بررسی کارایی شبکه‌های عصبی مصنوعی در پیش‌بینی ویژگی‌های فیزیکی، رئولوژیکی و رنگ‌سنجی نانوذرات کیتوزان

نویسندگان
الهام آل‌حسینی 1
سید مهدی جعفری 2
هدی شهیری طبرستانی 3
1 گروه مهندسی مواد و طراحی صنایع غذایی، دانشکده صنایع غذایی، دانشگاه علوم کشاورزی و منابع طبیعی گرگان، گرگان، ایران
2 استاد، گروه مهندسی مواد و طراحی صنایع غذایی، دانشکده صنایع غذایی، دانشگاه علوم کشاورزی و منابع طبیعی گرگان، گرگان، ایران
3 استادیار، گروه شیمی مواد غذایی، دانشکده صنایع غذایی، دانشگاه علوم کشاورزی و منابع طبیعی گرگان، گرگان، ایران
10.52547/fsct.18.113.77
چکیده
تشکیل نانوذرات کیتوزان با پایداری بالا به منظور استفاده در سیستم‌های تحویل مواد مغذی و دارویی، همچنان یک چالش عمده در صنایع غذایی و دارویی است. همچنین متغیرهای زیادی می‌توانند اندازه، مورفولوژی و سایر ویژگی‌های نانوذرات کیتوزان را در طی فرایند ژله‌ای شدن یونی و با استفاده از سدیم تری‌پلی‌فسفات (به عنوان متداول‌ترین عامل اتصال عرضی)، تحت تأثیر قرار دهند. لذا در این پژوهش، پس از تولید نانوذرات کیتوزان تحت تأثیر متغیرهای مستقل غلظت کیتوزان، غلظت سدیم تری‌پلی‌فسفات و نسبت کیتوزان به سدیم تری‌پلی‌فسفات، در گام بعدی، ویژگی‌های فیزیکی، رئولوژیکی، کدورت و رنگ‌سنجی نانوذرات تولیدی مورد اندازه‌گیری قرار گرفتند. در نهایت، از دو شبکه عصبی مصنوعی مدل پرسپترون چند لایه و شبکه تابع پایه‌‌ی شعاعی با یک لایه پنهان و با توابع آستانه، الگوریتم‌های یادگیری و ... مختلف، به منظور پیش‌بینی ویژگی‌های نانوذرات کیتوزان استفاده شد. نتایج نشان داد که شبکه عصبی پرسپترون چند لایه برای ویژگی‌های فیزیکی، ویسکوزیته، شاخص b* و chroma و شبکه تابع پایه شعاعی برای دیگر ویژگی‌های مورد بررسی (با بکارگیری الگوریتم یادگیری لونبرگ- مارکوارت و تعداد تکرار 1000)، قادر به پیش‌بینی آن‌ها با ضرایب تعیین بسیار بالا و میانگین مربعات خطای پایین بود. ضرایب تعیین برای اندازه نانوذرات، شاخص پراکندگی، پتانسیل زتا، ویسکوزیته و ضریب هدایت الکتریکی سوسپانسیون‌های نانوذرات کیتوزان به ترتیب برابر با 9881/0، 9534/0، 9431/0، 9212/0 و 9636/0 بودند. این در حالی بود که شبکه‌ی تابع پایه شعاعی با یک لایه پنهان، چیدمانی با 3 ورودی، 4 نرون در لایه پنهان و 3 خروجی، با تابع انتقال سیگموئید- سیگموئید، بهترین نتیجه را برای پیش‌بینی ویژگی‌های L*، ΔE و WI سوسپانسیون‌های نانوذرات کیتوزان داشت. ضرایب تعیین برای پیش‌بینی L*، ΔE و WI نانوذرات کیتوزان به ترتیب برابر با 9586/0، 9775/0 و 9457/0بودند. همچنین شاخص رفتار جریان سوسپانسیون‌های نانوذرات‌ کیتوزان کمتر از 1 بود که نشان دهنده رفتار سودوپلاستیک نمونه‌ها بود.
کلیدواژه‌ها
نانوذرات کیتوزان
مدل پرسپترون چند لایه
مدل تابع پایه شعاعی
ویژگی‌های فیزیکی
پارامترهای رنگ‌سنجی

