A Comparative Study of LOWESS and RBF Approximations for Visualization

TL;DR

This paper compares LOWESS and RBF approximation methods for visualization, highlighting their performance differences on noisy data across various dimensions, with LOWESS excelling in lower dimensions and RBF in higher dimensions.

Contribution

It provides a systematic comparison of LOWESS and RBF methods, emphasizing their suitability for different data dimensionalities in visualization tasks.

Findings

LOWESS performs better on lower-dimensional data.

RBF is more convenient for high-dimensional scattered data.

The study offers guidance on choosing approximation methods based on data dimensionality.

Abstract

Approximation methods are widely used in many fields and many techniques have been published already. This comparative study presents a comparison of LOWESS (Locally weighted scatterplot smoothing) and RBF (Radial Basis Functions) approximation methods on noisy data as they use different approaches. The RBF approach is generally convenient for high dimensional scattered data sets. The LOWESS method needs finding a subset of nearest points if data are scattered. The experiments proved that LOWESS approximation gives slightly better results than RBF in the case of lower dimension, while in the higher dimensional case