Rapid and Automated Method for Detecting and Quantifying Adulterations in High-Quality Honey Using Vis-NIRs in Combination with Machine Learning

Abstract

Honey is one of the most adulterated foods, usually through the addition of sweeteners or low-cost honeys. This study presents a method based on visible near infrared spectroscopy (Vis-NIRs), in combination with machine learning (ML) algorithms, for the correct identification and quantification of adulterants in honey. Honey samples from two botanical origins (orange blossom and sunflower) were evaluated and adulterated with low-cost honey in different percentages (5%, 10%, 15%, 20%, 25%, 30%, 35%, 40%, 45%, and 50%). The results of the exploratory analysis showed a tendency to group the samples according to botanical origin, as well as the presence of adulteration. A supervised analysis was performed to detect the presence of adulterations. The best performance with 100% accuracy was achieved by support vector machines (SVM) and random forests (RF). A regression study was also carried out to quantify the percentage of adulteration. The best result was obtained by support vector regression (SVR) with a coefficient of determination (R2) of 0.991 and a root mean squared error (RMSE) of 1.894. These results demonstrate the potential of combining ML with spectroscopic data as a method for the automated quality control of honey.

Machine learning assisted biosensing technology: An emerging powerful tool for improving the intelligence of food safety detection

“… optical SVM, KNN detection Salmonella spp. In raw meat, egg products, and milk Min et al (2021) doxycycline (DOX), tetracycline, oxytetracydine (OTC), and metacydine (MTC) optical SVM, LDA detection and identification of tetracyclines in river water and milk Xu et al (2020) indigo optical RF determine indigo in cream Zhang et al (2020) honey adulteration optical RF detection of honey adulteration Calle et al (2023) aflatoxin optical RF detection of aflatoxin-polluted corn kernels Cheng and Stasiewicz (2021) α-naphthalene acetic acid (NAA) electrochemical ANN detection of α-naphthalene acetic acid (NAA) residues in food Zhu et al, 2021a , Zhu et al, 2021b aflatoxin B1 and fumonisins electrochemical ANN aflatoxin B1 and fumonisins in maize Leggieri et al (2021) benzoic acid electrochemical ANN benzoic acid in cola-type carbonated beverages Yang et al (2021) pesticide residue optical SVM, RF, ANN determination of pesticide residue in food Khanal et al (2021) xanthine (XT) and hypoxanthine (HX) electrochemical …”

Enhancing Honey Adulteration Detection With Optimal Subspace Wavelength Reduction in Vis-NIR Reflection Spectroscopy

“…However, these methods are expensive, time-consuming, and potentially destructive [22]. Leveraging Visible-Near Infrared (Vis-NIR) spectroscopy alongside machine learning (ML) algorithms has demonstrated rapid detection of adulteration in honey from single botanical sources [7], [23], [24], [25], [26], and two botanical sources [27]. However, the application of this technology to detect adulteration across several honey types remains unexplored.…”

“…Numerous studies have explored the utility of ML algorithms in detecting honey adulteration. However, the majority of these investigations have predominantly relied on absorbance/transmittance Vis-NIR spectroscopy [7], [23], [24], [25], [26], [27]. A comparatively limited body of work has delved into reflectance Vis-NIR spectroscopy, with only a few notable studies contributing to this branch of research [28], [29].…”