Premium
Traceability of Boletaceae mushrooms using data fusion of UV–visible and FTIR combined with chemometrics methods
Author(s) -
Yao Sen,
Li Tao,
Liu HongGao,
Li JieQing,
Wang YuanZhong
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.8707
Subject(s) - traceability , chemometrics , computer science , support vector machine , fourier transform infrared spectroscopy , partial least squares regression , pattern recognition (psychology) , artificial intelligence , mathematics , food science , chemistry , machine learning , statistics , engineering , chemical engineering
BACKGROUND Boletaceae mushrooms are wild‐grown edible mushrooms that have high nutrition, delicious flavor and large economic value distributing in Yunnan Province, China. Traceability is important for the authentication and quality assessment of Boletaceae mushrooms. In this study, UV–visible and Fourier transform infrared (FTIR) spectroscopies were applied for traceability of 247 Boletaceae mushroom samples in combination with chemometrics. RESULTS Compared with a single spectroscopy technique, data fusion strategy can obviously improve the classification performance in partial least square discriminant analysis (PLS‐DA) and grid‐search support vector machine (GS‐SVM) models, for both species and geographical origin traceability. In addition, PLS‐DA and GS‐SVM models can provide 100.00% accuracy for species traceability and have reliable evaluation parameters. For geographical origin traceability, the accuracy of prediction in the PLS‐DA model by data fusion was just 64.63%, but the GS‐SVM model based on data fusion was 100.00%. CONCLUSION The results demonstrated that the data fusion strategy of UV–visible and FTIR combined with GS‐SVM could provide a higher synergic effect for traceability of Boletaceae mushrooms and have a good generalization ability for the comprehensive quality control and evaluation of similar foods. © 2017 Society of Chemical Industry