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 overcome the BP neural network's shortcomings, such as the slow convergence rate and easily fall into a local minimum value, the genetic algorithm is used to optimize the BP neural network. Firstly, the BP neural network's structure, initial weight and threshold values are optimized by genetic algorithm, and then the optimized BP neural network is trained by the samples, to get the knowledge...
An efficient infrared face recognition method by combining discrete wavelet transformation(DWT) and BP neural network was proposed. Firstly, to get the principle information and reduce the dimensions of face, each infrared face image was decomposed into DWT coefficients by using two-level DWT. Then, the DWT coefficients was used to extract the useful features. Finally, based on the useful features...
In order to predict pork prices and its trend, early-warning model based on the BP neural networks was established to protect the interest of producers of pigs and consumers. The programming of C# and MATLAB 2008b was mixed in implementation early-warning system of pork prices. C# realized man-machine interface of early-warning system and database operation, the training and simulation data of neural...
The purpose of this paper is to model tidal flat digital terrain. The study tidal flats are in the yellow sea radial sand ridges eastern China. Based on the regularity and variability characteristics of changeable tidal flats, combined with remote sensing and remote surveying technology and information, this research focuses on tidal flat digital terrain modeling by neural network. The model structure...
In this paper, according to the characteristics of BOT project risk, we combined the vertical tree of work breakdown with the horizontal tree of decomposing risk to form the WBS-RBS risk identification matrix. Based on the existing risk identification, we created the BP neural network model, and carried out the risk assessment through the learning and training of BP neural network, which has ensured...
The traditional BP neural network is widely used in pattern recognition, image processing and intelligent control, and achieve satisfactory results. However the network has its inherent deficiencies. When we research complex system, for instance, society and economic system, the input variables of the neural network are hard to determine. In the paper, aiming at the characteristics of neural network...
Based on the problem that when BP neural network is used in grain yield prediction, if the input space is too self relevant, the predicting accuracy of BP neural network would drop. This paper introduces the method handled on input variables in advance by the principal component analysis. Comparing with the common BP neural network model, the result indicates that the model of principal component...
This paper uses the conjugate gradient method to optimize the calculation and achieve rapid calculation on the network weights and thresholds, simulates the traditional gradient descent and conjugate gradient algorithm of BP neural network, and discusses the training speed, fault-tolerant generalization ability of the method. The goal is to variously verify the superiority of conjugate gradient algorithm...
This paper researches an interpolation method for lack of LiDAR DEM data area in tidal creeks. The study area is tidal flats in the yellow sea radial sand ridges eastern China. Based on a large of tidal creeks surveying data, combined with topography and geomorphology laws, this research focuses on an interpolation method for lack of LiDAR DEM data area in tidal creek by neural network. The interpolation...
According to the application features of Intelligent Transportation System based on Wireless Sensor Networks (WSNs), a simplified topology and an improved handover algorithm in high-speed mobile environment have been proposed. According to Okumura-Hata path loss model, the rxlevel (receive level), speed, distance and the data transmission interruption probability of four polynomials relations, the...
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.