Transfer of Multivariate Classification Models Between Laboratory and Process Near-Infrared Spectrometers for the Discrimination of Green Arabica and Robusta Coffee Beans
Authors: Myles, Anthony J.1; Zimmerman, Tyler A.1; Brown, Steven D.1
Source: Applied Spectroscopy, Volume 60, Issue 10, Pages 246A-272A and 1097-1216 (October 2006) , pp. 1198-1203(6)
Publisher: Society for Applied Spectroscopy
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Abstract:
Analogous to the situation found in calibration, a classification model constructed from spectra measured on one instrument may not be valid for prediction of class from spectra measured on a second instrument. In this paper, the transfer of multivariate classification models between laboratory and process near-infrared spectrometers is investigated for the discrimination of whole, green Coffea arabica (Arabica) and Coffea canefora (Robusta) coffee beans. A modified version of slope/bias correction, orthogonal signal correction trained on a vector of discrete class identities, and model updating were found to perform well in the preprocessing of data to permit the transfer of a classification model developed on data from one instrument to be used on another instrument. These techniques permitted development of robust models for the discrimination of green coffee beans on both spectrometers and resulted in misclassification errors for the transfer process in the range of 5-10%.Keywords: CHEMOMETRICS; CLASSIFICATION; STANDARDIZATION; TRANSFER; ORTHOGONAL SIGNAL CORRECTION; OSC; PARTIAL LEAST SQUARES; PLS; DISCRIMINANT ANALYSIS; NEAR-INFRARED SPECTROSCOPY; NIR SPECTROSCOPY; COFFEE BEANS
Document Type: Research article
DOI: 10.1366/000370206778664581
Affiliations: 1: Laboratory for Chemometrics, Department of Chemistry and Biochemistry, University of Delaware, Newark, Delaware 19716
- Free Content
- New Content
- Subscribed Content
- Free Trial Content
Click here for Page Help