In this study, moisture content of soybean was evaluated using visible near infrared (Vis-NIR) spectroscopy. Soybean were dried at 60˚C for up to 10 hours to get moisture variation. A total of 200 soybean were used in this study which made a total of 600 reflectance spectra scanned with Vis-NIR spectrometer at 400-1000 nm. All samples were randomly divided into calibration set (2/3 samples) and prediction set (1/3 samples). Partial least square regression (PLSR) was used for developing calibration model for determining moisture content of soybean seed. Original and several preprocessed spectra such as area normalization, standard normal variate (SNV), multiple scatter correction (MSC), Savitzky-Golay smoothing, and Savitzky-Golay derivative were used in PLSR. The best PLSR model was obtained using 2 nd Savitzky-Golay derivative with determination coefficient of calibration (R²C) of 0.93 and root mean square error of calibration (RMSEC) of 0.004%. The PLSR model was then applied to prediction data set which resulted in determination coefficient of prediction (R²P) of 0.82 and root mean square error of prediction (RMSEP) of 0.006%. The result showed the potency of Vis-NIR spectroscopy to predict moisture content in soybean seed.

Organic and non-organic soybean flours, although visually indifferent, have a significant difference in price and nutrition content. Therefore, the accurate authentication detection of organic soybean flour is necessary. Visible-near-infrared (Vis-NIR) spectroscopy coupled with chemometric methods is a non-destructive technique applied to detect authentic or adulterated organic soybean flour. The spectra of organic, adulterated organic, and non-organic soybean flours were captured using a Vis-NIR spectrometer at 350–1000 nm. The spectra were analyzed using partial least squares (PLS), principal component analysis (PCA), and the combination of these two with discriminant analysis (DA). The results showed that PCA using PC1 and PC2 could differentiate organic and non-organic soybean flours, whereas PC1 and PC4 can detect pure and adulterated organic soybean flours. The PCA–linear DA models showed 98.5% accuracy (Acc) for predicting pure organic and adulterated soybean flours and 100% Acc for predicting organic and non-organic flours. Moreover, PLS regression models resulted in a high R² of >95% for predicting organic and non-organic flours and pure and adulterated soybean flours. In addition, the PLS-DA models can differentiate organic from non-organic soybean flour and distinguish pure and adulterated soybean flours with 100% Acc and reliability.

The purpose of this study was to use study the potency of the modular Vis/NIR spectroscopy for determining viability of soybean seeds. Vis/NIR spectra of soybean seeds were collected and analysed using partial least squares discriminant analysis (PLS-DA) for discriminating non-viable soybean seeds from viable ones. The optimal classification models developed were compared with various spectral pre-processing methods. The result showed that the modular Vis/NIR spectroscopy performed perfectly (Accuracy and Reliability of 100%) in detecting soybean viability. The study showed that the Vis/NIR spectroscopy coupled with chemometric analysis are potential for rapid detection of viability of soybean seeds.