Comparative Machine Learning Models for Classifying Sugar Syrup Adulteration in Honey using FTIR Spectroscopy
DOI:
https://doi.org/10.25139/ijair.v7i2.10960Keywords:
Honey Adulteration, FTIR Spectroscopy, Machine Learning, Food AuthenticationAbstract
Honey adulteration with sugar syrups is a widespread issue that compromises product quality, safety, and consumer trust. This study used Fourier Transform Infrared (FTIR) spectroscopy in conjunction with machine learning methods to classify honey samples adulterated with sugar syrups at concentrations of 0%, 10%, 20%, and 40%. FTIR spectral data were pre-processed using Savitzky–Golay smoothing, followed by unsupervised and supervised analyses. Principal Component Analysis (PCA) revealed overlapping clusters among samples, indicating limited discriminatory power. In contrast, supervised classification models achieved higher classification accuracy, with Random Forest (RF) showing the best performance, achieving an accuracy of up to 100%. Followed by Linear Discriminant Analysis (LDA, 93.75%) and Support Vector Machine (SVM, 91.67%). These results demonstrate the strong potential of FTIR spectroscopy integrated with machine learning for rapid and non-destructive honey authentication. However, since the study utilized a publicly available dataset with limited sample information, future research should validate these models using larger, more diverse datasets to enhance reliability and applicability in real-world food authentication systems.
References
A. Girma Tura and D. Bersissa Seboka, "Review on Honey Adulteration and Detection of Adulterants in Honey," International Journal of Gastroenterology, vol. 4, no. 1, p. 1, 2020, doi: 10.11648/j.ijg.20200401.11.
G. Zhang and W. Abdulla, "On honey authentication and adulterant detection techniques," Food Control, vol. 138, p. 108992, Aug. 2022, doi: 10.1016/j.foodcont.2022.108992.
R. Fakhlaei et al., "The Toxic Impact of Honey Adulteration: A Review," Foods, vol. 9, no. 11, p. 1538, Oct. 2020, doi: 10.3390/foods9111538.
T. Damto, A. Zewdu, and T. Birhanu, "Impact of Different Adulterants on Honey Quality Properties and Evaluating Different Analytical Approaches for Adulteration Detection," J Food Prot, vol. 87, no. 4, p. 100241, Apr. 2024, doi: 10.1016/j.jfp.2024.100241.
J. Li et al., "The interaction between temperature and citric acid treatment in the anaerobic fermentation of Chinese cabbage waste," J Clean Prod, vol. 383, p. 135502, Jan. 2023, doi: 10.1016/j.jclepro.2022.135502.
C. Egido, J. Saurina, S. Sentellas, and O. Núñez, "Honey fraud detection based on sugar syrup adulterations by HPLC-UV fingerprinting and chemometrics," Food Chem, vol. 436, p. 137758, Mar. 2024, doi: 10.1016/j.foodchem.2023.137758.
S. Yan, M. Sun, X. Wang, J. Shan, and X. Xue, "A Novel, Rapid Screening Technique for Sugar Syrup Adulteration in Honey Using Fluorescence Spectroscopy," Foods, vol. 11, no. 15, p. 2316, Aug. 2022, doi: 10.3390/foods11152316.
Y. Gong, X. Chen, and W. Wu, "Application of fourier transform infrared (FTIR) spectroscopy in sample preparation: Material characterization and mechanism investigation," Advances in Sample Preparation, vol. 11, p. 100122, Aug. 2024, doi: 10.1016/j.sampre.2024.100122.
O. Elhamdaoui, A. El Orche, A. Cheikh, B. Mojemmi, R. Nejjari, and M. Bouatia, "Development of Fast Analytical Method for the Detection and Quantification of Honey Adulteration Using Vibrational Spectroscopy and Chemometrics Tools," J Anal Methods Chem, vol. 2020, pp. 1–9, Dec. 2020, doi: 10.1155/2020/8816249.
P. Tsakanikas, A. Karnavas, E. Z. Panagou, and G.-J. Nychas, "A machine learning workflow for raw food spectroscopic classification in a future industry," Sci Rep, vol. 10, no. 1, p. 11212, Jul. 2020, doi: 10.1038/s41598-020-68156-2.
J. L. P. Calle, M. Ferreiro-González, A. Ruiz-Rodríguez, D. Fernández, and M. Palma, "Detection of Adulterations in Fruit Juices Using Machine Learning Methods over FT-IR Spectroscopic Data," Agronomy, vol. 12, no. 3, Mar. 2022, doi: 10.3390/agronomy12030683.
