سامانه‌ی یکپارچه‌ جداساز مکاترونیکی مبتنی بر FTIR پوسته سخت بادام تلخ و شیرین بر پایه شبکه عصبی MLP

مقالات آماده انتشار

نوع مقاله : مقاله پژوهشی

نویسندگان

مجتبی افشاری پور ¹

محسن شمسی ¹

فهیمه قاسمیان ²

حجت الله خباززاده ³

¹ گروه مهندسی مکانیک بیوسیستم، دانشگاه شهید باهنر کرمان، کرمان، ایران

² گروه مهندسی کامپیوتر، دانشگاه شهید باهنر کرمان، کرمان، ایران

³ گروه شیمی، دانشگاه شهید باهنر کرمان، کرمان، ایران

https://doi.org/10.22067/jam.2026.97689.1470

چکیده

تشخیص بادام تلخ به‌دلیل محتوای آمیگدالین و خطر آزادسازی سیانید، یکی از چالش‌های ایمنی غذایی است. در حالی‌که اغلب روش‌های تشخیصی و جداسازی یا مخرب‌اند یا به مرحله تشخیص محدود می‌شوند، در این پژوهش، یک چارچوب یکپارچه مبتنی بر طیف‌سنجی FTIR پوسته بادام و یادگیری ماشین و عمیق برای تشخیص و جداسازی فیزیکی بادام تلخ و شیرین توسعه داده شد. مجموعه‌ داده‌ای شامل 200 نمونه بادام تلخ و شیرین جمع‌آوری و پس از پیش‌پردازش طیفی، عملکرد چهار الگوریتم SVM، RF، MLP و Autoencoder–MLP مقایسه شد. مدل MLP بالاترین کارایی را با دقت 95.5% و 0.984=AUC به‌دست آورد. تحلیل ویژگی‌ها، سه باند طیفی کلیدی cm^-1 1030، cm^-1 1740 و cm^-1 2920 را به‌عنوان نشانگرهای مرتبط با ترکیبات فنولیک و مشتقات آمیگدالین شناسایی کرد. خروجی مدل به یک سامانه جداساز خودکار مکاترونیکی منتقل گردید و دستگاه در آزمون‌های متوالی به میانگین دقت جداسازی 99.5% دست یافت. نتایج نشان می‌دهد که ترکیب FTIR پوسته همراه با یادگیری ماشین و عمیق می‌تواند به‌عنوان یک رویکرد غیرمخرب و عملی برای جداسازی بادام در مقیاس ‌صنعتی به‌کار رود.

کلیدواژه‌ها

آشکارسازی آمیگدالین

برچسب‌گذاری بادام

تحلیل غیرمخرب

جداسازی مکاترونیکی

طیف‌سنجی FTIR

یادگیری ماشین

موضوعات

• مهندسی پس‌ از برداشت، و فرآوری محصولات کشاورزی

---

Authors retain the copyright. This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