موضوعات

عنوان مقاله English

Evaluating the performance of artificial neural networks (ANNs) for predicting the physical, rheological, and colorimetric properties of chitosan nanoparticles (CSNPs)

نویسندگان English

Elham Alehosseini 1
Seid Mahdi Jafari 2
Hoda Shahiri Tabarestani 3
1 Department of Food Materials and Process Design Engineering, Faculty of Food Science and Technology, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
2 Professor, Department of Food Materials and Process Design Engineering, Faculty of Food Science and Technology, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
3 Assistant Professor, Department of Food Chemistry, Faculty of Food Science and Technology, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
چکیده English

The formation of chitosan nanoparticles (CSNPs) with a high stability still remains a main challenge in terms of applying the produced particles in the field of nutraceutical and drug delivery systems. Giving that there are many variables parameters which could affect the size, morphology, and other properties of fabricated CSNPs during ionic gelation process along with using sodium tripolyphosphate (STPP) as the most common cross-linking agent. In this study, after the production of CSNPs under the influence of various independent variables such as chitosan (CS) concentration, STPP concentration, and CS to STPP ratio, in the next step, the physical, rheological, turbidity, and colorimetric properties of the produced nanoparticles were measured. Finally, two artificial neural networks (ANNs) – multilayer perceptron (MLP) and radial basis function (RBF) – with a single hidden layer and different threshold functions, learning algorithms, etc. were employed to predict the CSNPs properties. The results revealed that MLP for the physical, viscosity, b*, and chroma properties and RBF for other properties – with a Levenberg-Marquardt (LM) learning algorithm of 1000 epochs – well predict them with a very high determination coefficients (R2) and low mean square error (MSE). R2 for nanoparticle size, poly dispersity index (PDI), zeta potential, viscosity, and electrical conductivity of CSNPs suspensions were determined 0.9881, 0.9534, 0.9431, 0.9212, and 0.9636, respectively. However, RBF with a single hidden layer comprising a set of 3 inputs, 4 neurons in hidden layer, and 3 outputs with the SigmoidAxon- SigmoidAxon transfer function presented the best results for predicting the L*, ΔE, and WI properties of CSNPs suspensions. In addition, R2 for L*, ΔE, and WI of CSNPs were calculated 0.9586, 0.9775, and 0.9457, respectively. Also, the flow behavior index of CSNPs suspensions was determined less than 1, which indicates the pseudoplastic behavior of the samples.

