پیش‌بینی رطوبت و دانسیته در میگو طی سرخ‌کردن هوای داغ با مدل شبکه‌های عصبی مصنوعی

نویسندگان
بهاره معروف پور 1
امان محمد ضیائی فر 2
حسن صباغی 3
محمد قربانی 2
سعید یلقی 4
1 علوم کشاورزی و منابع طبیعی گرگان، گرگان
2 دانشگاه علوم کشاورزی و منابع طبیعی گرگان
3 استادیار، گروه علوم و مهندسی صنایع غذایی، دانشکده کشاورزی و دامپروری، مجتمع آموزش عالی تربت جام، تربت جام، استان خراسان رضوی، ایران
4 مرکز تحقیقات شیلات استان گلستان
10.22034/FSCT.22.161.121
چکیده
در این پژوهش، شبکه‌های عصبی مصنوعی (ANN) برای پیش‌بینی تغییرات رطوبت و دانسیته میگو طی فرآیند سرخ‌کردن هوای داغ (در سه دمای 140، 160 و 180 درجه سانتی‌گراد به مدت  15 دقیقه) ارائه گردید. شبکه‌های عصبی به صورت پرسپترون چند لایه (MLP) با تابع انتقال تانژانت سیگموئید در لایه پنهان و تابع انتقال خطی در لایه خروجی برای پیش‌بینی رطوبت (با دو ورودی: دما و زمان) و دانسیته (با سه ورودی: دما، زمان و رطوبت) در نرم افزار MATLAB طراحی شد. الگوریتم­های مختلف پس­انتشار شامل لونبرگ-مارکوارت، گرادیان نزولی، گرادیان نزولی با نرخ تطبیقی یادگیری، انتشار برگشتی با نرخ یادگیری متغییر، گرادیان نزولی با مومنتم وگرادیان مزدوج مقیاس‌شده بودند. ساختار مدل‌ها با محاسبه ضریب تبیین (R2)، ریشه میانگین مربعات خطا (RMSE) و میانگین خطای مطلق (MAE) اعتبار سنجی شد. در نهایت، اهمیت ورودی‌ها از نظر تاثیر بر متغیر خروجی برای پیش‌بینی رطوبت و دانسیته با طراحی شبکه‌های عصبی پیش فرض تانژانت هایپربولیک در نرم افزار SPSS  بررسی گردید. نتایج نشان داد که با کاهش رطوبت و توسعه منافذ در میگو، دانسیته محصول نیز طی سرخ‌کردن هوای داغ به تدریج کاهش یافت و با افزایش دمای فرآیند کاهش بیشتری در دانسیته مشاهده شد. در مدل رطوبت، الگوریتم پس انتشار گرادیان نزولی با مومنتم (R2=0.989, RMSE=0.171, MAE=0.131) و در مدل دانسیته، الگوریتم لونبرگ-مارکوارت (R2=0.974, RMSE=0.0096, MAE=0.0066) کمترین میزان خطا را در آزمون نشان دادند. در محاسبات عصبی رطوبت، اهمیت متغیر زمان و دما به ترتیب برابر با 883/0 و 117/0 بود. در محاسبات عصبی دانسیته نیز اهمیت متغیر رطوبت، زمان و دما به ترتیب برابر با 588/0، 278/0 و 134/0 بود. از یافته‌های این پژوهش در طراحی هوش مصنوعی برای کنترل و ایجاد اتوماسیون در سرخ‌کن‌های هوای داغ می‌توان استفاده کرد.
کلیدواژه‌ها
شبکه‌های عصبی مصنوعی
رطوبت
دانسیته
میگو
سرخ کردن هوای داغ

موضوعات

عنوان مقاله English

Prediction of moisture and density in shrimp during hot air frying with artificial neural networks model

نویسندگان English

Bahareh Maroufpour 1
Aman Mohammad Ziaiifar 2
Hassan Sabbaghi 3
Mohammad Ghorbani 2
Saeed Yalghi 4
1 Gorgan University of Agricultural Sciences and Natural Resources
2 Gorgan University of Agricultural Sciences and Natural Resources
3 Assistant Professor, Department of Food Science and Technology, Faculty of Agriculture and Animal Science, University of Torbat-e Jam, Torbat-e Jam, Razavi Khorasan Province, Iran
4 Golestan Province Fisheries Research Center
چکیده English