مراجع

1. Al-Awadhi, M. A., & Deshmukh, R. R. (2025). Detection of Adulteration in Coconut Milk using Infrared Spectroscopy and Machine Learning. IEEE MTICTI 2021. https://doi.org/10.1109/mticti53925.2021.9664764
2. Arabizadeh, N., Mahmoudi, M., Mokhtar Gandomani, L., & Eizadi-Mood, N. (2024). Cyanide poisoning after bitter almond ingestion: A rare case report. Case Reports in Emergency Medicine, 2024, Article ID 123456. https://doi.org/10.1002/ccr3.8418
3. Arboleda, E. R., Fajardo, A. C., & Medina, R. P. (2018). Classification of coffee bean species using image processing, artificial neural network and K nearest neighbors. In 2018 IEEE International Conference on Innovative Research and Development (ICIRD) (pp. 1–5). IEEE. https://doi.org/10.1109/icird.2018.8376326
4. Balakrishnan, P., Anny Leema, A., Jothiaruna, N., Assudani, P. J., Sankar, K., Kulkarni, M. B., & Bhaiyya, M. (2025). Artificial intelligence for food safety: From predictive models to real-world safeguards. Trends in Food Science & Technology, 163, 105153. https://doi.org/10.1016/j.tifs.2025.105153
5. Béjar-Grimalt, J., Pérez-Guaita, D., Sánchez-Illana, Á., García-Contreras, R., Kataria, R., Bureau, S., de la Guardia, M., & Cadet, F. (2025). Classification of Apricot Varieties by Infrared Spectroscopy and Machine Learning. ACS Agricultural Science & Technology, 5(7), 1373-1381. https://doi.org/10.26434/chemrxiv-2025-f76xt
6. Borràs, E., Amigo, J. M., van den Berg, F., Boqué, R., & Busto, O. (2014). Fast and robust discrimination of almonds (Prunus amygdalus) with respect to their bitterness by using near infrared and partial least squares-discriminant analysis. In Food Chemistry (Vol. 153, pp. 15–19). Elsevier BV. https://doi.org/10.1016/j.foodchem.2013.12.032
7. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/a:1010933404324
8. Chu, C., Wang, H., Luo, X., Fan, Y., Nan, L., Du, C., Gao, D., Wen, P., Wang, D., Yang, Z., Yang, G., Liu, L., Li, Y., Hu, B., Zunongjiang, A., & Zhang, S. (2024). Rapid detection and quantification of melamine, urea, sucrose, water, and milk powder adulteration in pasteurized milk using Fourier transform infrared (FTIR) spectroscopy coupled with modern statistical machine learning algorithms. Heliyon, 10(12), e32720. https://doi.org/10.1016/j.heliyon.2024.e32720
9. Cochran, W. G. (1977). Sampling Techniques (3rd ed.). John Wiley & Sons.
10. Cortés, V., Talens, P., Barat, J. M., & Lerma-García, M. J. (2019). Discrimination of intact almonds according to their bitterness and prediction of amygdalin concentration by Fourier transform infrared spectroscopy. Postharvest Biology and Technology, 148, 236-241. https://doi.org/10.1016/j.postharvbio.2018.05.006
11. Das, M., Yeo, W. S., & Saptoro, A. (2025). A review of machine learning in hyperspectral imaging for food safety. Vibrational Spectroscopy, 139, 103828. https://doi.org/10.1016/j.vibspec.2025.103828
12. Deng, Z., Wang, T., Zheng, Y., Zhang, W., & Yun, Y. H. (2024). Deep learning in food authenticity: Recent advances and future trends. Trends in Food Science & Technology, 144, 104344. https://doi.org/10.1016/j.tifs.2024.104344
13. Dimakopoulou-Papazoglou, D., Serrano, S., Rodríguez, I., Ploskas, N., Koutsoumanis, K., & Katsanidis, E. (2025). FTIR spectroscopy combined with machine learning for the classification of Mediterranean honey based on origin. Journal of Food Composition and Analysis, 144, 107778. https://doi.org/10.1016/j.jfca.2025.107778
14. Dong, J. E., Li, J., Liu, H., & Wang, Y. Z. (2023). Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes. Food Research International, 167, 112679. https://doi.org/10.1016/j.foodres.2023.112679
15. Durak, T., & Depciuch, J. (2020). Effect of plant sample preparation and measuring methods on ATR-FTIR spectra results. Environmental and Experimental Botany, 169, 103915. https://doi.org/10.1016/j.envexpbot.2019.103915
16. Ezenarro, J., Riu, J., Ahmed, H. J., Busto, O., Giussani, B., & Boqué, R. (2024). Measurement errors and implications for preprocessing in miniaturised near-infrared spectrometers: Classification of sweet and bitter almonds as a case of study. Talanta, 276, 126271. https://doi.org/10.1016/j.talanta.2024.126271