کلیدواژه‌ها English

Chitosan nanoparticles (CSNPs)
Multilayer perceptron (MLP) model
Radial base function (RBF) model
Physical properties
Colorimetric parameters
[1] Shah, B.R., Y. Li, W. Jin, Y. An, L. He, Z. Li, W. Xu, and B. Li. 2016. Preparation and optimization of Pickering emulsion stabilized by chitosan-tripolyphosphate nanoparticles for curcumin encapsulation. Materials Science and Engineering. 52: 369-377.
[2] Vozza, G., M. Khalid, H.J. Byrne, S.M. Ryan, and J.M. Frias. 2019. Nutraceutical formulation, characterisation, and in-vitro evaluation of methylselenocysteine and selenocystine using food derived chitosan:zein nanoparticles. Food Research International. 120: 295-304.
[3] Maleki, G. and J.M. Milani. 2020. Chapter 6 - Functional properties of chitin and chitosan-based polymer materials, in Handbook of Chitin and Chitosan, S. Gopi, S. Thomas, and A. Pius, Editors, Elsevier. p. 177-198.
[4] Xia, W., P. Liu, J. Zhang, and J. Chen. 2011. Biological activities of chitosan and chitooligosaccharides. Food Hydrocolloids. 25(2): 170-179.
[5] Aranaz, I., M. Mengíbar, R. Harris, I. Paños, B. Miralles, N. Acosta, G. Galed, and Á. Heras. 2009. Functional characterization of chitin and chitosan. Current chemical biology. 3(2): 203-230.
[6] Akbari-Alavijeh, S., R. Shaddel, and S.M. Jafari. 2020. Encapsulation of food bioactives and nutraceuticals by various chitosan-based nanocarriers. Food Hydrocolloids. 105: 105774.
[7] Zhang, C., Y. Ding, Q. Ping, and L. Yu. 2006. Novel chitosan-derived nanomaterials and their micelle-forming properties. Journal of agricultural food chemistry. 54(22): 8409-8416.
[8] Baruch, L. and M. Machluf. 2006. Alginate–chitosan complex coacervation for cell encapsulation: Effect on mechanical properties and on long‐term viability. Biopolymers: Original Research on Biomolecules. 82(6): 570-579.
[9] Asada, M., H. Takahashi, H. Okamoto, H. Tanino, and K. Danjo. 2004. Theophylline particle design using chitosan by the spray drying. International Journal of pharmaceutics. 270(1-2): 167-174.
[10] Ribeiro, A.J., C. Silva, D. Ferreira, and F. Veiga. 2005. Chitosan-reinforced alginate microspheres obtained through the emulsification/internal gelation technique. European journal of pharmaceutical sciences. 25(1): 31-40.
[11] Lee, M., Y.W. Cho, J.H. Park, H. Chung, S.Y. Jeong, K. Choi, D.H. Moon, S.Y. Kim, I.-S. Kim, and I.C. Kwon. 2006. Size control of self-assembled nanoparticles by an emulsion/solvent evaporation method. Colloid Polymer Science. 284(5): 506-512.
[12] Mudhakir, D., C. Wibisono, and H. Rachmawati. 2014. Encapsulation of Risperidone into Chitosan-based Nanocarrier via Ionic Binding Interaction. Procedia Chemistry. 13: 92-100.
[13] Wu, J., Y. Wang, H. Yang, X. Liu, and Z. Lu. 2017. Preparation and biological activity studies of resveratrol loaded ionically cross-linked chitosan-TPP nanoparticles. Carbohydrate Polymers. 175: 170-177.
[14] Nair, R.S., A. Morris, N. Billa, and C.-O. Leong. 2019. An Evaluation of Curcumin-Encapsulated Chitosan Nanoparticles for Transdermal Delivery. AAPS PharmSciTech. 20(2): 69.
[15] Al-Nemrawi, N., S. Alsharif, and R. Dave. 2018. Preparation of chitosan-TPP nanoparticles: the influence of chitosan polymeric properties and formulation variables. International Journal of Applied Pharmaceutics. 10(5): 60-65.
[16] Shah, B.R., C. Zhang, Y. Li, and B. Li. 2016. Bioaccessibility and antioxidant activity of curcumin after encapsulated by nano and Pickering emulsion based on chitosan-tripolyphosphate nanoparticles. Food Research International. 89: 399-407.
