Support vector machines for modelling phosphocalcic hydroxyapatite by precipitation from a calcium carbonate solution and phosphoric acid solution

The aim of this work was to develop an effective quantitative relationship model using support vector machines for the synthesis of phosphocalcic hydroxyapatite by precipitation from a calcium carbonate solution and a phosphoric acid solution. The model was created using a set of factors consisting of the pH of the reaction solution, the Ca/P molar ratio of the reagents, the reaction time and the initial concentration of calcium. Previous studies modelled these relationships using different classification techniques. In this paper, a novel approach based on support vector machines (SVMs) is introduced. This latter approach yields the best result compared to polynomial regression (PR), linear regression (LR) and artificial neural networks (ANN). In addition, the contribution of each descriptor is evaluated. Thus, the proposed method can be successfully used to predict the Ca/P analysis directly from the considered factors.