In this research, artificial neural networks (ANN) was presented to predict changes in moisture and density of shrimp during hot air frying process (at three temperatures of 140, 160 and 180 degrees Celsius for 15 minutes). Neural networks in the form of multilayer perceptron (MLP) with sigmoid tangent transfer function in the hidden layer and linear transfer function in the output layer was designed to predict moisture (with two inputs: temperature and time) and density (with three inputs: temperature, time and moisture) in MATLAB software. Different backpropagation algorithms include Levenberg-Marquardt, Gradient descent, Gradient descent with adaptive learning rate, Adaptive learning rate backpropagation, Gradient descent with momentum, and Scaled conjugate gradient. The structure of the models was validated by calculating the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE). Finally, the importance of the inputs in terms of the effect on the output variable for predicting moisture and density was investigated by designing the default hyperbolic tangent neural networks in SPSS software. The results showed that with the decrease in moisture and the development of pores in shrimp, the density of the product gradually decreased during hot air frying, and with the increase in the temperature of the process, a further decrease in density was observed. In the moisture model, the backpropagation algorithm of Gradient descent with momentum (R2=0.989, RMSE=0.171, MAE=0.131) and in the density model, the Levenberg-Marquardt algorithm (R2=0.974, RMSE=0.0096, MAE=0.0066) showed the minimum error in testing. In the moisture neurocomputing, the importance of time and temperature variable was equal to 0.883 and 0.117, respectively. In the density neurocomputing, the importance of moisture, time and temperature variables were 0.588, 0.278 and 0.134, respectively. The Findings can be used in the design of artificial intelligence for controlling and creating automation in hot air fryers.

