Research paper on Agro-forestry | Determination of moisture content of peanut (Arachis hypogea Linn.) kernel using near-infrared hyper-spectral imaging technique

Jose D. Guzman from Cagayan State University, Tuguegarao City, Philippines, wrote a research paper on Agro-forestry entitle of Determination of moisture content of peanut (Arachis hypogea Linn.) kernel using near-infrared hyper-spectral imaging technique.

Moisture content is a very essential indicator for 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 latest technology. This study generally aims to investigate the potential of hyper spectral imaging technique in the near- infrared region (900nm – 1700nm) for determining and predicting moisture content of peanut kernels.

 

Source: wikiwand.com

 

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 mean 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 to 20 wavelengths identified. These wavelengths were used to build the optimized regression model which resulted to 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 was applied to the peanut kernel hyperspectral images in a pixel- wise manner obtaining peanut kernel moisture content distribution map. Results show promising potential of 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.

 

Journal of Biodiversity and Environmental Sciences-JBES is an open-access scholarly research journal, published by International Network for Natural Sciences-INNSPUB. JBES published original scientific articles in different field of Environmental Sciences and Biodiversity. JBES published 2 Volume and 12 issue per calender year.