Higuchi fractal dimension and deep learning on near-infrared spectroscopy for determination of free fatty acid (FFA) content in oil palm fruit

Abstract

Free fatty acid (FFA) content is an essential parameter with a significant influence on the quality of oil palm, with lower levels showing higher quality. The measurement of this parameter is often carried out with conventional methods in chemical laboratories using solvents and reagents, but these techniques have several limitations. Therefore, this study aimed to develop a rapid and non-destructive technique for determining FFA content based on near-infrared (NIR) spectroscopy. This technique comprised the use of Higuchi fractal dimension (HFD) and deep learning to process NIR spectra as a new chemometric analysis. The sample population consisted of 350 oil palm fruits at various maturity ages collected from the Cikabayan Oil Palm Plantation. Each sample had its NIR spectrum acquired with a wavelength of 1000–1500 nm. Good performance was shown by a low root mean squared error (RMSE) value and a high coefficient of determination (R2). Based on numerical analysis, this study proposed HFD with a maximum discrete time interval (kmax) value of 10 and deep learning with long short-term memory (LSTM) as a robust architectural model. The results showed that the proposed technique could predict oil palm fruit FFA levels with RMSE and R2 values of 0.167 and 0.959, respectively. Furthermore, it could identify FFA content at each process step, before and after harvesting. Based on these results, its implementation in oil palm control management was expected to enhance effectiveness and efficiency, leading to the production of high-quality products.