تخمین ماندگاری تخم مرغ در شرایط نگهداری مختلف با استفاده از شبکه عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم و مهندسی صنایع غذایی، دانشگاه زنجان

2 دانشیار، گروه علوم و مهندسی صنایع غذایی، دانشکده کشاورزی، دانشگاه زنجان

3 استادیار و هیأت‌علمی گروه شیمی، دانشگاه زنجان، زنجان، ایران

4 گروه فیزیک، دانشگاه تحصیلات تکمیلی علوم پایه زنجان

10.22034/fr.2025.59254.1909

چکیده

تعیین ماندگاری تخم‌مرغ در شرایط مختلف نگهداری نه تنها در سلامت مصرف کننده بلکه در کیفیت محصولات غذایی تهیه شده بر پایه تخم‌مرغ نیز از اهمیت زیادی برخوردار است. در این پژوهش به دنبال آن هستیم با استفاده از نتایج ارزیابی تجربی ماندگاری تخم‌مرغ در دمای اتاق و دمای یخچال، با کمک مدل سازی شبکه عصبی مصنوعی، ماندگاری تخم‌مرغ در شرایط دمایی مختلف تعیین شود. در این پژوهش، 160 تخم‌مرغ سالم و تازه جمع‌آوری شدند. آنگاه خصوصیات ظاهری تخم‌مرغ‌ها با استفاده از پردازش تصویر محاسبه شدند. آنگاه تخم‌مرغ ها به دو گروه تقسیم و در دمای اتاق و یخچال نگهداری شدند. آنگاه خصوصیات کیفی تخم‌مرغ مورد بررسی قرار گرفتند. با کمک نتایج تجربی، شبکه عصبی توسعه داده شد. اگرچه روند تغییرات کیفیت تخم‌مرغ در هر دو دما یکسان بود ولی در تمام این فراسنجه‌ها، نرخ تغییرات در دمای اتاق بیشتر از فراسنجه مذکور در دمای یخچال بود. تخم‌مرغ‌های نگهداری شده در دمای یخچال در طی 56 روز نگهداری در محدوده کیفیت AA باقی می مانند ولی تخم‌مرغ های نگهداری شده در دمای اتاق پس از یک هفته نگهداری دارای کیفیت A هستند و پس از دو هفته وارد محدوده B می شوند. براساس یافته های این پژوهش مشخص شد شبکه عصبی با تابع انتقال تانژانت اکسون خطی و الگوریتم لونبرگ مارکویت در لایه ورودی و تابع انتقال تانژانت اکسون خطی و الگوریتم مومنتوم در لایه خروجی با یک لایه پنهان و 4 گره دارای کمترین مجموع مربعات خطا بود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Estimation of egg shelf life in different storage conditions using artificial neural network

نویسندگان [English]

  • Fatemeh Koulivand 1
  • Iman Shahabi-Ghahfarrokhi 2
  • Rahmatollah Pourata 3
  • Ali-Reza Moradi 4
1 Department of Food Science and Engineering, University of Zanjan, Zanjan
2 Associate Professor, Dept. of Food Science and Engineering, Faculty of Agriculture, University of Zanjan
3 Assistant Professor. Department of Chemistry, Faculty of Science, University of Zanjan،Zanjan, Iran
4 Department of Physics, Institute for Advanced Studies in Basic Sciences
چکیده [English]

