CSRBF-Based Quasi-interpolation for Accurate and Fast Data Fitting

In this paper, quasi-interpolation based on compactly supported radial basis functions (CSRBFs) is presented for more accurate and efficient data fitting compared with global RBFs. Firstly, a CSRBF-based quasi-interpolator is constructed considering only the positions of the given data and their values. Then we make use of the first derivatives to propose a new quasi-interpolator which can achieve higher approximate order and better shape-preserving. Numerical examples demonstrate that the proposed CSRBF-based quasi-interpolation schemes are valid.