خشک کردن کف‌پوشی پنیر ریکوتا و پیش‌بینی ویژگی‌های آن با مدل شبکه عصبی مصنوعی

نویسندگان
زهرا باقری 1
علی معتمدزادگان 2
رضا خان بابائی 3
ایوب فرهادی 4
1 کارشناس ارشد صنایع غذایی دانشگاه علوم کشاورزی و منابع طبیعی ساری
2 عضو هیئت علمی گروه صنایع غذایی دانشگاه علوم کشاورزی و منابع طبیعی ساری
3 استادیار گروه فیزیک دانشگاه صنعتی نوشیروانی بابل
4 دانشیار گروه علوم دامی دانشگاه علوم کشاورزی و منابع طبیعی ساری
10.52547/fsct.18.115.20
چکیده
شبکه‌های عصبی مصنوعی مجموعه‌ای از معادلات غیرخطی هستند که توانایی برای خود سازگاری دارد تا ارتباطات غیرخطی پیچیده بین متغیرهای ورودی و خروجی را برقرار کنند. از مدل‌سازی شبکه عصبی مصنوعی برای پیشگوئی جهت تهیه پودر پنیر ریکوتا با کیفیت مطلوب استفاده شد. در این پژوهش، شبکه عصبی مصنوعی 4 کلاسه با مدل پرسپترون چندلایه برای پیش‌بینی داده‌های کف و پودر پنیر ریکوتا که به روش خشک کردن کف‌پوشی تهیه شدند، مورد استفاده قرار گرفت. این مدل‌سازی با روش شناسایی الگو و با استفاده از الگوریتم یادگیری ماشین انجام شد. شناسایی الگو، توانایی تشخیص ترتیب خصوصیات یا داده‌هایی است که اطلاعات مربوط به سیستم یا مجموعه داده‌ها را می‌دهد. مدل مورد استفاده برای این پژوهش دارای 10 نرون در لایه پنهان بود. 4 نسبت متفاوت شیر و آب‌پنیر (تیمارها) به عنوان ورودی و دانسیته کف، دانسیته پودر، هیگروسکوپی، فعالیت آبی، جذب آب و جذب روغن به عنوان خروجی‌های مدل در نظر گرفته شدند. در این مدل 70 درصد از داده‌ها برای آموزش، 15 درصد برای آزمایش و 15 درصد از داده‌ها برای اعتبارسنجی مورد استفاده قرار گرفت. بهترین عملکرد اعتبارسنجی در دوره 20 رخ داد. نتایج نهایی نشان داد که مدل مورد استفاده با دقت 8/94 درصد توانست داده‌های مربوط به هر کلاس را به درستی پیش‌بینی نماید.
کلیدواژه‌ها
خشک کردن کف‌پوشی
ریکوتا
شبکه عصبی مصنوعی
شناسایی الگو
مدل‌سازی

موضوعات

عنوان مقاله English

Foam Mat Drying of Ricotta Cheese and Predicting its Characteristics with Artificial Neural Network Model

نویسندگان English

Zahra Bagheri 1
Ali Motamedzadegan 2
Reza Khanbabaie 3
Ayoub Farhadi 4
1 Department of Food Science and Technology, Sari Agricultural Sciences and Natural Resources University
2 Department of Food Science and Technology, Sari Agricultural Sciences and Natural Resources University
3 Department of Physics, Babol Noushirovani University of Technology
4 Department of Animal Sciences, Sari Agricultural Sciences and Natural Resources University
چکیده English

Artificial neural networks are a set of nonlinear equations that have the ability to adapt to establish complex nonlinear relationships between input and output variables. Artificial neural network modeling was used to predict the production of Ricotta cheese powder with the desired quality. In this study, a 4-class artificial neural network with a multilayer perceptron model was used to predict foam and Ricotta cheese powder data prepared by foam mat drying. This modeling was performed by pattern recognition method and using machine learning algorithm. Pattern recognition is the ability to recognize the order of properties or data that gives information about a system or data set. The model used for this study had 10 neurons in the hidden layer. 4 different ratios of milk and whey (treatments) were considered as input and foam density, powder density, hygroscopy, water activity, water absorption and oil absorption as model outputs. In this model, 70% of the data were used for training, 15% for testing and 15% of the data for validation. The best validation performance occurred in the 20th period. The final results showed that the model used was able to accurately predict the data related to each class with 94.8% accuracy.

