بررسی تاثیر پوشش‌دهی با صمغ فارسی حاوی روغن شاهدانه بر تغییرات جرم و حجم انگور با استفاده از سیستم‌های بینایی ماشین و یادگیری ماشین

نویسندگان
علی گنجلو 1
محسن زندی 2
ماندانا بی مکر 2
ابوالفضل قره باغی 3
1 دانشیار، گروه علوم و مهندسی صنایع غذایی، دانشکده کشاورزی، دانشگاه زنجان، زنجان، ایران
2 استادیار، گروه علوم و مهندسی صنایع غذایی، دانشکده کشاورزی، دانشگاه زنجان، زنجان، ایران
3 دانش آموخته کارشناسی، گروه علوم و مهندسی صنایع غذایی، دانشکده کشاورزی، دانشگاه زنجان، زنجان، ایران
10.52547/fsct.18.113.157
چکیده
در این پژوهش تاثیر پوشش خوراکی صمغ فارسی (0، 5/1 و 3 درصد) حاوی روغن شاهدانه (0، 075/0 و 15/0 درصد) بر تغییرات جرم و حجم طی نگهداری در دمای 4 درجه سلسیوس به مدت 28 روز بررسی گردید. سیستم بینایی ماشین به همراه انواع روش‌های یادگیری ماشین برای استخراج تصویر انگور از تصویر و تخمین جرم و حجم بر اساس خصیصه‌های تصویر (طول، عرض، ارتفاع و سطح) استفاده شد. برای پیش‌بینی جرم و حجم حبه انگور 4 مدل یادگیری ماشین شامل رگرسیون خطی (LR)، شبکه عصبی مصنوعی (ANN)، ماشین بردار پشتیبان بر پایه تابع شعاعی (RBF-SVR) و ماشین بردار پشتیبان بر پایه تابع خطی (LBF-SVR) توسعه یافت. به‌منظور بررسی کارایی مدل‌های توسعه یافته داده‌های تخمین جرم و حجم انگور با داده‌های تجربی مقایسه گردید. جرم و حجم طی نگهداری در کل تیمارها کاهش یافت. از طرفی تغییرات جرم و حجم با افزایش غلظت صمغ فارسی و روغن شاهدانه کاهش یافت. بر اساس نتایج ارزیابی مدل، عملکرد پیش‌بینی مدل RBF-SVR در مقایسه با مدل‌های LR، ANN و LBF-SVR دقیق‌تر بود و توانست جرم و حجم را به ترتیب با ضریب تبیین 998/0 و 989/0 تخمین بزند که نشان‌دهنده همبستگی خوب بین نتایج واقعی و پیش‌بینی است. این نتایج تائید می‎‌نماید که مدل SVR ابزاری قابل قبول در تخمین جرم و حجم انگور پوشش‌دار شده طی نگهداری در دمای سردخانه است.
کلیدواژه‌ها
پوشش‌دهی
پردازش تصویر
ماشین بردار پشتیبان
شبکه عصبی مصنوعی
پیش‌بینی

موضوعات

عنوان مقاله English

Evaluation the Effect of Farsi Gum Containing Hemp seed oil Coating on Mass and Volume Changes of Grape using Machine Vision and Machine Learning Systems

نویسندگان English

Ali Ganjloo 1
Mohsen Zandi 2
Mandana Bimakr 2
Abolfazl Ghareh Baghi 3
1 -
2 Assistant professor, Department Food Science and Engineering, Faculty of Agriculture, University of Zanjan, Zanjan, Iran.
3 -
چکیده English

In this study, the effects of Farsi gum (0, 1.5% and 3%) coating containing hemp seed oil (0, 0.075% and 0.15%) on mass and volume changes of grape were investigated during storage at 4°C for 28 days. Machine vision system with learning machine methods was used to detect coated grapes from an image and estimate their mass and volume based on the image features (length, width, height and area). Four machine learning models, including linear regression (LR), artificial neural networks (ANN), radial basis function support vector regression (RBF-SVR) and Linear basis function support vector regression (LBF-SVR) were developed to predict the mass and volume of the single grape. The estimated grape mass and volume by these methods was compared statistically with actual values. The mass and volume in all treatments showed a decreasing pattern during the cold storage. The results indicated that mass and volume change decrease with Farsi gum and hemp seed oil increasing. Furthermore, according to the model evaluation results, the prediction performance of RBF-SVR model had achieved better predictive accuracy compared with the results of LR, ANN and LBF-SVR models, with R2 of 0.998 and 0.989 for mass and volume estimation, respectively, which also showed a good agreement between actual and predicted values. These results revealed that SVR model was a promising tool for estimating the mass and volume of grape during storage.