[17] Fan, W., W. Yan, Z. Xu, and H. Ni. 2012. Formation mechanism of monodisperse, low molecular weight chitosan nanoparticles by ionic gelation technique. Colloids surfaces B: Biointerfaces. 90: 21-27.
[18] Csaba, N., M. Köping-Höggård, and M.J. Alonso. 2009. Ionically crosslinked chitosan/tripolyphosphate nanoparticles for oligonucleotide and plasmid DNA delivery. International journal of pharmaceutics. 382(1-2): 205-214.
[19] Pillai, C.K.S., W. Paul, and C.P. Sharma. 2009. Chitin and chitosan polymers: Chemistry, solubility and fiber formation. Progress in Polymer Science. 34(7): 641-678.
[20] Laplante, S., S.L. Turgeon, and P. Paquin. 2005. Emulsion stabilizing properties of various chitosans in the presence of whey protein isolate. Carbohydrate Polymers. 59(4): 425-434.
[21] Ribeiro, E.F., J. Borreani, G. Moraga, V.R. Nicoletti, A. Quiles, and I. Hernando. 2020. Digestibility and Bioaccessibility of Pickering Emulsions of Roasted Coffee Oil Stabilized by Chitosan and Chitosan-Sodium Tripolyphosphate Nanoparticles. Food Biophysics. 15(2): 196-205.
[22] Hadidi, M., S. Pouramin, F. Adinepour, S. Haghani, and S.M. Jafari. 2020. Chitosan nanoparticles loaded with clove essential oil: Characterization, antioxidant and antibacterial activities. Carbohydrate Polymers. 236: 116075.
[23] de Carvalho, F.G., T.C. Magalhães, N.M. Teixeira, B.L.C. Gondim, H.L. Carlo, R.L. dos Santos, A.R. de Oliveira, and Â.M.L. Denadai. 2019. Synthesis and characterization of TPP/chitosan nanoparticles: Colloidal mechanism of reaction and antifungal effect on C. albicans biofilm formation. Materials Science and Engineering: C. 104: 109885.
[24] Yegnanarayana, B. 2009. Artificial neural networks. PHI Learning Pvt. Ltd.
[25] Fausett, L.V. 2006. Fundamentals of neural networks: architectures, algorithms and applications. Pearson Education India.
[26] Walczak, S. 2019. Artificial neural networks, in Advanced Methodologies and Technologies in Artificial Intelligence, Computer Simulation, and Human-Computer Interaction, IGI Global. p. 40-53.
[27] Caccavo, D. 2019. An overview on the mathematical modeling of hydrogels’ behavior for drug delivery systems. International Journal of Pharmaceutics. 560: 175-190.
[28] Liu, J. 2013. Radial Basis Function (RBF) neural network control for mechanical systems: design, analysis and Matlab simulation. Springer Science & Business Media.
[29] Priddy, K.L. and P.E. Keller. 2005. Artificial neural networks: an introduction. Vol. 68: SPIE press.
[30] Calvo, P., C. Remunan‐Lopez, J.L. Vila‐Jato, and M. Alonso. 1997. Novel hydrophilic chitosan‐polyethylene oxide nanoparticles as protein carriers. Journal of Applied Polymer Science. 63(1): 125-132.
[31] Rezaeinia, H., B. Ghorani, B. Emadzadeh, and N. Tucker. 2019. Electrohydrodynamic atomization of Balangu (Lallemantia royleana) seed gum for the fast-release of Mentha longifolia L. essential oil: Characterization of nano-capsules and modeling the kinetics of release. Food Hydrocolloids. 93: 374-385.
[32] Alehosseini, A., M. Sarabi-Jamab, B. Ghorani, and R. Kadkhodaee. 2019. Electro-encapsulation of Lactobacillus casei in high-resistant capsules of whey protein containing transglutaminase enzyme. LWT. 102: 150-158.
[33] Wang, X.-Y. and M.-C. Heuzey. 2016. Chitosan-based conventional and Pickering emulsions with long-term stability. J Langmuir. 32(4): 929-936.
[34] Ghasemi, S., S.M. Jafari, E. Assadpour, and M. Khomeiri. 2018. Nanoencapsulation of d-limonene within nanocarriers produced by pectin-whey protein complexes. Food Hydrocolloids. 77: 152-162.
[35] Ojagh, S.M., M. Rezaei, S.H. Razavi, and S.M.H. Hosseini. 2010. Development and evaluation of a novel biodegradable film made from chitosan and cinnamon essential oil with low affinity toward water. Food Chemistry. 122(1): 161-166.
