Premium
Hyperspectral imaging for predicting the allicin and soluble solid content of garlic with variable selection algorithms and chemometric models
Author(s) -
Rahman Anisur,
Faqeerzada Mohammad A,
Cho ByoungKwan
Publication year - 2018
Publication title -
journal of the science of food and agriculture
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.782
H-Index - 142
eISSN - 1097-0010
pISSN - 0022-5142
DOI - 10.1002/jsfa.9006
Subject(s) - hyperspectral imaging , allicin , partial least squares regression , support vector machine , feature selection , artificial intelligence , chemometrics , calibration , pattern recognition (psychology) , mathematics , biological system , computer science , machine learning , chemistry , statistics , food science , biology
BACKGROUND Allicin and soluble solid content (SSC) in garlic is the responsible for its pungent flavor and odor. However, current conventional methods such as the use of high‐pressure liquid chromatography and a refractometer have critical drawbacks in that they are time‐consuming, labor‐intensive and destructive procedures. The present study aimed to predict allicin and SSC in garlic using hyperspectral imaging in combination with variable selection algorithms and calibration models. RESULTS Hyperspectral images of 100 garlic cloves were acquired that covered two spectral ranges, from which the mean spectra of each clove were extracted. The calibration models included partial least squares (PLS) and least squares‐support vector machine (LS‐SVM) regression, as well as different spectral pre‐processing techniques, from which the highest performing spectral preprocessing technique and spectral range were selected. Then, variable selection methods, such as regression coefficients, variable importance in projection (VIP) and the successive projections algorithm (SPA), were evaluated for the selection of effective wavelengths (EWs). Furthermore, PLS and LS‐SVM regression methods were applied to quantitatively predict the quality attributes of garlic using the selected EWs. Of the established models, the SPA‐LS‐SVM model obtained an R pred 2 of 0.90 and standard error of prediction (SEP) of 1.01% for SSC prediction, whereas the VIP‐LS‐SVM model produced the best result with an R pred 2 of 0.83 and SEP of 0.19 mg g −1 for allicin prediction in the range 1000–1700 nm. Furthermore, chemical images of garlic were developed using the best predictive model to facilitate visualization of the spatial distributions of allicin and SSC. CONCLUSION The present study clearly demonstrates that hyperspectral imaging combined with an appropriate chemometrics method can potentially be employed as a fast, non‐invasive method to predict the allicin and SSC in garlic. © 2018 Society of Chemical Industry