17. Ganaie, M. A., Tanveer, M., Suganthan, P. N., & Snasel, V. (2022). Oblique and rotation double random forest. Neural Networks, 153, 496-517. https://doi.org/10.1016/j.neunet.2022.06.012
18. Gökalp, Ç., & Mübarek Mazhar, Ç. (2024). An improved pistachio detection approach using YOLO-v8 Deep Learning Models. BIO Web of Conferences, 85, 01013. https://doi.org/10.1051/bioconf/20248501013
19. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press.
20. Hong, Y., Birse, N., Quinn, B., Li, Y., Jia, W., McCarron, P., Wu, D., da Silva, G. R., Vanhaecke, L., van Ruth, S., & Elliott, C. T. (2023). Data fusion and multivariate analysis for food authenticity analysis. Nature Communications, 14(1), 7738. https://doi.org/10.1038/s41467-023-38382-z
21. Hou, L., Liu, Z., You, J., Liu, Y., Xiang, J., Zhou, J., & Pan, Y. (2024). Tomato Sorting System Based on Machine Vision. Electronics, 13(11), 2114. https://doi.org/10.3390/electronics13112114
22. International Organization for Standardization. (2002). Sensory analysis Methodology General guidance for measuring odour, flavour and taste detection thresholds by a 3-AFC procedure (ISO 13301:2002). Retrieved from: https://www.iso.org/standard/36791.html
23. Jahnke, S., Roussel, J., Hombach, T., Kochs, J., Fischbach, A., Huber, G., & Scharr, H. (2016). phenoSeeder - A Robot System for Automated Handling and Phenotyping of Individual Seeds. Plant Physiology, 172(3), 1358-1370. https://doi.org/10.1104/pp.16.01122
24. Lacerda, M., Franca, T., Calvani, C., Marangoni, B., Teodoro, P., Campos, C. N. S., Baio, F. H. R., Azevedo, G. B., & Cena, C. (2024). A simple method for Eucalyptus species discrimination: FTIR spectroscopy and machine learning. Results in Chemistry, 7, 101233. https://doi.org/10.1016/j.rechem.2023.101233
25. Lawless, H. T., & Heymann, H. (1999). Principles of Good Practice. In Food science text series (pp. 83-115). Springer US. https://doi.org/10.1007/978-1-4419-7452-5_3
26. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
27. Lin, S., Liu, Z., Qin, H., Jiang, L., Zhao, D., Li, Q., & Ou, Q. (2025). Developing a fast Fourier transform infrared spectroscopy system for precise and reliable grade differentiation of Gastrodia elata. Vibrational Spectroscopy, 136, 103769. https://doi.org/10.1016/j.vibspec.2025.103769
28. Mekonnen, K. D. (2023). Fourier transform infrared spectroscopy as a tool for identifying the unique characteristic bands of lipid in oilseed components: Confirmed via Ethiopian indigenous desert date fruit. Heliyon, 9(4), e14699. https://doi.org/10.1016/j.heliyon.2023.e14699
29. Mustafa, G., Wang, H., Liu, Y., Wang, L., Ali, M., Yao, Z., Quan, H., & He, K. (2025). Recent Advances in Spectroscopy and Machine Learning for Non-Destructive and Real-Time Detection of Mycotoxins in Cereals. Trends in Food Science & Technology, 157, 105246. https://doi.org/10.1016/j.tifs.2025.105246
30. Naes, T., Isaksson, T., Fearn, T., & Davies, T. (2002). A user-friendly guide to multivariate calibration and classification. NIR Publications.
31. Nasirahmadi, A., & Miraei Ashtiani, S. H. (2017). Bag-of-Feature model for sweet and bitter almond classification. Biosystems Engineering, 156, 51-60. https://doi.org/10.1016/j.biosystemseng.2017.01.008
32. Park, H., Chung, H., Choi, S., Bahn, Y. S., & Son, J. (2024). Evaluation of exposure to cyanogenic glycosides and potential hydrogen cyanide release in commercially available foods among the Korean population. Food Chemistry, 456, 139872. https://doi.org/10.1016/j.foodchem.2024.139872
33. Prata, J. C., & da Costa, P. M. (2024). Fourier Transform Infrared Spectroscopy Use in Honey Characterization and Authentication: A systematic review. ACS Food Science & Technology, 4(8), 1817-1828. https://doi.org/10.1021/acsfoodscitech.4c00377
34. Rahimzadeh, M., & Attar, A. (2020). Detecting and Counting Pistachios based on Deep Learning. arXiv. https://doi.org/10.48550/ARXIV.2005.03990
35. Romano, R., Vestergaard, J. S., Kompany-Zareh, M., & Bredie, W. L. P. (2010). Monitoring Panel Performance Within and Between Sensory Experiments by Multi-Way Analysis. In Studies in Classification, Data Analysis, and Knowledge Organization (pp. 335–342). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-13312-1_35
