Distinguishing slivered almonds from peanuts using electronic nose

Document Type : Research Paper

Authors

1 Department of Biosystem Mechanical Engineering, Faculty of Agriculture, Razi University, Kermanshah, Iran.

2 Department of Agricultural Machinery Engineering, Sonqor Faculty of Agriculture, Razi University, Kermanshah,Iran

Abstract

 
Almonds are one of the most important types of nuts around the world, which are transformed from a convenient snack to a healthy food for human health.Also, peanut is one of the essential and economic plants in the world, which is very rich in terms of nutrition.The purpose of this research was to investigate the performance of the electronic nose in distinguishing slivered almonds from slivered peanuts.In order to conduct experiments in this research, three types of slivered almond and three types of slivered peanut were used.The samples were tested with an electronic nose made of 10 metal oxide semiconductor (MOS) sensors.In this research, linear discriminant analysis (LDA), principal component analysis (PCA), support vector machine (SVM) and quadratic discriminant analysis (QDA) were used for data analysis. The QDA method with 100% accuracy had a good performance in the classification of slivered almonds varieties and slivered peanuts varieties. Also, the LDA method was able to classify slivered peanuts varieties with 100% accuracy. The LDA method was able to distinguish slivered almonds from slivered peanuts with with an average accuracy 91%. The SVM method was able to distinguish slivered almonds from slivered peanuts with with an average accuracy 84%. The results showed that the lectronic nose is a suitable tool for distinguishing slivered almonds from slivered peanuts.

Keywords

Main Subjects

Distinguishing slivered almonds from peanuts using electronic nose

 

EXTENDED ABSTRACT

 

 

Goal

Due to the importance of identifying varieties of slivered almonds and slivered peanuts, as well as the importance of detecting common fraud in the field of replacing slivered almonds with slivered peanuts, this research was carried out by electronic nose. The features extracted from the signals obtained from the electronic nose were processed by LDA, PCA, SVM and QDA, and the results were compared with each other.

Research method

In order to conduct experiments, three varities of slivered almonds and three varities of slivered peanut were prepared and tested. The tests were performed by an electronic nose device E-nose system was based on ten metal oxide semiconductor sensors (MOS) (Table 1), where the actual images of this system are shown in Fig. 2. The system consisted of a sensor compartment, sample chamber, a micro pump, three two-way solenoid valves, data collection system (USB), 5 and 12 V power supply, inlet air filter (activated carbon), and graphical interface (LabVIEW 2014). The pre-processed data were analyzed by linear discriminant analysis (LDA), principal component analysis (PCA), and support vector machine (SVM) and quadratic discriminant analysis (QDA) using Unscrambler V 9.7 and Matlab 2015a software.

Findings

The results obtained from the PCA method for slivered almond varieties, showed that the value of the two main components were78% and 10%, respectively, and the amount of variance between the samples described a total of 88% of the data. The results of PCA classification for slivered peanut varieties showed that the value of the two main components PC-1 and PC-2 were 69% and 12%, respectively, and described 81% of the total variance of the data. The results of PCA for distinguishing slivered almond from slivered peanut showed that the two main components PC-1 and PC-2 are 63% and 17%, respectively, and the amount of variance between the samples is 80% of the total data. LDA method was able to distinguish slivered almond varieties with an average accuracy 94%. The LDA method was able to distinguish slivered almond from slivered peanut with with an average accuracy 91%. The SVM method was able to distinguish slivered almond from slivered peanut with with an average accuracy 84%. The QDA method was able to distinguish different types of almond slices with 100% accuracy. The classification accuracy of QDA for the classification slivered almond varieties and slivered peanut varieties  was 100%. Also, the QDA method was able to distinguish slivered almond from slivered peanut with with an average accuracy 97%.

Conclusion

In this research, the PCA method was able to distinguish slivered almond varieties and slivered peanut varieties with an accuracy of 88% and 81%, respectively. LDA method was able to classify slivered peanuts varieties with 100% accuracy. The SVM method did not have a good performance in the classification of slivered almond varieties and slivered peanut varieties. The QDA method with an accuracy 100% had a good performance in classifying slivered almond varieties and slivered peanut varieties. TGS2610, MQ3 and TGS822 sensors had the most effect in discrimintion slivered almond varieties, MQ135 and TGS2610 sensors had the most effect in distinguishing slivered peanut varieties and also distinguishing slivered almond from slivered peanut.