کلیدواژه‌ها English

artificial neural network
foam mat drying
Modeling
pattern recognition
Ricotta
[1] Moatamedzadegan, A., & Ghodratighoroghi, H. (2005). Investigation of dairy wastewater status and energy consumption in dairy factories in Mazandaran province. Milk Festival North of country.
]2] Najafi, H., & Moatamedzadegan, A. (2010). Process Optimization of Ricotta Cheese According to Iranian Preferences. Journal of Agricultural Science and Technology, 3, 237-240.
]3] Fernandes, M.d.S., Fujimoto, G., Schneid, I., Kabuki, D.Y., Kuaye, A.Y. (2014). Enterotoxigenic Profile, Antimicrobial Susceptibility And Biofilm Formation Of Bacillus Cereus Isolated From Ricotta Processing, International Dairy Journal.
]4] Azizpour, M., Mohebbi, M., & Khodaparast, M. H. H. (2016). Effects of foam-mat drying temperature on physico-chemical and microstructural properties of shrimp powder. Innovative Food Science & Emerging Technologies, 34, 122-126.
]5] Lobo, F. A., Nascimento, M. A., Domingues, J. R., Falcão, D. Q., Hernanz, D., Heredia, F. J., & de Lima Araujo, K. G. (2017). Foam mat drying of Tommy Atkins mango: Effects of air temperature and concentrations of soy lecithin and carboxymethylcellulose on phenolic composition, mangiferin, and antioxidant capacity. Food chemistry, 221, 258-266.
]6] Banakar, A., & Akandi, S. K. (2012). Genetic algorithm optimizing approach in rosa petals hot air dryer. International Journal of Agricultural and Food Science, 2(3), 60-65.
]7] Tripathy, P. P., & Kumar, S. (2009). Neural network approach for food temperature prediction during solar drying. International journal of thermal sciences, 48(7), 1452-1459.
]8] Ata, R. (2015). RETRACTED: Artificial neural networks applications in wind energy systems: a review.
]9] Raharitsifa, N., & Ratti, C. (2010). Foam‐mat freeze‐drying of apple juice part 1: Experimental data and ANN simulations. Journal of Food Process Engineering, 33, 268-283.
]10] Bishop, C. M. (2006). Pattern recognition and machine learning. Springer Science+ Business Media.
]11] Vásquez, N., Magán, C., Oblitas, J., Chuquizuta, T., Avila-George, H., & Castro, W. (2018). Comparison between artificial neural network and partial least squares regression models for hardness modeling during the ripening process of Swiss-type cheese using spectral profiles. Journal of Food Engineering, 219, 8-15.
]12] Khawas, P., Dash, K. K., Das, A. J., & Deka, S. C. (2016). Modeling and optimization of the process parameters in vacuum drying of culinary banana (Musa ABB) slices by application of artificial neural network and genetic algorithm. Drying Technology, 34(4), 491-503.
]13] Fadaie M, Hosseini Ghaboos S H, Beheshti B. Characterization of Dried Persimmon using Infrared Dryer and Process Modeling using Genetic Algorithm-Artificial Neural Network Method. FSCT. 2020; 17 (100) :189-200.
]14] Salehi, F., Abasi Shahkooh, Z., & Goodarzi, M. (2015). Characteristics of dried persimmon using infrared dryer and process modeling by genetic algorithm-artificial neural network method. Journal of Innovation in Food Science and Technology, 7(1), 65-76.
]15] Moatamedzadegan, A., & Habibi, M. (2001). Optimization of Ricotta cheese processing according to Iranian taste. Journal of Technology and Agricultural Sciences, 3, 237-240.
]16] Azizpour, M., Mohebbi, M., Yolmeh, M., Abbasi, E., & Sangatash, M. M. (2017). Effects of different hydrocolloids on foaming properties of shrimp puree: a cluster analysis. Journal of Food Measurement and Characterization, 11(4), 1892-1898.
]17] Erbay, Z., & Koca, N. (2015). Effects of whey or maltodextrin addition during production on physical quality of white cheese powder during storage. Journal of dairy science, 98(12), 8391-8404.
