Detection of Aspartic Acid in Fermented Cordyceps Powder Using Near Infrared Spectroscopy Based on Variable Selection Algorithms and Multivariate Calibration Methods

Near infrared (NIR) spectroscopy combined with chemometrics was employed to detect the aspartic acid content in fermented Cordyceps powder. One hundred sixty-nine samples were applied for calibration (n = 113) and prediction (n = 56). Six different pretreatment methods were compared to determine the optimal pretreatment method for analysis. The wavelength variables selected by regression coefficient analysis, successive projections algorithm, and genetic algorithm-partial least squares analysis (GAPLS) were used as the inputs of partial least-squares analysis, multiple linear regression (MLR), and least-squares support vector machine. The performances of these calibration methods were also compared to determine the best model. The results indicated that GAPLS-MLR obtained the highest precision with a correlation coefficient of prediction r (pre) = 0.9223, root mean square of prediction RMSEP = 0.0751 g/100 g, and coefficient of variation CV = 5.15 %. The overall results showed that NIR was feasible for the determination of aspartic acid in fermented Cordyceps powder and GAPLS could perform well with less input dimension and computation complexity in the aspartic acid estimation.