Document Type : Research Paper
Authors
1 Ms. C student, Mechanical Engineering of Biosystems Department, Faculty of Agriculture, Razi University, Kermanshah, Iran
2 Associate Professor, Mechanical Engineering of Biosystems Department, Faculty of Agriculture, Razi University, Kermanshah, Iran
3 Postdoctoral Researcher, Department of Signal and Information Processing for Sensing Systems, Institute for Bioengineering of Catalonia (IBEC)
Abstract
Introduction: Coffee is a common drink which is obtained from the roasted and ground beans of the coffee plant. Coffee beverages are widely consumed as a stimulant, a property largely attributed to the presence of caffeine, which is the most active pharmaceutical ingredient consumed worldwide. When the fruit of the coffee plant ripens, the coffee beans are harvested, processed, and finally dried. Dried coffee beans are roasted to different degrees and graded depending on the desired aroma and taste. It is very important to detect natural and unnatural impurities and adulteration in coffee.
Materials and Methods: An odor machine system based on eight MOS sensors was used to investigate the effect of bread storage time based on odor characteristics. The designed system includes a data acquisition system, sensors, sensor shield, sample container, power supply, connections, electric valves, air pump, and air filter. The sensor array consisted of 8 MOS sensors, including MQ136, TGS822, MQ9, MQ3, TGS813, TG2620, TG2602, and MQ135, each reacting to specific volatile compounds. These sensors are widely used in olfactory machines because of their high chemical stability, high durability, low response to moisture, and affordable prices. They are the most commonly used sensors in electronic nose systems. Sensors are the main components of an electronic nose system; therefore, it is necessary to select sensors able to detect differences among samples. In this research, the use of electronic nose technology and artificial intelligence was evaluated to detect common adulteration in Arabica coffee (Medium Dark). Robusta coffee samples with weight percentages of 10, 40, 30, 20, and 50% were used for experiments and adulteration. An electronic nose equipped with eight metal oxide sensors was used to carry out experiments related to odor. The data received from 8 sensors was first recorded and stored as raw data. In this research, the fractional method was used to normalize the data. Preprocessed data were used as the input matrix for multivariate analytical methods. The unsupervised multivariate principal component analysis (PCA) method was used to analyze the data. The LDA method was used to reduce classification differences and expand the differences between different groups. The artificial neural networks (ANN) method was used for classification. All calculations and analyses were done using Excel 2016, Unscrambler x10.4, and MATLAB software. Model evaluation criteria are used to evaluate algorithm performance in supervised learning. To analyze the system's performance, common criteria including Specificity, Recall, Precision, Accuracy, Area Under the Curve (AUC), and F-score were used.
Results and Discussion: The results of PCA showed that 87% of the total variance of the data was explained by PC1, and 8% by PC2, and the two main components constituted 95% of the total variance of the normalized data. Based on the results, pure Robusta coffee (B) was located on the right side of the PCA diagram and completely separate from other levels of adulteration. Also, pure Arabica coffee (A) was placed in the vicinity of counterfeit samples, and all counterfeit samples showed the same behavior as Arabica coffee, which is very difficult to distinguish. The loading diagram was examined to determine the role of sensors in separating the groups. Based on the loading diagram for coffee adulteration detection, the sensors that had the highest value on the principal component were MQ9, TGS822, and MQ136. Other sensors also showed a high correlation with the smell of the samples. In other words, other sensors could be neglected. The models of artificial neural networks analysis were evaluated by the correct classification rate (CCR), root mean square error (RMSE), and coefficient of determination (R2). According to the results obtained for 7 different coffee groups, the 7-8-8 structure had the best results. This structure has 8 neurons in the input layer (number of sensors), a hidden layer with 8 neurons, and 7 neurons in the output layer (7 groups). The average values of the class obtained from the ANN model for the parameters of accuracy, precision, recall, specificity, area under the curve (AUC), and F-score were equal to 0.984, 0.952, 0.943, 0.990, 0.971, and 0.942, respectively. Also, the ANN method showed higher accuracy than the LDA method.
Conclusion: The electronic nose showed that it is a fast and effective tool for detecting adulteration substances in coffee.
