Premium
Detection of mites Tyrophagus putrescentiae and Cheyletus eruditus in flour using hyperspectral imaging system coupled with chemometrics
Author(s) -
He Peihuan,
Wu Yi,
Wang Jingjing,
Ren Yi,
Ahmad Waqas,
Liu Rui,
Ouyang Qin,
Jiang Hui,
Chen Quansheng
Publication year - 2020
Publication title -
journal of food process engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.507
H-Index - 45
eISSN - 1745-4530
pISSN - 0145-8876
DOI - 10.1111/jfpe.13386
Subject(s) - tyrophagus putrescentiae , chemometrics , hyperspectral imaging , principal component analysis , pattern recognition (psychology) , artificial intelligence , multispectral image , acaridae , mathematics , mite , food science , biology , computer science , ecology , acariformes , machine learning
An automatic method for detecting mites in flour has been established using hyperspectral imaging (HSI) system coupled with chemometrics. Reflectance differences among flour, Tyrophagus putrescentiae , and Cheyletus eruditus were relatively distinct. Majority of the shape features, including area, perimeter, the major, and minor axis in C. eruditus were remarkably larger than flour and T. putrescentiae . Textural features reached the level of the maximum significance except for contrast with one‐way analysis of variance. Images under the ant colony optimization (ACO) wavebands in random forests (RF) classification showed at least 89% recognition rates, better than the successive projections algorithm wavebands. Artificial neural networks (ANN) with ACO wavebands gave higher recognition accuracies in training and validation sets than RF. Further analysis verified hyperspectrum with ACO‐PCA‐ANN (PCA, principal component analysis), which showed over 98% accuracy. This study revealed the promising potential of HSI coupled with ACO‐PCA‐ANN as an accurate and rapid method for detecting mites in flour. Practical applications Mite infection in flour is a global problem and an important research area related to stored food safety and quality control in the food industry. An effective classification method for mite contaminants with automated detection has not been previously established in the literature. Therefore, the current study reports an automated hyperspectral imaging (HSI) system coupled with chemometrics to detect mites Tyrophagus putrescentiae and Cheyletus eruditus in flour. This study revealed the promising potential of HSI coupled with ACO‐PCA‐ANN as an accurate and rapid method for detecting mites T. putrescentiae and C. eruditus in flour. We believe the knowledge gained in this research could be incorporated in the food storage and processing industry to promote the accuracy of detecting and identifying mites by using HSI system combined with chemometric algorithms.