Introduction: Eggs have always been considered a high-quality and affordable source of animal protein. Determining the shelf life of eggs under different storage conditions is crucial not only for consumer health but also for the quality of food products made with eggs. While the guidelines from the country's veterinary organization and the national standard of Iran set the refrigerator shelf life for eggs at approximately 30 days, most eggs in the country are stored outside the refrigerator during distribution. Therefore, it is necessary to evaluate the shelf life of eggs both inside and outside the refrigerator, identify the factors influencing it, and assess their extent of impact. Additionally, many egg evaluation tests are destructive and time-consuming, requiring significant resources. Hence, modeling techniques can play a significant role in reducing costs and expediting the determination of egg shelf life under various conditions. This research aims to determine the shelf life of eggs in different temperature conditions by employing artificial neural network modeling based on the experimental evaluation of eggs stored at room temperature and in the refrigerator.
Materials and methods: In this study, 160 healthy and fresh eggs were collected from a laying hen farm. The eggs' visual characteristics, including shape index, number of shell pores, and their respective areas, were assessed by illuminating the eggs from behind and capturing images at an angle of approximately 180 degrees relative to the light source. The obtained images were analyzed using ImageJ software to calculate these features. Subsequently, the eggs were randomly divided into two groups of 80. The first group was stored at room temperature (22.5±2.5 degrees Celsius) and a humidity range of 27 to 32%, while the second group was stored in the refrigerator (6.5±2.5 degrees Celsius) and a humidity range of 55 to 85%. Over an 8-week period, eggs were randomly sampled at 7-day intervals with 10 repetitions. The eggs' quality characteristics were then examined based on qualitative parameters such as weight loss, Haugh unit, yolk index, and air sac depth. Artificial neural network modeling was subsequently employed using the experimental results to predict egg quality. A multi-layer perceptron neural network was developed, consisting of an input layer with five neurons (temperature, storage time, shape index, number of pores, and pore area) and an output layer with four neurons (Haugh unit, yolk index, weight loss, and air sac depth). A total of 1440 data points were utilized for training the artificial neural network, with 60% for training, 25% for evaluation, and 15% for validation. The artificial neural network was trained using four transfer functions (tangent, sigmoid, linear axon tangent, and linear sigmoid) and two learning algorithms (Levenberg-Marquardt and Momentum). The network with the lowest mean squared error was selected as the optimal network through trial and error. Lastly, a sensitivity test was conducted to measure the influence of each input on the artificial neural network's output predictions.
Results and discussion: The research findings indicated that the visual characteristics of eggs in the two groups (room temperature and refrigerator temperature) did not significantly differ. However, the qualitative parameters of eggs stored at room temperature and refrigerator temperature exhibited significant differences throughout the storage period. Both temperature conditions showed similar trends in parameter changes, but the rate of change was higher for eggs stored at room temperature. Eggs stored in the refrigerator for 56 days remained within the AA quality range based on the Haugh unit. In contrast, eggs stored at room temperature entered the A quality range after one week of storage and the B range after two weeks. Regarding air sac depth, eggs stored at room temperature entered the B quality range after one week, while eggs stored in the refrigerator entered the B quality range after three weeks. The optimal artificial neural network consisted of a linear tangent transfer function and the Levenberg-Marquardt algorithm in the input layer, and a linear tangent transfer function and the Momentum algorithm in the output layer, with a single hidden layer containing four nodes. Under this configuration, the artificial neural network achieved a correlation coefficient of 0.96 for weight loss, 0.94 for yolk index, 0.93 for air sac depth, and 0.88 for the Haugh unit, enabling the prediction of these quality parameters. Temperature and storage duration exerted the greatest influence on the quality parameters, with the Haugh unit being strongly affected by storage temperature.
Conclusion:The research results indicate that eggs stored at room temperature can maintain the desired quality for a maximum of one week, while eggs stored in the refrigerator can easily preserve the desired quality for up to a month. Moreover, the use of artificial neural network modeling can effectively predict the quality characteristics of eggs under different storage conditions. a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a a

کلیدواژه‌ها [English]

  • Prediction
  • Egg
  • Artificial neural network
  • Shelf life

Akyurek, H., & Okur, A. A. 2009. Effect of storage time, temperature and hen age on egg quality in free-range layer hens. Journal of Animal and Veterinary Advances, 8(10): 1953–1958.

Al-Hajo, N. N., Zangana, B. S., Al-Janabi, L. A., & Al-Khalani, F. 2012a. Effect of coating materials (gelatin) and storage time on internal quality of chicken and quail eggs under refrigerated storage. Egyptian Poultry Science Journal, 32: 107–115.