کلیدواژه‌ها English

artificial neural networks
moisture
Density
Shrimp
Hot air frying
Zaghi, A. N., Barbalho, S. M., Guiguer, E. L., & Otoboni, A. M. (2019). Frying Process: From Conventional to Air Frying Technology. Food Reviews International, 35(8), 763-777.
Santos, C. S., Cunha, S. C., & Casal, S. (2017). Deep or air frying? A comparative study with different vegetable oils. European Journal of Lipid Science and Technology, 119(6), 1600375.
Andrés, A., Arguelles, Á., Castelló, M. L., & Heredia, A. (2013). Mass transfer and volume changes in French fries during air frying. Food and Bioprocess Technology, 6(8), 1917-1924.
Teruel, M. D. R., Gordon, M., Linares, M. B., Garrido, M. D., Ahromrit, A., & Niranjan, K. (2015). A comparative study of the characteristics of french fries produced by deep fat frying and air frying. Journal of Food Science, 80(2), E349-E358.
Heredia, A., Castelló, M. L., Argüelles, A., & Andrés, A. (2014). Evolution of mechanical and optical properties of French fries obtained by hot air-frying. LWT-Food Science and Technology, 57(2), 755-760.
Giovanelli, G., Torri, L., Sinelli, N., & Buratti, S. (2017). Comparative study of physico-chemical and sensory characteristics of French fries prepared from frozen potatoes using different cooking systems. European Food Research and Technology, 243(9), 1619-1631.
Czech, A., Grela, E. R., & Ognik, K. (2015). Effect of frying on nutrients content and fatty acid composition of muscles of selected freezing seafoods. Journal of Food and Nutrition Research, 3(1), 9-14.
Akuamoa, F., Odamtten, G. T., & Kortei, N. K. (2018). Nutritional and shelf-life studies of dry smoked and gamma irradiated shrimps (Penaeus notialis) from three different water sources in Ghana. Cogent Food & Agriculture, 4(1), 1505803.
Jeyasantha, K. I., & Patterson, J. (2017). Effect of formulated feed on the biochemical composition of cultured shrimp, Penaeus monodon (Fabricius, 1798). International Journal of Fisheries and Aquatic Research, 2, 15-22.
Ali, S. S. R., Ramachandran, M., Chakma, S. K., & Sheriff, M. A. (2017). Proximate composition of commercially important marine fishes and shrimps from the Chennai coast, India. International Journal of Fisheries and Aquatic Studies, 5(5), 113-119.
Dincer, M. T., & Aydin, I. (2014). Proximate composition and mineral and fatty acid profiles of male and female jinga shrimps (Metapenaeus affinis, H. Milne Edwards, 1837). Turkish Journal of Veterinary & Animal Sciences, 38(4), 445-451.
Dayal, J. S., Ponniah, A. G., Khan, H. I., Babu, E. M., Ambasankar, K., & Vasagam, K. K. (2013). Shrimps–a nutritional perspective. Current science, 1487-1491.
Peralta, E. M., Hatate, H., Watanabe, D., Kawabe, D., Murata, H., Hama, Y., & Tanaka, R. (2005). Antioxidative activity of Philippine salt-fermented shrimp and variation of its constituents during fermentation. Journal of Oleo Science, 54(10), 553-558.
Sabbaghi, H., Ziaiifar, A. M., Sadeghi, A. R., Kashaninejad, M., and Mirzaei, H. (2017). Kinetic modeling of color changes in french fries during frying process. Journal of Food Technology and Nutrition, 14(1), 65-76.
Niamnuy, C., Devahastin, S., Soponronnarit, S., & Raghavan, G. V. (2008). Modeling coupled transport phenomena and mechanical deformation of shrimp during drying in a jet spouted bed dryer. Chemical Engineering Science, 63(22), 5503-5512.
Sabbaghi H, Ziaifar, AM, and Kashaninejad M. (2017). Mechanical study for texture degradation of potato strip during frying process. Iranian Food Science and Technology Research Journal, 13(1): 92-104.
Erdoǧdu, F., Balaban, M. O., & Otwell, W. S. (2003). Construction of shrimp cooking charts using previously developed mathematical models for heat transfer and yield loss predictions. Journal of food engineering, 60(1), 107-110.
Sabbaghi H, Ziaiifar AM, and Kashaninejad M. (2020). Textural profile analysis (TPA) of dried apple slices using infrared radiation with intermittent heating method. Iranian Food Science and Technology Research Journal 16(1): 57-72.
Bhagya Raj, G. V. S., & Dash, K. K. (2022). Comprehensive study on applications of artificial neural network in food process modeling. Critical reviews in food science and nutrition, 62(10), 2756-2783.
Ferreira, F. S., Sampaio, G. R., Keller, L. M., Sawaya, A. C., Chávez, D. W., Torres, E. A., & Saldanha, T. (2017). Impact of air frying on cholesterol and fatty acids oxidation in sardines: Protective effects of aromatic herbs. Journal of food science, 82(12), 2823-2831.
Joshy, C. G., Ratheesh, G., Ninan, G., Kumar, K. A., & Ravishankar, C. N. (2020). Optimizing air-frying process conditions for the development of healthy fish snack using response surface methodology under correlated observations. Journal of Food Science and Technology, 1-8.
Yu, X., Li, L., Xue, J., Wang, J., Song, G., Zhang, Y., & Shen, Q. (2020). Effect of air-frying conditions on the quality attributes and lipidomic characteristics of surimi during processing. Innovative Food Science & Emerging Technologies, 60, 102305.
Fang, M., Huang, G. J., & Sung, W. C. (2021). Mass transfer and texture characteristics of fish skin during deep-fat frying, electrostatic frying, air frying and vacuum frying. Lwt, 137, 110494.
Ahmad, I., Jeenanunta, C., Chanvarasuth, P., & Komolavanij, S. (2014). Prediction of physical quality parameters of frozen shrimp (Litopenaeus vannamei): an artificial neural networks and genetic algorithm approach. Food and bioprocess technology, 7(5), 1433-1444.
AOAC. (1995). Official methods of analysis, 16th ed. Association of Official Analytical Chemists, Washington, DC, Unites States.
Sabbaghi, H., Ziaiifar, A. M., Sadeghi Mahoonak, A., Kashani-Nejad, M., & Mirzaee, H. (2015). Estimation of convective heat transfer coefficient as function of the water loss rate during frying process. Iranian Food Science and Technology Research Journal, 11(4), 473-484.
Yan, Z., Sousa-Gallagher, M. J., & Oliveira, F. A. (2008). Shrinkage and porosity of banana, pineapple and mango slices during air-drying. Journal of Food Engineering, 84(3), 430-440.
Sabbaghi, H., Ziaiifar, A. M., & Kashaninejad, M. (2021). Estimation of shrinkage and rehydration in apple slices dried by infrared radiation using intermittent heating method. Food Research Journal, 31(4), 35-49.
Mayor, L., & Sereno, A. (2004). Modelling shrinkage during convective drying of food materials: a review. Journal of Food Engineering, 61(3), 373-386.
Gouyo, T., Mestres, C., Maraval, I., Fontez, B., Hofleitner, C., & Bohuon, P. (2020). Assessment of acoustic-mechanical measurements for texture of French fries: Comparison of deep-fat frying and air frying. Food Research International, 131, 108947.
Kim, D. S., Lee, J. H., & Shin, H. J. (2023). Optimization of Vacuum Frying Process for Sweet Potato Chip Manufacturing Using Response Surface Methodology and Artificial Neural Network Model. Biotechnology and Bioprocess Engineering, 28(4), 554-567.
Samuel, O. D., & Okwu, M. O. (2019). Comparison of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) in modelling of waste coconut oil ethyl esters production. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 41(9), 1049-1061.
Duran, M., Pedreschi, F., Moyano, P., and Troncoso, E. (2007). Oil partition in pre-treated potato slices during frying and cooling, Journal of Food Engineering, 81:257-265.
Ziaiifar, A.M., Heyd, B., and Courtois, F. (2009). Investigation of effective thermal conductivity kinetics of crust and core regions of potato during deep-fat frying using a modified Lees method. Journal of Food Engineering, 95: 373-378.
Krokida, M.K., Oreopoulou, V., Maroulis, Z.B., and Marinos-Kouris, D. (2001). Effects of osmotic dehydration pretreatment on quality of French fries. Journal of Food Engineering, 49: 339-345.
Pedreschi, F., Herna´ ndez, P., Figueroa, C., and Moyano, P.C. (2005). Modeling water loss during frying of potato slices. International Journal of Food Properties, 8: 289-299.
Pan, G., Ji, H., Liu, S., & He, X. (2015). Vacuum frying of breaded shrimps. LWT-Food Science and Technology, 62(1), 734-739.
Yang, D., Wu, G., Lu, Y., Li, P., Qi, X., Zhang, H., ... & Jin, Q. (2021). Comparative analysis of the effects of novel electric field frying and conventional frying on the quality of frying oil and oil absorption of fried shrimps. Food Control, 128, 108195.
Costa, R.M., Oliveira, F.A.R., Delaney, O., and Gekas, V. (1999). Analysis of the heat transfer coefficient during potato frying, Journal of Food Engineering, 39:293-299.
Farkas, B.E., and Hubbard, L.J. (2000). Analysis of convective heat transfer during immersion frying, Drying Technology, 18: 1269-1285.
Krokida, M. K., Oreopoulou, V., & Maroulis, Z. B. (2000). Effect of frying conditions on shrinkage and porosity of fried potatoes. Journal of food engineering, 43(3), 147-154.
Pinthus, E. J., Weinberg, P., & Saguy, I. S. (1995). Oil uptake in deep fat frying as affected by porosity. Journal of Food Science, 60(4), 767-769.
Mittal, G. S., & Zhang, J. (2001). Artificial neural network for the prediction of temperature, moisture and fat contents in meatballs during deep‐fat frying. International journal of food science & technology, 36(5), 489-497.
Math, R. G., Velu, V., Nagender, A., & Rao, D. G. (2004). Effect of frying conditions on moisture, fat, and density of papad. Journal of Food Engineering, 64(4), 429-434.