Application of DM in data safety of machine learning based on combined grey neural network

Abstract

Using the theory of grey system, DM technology and radial basis function (RBF) neural network method, a new model, the combined model of grey system and RBF neural network is setup, which aims at solving the user's received data safety of machine learning. The results show that, in shortterm prediction of data safety of machine learning, GM is an effective way and RBF has perfect ability to study and map. The combined model of grey system and neural network, to a large extent, has the dual properties of trend and fluctuation under the condition of combining with the time-dependent sequence data. It is concluded that great improvement comparing with any method of trend prediction and simple factor in combined grey neural network (CGNN) comparing with the any model of grey system and RBF neural network in data safety of machine learning of machine learning.