References

Adibzadeh, A., Zaki Dizaji, H., & Aghili Nategh, N. (2019). The possibility of distinguishing different varieties of sugarcane with the electronic nose technique in sugarcane syrup. Biosystem Engineering of Iran, 51(1), 1-10 (In Persian).
Ayari, F. (2018). Development and implementation of an electronic nose system for detection of cow ghee from adulterated samples. Faculty of Agriculture Department of Mechanical Engineering of Biosystems, Razi University.
Al-Maskari, S., Li, X., & Liu Q. (2014). An effective approach to handling noise and drift in electronic noses. In: Wang H, Sharaf MA (eds) Databases theory and applications. Lecture Notes in Computer Science, Springer, Cham, pp, 223–230
Aghili Nategh, N., Anwar, A. & Dalvand, M.J. (2019). Determining the degree of ripeness of strawberries with the help of an electronic nose. Agricultural Machinery Mechanics Research 9: 71-80 (In Persian).
Barreca, D., Nabavi, S. M., Sureda, A., Rasekhian, M., Raciti, R., Silva, A. S., & Mandalari, G. (2020). Almonds (Prunus dulcis Mill. DA webb): A source of nutrients and health-promoting compounds. Nutrients, 12(3), 672.
Becerra-Tomás, N., Paz-Graniel, I., WC Kendall, C., Kahleova, H., Rahelić, D., Sievenpiper, J. L., & Salas-Salvadó, J. (2019). Nut consumption and incidence of cardiovascular diseases and cardiovascular disease mortality: a meta-analysis of prospective cohort studies. Nutrition reviews, 77(10), 691-709.
Mejia, S. B., Kendall, C. W., Viguiliouk, E., Augustin, L. S., Ha, V., Cozma, A. I., ... & Sievenpiper, J. L. (2014). Effect of tree nuts on metabolic syndrome criteria: a systematic review and meta-analysis of randomised controlled trials. BMJ open, 4(7).
Bechthold, A., Boeing, H., Schwedhelm, C., Hoffmann, G., Knüppel, S., Iqbal, K., ... & Schwingshackl, L. (2019). Food groups and risk of coronary heart disease, stroke and heart failure: a systematic review and dose-response meta-analysis of prospective studies. Critical reviews in food science and nutrition, 59(7), 1071-1090.
Barreira, J. C., Casal, S., Ferreira, I. C., Peres, A. M., Pereira, J. A., & Oliveira, M. B. P. (2012). Supervised chemical pattern recognition in almond (Prunus dulcis) Portuguese PDO cultivars: PCA-and LDA-based triennial study. Journal of agricultural and food chemistry, 60(38), 9697-9704.
Chinipardaz, R., Rekabdar, Q., & Yousefi Hajiabad, R. (2015). Studying the human development of countries using mixed audit analysis methods. Quarterly Journal of Economic Studies,3(3), 5-20.( In Persian).
Casas-Agustench, P., Salas-Huetos, A., & Salas-Salvadó, J. (2011). Mediterranean nuts: origins, ancient medicinal benefits and symbolism. Public health nutrition, 14(12A), 2296-2301.
Chang, A. S., Sreedharan, A., & Schneider, K. R. (2013). Peanut and peanut products: A food safety perspective. Food Control, 32(1), 296-303.
De Souza, R. G. M., Schincaglia, R. M., Pimentel, G. D., & Mota, J. F. (2017). Nuts and human health outcomes: a systematic review. Nutrients, 9(12), 1311.
Esteki, M., Farajmand, B., Kolahderazi, Y., & Simal-Gandara, J. (2017). Chromatographic fingerprinting with multivariate data analysis for detection and quantification of apricot kernel in almond powder. Food Analytical Methods, 10, 3312-3320.
Fathizad, H., Safari, A., Bazgir, M., & KHosravi, GH.. (2017). Evaluation of SVM with Kernel method (linear, polynomial, and radial basis) and neural network for land use classification. Iranian Journal of Range and Desert Research, 23(4 ), 729-743. ( In Persian).
Gorji Chakespari, A., Mohammad Nilbakht, A., Sefidkon, F., & Ghasemi Varnamkhasti, M. (2017). Investigation of electronic nose system in classification of Rosa damascena Mill. essential oil by artificial neural network. Iranian Journal of Medicinal and Aromatic Plants Research, 33(3), 339-349.‏
Gholami, R., Aghili Nategh, N., & Rabbani, H. (2023). Evaluation the effects of temperature and packaging conditions on the quality of button mushroom during storage using e-nose system. Journal of Food Science and Technology, 60(4), 1355-1366.