کلیدواژه‌ها English

Coating
Image processing
Support vector machine
artificial neural network
Prediction
1. Prakash, B., Mathematical modeling of moisture movement within a rice kernel during convective and infrared drying. 2011, University of California, Davis.
2. Singh, S.K., S.K. Vidyarthi, and R. Tiwari, Machine learnt image processing to predict weight and size of rice kernels. Journal of Food Engineering, 2020. 274: p. 109828.
3. Wang, D., et al., Computer vision for bulk volume estimation of apple slices during drying. Drying Technology, 2017. 35(5): p. 616-624.
4. Soltani, M., M. Omid, and R. Alimardani, Egg volume prediction using machine vision technique based on pappus theorem and artificial neural network. Journal of food science and technology, 2015. 52(5): p. 3065-3071.
5. Martynenko, A. and M.A. Janaszek, Texture changes during drying of apple slices. Drying Technology, 2014. 32(5): p. 567-577.
6. Ganjloo, A., et al., Indirect Estimation of Mass and Shape Ratio Changes of Aloe vera gel Coated Cherry Tomatoes Using Image Processing Technique (In persian). Innovative Food Technologies (JIFT), (2021) In press.
7. Zandi, M., et al., Application of neural-fuzzy inference system (ANFIS) and fuzzy logic for prediction of physicochemical changes and classification of coated sweet lemon during storage (In persian). Iranian Food Science and Technology Research Journal, 2021. 17(2).
8. Zandi, M., A. Ganjloo, and M. Bimakr, Computer Vision System Applied to Classification of Medlar (Mespilus germanica) during ripening stage at cold storage (In persian). Innovative Food Technologies (JIFT), 2020. 7(3).
9. Su, Q., et al., Potato feature prediction based on machine vision and 3D model rebuilding. Computers and Electronics in Agriculture, 2017. 137: p. 41-51.
10. Vidyarthi, S.K., R. Tiwari, and S.K. Singh, Stack ensembled model to measure size and mass of almond kernels. Journal of Food Process Engineering, 2020. 43(4): p. e13374.
11. Vidyarthi, S.K., et al., Prediction of size and mass of pistachio kernels using random Forest machine learning. Journal of Food Process Engineering, 2020. 43(9): p. e13473.
12. Bejagam, K.K., et al., Machine-learned coarse-grained models. The journal of physical chemistry letters, 2018. 9(16): p. 4667-4672.
13. Halac, D., E. Sokic, and E. Turajlic. Almonds classification using supervised learning methods. in 2017 XXVI International Conference on Information, Communication and Automation Technologies (ICAT). 2017. IEEE.
14. Whan, A.P., et al., GrainScan: a low cost, fast method for grain size and colour measurements. Plant methods, 2014. 10(1): p. 23.
15. Su, Q., et al., Potato quality grading based on machine vision and 3D shape analysis. Computers and electronics in agriculture, 2018. 152: p. 261-268.
16. Vivek Venkatesh, G., et al., Estimation of volume and mass of axi-symmetric fruits using image processing technique. International Journal of Food Properties, 2015. 18(3): p. 608-626.
17. Nouri-Ahmadabadi, H., et al., Design, development and evaluation of an online grading system for peeled pistachios equipped with machine vision technology and support vector machine. Information Processing in Agriculture, 2017. 4(4): p. 333-341.
18. Nyalala, I., et al., Tomato volume and mass estimation using computer vision and machine learning algorithms: Cherry tomato model. Journal of Food Engineering, 2019. 263: p. 288-298.
19. Calixto, R.R., et al., A computer vision model development for size and weight estimation of yellow melon in the Brazilian northeast. Scientia Horticulturae, 2019. 256: p. 108521.
20. Utai, K., et al., Mass estimation of mango fruits (Mangifera indica L., cv.‘Nam Dokmai’) by linking image processing and artificial neural network. Engineering in Agriculture, Environment and Food, 2019. 12(1): p. 103-110.
