TY - JFULL AU - Siti Nurhidayah Naqiah Abdull Rani and Herlina Abdul Rahim and Rashidah Ghazali and Noramli Abdul Razak PY - 2015/2/ TI - Free Fatty Acid Assessment of Crude Palm Oil Using a Non-Destructive Approach T2 - International Journal of Agricultural and Biosystems Engineering SP - 57 EP - 61 VL - 9 SN - 1307-6892 UR - https://publications.waset.org/pdf/10000221 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 97, 2015 N2 - Near infrared (NIR) spectroscopy has always been of great interest in the food and agriculture industries. The development of prediction models has facilitated the estimation process in recent years. In this study, 110 crude palm oil (CPO) samples were used to build a free fatty acid (FFA) prediction model. 60% of the collected data were used for training purposes and the remaining 40% used for testing. The visible peaks on the NIR spectrum were at 1725 nm and 1760 nm, indicating the existence of the first overtone of C-H bands. Principal component regression (PCR) was applied to the data in order to build this mathematical prediction model. The optimal number of principal components was 10. The results showed R2=0.7147 for the training set and R2=0.6404 for the testing set. ER -