Caffeine content calibration model on green beans arabica Mandailing Natal coffee using NIRS and artificial neural network

Generally, Near Infrared Reflectance (NIR) spectroscopy is a non-destructive method that can identify the chemical content of agricultural products. In this study, several pretreatment data were used to reduce some noises from original NIR spectra, namely normalization (0-1) and Multiple Scatter Correction (MSC) calibration model caffeine using Artificial Neural Network (ANN). Result wavelength analysis showed Mandailing Natal green bean arabica coffee was in wavelengths 1,208.9 nm 1,728.91 nm. A good ANN architecture result obtained with normalization/MSC which 13-3-1 at 1,000 iterations, indicated by r = 0.9845, CV 4.80% │RMSEC-RMSEP│= 0.0383.