Removal of conveyor belt near infrared signals in in-line monitoring of proximal ground beef composition

On monitoring the proximal composition of ground beef on a conveyor belt with a NIR reflectance sensor, interference by signals from the belt itself showed up to be a serious problem. A SIMCA classification method proved useful in identifying spectra with belt components, which consequently were removed to yield pure meat spectra. PLS regression on basis of the corrected spectra yielded improved models for proximal analysis of the ground beef.