Multi-kernel linear programming support vector regression with prior knowledge

This paper proposes a multi-kernel linear programming support vector regression with prior knowledge in order to obtain an accurate regression model in the case of the scarcity of measured data available. In the algorithm, multi-kernel and prior knowledge which may be exact or biased from a calibrated simulator have been incorporated into the framework of linear programming support vector regression by utilizing multiple feature spaces and modifying optimization formulation. Some experiments from a synthetic example have been carried out, and the results show that the proposed algorithm is effective, and that the obtained model is sparse and accurate. The proposed algorithm shows great potential in some practical applications where the experimental data is few and the prior knowledge from a simulator is available.