Feasibility of Visible/Near Infrared Spectroscopy in order to detect pomace olive oil fraud with LDA and SVM detection methods

Document Type : Research Article

Authors

1 Biosystem engineering. تربیت modares university, tehran , iran

2 Tarbiat Modares University

3 Associate Professor, Agricultural Engineering Research Institute, Agricultural Research, Education and Extension Organization (AREEO)

Abstract

Olive is a Mediterranean fruit that is cultivated mainly for its oil. Extra virgin olive oil has always been the attention and demand of users. Therefore, fraud in virgin and extra virgin olive oils is observed by adding valuable food oils and lower prices such as canola, sunflower, olive pomace, etc. Fraud detection with conventional methods such as gas chromatography is difficult, time-consuming, and requires sample and operator preparation. For this reason, the use of non-destructive technologies for fraud detection is important. In this research, detection of adulteration of pomace oil (olive pomace oil) was investigated using visible/near-infrared spectroscopy (Vis/NIR) technology. Three types of extra virgin olive oil, virgin and refined olive oil were used for sampling. Moreover, the samples were made in six categories of pure, 11, 20, 33, 50 and 100% fraud. Each treatment was prepared and tested in ten samples. Next, in order to analyze the qualitative features and classify the data extracted from the spectrometer, pattern recognition methods including linear discriminant analysis (LDA) and support vector machine (SVM) were used. The obtained results showed that visible/near infrared (Vis/NIR) spectroscopy is able to distinguish olive oil samples based on different percentages of pomace adulteration. Although the LDA method was able to classify olive oil samples with acceptable accuracy according to the adulteration rate, the SVM method had a better accuracy and fit with a training accuracy of 96.69% and a validation of 94.21%. According to the results, the linear function was suggested as the best function for building the classification models using the SVM method.

Graphical Abstract

Feasibility of Visible/Near Infrared Spectroscopy in order to detect pomace olive oil fraud with LDA and SVM detection methods

Highlights

  • Spectroscopy (Vis/NIR) is able to distinguish olive oil samples based on pomace adulteration rate.
  • The SVM method was the best method to classify the samples with 96.69 training accuracy and 94.21 validation accuracy.
  • Based on the results, the linear function was determined as the best function for building the classification model using the SVM method.
  • It is the first time that the lower range of near infrared i.e. the range of 780-850 nm has been used in addition to the visible region in order to accurately identify pomace adulteration in different types of olive oil.

