Journal
JOURNAL OF FOOD COMPOSITION AND ANALYSIS
Volume 109, Issue -, Pages -Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jfca.2022.104511
Keywords
Honey; Botanical origin; Brand; Hyperspectral imaging; Machine learning; Deep learning
Categories
Funding
- University of Auckland
Ask authors/readers for more resources
This study categorizes 56 New Zealand honey products using hyperspectral imaging dataset and four different algorithms. The results show high accuracy rates and also reveal distinct spectral characters of honey products from different brands, even with the same botanical origin labels.
Identifying honey botanical origins and analyzing honey products of the same floral origin from different honey product brands are crucial to protect consumers' interest. Hyperspectral imaging is a promising approach to differentiate various honey products. In this study, the honey hyperspectral imaging dataset, which contains 56 New Zealand honey products of 21 botanical origins from 11 different producers, was categorized using four different algorithms, including Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Convolutional Neural Network (CNN). The experimental results showed that RF and SVM achieved >= 98% and >= 99% accuracy rates, respectively. In addition, by analyzing the spectral data of different honey products, we find that most of the honey products from different brands present distinct spectral characters although they have the same botanical origin labels. Some producers label honey products with different botanical origin labels, even though these products have similar spectral curves.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available