The Research & Application Of Data Mining Model Based On Neural Network Theory

Data Mining (DM) is the process of discovering interesting knowledge from large amounts of Data stored either in Databases, Data Warehouses, or other information repositories. Artificial neural network (ANN) is a kind of simulation of the biological neural network of human brain. It is constructed by several neurons, which are connected according to some rules and have processing capacities. ANN can cope with problems including inexact data and complex nonlinear mapping.Some traditional method of data mining is only suitable for exact set, not for inexact set. Since many sets of data in reality are imprecise, the DM model based on ANN is studied in this dissertation. Then an Evolutionary unitary BP model is introduced which is mainly combined with evolutionary programming technique and unitary BP algorithm. Compared with the old model, the improved model has faster training pace and higher precision.In this dissertation, a clothes size classification model based on the new model is brought forward, which realizes the automation of clothes size classification process. The comparison between the new model and the multivariate regression model certifies that the new model is more effective and practical.