Table 4.
The performance statistics of Partial Least Square Regression (PLSR) models developed using a training (n = 102) and an external validation (n = 16) data set based on Raman and NIR spectral data for estimating palmitic, oleic, linoleic acid composition in potato chip samples.
| Approach | Fatty Acid | Training Model | External Validation Model | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Range | N a | Factor | SECV b | Rcal | Range | N c | SEP d | Rval | ||
| Raman | Palmitic (%) | 2.4–36.3 | 101 | 6 | 1.08 | 0.98 | 3.7–20.3 | 16 | 1.08 | 0.97 |
| Oleic (%) | 18.9–86.9 | 102 | 6 | 2.26 | 1 | 19.1–84.9 | 16 | 1.84 | 1 | |
| Linoleic (%) | 5.3–62.4 | 102 | 6 | 1.48 | 1 | 7.5–57.5 | 16 | 1.31 | 1 | |
| NIR | Palmitic (%) | 2.5–27.2 | 94 | 6 | 1.06 | 0.98 | 3.7–20.3 | 16 | 1.60 | 0.97 |
| Oleic (%) | 18.9–86.9 | 95 | 6 | 2.61 | 0.99 | 19.1–84.9 | 16 | 2.87 | 0.99 | |
| Linoleic (%) | 5.3–62.4 | 101 | 6 | 2.47 | 0.99 | 7.5–57.5 | 16 | 3.55 | 0.99 | |
a Sample number in the training models. b Standard error of cross validation. c Sample number in the external validation models. d Standard error of prediction.