Paper A24

A Method to Compensate the Influence of Different Particle
Size of Coffee Powder in NIR Calibration Model
Performance

Diding Suhandy*,1 Meinilwita Yulia2
1Department of Agricultural Engineering, The University of Lampung, Indonesia
2Department of Agricultural Technology, Lampung State Polytechnic, Indonesia
Email: diding.sughandy@fp.unila.ac.id*

Abstract

In this research, a method to compensate the influence of different particle size of coffee powder in NIR calibration model performance was evaluated. A number of 220 coffee powder samples with two different types of coffee (civet and non-civet) and two different particle sizes (212 and 500 μm) were prepared. Spectral data was acquired using NIR spectrometer equipped with an integrating sphere for diffuse reflectance measurement. A discrimination method based on PLS-DA was conducted and the influence of different particle size on the performance of PLS-DA was investigated. Using the best local calibration models at 221μm and 500μm, prediction results for a prediction sample set at 221 and 500 μm were excellent, with low RMSEP values. However, SEP was significantly increased when samples from different particles size were used in these models; higher RMSEPs resulted. On the other hand, global calibration model based on combinations of different particle size gave better prediction results, with lower RMSEP values for all prediction samples at 221 and 500μm.

Keywords: Compensation method, global model, local model, particle size, PLS-DA.

Full Text PDF of A24 Diding Suhandy et al