The Intelligent Producing And Post-processing Of Small Sample Visualization Data

Visualization in Scientific Computing is emerging in the 1980s as a new technology and now it has been focused more and more by many fields all over the world because of the appearance of volume visualization.A good visualization effect is based on a lot of accurate data, however, due to the limitation of measure condition and technology ability, the acquirement of many visualization data is difficult. On the contrary, small sample data are at large.At first, the paper states the characters of small sample data, and then analyzes the complexity and the particularity of estimating small samples, at the meantime, analyzes some kinds of prediction model and their methods. At last, two methods are proposed by comparison and validate, and the thinking, which are based on grey prediction model and neural network technology, is adopted.In the paper, a new SGRBF static model is established on the basis of RBF (Radial Basis Function) and Grey Model (0, N). The model can deal with the prediction problem very well, because it makes use of the RBF's good ability of in approaching nonlinear function, and the accuracy of Grey r4Model (0,N) in making a prediction of small sample data. Furthermore, the SGRBF model adopts FCM-ROLS algorithm to train RBFNN in order to obtain a higher accuracy.A DGRBF dynamic model is established in the paper, which can select the best initialization conditions and dynamic identifying parameters and is fit for dynamic and long-term data prediction.At last, the paper proposed a neural network based visualization data intelligent post-processing expert system (NVDIPES), and then develops an environment with Matlab and VC++. The environment not only produces the small sample data but also makes a post-processing to them. The application proves that the SGRBF, DGRBF model and the NVDIPES are easy, convenient, accurate and good practicality.