A kernel distance-based representative subset selection method

This paper proposes a new representative subset selection method called kernel distance-based sample set partitioning based on joint x–y distances, referred to as KSPXY. The proposed method is a modified version of the original sample set partitioning based on joint x–y distances (SPXY) algorithm, where the kernel distance is used as an alternative to the Euclidean distance. The proposed KSPXY algorithm is used with partial least-squares (PLS) to predict three chemical quality characteristics of diesel fuel. We compare the PLS-KSPXY modelling strategy with two modelling strategies involving the use of SPXY and Kennard–Stone (KS) algorithms with PLS. Based on the root mean-squared error of prediction, results show that the proposed KSPXY algorithm performs better than SPXY and KS algorithms in improving the predictive ability of the PLS model. The difference between PLS–KSPXY and the other two modelling strategies is statistically significant. The paper provides also the MATLAB code for the proposed KSPXY algorithm, developed by the authors.