Keywords

Main Subjects

References

[1]         M. Rashvand, O. Mahmood, H. Mobli, and M. Soltanifiroz, “Evaluation of olive oil adulteration detection system based on image processing and dielectric spectroscopy,” Agric. Mach. Mech. Res. J., vol. 6, no. 2, pp. 29–19, 2017.
[2]         B. Vega-Márquez, I. Nepomuceno-Chamorro, N. Jurado-Campos, and C. Rubio-Escudero, “Deep Learning Techniques to Improve the Performance of Olive Oil Classification,” Front. Chem., vol. 7, no. January, pp. 1–10, 2020, doi: 10.3389/fchem.2019.00929.
[3]         A. M. Giuffré, M. Caracciolo, C. Zappia, M. Capocasale, and M. Poiana, “Effect of heating on chemical parameters of extra virgin olive oil, pomace olive oil, soybean oil and palm oil,” Ital. J. Food Sci., vol. 30, no. 4, pp. 715–739, 2018.
[4]         M. I. Covas, “Olive oil and the cardiovascular system,” Pharmacol. Res., vol. 55, no. 3, pp. 175–186, 2007, doi: 10.1016/j.phrs.2007.01.010.
[5]         C. Fauhl, F. Reniero, and C. Guillou, “1H NMR as a tool for the analysis of mixtures of virgin olive oil with oils of different botanical origin,” Magn. Reson. Chem., vol. 38, no. 6, pp. 436–443, 2000, doi: 10.1002/1097-458X(200006)38:6<436::AID-MRC672>3.0.CO;2-X.
[6]         S. Ok, “Detection of olive oil adulteration by low-field NMR relaxometry and UV-Vis spectroscopy upon mixing olive oil with various edible oils,” Grasas y Aceites, vol. 68, no. 1, pp. 1–13, 2017, doi: 10.3989/gya.0678161.
[7]         S. A. Mahesar, M. Lucarini, A. Durazzo, A. Santini, A. I. Lampe, and J. Kiefer, “Application of Infrared Spectroscopy for Functional Compounds Evaluation in Olive Oil : A Current Snapshot,” vol. 2019, 2019.
[8]         S. Cicerale, X. A. Conlan, A. J. Sinclair, and R. S. J. Keast, “Chemistry and health of olive oil phenolics,” Crit. Rev. Food Sci. Nutr., vol. 49, no. 3, pp. 218–236, 2009, doi: 10.1080/10408390701856223.
[9]         P. Vossen, “Olive oil: History, production, and characteristics of the world’s classic oils,” HortScience, vol. 42, no. 5, pp. 1093–1100, 2007, doi: 10.21273/hortsci.42.5.1093.
[10]       R. Rodriguez-Rodriguez, M. D. Herrera, M. A. de Sotomayor, and V. Ruiz-Gutierrez, “Pomace Olive Oil Improves Endothelial Function in Spontaneously Hypertensive Rats by Increasing Endothelial Nitric Oxide Synthase Expression,” Am. J. Hypertens., vol. 20, no. 7, pp. 728–734, 2007, doi: 10.1016/j.amjhyper.2007.01.012.
[11]       K. Antonopoulos, N. Valet, D. Spiratos, and G. Siragakis, “Olive oil and pomace olive oil processing,” Grasas y Aceites, vol. 57, no. 1, pp. 56–67, 2006, doi: 10.3989/gya.2006.v57.i1.22.
[12]       F. Pérez-Jiménez, J. Ruano, P. Perez-Martinez, F. Lopez-Segura, and J. Lopez-Miranda, “The influence of olive oil on human health: Not a question of fat alone,” Mol. Nutr. Food Res., vol. 51, no. 10, pp. 1199–1208, 2007, doi: 10.1002/mnfr.200600273.
[13]       L. Di Giovacchino, S. Sestili, and D. Di Vincenzo, “Influence of olive processing on virgin olive oil quality,” Eur. J. Lipid Sci. Technol., vol. 104, no. 9–10, pp. 587–601, 2002, doi: 10.1002/1438-9312(200210)104:9/10<587::AID-EJLT587>3.0.CO;2-M.
[14]       V. Maestrello, P. Solovyev, L. Bontempo, L. Mannina, and F. Camin, “Nuclear magnetic resonance spectroscopy in extra virgin olive oil authentication,” Compr. Rev. Food Sci. Food Saf., vol. 21, no. 5, pp. 4056–4075, 2022, doi: 10.1111/1541-4337.13005.
[15]       D. Tura, C. Gigliotti, S. Pedò, O. Failla, D. Bassi, and A. Serraiocco, “Influence of cultivar and site of cultivation on levels of lipophilic and hydrophilic antioxidants in virgin olive oils (Olea Europea L.) and correlations with oxidative stability,” Sci. Hortic. (Amsterdam)., vol. 112, no. 1, pp. 108–119, 2007, doi: 10.1016/j.scienta.2006.12.036.
[16]       S. K. Dwivedi, M. Vishwakarma, and P. A. Soni, “Advances and Researches on Non Destructive Testing: A Review,” Mater. Today Proc., vol. 5, no. 2, pp. 3690–3698, 2018, doi: 10.1016/j.matpr.2017.11.620.