Jamalizadeh, F., Ghasemi-Varnamkhasti, M., Ghasemi Nafchi, M., Tohidi, M., & Dowlati, M. (2020). Implementation of an olfactory machine system for the classification of different types of black pepper based on geographical origin and detection of cheating in Indian black pepper. Iranian Food Science and Technology Research Journal, 16(4), 479-491.‏
Karami, H., Rasekh, M., & 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.
Kodad, O., Socias i Company, R., & Alonso, J. M. (2018). Genotypic and environmental effects on tocopherol content in almond. Antioxidants, 7(1), 6.
Khazaei, J., Borghei, A.M., & Rasekh, M. (2003). Determining The Physical and Mechanical Properties of almond and It's Kernel. Journal of Agricultural Sciences, 9(3), 11-34. (In Persian).
Lashgari, M., & MohammadiGol, R. (2016). Discrimination of Golab apple storage time using acoustic impulse response and LDA and QDA discriminant analysis techniques. Iran Agricultural Research, 35(2), 65-70.
Modupalli, N., Naik, M., Sunil, C. K., & Natarajan, V. (2021). Emerging non-destructive methods for quality and safety monitoring of spices. Trends in Food Science & Technology, 108, 133-147.
Mu, F., Gu, Y., Zhang, J., & Zhang, L. (2020). Milk source identification and milk quality estimation using an electronic nose and machine learning techniques. Sensors, 20(15), 4238.
Makarichian, A., Chayjan, R. A., Ahmadi, E., & Zafari, D. (2022). Early detection and classification of fungal infection in garlic (A. sativum) using electronic nose. Computers and Electronics in Agriculture, 192, 106575.
Oliveira, I., Meyer, A. S., Afonso, S., Aires, A., Goufo, P., Trindade, H., & Gonçalves, B. (2019). Phenolic and fatty acid profiles, α‐tocopherol and sucrose contents, and antioxidant capacities of understudied Portuguese almond cultivars. Journal of food biochemistry, 43(7), e12887.
Pearce, T. C., Schiffman, S. S., Nagle, H. T., & Gardner, J. W. (Eds.). (2006). Handbook of machine olfaction: electronic nose technology. John Wiley & Sons.
Sanaeifar, A., Mohtasebi, S., Ghasemi-Varnamkhasti, M., Ahmadi, H., & Lozano Rogado, J. S. (2014). Development and application of a new low cost electronic nose for the ripeness monitoring of banana using computational techniques (PCA, LDA, SIMCA, and SVM).‏
Sadriyan, S., Javadikia, H., Aghili Nategh, N., Naderloo, L., & Sharifi, R. (2023). Diagnosis of disease in tomato paste by Bacillus subtilis bacteria, Penicillium fungi and Aspergillus fungi with the help of electronic nose. Iranian Journal of Biosystems Engineering, 54(2), 33-47.‏ ( In Persian).
Taheri Garavand, A., Mirzaee Ghaleh, E., & Ayari, F. (2020). Intelligent Classification of Fresh Chicken Meat from Frozen-Thawed Using Olfactory Machine. Journal of Food Technology and Nutrition, 17(2 (66) ), 13-22.
‏Tahri, K., Tiebe, C., Bougrini, M., Saidi, T., El Hassani, N. E. A., El Bari, N., ... & Bouchikhi, B. (2015). Characterization and discrimination of saffron by multisensory systems, SPME-GC-MS and UV-Vis spectrophotometry. Analytical methods, 7(24), 10328-10338.
USDA (2020). https://apps.fas.usda.gov/psdonline/circulars/production.pdf
Wei, Z., Xiao, X., Wang, J., & Wang, H. (2017). Identification of the rice wines with different marked ages by electronic nose coupled with smartphone and cloud storage platform. Sensors, 17(11), 2500.
Xie, Y., Lin, Y., Li, X., Yang, H., Han, J., Shang, C., ... & Lu, F. (2023). Peanut drying: Effects of various drying methods on drying kinetic models, physicochemical properties, germination characteristics, and microstructure. Information processing in agriculture, 10(4), 447-458.‏
Yang, H., Ni, J., Gao, J., Han, Z., & Luan, T. (2021). A novel method for peanut variety identification and classification by Improved VGG16. Scientific Reports, 11(1), 15756.
Zhang, H., Wang, J., Ye, S., & Chang, M. (2012). Application of electronic nose and statistical analysis to predict quality indices of peach. Food and Bioprocess Technology, 5, 65-72.
Iranian Journal of Biosystems Engineering
Volume 54, Issue 3
October 2023
Pages 61-74

Files

History

  • Receive Date: 01 November 2023
  • Revise Date: 16 February 2024
  • Accept Date: 20 February 2024

Share

How to cite

Statistics