The following is an abstract for the selected article. A PDF download of the full text of this article is available here. Members may download full texts at no charge. Non-members may be charged a small fee for certain articles.

Locally Weighted Regression in Diffuse Near-Infrared Transmittance Spectroscopy

Volume 46, Number 1 (Jan. 1992) Page 34-43

Næs, Tormod; Isaksson, Tomas

This paper presents an application of locally weighted regression (LWR) in diffuse near-infrared transmittance spectroscopy. The data are from beef and pork samples. The LWR method is based on the idea that a nonlinearity can be approximated by local linear equations. Different weight functions (for the samples) as well as different distance measures for "closeness" are tested. The LWR is compared to principal component regression and partial least-squares regression. The LWR with weighted principal components is shown to give the best results. The improvements with respect to linear regression are up to 15% of the prediction errors.