turbine generator based on supervision of data-driven is proposed. This algorithm begin with the given classification data, using the representative points on behalf...
Divide-and-conquer principle is a fashionable strategy to handle large-scale classification problems. However, many works have revealed that generalization ability is decreased by partitioning training set in most cases, because partitioning training set can lead to losing classification information. Aiming to handle this problem, an ensemble learning algorithm was proposed. It used many sets of parallel...
Road information understanding is a necessary task for both intelligent vehicles and driving assistance systems. Previous research mostly focused on the detection of lane position. Other information provided by arrow markings was scarcely mentioned. In this paper, Arrow extraction is carried out by projection histogram on Inverse perspective image and an arrow markings recognition algorithm is presented...
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.