36. Rong, D., Wang, H., Ying, Y., Zhang, Z., & Zhang, Y. (2020). Peach variety detection using VIS-NIR spectroscopy and deep learning. Computers and Electronics in Agriculture, 175, 105553. https://doi.org/10.1016/j.compag.2020.105553
37. Salamah, N., Cantika, C. D., Nurani, L. H., & Guntarti, A. (2024). Authentication of citrus peel oils from different species and commercial products using FTIR Spectroscopy combined with chemometrics. Pharmacia, 71, 1-7. https://doi.org/10.3897/pharmacia.71.e118789
38. Sheahata, D., ElGamal, R., Radwan, S., & Elmasry, G. (2025). Detection of impurities on faba bean (Vicia faba) by NIR spectroscopy. Journal of Plant Production Sciences, 14(1), 43-53. https://doi.org/10.21608/jpps.2025.390691.1013
39. Shen, C., Wang, R., Nawazish, H., Wang, B., Cai, K., & Xu, B. (2024). Machine vision combined with deep learning–based approaches for food authentication: An integrative review and new insights. Comprehensive Reviews in Food Science and Food Safety, 23(6), e13785. https://doi.org/10.1111/1541-4337.70054
40. Sipos, L., Nyitrai, Á., Hitka, G., Friedrich, L. F., & Kókai, Z. (2021). Sensory Panel Performance Evaluation Comprehensive Review of Practical Approaches. Applied Sciences, 11(24), 11977. https://doi.org/10.3390/app112411977
41. Sluijterman, L., Cator, E., & Heskes, T. (2025). Likelihood-ratio-based confidence intervals for neural networks. Machine Learning, 114(4), 2319-2347. https://doi.org/10.1007/s10994-024-06639-3
42. Syafri, S., Jaswir, I., Yusof, F., Rohman, A., & Hamidi, D. (2022). The use of GC-MS and FTIR spectroscopy coupled with multivariate analysis for the detection of red ginger oil adulteration. Rasayan Journal of Chemistry, 15(4), 2231-2236. https://doi.org/10.31788/rjc.2022.1547039
43. Tachie, C. Y. E., Obiri-Ananey, D., Alfaro-Cordoba, M., Tawiah, N. A., & Aryee, A. N. A. (2024). Classification of oils and margarines by FTIR spectroscopy in tandem with machine learning. Food Chemistry, 431, 137077. https://doi.org/10.1016/j.foodchem.2023.137077
44. Taş, N. G., & Gökmen, V. (2017). Phenolic compounds in natural and roasted nuts and their skins: a brief review. Current Opinion in Food Science, 14, 103-109. https://doi.org/10.1016/j.cofs.2017.03.001
45. Torres-Rodríguez, I., Sánchez, M. T., Entrenas, J. A., Vega-Castellote, M., Garrido-Varo, A., & Pérez-Marín, D. (2022). Hyperspectral Imaging for the Detection of Bitter Almonds in Sweet Almond Batches. Applied Sciences, 12(10), 4842. https://doi.org/10.3390/app12104842
46. Unuvar, A., Boyaci, I. H., & Koksel, H. (2021). A novel approach for rapid discrimination of common and durum wheat flours using spectroscopic analyses combined with chemometrics. Journal of Cereal Science, 100, 103269. https://doi.org/10.1016/j.jcs.2021.103269
47. Uzer, M. S. (2025). Deep Learning-Based Classification Consisting of Pre-Trained Models and Proposed Model Using K-Fold Cross-Validation for Pistachio Species. Applied Sciences, 15(8), 4516. https://doi.org/10.3390/app15084516
48. Yuan, Y., Ji, Z., Fan, Y., Xu, Q., Shi, C., Lyu, J., & Ertbjerg, P. (2025). Deep learning-assisted fluorescence spectroscopy for food quality and safety analysis. Trends in Food Science & Technology, 156, 104821. https://doi.org/10.1016/j.tifs.2024.104821
49. Zahedi, A., Shafei, A. M., & Shamsi, M. (2023). Application of hybrid robotic systems in crop harvesting: Kinematic and dynamic analysis. Computers and Electronics in Agriculture, 107724. https://doi.org/10.1016/j.compag.2023.107724
50. Zhang, L., Boom, R. M., & Ma, Y. (2025). Machine Learning in Automated Food Processing: A Mini Review. Annual Review of Food Science and Technology, 16(1), 25-37. https://doi.org/10.1146/annurev-food-111523-122039
51. Ziani, I., Bouakline, H., El Guerraf, A., El Bachiri, A., Marie-Laure Fauconnier, & Sher, F. (2025). Integrating AI and advanced spectroscopic techniques for precision food safety and quality control. Trends in Food Science & Technology, 156, 104850. https://doi.org/10.1016/j.tifs.2024.104850