طبقه‌بندی آرد گندم ایرانی با استفاده از طیف‌سنجی FT-MIR بر پایه‌ی انتخاب طول موج با بیشینه‌ی ارتباط و کمینه‌ی افزونگی، همراه با ماشین بردار پشتیبان SVM

نوع مقاله : مقاله پژوهشی لاتین

نویسندگان

• امیر کاظمی ¹
• اصغر محمودی ¹
• سید حسین فتاحی ²

¹ گروه مهندسی بیوسیستم، دانشگاه تبریز، تبریز، ایران

² گروه مهندسی بیوسیستم، دانشکده کشاورزی، دانشگاه مراغه، مراغه، ایران

https://doi.org/10.22067/ifstrj.2024.88624.1342

چکیده

انواع واریته گندم، به‌عنوان یکی از محصولات راهبردی، در ایران بر اساس شرایط خاص جغرافیایی و اقلیمی هر منطقه کشت می‌شوند. طبقه‌بندی این واریته‌های گندم برای تضمین کیفیت محصولات نهایی حاصل از آرد گندم اهمیت دارد. در این پژوهش، از طیف‌سنجی مادون قرمز میان‌ناحیه با تبدیل فوریه (FT-MIR) به‌عنوان روشی غیرمخرب، همراه با شیمی‌سنجی، برای طبقه‌بندی چهار رقم از گندم ایرانی استفاده شد. در مجموع 160 نمونه مورد تحلیل قرار گرفت و از الگوریتم‌های مختلف پیش‌پردازش برای حذف اطلاعات ناخواسته بهره گرفته شد. سپس، از تحلیل مؤلفه‌های اصلی (PCA) به‌عنوان مدل بدون ناظر و ماشین بردار پشتیبان (SVM) به‌عنوان مدل با ناظر، همراه با الگوریتم انتخاب ویژگی با بیشینه‌ی ارتباط و کمینه‌ی افزونگی (MRMR)، برای بررسی رده‌بندی این گونه‌ها استفاده شد. بهترین نتیجه مدل SVM بدون انتخاب ویژگی، با پیش‌پردازش ترکیبی S-G+D2+MSC، دقتی برابر با 99.4٪ به‌دست آورد. خروجی 100٪ حاصل از مدل SVM همراه با الگوریتم انتخاب ویژگی MRMR، توانمندی روش طیف‌سنجی FT-MIR را در رده‌بندی گونه‌های آرد گندم ایرانی تأیید کرد.

کلیدواژه‌ها

• آرد گندم
• پیش‌پردازش
• طبقه بندی
• طیف‌سنجی تبدیل فوریه

موضوعات

• شیمی مواد غذایی

عنوان مقاله [English]

Classification of Iranian Wheat Flour by FT-MIR Spectroscopy based on Max-Relevance Min-Redundancy Wavelength Selection Coupled with SVM

نویسندگان [English]

• Amir Kazemi ¹
• Asghar Mahmoudi ¹
• Seyyed Hossein Fattahi ²

¹ Department of Biosystems Engineering, University of Tabriz, Tabriz, Iran

² Department of Biosystems Engineering, University of Maragheh, Maragheh, Iran

چکیده [English]

Different varieties of wheat as one of the strategic crops are cultivated in Iran based on the specific geographical and climatic conditions of each area. Classification of wheat varieties is important in order to guarantee the final products acquired from wheat flour. Fourier Transform-Mid Infrared (FT-MIR) spectroscopy as a nondestructive approach combined with chemometrics was employed to classify four varieties of Iranian wheat. 160 samples were analyzed and various preprocessing algorithms were used to correct unwanted information. Then, Principal Component Analysis (PCA) as unsupervised and Support Vector Machine (SVM) as supervised models with Max-Relevance Min-Redundancy (MRMR) feature selection algorithm were applied to investigate the classification of these varieties. The best result of SVM model without feature selection was with S-G+D2+MSC preprocessing with 99.4% of accuracy. The output of 100% with SVM model and MRMR feature selection algorithm confirmed the capability of FT-MIR spectroscopy method for classification of Iranian wheat flour varieties.

کلیدواژه‌ها [English]