[36] Alehosseini, E. 2013. Modeling of the effect of cleaning, moisture, and temperature on the quantitative and qualitative characteristics of wheat and application of artificial neural networks (ANN) to predict the related indicators, in Department of Food Science and Technology, Islamic Azad University: Science and Research Branch.
[37] Hashad, R.A., R.A.H. Ishak, S. Fahmy, S. Mansour, and A.S. Geneidi. 2016. Chitosan-tripolyphosphate nanoparticles: Optimization of formulation parameters for improving process yield at a novel pH using artificial neural networks. International Journal of Biological Macromolecules. 86: 50-58.
[38] Bozuyuk, U., N.O. Dogan, and S. Kizilel. 2018. Deep insight into PEGylation of bioadhesive chitosan nanoparticles: Sensitivity study for the key parameters through artificial neural network model. ACS applied materials interfaces. 10(40): 33945-33955.
[39] Esmaeilzadeh-Gharedaghi, E., M.A. Faramarzi, M.A. Amini, A. Rouholamini Najafabadi, S.M. Rezayat, and A. Amani. 2012. Effects of processing parameters on particle size of ultrasound prepared chitosan nanoparticles: An Artificial Neural Networks Study. Pharmaceutical development technology. 17(5): 638-647.
[40] Youshia, J., M.E. Ali, and A. Lamprecht. 2017. Artificial neural network based particle size prediction of polymeric nanoparticles. European Journal of Pharmaceutics and Biopharmaceutics. 119: 333-342.
[41] Heidari, E., M.A. Sobati, and S. Movahedirad. 2016. Accurate prediction of nanofluid viscosity using a multilayer perceptron artificial neural network (MLP-ANN). Chemometrics and Intelligent Laboratory Systems. 155: 73-85.
[42] Hezave, A.Z., M. Lashkarbolooki, and S. Raeissi. 2012. Using artificial neural network to predict the ternary electrical conductivity of ionic liquid systems. Fluid Phase Equilibria. 314: 128-133.
[43] Abdou, E.S., A. Osheba, and M. Sorour. 2012. Effect of chitosan and chitosan-nanoparticles as active coating on microbiological characteristics of fish fingers. International Journal of Applied. 2(7).
[44] Gaya, M., M. Zango, L. Yusuf, M. Mustapha, B. Muhammad, A. Sani, A. Tijjani, N. Wahab, and M. Khairi. 2017. Estimation of turbidity in water treatment plant using Hammerstein-Wiener and neural network technique. Indonesian Journal of Electrical Engineering Computer Science. 5(3): 666-672.
[45] Marić, L., E. Malešić, A. Jurinjak Tušek, M. Benković, D. Valinger, T. Jurina, and J. Gajdoš Kljusurić. 2020. Effects of drying on physical and chemical properties of root vegetables: Artificial neural network modelling. Food and Bioproducts Processing. 119: 148-160.
[46] Gürgen, A., E. Topaloğlu, D. Ustaömer, S. Yıldız, and N. Ay. 2019. Prediction of the colorimetric parameters and mass loss of heat-treated bamboo: Comparison of multiple linear regression and artificial neural network method. Color research and application. 44(5): 824-833.
[47] Alehossein, E., S.M. Jafari, A. Motamedzadegan, and A. Alehossein. 2016. Evaluation of artificial neural networks (ANNs) in predicting the effects of cleaning, moisture content, temperature and time on the physical and microbial characteristics of wheat. Journal of Food Research (Agricultural Science). 26(4): 577-588.
[48] Alehosseini, A., M. Sarabi Jamab, B. Ghorani, R. Kadkhodaee, and S. Wongsasulak. 2017. Evaluating the performance of artificial neural networks (ANNs) for predicting the effect of polymer concentration and operating voltage on the physical properties of electrosprayed particles. Innovative food technologies. 4(4): 31-43.