14 January 1999 Locally weighted regression for accessing a database containing wheat grain NIR transmission spectra and grain quality parameters
Author Affiliations +
Proceedings Volume 3543, Precision Agriculture and Biological Quality; (1999) https://doi.org/10.1117/12.336876
Event: Photonics East (ISAM, VVDC, IEMB), 1998, Boston, MA, United States
Abstract
Networks of NIR transmission spectrometers operating in the range 850 to 1050 nm are used worldwide to determine wheat grain quality parameters such as protein content. These instrumental system often require maintenance of calibrations for each grain class, and updating of calibrations for each crop year. In order to facilitate annual updates nd eliminate the need for multiple wheat class calibration models, this laboratory is pursuing a modeling strategy that uses locally weighted regression (LWR) to access a spectral database. With LWR, the calibration model defines the procedure to access the database and calculate the prediction, and this model can potentially remain the same for all classes and crop years. Incorporation of new sample variation is accomplished by new additions to the spectral database. Details are presented on development of an NIR model for determination of protein in multiple wheat-classes using the LWR approach with Y- distance weighting. This model is compared with a linear partial least-squares regression model spanning the same diverse set of samples. Initial steps were taken to validate these models with spectra measured on seven instruments at two remote locations.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Douglas D. Archibald, Douglas D. Archibald, David B. Funk, David B. Funk, Franklin E. Barton, Franklin E. Barton, } "Locally weighted regression for accessing a database containing wheat grain NIR transmission spectra and grain quality parameters", Proc. SPIE 3543, Precision Agriculture and Biological Quality, (14 January 1999); doi: 10.1117/12.336876; https://doi.org/10.1117/12.336876
PROCEEDINGS
11 PAGES


SHARE
Back to Top