| Autor: |
Dandan Kong, Dawei Sun, Ruicheng Qiu, Wenkai Zhang, Yufei Liu, Yong He |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy. 273 |
| ISSN: |
1873-3557 |
| Popis: |
Pure fishmeal (PFM) from whole marine-origin fish is an expensive and indispensable protein ingredient in most aquaculture feeds. In China, the supply shortage of domestically produced PFM has caused frequent PFM adulteration with low-cost protein sources such as feather meal (FTM) and fishmeal from by-products (FBP). The aim of this study was to develop a rapid and nondestructive detection method using near-infrared hyperspectral imaging (NIR-HSI) combined with machine learning algorithms for the identification of PFM adulterated with FTM, FBP, and the binary adulterant (composed of FTM and FBP). A hierarchical modelling strategy was adopted to acquire a better classification accuracy. Partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) coupled with four spectral preprocessing methods were employed to construct classification models. The SVM with baseline offset (BO-SVM) model using 20 effective wavelengths selected by successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) achieved classification accuracy of 100% and 99.43% for discriminating PFM from the adulterants (FTM, FBP) and adulterated fishmeal (AFM), respectively. This study confirmed that NIR-HSI offered a promising technique for feed mills to identify AFM containing FTM, FBP, or binary adulterants. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect