Study of relevance vector machine and its application in copper-matte converting

Relevance vector machine(RVM) technique as a new machine learning method is based on statistical learning theory,and it is developed on the basis of sparse Bayesian learning theory.RVM has more merits than support vector machine(SVM),and it is proven to be a valid data mining tool.RVM and its application was discussed,which in copper-matte converting mainly.RVM was used to optimizing and forecasting the parameter of the copper-matte converting process of a factory,Experimental results show that RVM is very suitable for handing the small sample、nonlinear、high dimensional optimization problem,and some performances are better than SVM.