[17]       H. Xiao, L. Feng, D. Song, K. Tu, J. Peng, and L. Pan, “Grading and sorting of grape berries using visible-near infrared spectroscopy on the basis of multiple inner quality parameters,” Sensors (Switzerland), vol. 19, no. 11, 2019, doi: 10.3390/s19112600.
[18]       P. Galvin-King, S. A. Haughey, and C. T. Elliott, “Garlic adulteration detection using NIR and FTIR spectroscopy and chemometrics,” J. Food Compos. Anal., vol. 96, p. 103757, 2021, doi: 10.1016/j.jfca.2020.103757.
[19]       M. De Luca et al., “Derivative FTIR spectroscopy for cluster analysis and classification of morocco olive oils,” Food Chem., vol. 124, no. 3, pp. 1113–1118, 2011, doi: 10.1016/j.foodchem.2010.07.010.
[20]       R. De Bei et al., “Non-destructive measurement of grapevine water potential using near infrared spectroscopyDe Bei, R., Cozzolino, D., Sullivan, W., Cynkar, W., Fuentes, S., Dambergs, R., Pech, J., & Tyerman, S. D. (2011). Non-destructive measurement of grapevine water pote,” Aust. J. Grape Wine Res., vol. 17, no. 1, pp. 62–71, 2011, doi: 10.1111/j.1755-0238.2010.00117.x.
[21]       X. Li et al., “Review of NIR spectroscopy methods for nondestructive quality analysis of oilseeds and edible oils,” Trends Food Sci. Technol., vol. 101, no. March, pp. 172–181, 2020, doi: 10.1016/j.tifs.2020.05.002.
[22]       S. Bureau and B. Gouble, “rapid and non-destructive analysis of apricot fruit quality using ft-near infrared spectroscopy,” Mater. Struct., no. 2014, pp. 32–35, 2015.
[23]       A. C. de Lima, L. Aceña, M. Mestres, and R. Boqué, “An Overview of the Application of Multivariate Analysis to the Evaluation of Beer Sensory Quality and Shelf-Life Stability,” Foods, vol. 11, no. 14, pp. 1–15, 2022, doi: 10.3390/foods11142037.
[24]       A. Amari, N. El Bari, and B. Bouchikhi, “Electronic Nose for Anchovy Freshness Monitoring Based on Sensor Array and Pattern Recognition Methods: Principal Components Analysis, Linear Discriminant Analysis and Support Vector Machine,” Int. J. Comput., vol. 6, no. 3, pp. 61–67, 2014, doi: 10.47839/ijc.6.3.452.
[25]       M. W. Huang, C. W. Chen, W. C. Lin, S. W. Ke, and C. F. Tsai, “SVM and SVM ensembles in breast cancer prediction,” PLoS One, vol. 12, no. 1, pp. 1–14, 2017, doi: 10.1371/journal.pone.0161501.
[26]       Z. Liu and J. Tan, “Qualitative and quantitative detection of Sudan I and II adulterated in chili powders by front-face synchronous fluorescence spectroscopy ： Aggregation-induced emission in solid food,” pp. 1–21, 2022.
[27]       N. Abu-khalaf and M. Hmidat, “Visible / Near Infrared ( VIS / NIR ) spectroscopy as an optical sensor for evaluating olive oil quality,” Comput. Electron. Agric., vol. 173, no. December 2019, p. 105445, 2020, doi: 10.1016/j.compag.2020.105445.
[28]       H. Cen, Y. He, and M. Huang, “Combination and comparison of multivariate analysis for the identification of orange varieties using visible and near infrared reflectance spectroscopy,” Eur. Food Res. Technol., vol. 225, no. 5–6, pp. 699–705, 2007, doi: 10.1007/s00217-006-0470-2.
[29]       Y. G. M. Kongbonga et al., “Characterization of Vegetable Oils by Fluorescence Spectroscopy,” Food Nutr. Sci., vol. 02, no. 07, pp. 692–699, 2011, doi: 10.4236/fns.2011.27095.
[30]       T. Wang, Y. Zhang, Y. Liu, Z. Zhang, and T. Yan, “Intelligent Evaluation of Stone Cell Content of Korla Fragrant Pears by Vis/NIR Reflection Spectroscopy,” Foods, vol. 11, no. 16, 2022, doi: 10.3390/foods11162391.
[31]       m Zarezade, Mohammad Reza, abonajmi, M. Ghasemi-varnamkhasti, and  f azarikia, “Estimation of the Best Classification Algorithm and Fraud Detection of Olive Oil by Olfaction Machine,” vol. 11, no. 2, pp. 371–383, 2021, doi: 10.22067/jam.v11i2.84105. [In persion]
[32]       M. Bahmaei, R. Nazeri, F. Kalantari, N. T. Branch, and S. B. Company, “Archive of SID Detection of adulteration in canola-virgin olive admixture using instrumental gas liquid chromatography and UV spectroscopy”. [In persion]
 
Innovative Food Technologies
Volume 11, Issue 2
February 2024
Pages 155-171

Files

History

  • Receive Date: 19 October 2023
  • Revise Date: 14 May 2024
  • Accept Date: 27 May 2024

Share

How to cite

Statistics