Al-Hajo, N. N., Zangana, B. S., Al-Janabi, L. A., & Al-Khalani, F. 2012b. Effect of coating materials (gelatin) and storage time on internal quality of chicken and quail eggs under refrigerated storage. Egyptian Poultry Science, 32: 107–115.

Biladeau, A., & Keener, K. 2009. The effects of edible coatings on chicken egg quality under refrigerated storage. Poultry Science, 88(6): 1266–1274.

Caner, C. 2005. Whey protein isolate coating and concentration effects on egg shelf life. Journal of the Science of Food and Agriculture, 85(13): 2143–2148.

Caner, C., & Cansiz, O. 2007. Effectiveness of chitosan-based coating in improving shelf-life of eggs. Journal of the Science of Food and Agriculture, 87(2): 227–232.

Commission, E. 2008. Commission Regulation (EC) No. 589/2008 of 23 June 2008 laying down detailed rules for implementing Council Regulation (EC) No. 1234/2007 as regards marketing standards for eggs. Official Journal of the European Union, 50: 6–23.

De Ketelaere, B., Bamelis, F., Kemps, B., Decuypere, E., & De Baerdemaeker, J. 2004. Non-destructive measurements of the egg quality. World's Poultry Science Journal, 60(3): 289–302.

Duman, M., Sekeroglu, A., Yildirim, A., Eleroglu, H., & Camci, O. 2016. Relation between egg shape index and egg quality characteristics. European Poultry Science, 80(1): 1–9.

Food and Agriculture Organization of the United Nations. 2023. FAOSTAT. [Online]. Available: https://www.fao.org/faostat/en/#home

Ghazanfari, S., Nobari, K., & Tahmoorespur, M. 2011. Prediction of egg production using artificial neural network.

Goyal, S., & Goyal, G. K. 2012. Shelf life estimation of processed cheese by artificial neural network expert systems. Journal of Advanced Computer Science and Technology, 1(1): 32–41.

Grashorn, M., Juergens, A., & Bessei, W. 2016. Effects of storage conditions on egg quality. Lohmann Information, 50: 22–27.

Hauver, W. E. 1961. Egg grading manual. US Department of Agriculture, Agricultural Marketing Service.

Haykin, S. 2010. Neural networks: a comprehensive foundation. McMillan, New Jersey.

Institute of Standards and Industrial Research of Iran. 2007. Preparation and storage of edible egg – Code of practice (Vol. 3676). Tehran.

Institute of Standards and Industrial Research of Iran. 2010. Code of hygienic practice for eggs and egg products (Vol. 5013).

Iran Veterinary Organization. 2019. National Program for Improving the Quality and Safety Assurance of Eggs (Vol. IVO/20/98).

Jahangir-Esfahani, H., Soltanizadeh-Gargari, I., & Pourata, R. 2021. Investigation into extending shelf life of chicken eggs using UV-C irradiated starch-oleic acid coating solutions. Journal of Food Research (Agricultural Science), 31: 67–81.

Menhaj, M. B. 2017. Fundamentals of neural networks.

Mine, Y., Guyonnet, V., Hatta, H., & Nau, N. 2023. Handbook of Egg Science and Technology (1st ed.).

Narushin, V., Romanov, M. N., & Bogatyr, V. 2002. AP–animal production technology: relationship between pre-incubation egg parameters and chick weight after hatching in layer breeds. Biosystems Engineering, 83(3): 373–381.

Nematinia, E., & Abdanan Mehdizadeh, S. 2018. Assessment of egg freshness by prediction of Haugh unit and albumen pH using an artificial neural network. Journal of Food Measurement and Characterization, 12(3): 1449–1459.

Nematinia, E., & Mehdizadeh, S. A. 2018. Assessment of egg freshness by prediction of Haugh unit and albumen pH using an artificial neural network. Journal of Food Measurement and Characterization, 12(3): 1449–1459.

