|
Partial least squares (PLS) and generalized regression neural networks (GRNN) prediction model for fibre, starch and protein in potato had been established with good veracity. 12 peak value data from 3 principal components straight ahead compressed from original data by PLS were taken as inputs of GRNN while 3 predictive targets as outputs. 0.1 was chosen as smoothing factor for its good approximation and prediction with the lowest error compared with 0.2, 0.3, 0.4, and 0.5. Predictive correlation coefficient of three components by the model are 0.945, 0.992, and 0.938. The results show that PLS-GRNN using in NIRS is a rapid, effective means for measuring fibre, starch and protein in potato. The results are important in quality controlling and evaluating in fruit and vegetable industry, and can also be used in quantitative analysis of other samples. |
|
Keywords:Near infrared spectroscopy (NIRS);Potato;PLS;GRNN;Multi-component quantitative analysis |
|