Predicting the free calcium oxide content in cement clinker on the basis of rough sets and support vector machines

In this study, we combined the rough set theory and the fuzzy clustering theory with the support vector machine (SVM) and proposed a rough SVM model to predict the free calcium oxide content in cement clinker. We used the fuzzy clustering method to conduct discretization treatment of our data and applied the rough set theory to conduct attribute reduction so as to reduce the quantity of the input space dimensions of the SVM and further reduce the number of the sample. After that, we conducted training by using the least squares support vector machines (LS-SVM) and determined the optimal parameters of the LS-SVM by means of grid searching and cross validation. Our simulation findings indicate that this model can effectively predict the content of free calcium oxide in cement clinker.