Identifying type of sugar adulterants in honey: Combined application of NMR spectroscopy and supervised machine learning classification

Nuclear magnetic resonance (NMR) is a powerful analytical tool which can be used for authenticating honey, at chemical constituent levels by enabling identification and quantification of the spectral patterns. However, it is still challenging, as it may be a person-centric analysis or a time-consumi...

Full description

Saved in:
Bibliographic Details
Published in:Current research in food science Vol. 5; pp. 272 - 277
Main Authors: Rachineni, Kavitha, Rao Kakita, Veera Mohana, Awasthi, Neeraj Praphulla, Shirke, Vrushali Siddesh, Hosur, Ramakrishna V., Chandra Shukla, Satish
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01-01-2022
Elsevier
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Nuclear magnetic resonance (NMR) is a powerful analytical tool which can be used for authenticating honey, at chemical constituent levels by enabling identification and quantification of the spectral patterns. However, it is still challenging, as it may be a person-centric analysis or a time-consuming process to analyze many honey samples in a limited time. Hence, automating the NMR spectral analysis of honey with the supervised machine learning models accelerates the analysis process and especially food chemistry researcher or food industry with non-NMR experts would benefit immensely from such advancements. Here, we have successfully demonstrated this technology by considering three major sugar adulterants, i.e., brown rice syrup, corn syrup, and jaggery syrup, in honey at varying concentrations. The necessary supervised machine learning classification analysis is performed by using logistic regression, deep learning-based neural network, and light gradient boosting machines schemes. [Display omitted] •NMR helps to identify the fingerprints of honey chemical constituents.•Combined NMR and ML tools can determine the type of adulteration in honey.•Supervised classification schemes, Logistic regression, DNN, and LGBM are utilized.•Corn, brown rice, and jaggery adulterations are discriminated in honey.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Present address: Indrashil University, Department of Chemistry, School of Sciences, Rajpur, Taluka: Kadi, Ahmedabad-Mehsana Highway, Gujarat 382,740, India.
ISSN:2665-9271
2665-9271
DOI:10.1016/j.crfs.2022.01.008