]18] Da Silva, D. F., Ahrne, L., Larsen, F. H., Hougaard, A. B., & Ipsen, R. (2018). Physical and functional properties of cheese powders affected by sweet whey powder addition before or after spray drying. Powder Technology, 323, 139-148.
]19] Sathivel, S., Bechtel, P. J., Babbitt, J. K., Prinyawiwatkul, W., & Patterson, M. (2005). Functional, nutritional, and rheological properties of protein powders from arrowtooth flounder and their application in mayonnaise. Journal of Food Science, 70(2), E57-E63.
]20] Shahidi, F., & Zhong, Y. (2005). Lipid oxidation: measurement methods. Bailey's industrial oil and fat products.
]21] Santhalakshmy, S., Bosco, S. J. D., Francis, S., & Sabeena, M. (2015). Effect of inlet temperature on physicochemical properties of spray-dried jamun fruit juice powder. Powder Technology, 274, 37-43.
]22] Németh, P., Ladinig, T. B., & Ferenczi, B. (2016). Use of Artificial Neural Networks in the Production Control of Small Batch Production. In Proceedings on the International Conference on Artificial Intelligence (ICAI) (p. 237). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp).
]23] Altunok, E., Taha, M. M. R., Epp, D. S., Mayes, R. L., & Baca, T. J. (2006). Damage pattern recognition for structural health monitoring using fuzzy similarity prescription. Computer‐Aided Civil and Infrastructure Engineering, 21(8), 549-560.
]24] Khashei, M., Bijari, M., & Mokhatab Rafiei, F. (2014). Variable selection in multilayer perceptron neural networks for prediction using self-organizing scripts (SOM). Computational Methods in Engineering, 33(1), 125-139.
]25] Martínez-Padilla, L. P., García-Rivera, J. L., Romero-Arreola, V., & Casas-Alencáster, N. B. (2015). Effects of xanthan gum rheology on the foaming properties of whey protein concentrate. Journal of Food Engineering, 156, 22-30.
]26] Rahmani, S. (2018). Evaluation the effect of milk /whey ratio and drying temperature on physicochemical and sensory characteristics of dried ricotta cheese by using foam mat drying. Master thesis. Sari Agricultural Sciences and Natural Resources.Sari. Iran. 76.
]27] Kockel, T. K., Allen, S., Hennigs, C., & Langrish, T. A. G. (2002). An experimental study of the equilibrium for skim milk powder at elevated temperatures. Journal of Food Engineering, 51(4), 291-297.
]28] Kaur, M., & Singh, N. (2005). Studies on functional, thermal and pasting properties of flours from different chickpea (Cicer arietinum L.) cultivars. Food chemistry, 91(3), 403-411.
]29] Adebowale, K. O., & Lawal, O. S. (2004). Comparative study of the functional properties of bambarra groundnut (Voandzeia subterranean), jack bean (Canavalia ensiformis) and mucuna bean (Mucuna pruriens) flours. Food Research International, 37(4), 355-365.
]30] Jangam, S. V., & Mujumdar, A. S. (2010). Basic concepts and definitions. Drying of foods, vegetables and fruits, 1, 1-30.
]31] O'Sullivan, J. J., Schmidmeier, C., Drapala, K. P., O'Mahony, J. A., & Kelly, A. L. (2017). Monitoring of pilot-scale induction processes for dairy powders using inline and offline approaches. Journal of Food Engineering, 197, 9-16.
]32] Schuck, P. (2011). Milk powder: physical and functional properties of milk powders.
]33] Thankitsunthorn, S., Thawornphiphatdit, C., Laohaprasit, N., & Srzednicki, G. (2009). Effects of drying temperature on quality of dried Indian Gooseberry powder. International food research journal, 16(3), 355-361.
]34] Fellows, P. J. (2009). Food processing technology: principles and practice. Elsevier.
]35] Basha, S. M., & Rajput, D. S. (2018). Fitting a Neural Network Classification Model in MATLAB and R for Tweeter Data set. In Proceedings of International Conference on Recent Advancement on Computer and Communication (pp. 11-18). Springer, Singapore.