Keywords
Main Subjects
1. Marek, G., Dobrzański, B., Oniszczuk, T., Combrzyński, M., Ćwikła, D., and Rusinek, R. 2020. Detection and Differentiation of Volatile Compound Profiles in Roasted Coffee Arabica Beans from Different Countries Using an Electronic Nose and GC-MS. Sensors, 20: 2124.
2. Gancarz, M., Dobrzański, B., Malaga-Toboła, U., Tabor, S., Combrzyński, M., Ćwikła, D., Strobel, W.R., Oniszczuk, A., Karami, H., and Darvishi, Y. 2022. Impact of Coffee Bean Roasting on the Content of Pyridines Determined by Analysis of Volatile Organic Compounds. Molecules, 27: 1559.
3. Gonzalez Viejo, C., Tongson, E. and Fuentes S. 2021. integrating a Low-Cost Electronic Nose and Machine Learning Modelling to Assess Coffee Aroma Profile and Intensity. Sensors, 21(6).
4. Buratti, S., Sinelli, N., Bertone, E., Venturello, A., Casiraghi, E., and Geobaldo, F. 2015. Discrimination between washed Arabica, natural Arabica and Robusta coffees by using near infrared spectroscopy, electronic nose and electronic tongue analysis. J Sci Food Agric, 95.
5. Karami, H., Kamruzzaman, M., Covington, J.A., Hassouna, M., Darvishi, Y., Ueland, M., Fuentes, S., and Gancarz, M. 2024. Advanced Evaluation Techniques: Gas Sensor Networks, Machine Learning, and Chemometrics for Fraud Detection in Plant and Animal Products. Sensors and Actuators A: Physical, 115192.
6. Rusinek, R., Dobrzański Jr., B., Gawrysiak-Witulska, M., Siger, A., Żytek, A., Karami, H., Umar, A., Lipa, T., and Gancarz, M. 2024. Effect of the roasting level on the content of bioactive and aromatic compounds in Arabica coffee beans. International Agrophysics, 38: 31-42.
7. Toci, A., Pezza, L., Farah, A., and Redigolo Pezza, H. 2016. Coffee Adulteration: More than two decades of research. Critical Reviews in Analytical Chemistry, 46: 106.
8. Flambeau, K.J., Lee, W.-J. and Yoon, J. 2017. Discrimination and geographical origin prediction of washed specialty Bourbon coffee from different coffee growing areas in Rwanda by using electronic nose and electronic tongue. Food Science and biotechnology, 26(5): 1245-1254.
9. Thazin, Y., Pobkrut, T., and Kerdcharoen, T. 2018. Prediction of acidity levels of fresh roasted coffees using e-nose and artificial neural network. 10th International Conference on Knowledge and Smart Technology (KST), IEEE.
10. Dong, W., Hu, R., Long, Y., Li, H., Zhang, Y., Zhu, K., and Chu, Z. 2019. Comparative evaluation of the volatile profiles and taste properties of roasted coffee beans as affected by drying method and detected by electronic nose, electronic tongue, and HS-SPME-GC-MS. Food Chemistry, 272: 723-731.
11. Gonzalez Viejo, C., Tongson, E., and Fuentes, S. 2021. Integrating a Low-Cost Electronic Nose and Machine Learning Modelling to Assess Coffee Aroma Profile and Intensity. Sensors, 21(6): 2016.
12. Núñez, N., Saurina, J., and Núñez, O. 2021. Non-targeted HPLC-FLD fingerprinting for the detection and quantitation of adulterated coffee samples by chemometrics. Food Control, 124: 107912.
13. Esteban-Díez, I., González-Sáiz, J.M., Sáenz-González, C., and Pizarro, C. 2007. Coffee varietal differentiation based on near infrared spectroscopy. Talanta, 71: 221-229.
14. El-Abassy, R.M., P. Donfack, and A. Materny, Discrimination between Arabica and Robusta green coffee using visible micro Raman spectroscopy and chemometric analysis. Food Chemistry, 2011. 126(3): 1443-1448.
15. Obeidat, S.M., Hammoudeh, A.Y., and Alomary, A.A., 2018. Application of FTIR Spectroscopy for Assessment of Green Coffee Beans According to Their Origin. Journal of Applied Spectroscopy, 84(6): 1051-1055.
