Key Words: Near-infrared hyperspectral imaging, Optimal wavelengths, Partial least square regression, Peanut kernel, Peanut moisture content J. Bio. Env. Sci. 15(4), 43-51, October 2019. Moisture content is a very essential indicator for the quality and storage stability of peanuts but its measurement is tedious and time-consuming. This study ventured in a rapid and non-destructive way of determining and predicting the moisture content of peanut kernels utilizing the latest technology. This study generally aims to investigate the potential of hyperspectral imaging technique in the near-infrared region (900nm – 1700nm) for determining and predicting the moisture content of peanut kernels. Using partial least square regression (PLSR), spectral data from the peanut kernel hyperspectral images were extracted to predict MC. The MC PLSR model displayed good performance with determination coefficient of calibration (R2c), cross-validation (R2cv) and prediction (R2p) of 0.9309, 0.9094 and 0.9316, respectively. In addition, root means a square error of calibration (RMSEC), cross-validation (RMSECV), and prediction (RMSEP) of 1.6978, 1.9571, and 1.8715, respectively. Optimization was done by selecting wavelengths with the highest absolute weighted regression coefficients resulting in 20 wavelengths identified. These wavelengths were used to build the optimized regression model which resulted in a better model with R2c of 0.9357, R2cv of 0.9142, and R2p of 0.9445 as well as RMSEC, RMSECV, and RMSEP of 1.6822, 1.8316, and 1.9519, respectively. The optimized model has applied to the peanut kernel hyperspectral images in a pixel-wise manner obtaining a peanut kernel moisture content distribution map. Results show promising potential of a hyperspectral imaging system in the near-infrared region combined with partial least square regression (PLSR) for rapid and non-destructive prediction of moisture content of peanut kernels.

Jose D. Guzman. Determination of moisture content of peanut (Arachis hypogea Linn.) kernel using near-infrared hyper-spectral imaging technique. J. Bio. Env. Sci. 15(4), 43-51, October 2019.