D. Prajna et al., "Enhanced Differentiation of Wild and Feeding Civet Coffee Using Near-Infrared Spectroscopy with Various Sample Pretreatments and Chemometric Approaches," Horticulturae, vol. 9, no. 7, Jul. 2023, doi: 10.3390/horticulturae9070778.
D. Prajna, M. Barea-Sepúlveda, J. L. P. Calle, D. Suhandy, W. Setyaningsih, and M. Palma, "Headspace gas chromatography with various sample preparation and chemometric approaches to improve discrimination of wild and feeding civet coffee," in IOP Conference Series: Earth and Environmental Science, Institute of Physics, 2024. doi: 10.1088/1755-1315/1356/1/012037.
Alfaturk, "FTIR Honey Dataset," Kaggle. https://www.kaggle.com/datasets/alfaturk/ftir-honey-dataset.
D. K. Agustika, M. R. Nawawi, R. Prasetyowati, S. H. Hidayat, D. D. Iliescu, and M. S. Leeson, "Savitzky-Golay Parameter Optimization by using Linear Discriminant Analysis for FTIR Spectra," in 2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI), IEEE, Aug. 2022, pp. 123–128. doi: 10.1109/RTSI55261.2022.9905171.
A. S. Tsagkaris et al., "Investigating the impact of spectral data pre-processing to assess honey botanical origin through Fourier transform infrared spectroscopy (FTIR)," Journal of Food Composition and Analysis, vol. 119, p. 105276, Jun. 2023, doi: 10.1016/j.jfca.2023.105276.
G. G. Dumancas and H. Ellis, "Comprehensive examination and comparison of machine learning techniques for the quantitative determination of adulterants in honey using Fourier infrared spectroscopy with attenuated total reflectance accessory," Spectrochim Acta A Mol Biomol Spectrosc, vol. 276, p. 121186, Aug. 2022, doi: 10.1016/j.saa.2022.121186.
M. Schmid, D. Rath, and U. Diebold, "Why and How Savitzky–Golay Filters Should Be Replaced," ACS Measurement Science Au, vol. 2, no. 2, pp. 185–196, Apr. 2022, doi: 10.1021/acsmeasuresciau.1c00054.
F. Guyon, E. Logodin, D. A. Magdas, and L. Gaillard, "Potential of FTIR- ATR diamond in discriminating geographical and botanical origins of honeys from France and Romania," Talanta Open, vol. 3, p. 100022, Aug. 2021, doi: 10.1016/j.talo.2020.100022.
A. G. Ioannou et al., "Highlighting the Potential of Attenuated Total Reflectance – Fourier Transform Infrared (ATR-FTIR) Spectroscopy to Characterize Honey Samples with Principal Component Analysis (PCA)," Anal Lett, vol. 56, no. 5, pp. 789–806, Mar. 2023, doi: 10.1080/00032719.2022.2103143.
N. S. binti Zulkiflee, A. S. Zoolfakar, R. Abdul Rani, D. Aryani, and M. Zolkapli, "Detection and Classification of Honey Adulteration Combined with Multivariate Analysis," International Journal of Integrated Engineering, vol. 14, no. 3, Jun. 2022, doi: 10.30880/ijie.2022.14.03.028.
J. Zheng and C. Rakovski, "On the Application of Principal Component Analysis to Classification Problems," Data Sci J, vol. 20, Aug. 2021, doi: 10.5334/dsj-2021-026.
A. Matwijczuk et al., "Classification of Honey Powder Composition by FTIR Spectroscopy Coupled with Chemometric Analysis," Molecules, vol. 27, no. 12, p. 3800, Jun. 2022, doi: 10.3390/molecules27123800.
G. Dumancas, H. Ellis, J. Neumann, and K. Smith, "Comparison of Various Signal Processing Techniques and Spectral Regions for the Direct Determination of Syrup Adulterants in Honey Using Fourier Transform Infrared Spectroscopy and Chemometrics," Chemosensors, vol. 10, no. 2, p. 51, Jan. 2022, doi: 10.3390/chemosensors10020051.
L. F. Huang et al., "Fingerprint developing of coffee flavor by gas chromatography-mass spectrometry and combined chemometrics methods," Anal Chim Acta, vol. 588, no. 2, pp. 216–223, Apr. 2007, doi: 10.1016/j.aca.2007.02.013.
M. Ciulu et al., "Classification of Unifloral Honeys from SARDINIA (Italy) by ATR-FTIR Spectroscopy and Random Forest," Molecules, vol. 26, no. 1, p. 88, Dec. 2020, doi: 10.3390/molecules26010088.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with International Journal of Artificial Intelligence & Robotics (IJAIR) agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