21. Sheng, K., et al., Comparison of postharvest UV-B and UV-C treatments on table grape: Changes in phenolic compounds and their transcription of biosynthetic genes during storage. Postharvest Biology and Technology, 2018. 138: p. 74-81.
22. Zhou, X., et al., The biocontrol of postharvest decay of table grape by the application of kombucha during cold storage. Scientia Horticulturae, 2019. 253: p. 134-139.
23. Jia, X., et al., Storage quality of “Red Globe” table grape (Vitis vinifera L.): Comparison between automatic periodical gaseous SO2 treatments and MAP combined with SO2 pad. Journal of Food Processing and Preservation, 2020. 44(8): p. e14507.
24. Cazón, P., et al., Polysaccharide-based films and coatings for food packaging: A review. Food Hydrocolloids, 2017. 68: p. 136-148.
25. Joukar, F., et al., Effect of Farsi gum-based antimicrobial adhesive coatings on the refrigeration shelf life of rainbow trout fillets. LWT, 2017. 80: p. 1-9.
26. Dehghani, P., et al., Shelf-life extension of refrigerated rainbow trout fillets using total Farsi gum-based coatings containing clove and thyme essential oils emulsions. Food Hydrocolloids, 2018. 77: p. 677-688.
27. Shahbazi, Y. and N. Shavisi, Application of active Kurdi gum and Farsi gum-based coatings in banana fruits. Journal of Food Science and Technology, 2020: p. 1-11.
28. Chang, C.-C. and C.-J. Lin, LIBSVM: A library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2011. 2(3): p. 1-27.
29. Patel, A.K., S. Chatterjee, and A.K. Gorai, Development of a machine vision system using the support vector machine regression (SVR) algorithm for the online prediction of iron ore grades. Earth Science Informatics, 2019. 12(2): p. 197-210.
30. Qu, C., et al., A moisture content prediction model for deep bed peanut drying using support vector regression. Journal of Food Process Engineering, 2020: p. e13510.
31. Ciccarese, A., et al., Effectiveness of pre-and post-veraison calcium applications to control decay and maintain table grape fruit quality during storage. Postharvest Biology and Technology, 2013. 75: p. 135-141.
32. Khorram, F., A. Ramezanian, and S.M.H. Hosseini, Shellac, gelatin and Persian gum as alternative coating for orange fruit. Scientia Horticulturae, 2017. 225: p. 22-28.
33. Salarnia, M., et al., Physical, Barrier and Antimicrobial Properties of Sodium Caseinate-based Edible Film Containing Hemp Seed oil (in persian). journal of Innovative Food Technologies (JIFT) 2018. 5(3): p. 485-497.
34. Leizer, C., et al., The composition of hemp seed oil and its potential as an important source of nutrition. Journal of Nutraceuticals, functional & medical foods, 2000. 2(4): p. 35-53.
35. Cozmuta, A.M., et al., Preparation and characterization of improved gelatin films incorporating hemp and sage oils. Food Hydrocolloids, 2015. 49: p. 144-155.
36. Arendse, E., et al., Non-destructive characterization and volume estimation of pomegranate fruit external and internal morphological fractions using X-ray computed tomography. Journal of Food Engineering, 2016. 186: p. 42-49.
37. Pereira, T.M., P.D. Gaspar, and M.P. Simões. Fruit recognition and classification based on SVM method for production prediction of peaches. in IV Balkan Symposium on Fruit Growing. IV Balkan Symposium on Fruit Growing (BSFG 2019).
38. Siswantoro, J., M. Hilman, and M. Widiasri. Computer vision system for egg volume prediction using backpropagation neural network. in IOP Conference Series: Materials Science and Engineering. 2017.
39. Thipakorn, J., R. Waranusast, and P. Riyamongkol. Egg weight prediction and egg size classification using image processing and machine learning. in 2017 14th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON). 2017. IEEE.
40. Ziaratban, A., M. Azadbakht, and A. Ghasemnezhad, Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network. International Journal of Food Properties, 2017. 20(4): p. 762-768.