16. Reis, N., Franca, A.S., and Oliveira, L.S. 2013. Quantitative evaluation of multiple adulterants in roasted coffee by Diffuse Reflectance Infrared Fourier Transform Spectroscopy (DRIFTS) and chemometrics. Talanta, 115: 563-568.
17. Ebrahimi-Najafabadi, H., Leardi, R., Oliveri, P., Chiara Casolino, M., Jalali-Heravi, M., and Lanteri, S. 2012. Detection of addition of barley to coffee using near infrared spectroscopy and chemometric techniques. Talanta, 99: 175-179.
18. Wilson, A.D. and Baietto, M. 2009. Applications and Advances in Electronic-Nose Technologies. Sensors, 9(7): 5099-5148.
19. Rasekh, M., Karami, H., Wilson, A.D., and Gancarz, M. 2021. Classification and Identification of Essential Oils from Herbs and Fruits Based on a MOS Electronic-Nose Technology. Chemosensors, 9: 142.
20. Rasekh, M., Karami, H., Wilson, A.D., and Gancarz, M. 2021. Performance Analysis of MAU-9 Electronic-Nose MOS Sensor Array Components and ANN Classification Methods for Discrimination of Herb and Fruit Essential Oils. Chemosensors, 9: 243.
21. Karami, H., Karami Chemeh, S., Azizi, V., Sharifnasab, H., Ramos, J., and Kamruzzaman, M. 2024. Gas sensor-based machine learning approaches for characterizing tarragon aroma and essential oil under various drying conditions. Sensors and Actuators A: Physical, 365: 114827.
22. Rasekh, M., Karami, H., Kamruzzaman, M., Azizi, V., and Gancarz, M. 2023. Impact of different drying approaches on VOCs and chemical composition of Mentha spicata L. essential oil: A combined analysis of GC/MS and E-nose with chemometrics methods. Industrial Crops and Products, 206: 117595.
23. Mohammadian, N., Ziaiifar, A.M., Mirzaee-Ghaleh, E., Kashaninejad, M., and Karami, H. 2023. Nondestructive Technique for Identifying Adulteration and Additives in Lemon Juice Based on Analyzing Volatile Organic Compounds (VOCs). Processes, 11: 1531.
24. Rasekh, M. and Karami, H. 2021. E-nose coupled with an artificial neural network to detection of fraud in pure and industrial fruit juices. International Journal of Food Properties, 24(1): 592-602.
25. Rusinek, R., Dobrzański, B., Oniszczuk, A., Gawrysiak-Witulska, M., Siger, A., Karami, H., Ptaszyńska, A.A., Żytek, A., Kapela, K., and Gancarz, M. 2022. How to Identify Roast Defects in Coffee Beans Based on the Volatile Compound Profile. Molecules, 27: 8530.
26. Rasekh, M. and Karami, H. 2021. Application of electronic nose with chemometrics methods to the detection of juices fraud. Journal of Food Processing and Preservation, 45(5): e15432.
27. Tatli, S., Mirzaee-Ghaleh, E., Rabbani, H., Karami, H., and Wilson, A.D. 2022. Prediction of Residual NPK Levels in Crop Fruits by Electronic-Nose VOC Analysis following Application of Multiple Fertilizer Rates. Applied Sciences, 12: 11263.
28. Khorramifar, A., Rasekh, M., Karami, H., Malaga-Toboła, U., and Gancarz, M. A. 2021. Machine Learning Method for Classification and Identification of Potato Cultivars Based on the Reaction of MOS Type Sensor-Array. Sensors, 21: 5836.
29. Khorramifar, A., Karami, H., Wilson, A.D., Sayyah, A.H.A., Shuba, A., and Lozano, J. 2022. Grape Cultivar Identification and Classification by Machine Olfaction Analysis of Leaf Volatiles. Chemosensors, 10: 125.
30. Rasekh, M., Karami, H., Fuentes, S., Kaveh, M., Rusinek, R., and Gancarz, M. 2022. Preliminary study non-destructive sorting techniques for pepper (Capsicum annuum L.) using odor parameter. LWT, 164: 113667.