• Classification
• FT-MIR spectroscopy
• PCA
• Preprocessing
• Wheat flour

©2025 The author(s). This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

مراجع

1. Barbin, D.F., Badaro, A.T., Honorato, D.C., Ida, E.Y., & Shimokomaki, M. (2020). Identification of turkey meat and processed products using near infrared spectroscopy. Food Control, 107, 106816. https://org/10.1016/j.foodcont.2019.106816
2. Coţovanu, I., & Mironeasa, S. (2022). Influence of buckwheat seed fractions on dough and baking performance of wheat bread. Agronomy, 12(1), 137. https://org/10.3390/agronomy12010137
3. De Girolamo, A., Arroyo, M.C., Cervellieri, S., Cortese, M., Pascale, M., Logrieco, A.F., & Lippolis, V. (2020). Detection of durum wheat pasta adulteration with common wheat by infrared spectroscopy and chemometrics: A case study. LWT, 127, 109368. https://doi.org/10.1016/j.lwt.2020.109368
4. Deniz, E., Güneş Altuntaş, E., Ayhan, B., İğci, N., Özel Demiralp, D., & Candoğan, K. (2018). Differentiation of beef mixtures adulterated with chicken or turkey meat using FTIR spectroscopy. Journal of Food Processing and Preservation, 42(10), e13767. https://org/10.1111/jfpp.13767
5. Ellis, D.I., Muhamadali, H., Haughey, S.A., Elliott, C.T., & Goodacre, R. (2015). Point-and-shoot: rapid quantitative detection methods for on-site food fraud analysis–moving out of the laboratory and into the food supply chain. Analytical Methods, 7(22), 9401-9414. https://doi.org/10.1039/C5AY02048D
6. Granato, D., Santos, J.S., Escher, G.B., Ferreira, B.L., & Maggio, R.M. (2018). Use of principal component analysis (PCA) and hierarchical cluster analysis (HCA) for multivariate association between bioactive compounds and functional properties in foods: A critical perspective. Trends in Food Science & Technology, 72, 83-90. https://doi.org/10.1016/j.tifs.2017.12.006
7. Holden, N.M., Wolfe, M.L., Ogejo, J.A., & Cummins, E.J. (2021). Introduction to biosystems engineering Introduction to Biosystems Engineering (pp. 0): American Society of Agricultural and Biological Engineers. https://doi.org/10.21061/intro2biosystemsengineering
8. Karimi, N., Kondrood, R.R., & Alizadeh, T. (2017). An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms. Measurement, 107, 68-76. https://doi.org/10.1016/j.measurement.2017.05.009
9. Kazemi, A., Mahmoudi, A., & Khojastehnazhand, M. (2023). Detection of sodium hydrosulfite adulteration in wheat flour by FT-MIR spectroscopy. Journal of Food Measurement and Characterization, 17(2), 1932-1939. https://org/10.1007/s11694-022-01763-x
10. Keshavarzi, Z., Barzegari Banadkoki, S., Faizi, M., Zolghadri, Y., & Shirazi, F.H. (2020). Comparison of transmission FTIR and ATR spectra for discrimination between beef and chicken meat and quantification of chicken in beef meat mixture using ATR-FTIR combined with chemometrics. Journal of Food Science and Technology, 57, 1430-1438. https://doi.org/10.1007/s13197-019-04178-7
11. Khojastehnazhand, M., & Roostaei, M. (2022). Classification of seven Iranian wheat varieties using texture features. Expert Systems with Applications, 199, 117014. https://doi.org/10.1016/j.eswa.2022.117014
12. López-Maestresalas, A., Insausti, K., Jarén, C., Pérez-Roncal, C., Urrutia, O., Beriain, M.J., & Arazuri, S. (2019). Detection of minced lamb and beef fraud using NIR spectroscopy. Food Control, 98, 465-473. https://doi.org/10.1016/j.foodcont.2018.12.003
13. Ma, X.-H., Chen, Z.-G., & Liu, J.-M. (2024). Wavelength selection method for near-infrared spectroscopy based on Max-Relevance Min-Redundancy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 310, 123933. https://doi.org/10.1016/j.saa.2024.123933
14. Mohamed, M.Y., Solihin, M.I., Astuti, W., Ang, C.K., & Zailah, W. (2019). Food powders classification using handheld near-infrared spectroscopy and support vector machine. Paper presented at the Journal of Physics: Conference Series. https://doi.org/10.1088/1742-6596/1367/1/012029
15. Ramírez‐Gallego, S., Lastra, I., Martínez‐Rego, D., Bolón‐Canedo, V., Benítez, J.M., Herrera, F., & Alonso‐Betanzos, A. (2017). Fast‐mRMR: Fast minimum redundancy maximum relevance algorithm for high‐dimensional big data. International Journal of Intelligent Systems, 32(2), 134-152. https://doi.org/10.1002/int.21833
16. Sacré, P.-Y., De Bleye, C., Chavez, P.-F., Netchacovitch, L., Hubert, P., & Ziemons, E. (2014). Data processing of vibrational chemical imaging for pharmaceutical applications. Journal of Pharmaceutical and Biomedical Analysis, 101, 123-140. https://doi.org/1016/j.jpba.2014.04.012
17. Sampaio, P.S., Castanho, A., Almeida, A.S., Oliveira, J., & Brites, C. (2020). Identification of rice flour types with near-infrared spectroscopy associated with PLS-DA and SVM methods. European Food Research and Technology, 246, 527-537. https://org/10.1007/s00217-019-03419-5
18. Wadood, S.A., Guo, B., Zhang, X., & Wei, Y. (2019). Geographical origin discrimination of wheat kernel and white flour using near‐infrared reflectance spectroscopy fingerprinting coupled with chemometrics. International Journal of Food Science & Technology, 54(6), 2045-2054. https://doi.org/10.1111/ijfs.14105