No, H., Meyers, S. P., Prinyawiwatkul, W., & Xu, Z. 2007. Applications of chitosan for improvement of quality and shelf life of foods: a review. Journal of Food Science, 72(5): R87–R100.

Norusis, M. J. 1993. SPSS. SPSS Incorporated.

Pekel, E., & Kara, S. S. 2017. A comprehensive review for artificial neural network application to public transportation. Sigma Journal of Engineering and Natural Sciences, 35(1): 157–179.

Pescatore, T., & Jacob, J. 2011. Grading table eggs. University of Kentucky Cooperative Extension, Lexington.

RANJBAR, M., ALIJANI, S., MIRGHELENJ, S., & DAGHIGHKIA, H. 2015. Estimation of genetic and phenotypic parameters for internal egg quality traits of Azerbaijan native chickens.

Seregély, Z., Farkas, J., Tuboly, E., & Dalmadi, I. 2006. Investigating the properties of egg white pasteurised by ultra-high hydrostatic pressure and gamma irradiation by evaluating their NIR spectra and chemosensor array sensor signal responses using different methods of qualitative analysis. Chemometrics and Intelligent Laboratory Systems, 82(1–2): 115–121.

Shahram, M., Ghanbarzadeh, B., Souti, M., Qiyasi Far, S., & Jalali, S. H. 2012. The use of edible active coatings based on carboxymethyl cellulose containing oleic acid and antimicrobial compounds to improve the quality and increase the shelf life of eggs. Iranian Food Science and Technology Research Journal, 8(2): 235–244.

Siyar, S. H., Aliarabi, H., Ahmadi, A., & Ashori, N. 2007. Effect of different storage conditions and hen age on egg quality parameters. Proceedings of the 19th Australian Poultry Science Symposium, Sydney, New South Wales, Australia, 12–14 February 2007.

Soltani, M., Omid, M., & Alimardani, R. 2015. Egg quality prediction using dielectric and visual properties based on artificial neural network. Food Analytical Methods, 8(3): 710–717.

Statistical Centre of Iran. 2020. Summary of the census of chicken farms breeding laying hens.

Suktanarak, S., & Teerachaichayut, S. 2017. Non-destructive quality assessment of hens' eggs using hyperspectral images. Journal of Food Engineering, 215: 97–103.

Suppakul, P., Jutakorn, K., & Bangchokedee, Y. 2010. Efficacy of cellulose-based coating on enhancing the shelf life of fresh eggs. Journal of Food Engineering, 98(2): 207–213.

Tabidi, M. H. 2011. Impact of storage period and quality on composition of table egg. Advances in Environmental Biology, 5(5): 856–861.

Tajik, H., Aminzare, Y., & Moradi, M. 2010. Effects of edible zein and chitosan coating assimilated by oregano essential oil on the quality parameters of egg. Journal of Food Research (Agricultural Science), 20(3): 73–90.

Torrico, D. D. 2010. Effects of emulsion coatings on the internal quality and shelf life of eggs.

Vojdani, F., & Torres, J. A. 1990. Potassium sorbate permeability of methylcellulose and hydroxypropyl methylcellulose coatings: Effect of fatty acids. Journal of Food Science, 55(3): 841–846.

Wardy, W., Torrico, D. D., Herrera Corredor, J. A., No, H. K., Zhang, X., Xu, Z., & Prinyawiwatkul, W. 2013. Soybean oil‐chitosan emulsion affects internal quality and shelf‐life of eggs stored at 25 and 4 C. International Journal of Food Science & Technology, 48(6): 1148–1156.

Wardy, W., Torrico, D. D., No, H. K., Prinyawiwatkul, W., & Saalia, F. K. 2010. Edible coating affects physico‐functional properties and shelf life of chicken eggs during refrigerated and room temperature storage. International Journal of Food Science & Technology, 45(12): 2659–2668.