31. Mojrian, F., Moeenfard, M., Farhoosh, R., and Mahdavian Mehr, H. 2022. Investigation of the Coffea Arabica substitution with roasted date seed on physicochemical and sensory properties of coffee brew. Iranian Food Science and Technology Research Journal, 18: 96-112. (in Persian with English abstract)
32. Khodamoradi, F., Mirzaee-Ghaleh, E., Dalvand, M.J., and Sharifi, R. 2021. Classification of basil plant based on the level of consumed nitrogen fertilizer using an olfactory machine. Food Analytical Methods, 14: 2617–2629.
33. Ayari, F., Mirzaee-Ghaleh, E., Rabbani, H., and Heidarbeigi, K. 2018. Detection of the adulteration in pure cow ghee by electronic nose method (case study: sunflower oil and cow body fat). International Journal of Food Properties, 21 (1): 1670-1679.
34. Zorpeykar, S., Mirzaee-Ghaleh, E., Karami, H., Ramedani, Z., and Wilson, A.D. 2022. Electronic Nose Analysis and Statistical Methods for Investigating Volatile Organic Compounds and Yield of Mint Essential Oils Obtained by Hydrodistillation. Chemosensors, 10: 486.
35. Karami, H., Rasekh, M., and Mirzaee – Ghaleh, E. 2020. Comparison of chemometrics and AOCS official methods for predicting the shelf life of edible oil. Chemometrics and Intelligent Laboratory Systems, 206: 104165.
36. Ayari, F., Mirzaee- Ghaleh, E., Rabbani, H., and Heidarbeigi, K. 2018. Using an E-nose machine for detection the adulteration of margarine in cow ghee. Journal of Food Process Engineering, 41: e12806.
37. Karami, H., Rasekh, M., and Mirzaee-Ghaleh, E. 2020. Qualitative analysis of edible oil oxidation using an olfactory machine. Journal of Food Measurement and Characterization, 14(5): 2600-2610.
38. Rusinek, R., Dobrzański Jr., B., Gawrysiak-Witulska, M., Siger, A., Żytek, A., Karami, H., Umar, A., Lipa, T., and Gancarz, M. 2024. Effect of the roasting level on the content of bioactive and aromatic compounds in Arabica coffee beans. International Agrophysics, 38: 31-42.
39. Khorramifar, A., Rasekh, M., Karami, H., Covington, J.A., Derakhshani, S.M., Ramos, J., and Gancarz, M. 2022. Application of MOS Gas Sensors Coupled with Chemometrics Methods to Predict the Amount of Sugar and Carbohydrates in Potatoes. Molecules, 27: 3508.
40. Brudzewski, K., Osowski, S., and Dwulit, A. 2012. Recognition of Coffee Using Differential Electronic Nose. IEEE Transactions on Instrumentation and Measurement, 61: 1803-1810.
41. Karami, H., Rasekh, M., and Mirzaee-Ghaleh, E. 2021. Identification of olfactory characteristics of edible oil during storage period using metal oxide semiconductor sensor signals and ANN methods. Journal of Food Processing and Preservation, 45(10): e15749.
42. Khodamoradi, F. Mirzaee-Ghaleh, E. Dalvand M.J. and Sharifi. R. 2019. Classification of savory (Satureja hortensis L.) based on the level of used urea fertilizer consumed using an olfactory machine. Iranian Journal of Medicinal and Aromatic Plants, Vol. 35(5): 789- 801. (in Persian with English abstract)
43. Zorpeykar, S., Mirzaee-Ghaleh, E., Karami, H., Ramedani, Z., and Wilson, A. D. 2022. Electronic Nose Analysis and Statistical Methods for Investigating Volatile Organic Compounds and Yield of Mint Essential Oils Obtained by Hydrodistillation. Chemosensors, 10(11): 486.
44. Adibzadeh, A., Zaki Dizaji, H., Aghili Nategh, N. 2020. Feasibility of Detecting Sugarcane Varieties by Electronic Nose Technique in Sugarcane Syrup. Iranian Journal of Biosystems Engineering, 51(1): 1-10. (in Persian with English abstract)
45.Zaki Dizaji, H., Adibzadeh, A. & Aghili Nategh, N. 2021. Application of E-nose technique to predict sugarcane syrup quality based on purity and refined sugar percentage. Journal of Food Science and Technology. 58: 4149–4156.
)