بررسی کارایی شبکه‌های عصبی مصنوعی در پیش‌بینی تأثیر غلظت پلیمر و ولتاژ فرایند الکتروپاشش بر ویژگی‌های فیزیکی ذرات

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکترای مهندسی مواد و طراحی صنایع غذایی، پژوهشکده علوم و صنایع غذایی، مشهد، ایران

2 استادیار، گروه زیست فناوری مواد غذایی، پژوهشکده علوم و صنایع غذایی، مشهد، ایران

3 استادیار، گروه نانوفناوری مواد غذایی، پژوهشکده علوم و صنایع غذایی، مشهد، ایران

4 دانشیار، گروه نانوفناوری مواد غذایی، پژوهشکده علوم و صنایع غذایی، مشهد، ایران

5 استادیار، گروه مهندسی مواد غذایی، دانشگاه کینگ مونگکات، بانکوک، تایلند

چکیده

با توجه به حساسیت ترکیبات زیست فعال، به تازگی استفاده از روش نوین پاشش الکتروهیدرودینامیکی جهت ریزپوشانی این ترکیبات پیشنهاد شده است. پارامترهای مؤثر بر اندازه و مورفولوژی ذرات تولیدی به دلیل تأثیری که بر حفاظت ترکیبات زیست فعال و رهایش کنترل شده آنها در مکان و زمان مناسب دارند، از اهمیت فراوانی برخوردارند. از اینرو در مطالعه حاضر ابتدا اثرات میزان غلظت کنسانتره پروتئین آب پنیر، صمغ عربی، شیر خشک و ولتاژ روی برخی از ویژگی‌های فیزیکی محلول پلیمری و اندازه ذرات تولیدی به روش پاشش الکتروهیدرودینامیکی تعیین شد و سپس توسط مدل شبکه‌ی عصبی مصنوعی پرسپترون چند لایه و شبکه با تابع پایه‌ی شعاعی شبیه‌سازی گردید. این دو مدل همراه با توابع آستانه‌ی مختلف در پیش‌بینی مقادیر ویسکوزیته، کشش سطحی، هدایت الکتریکی محلول پلیمری و اندازه کپسول‌های تولیدی مورد استفاده قرار گرفتند. نتایج نشان داد که مدل شبکه‌ی پرسپترون چند لایه متشکل از چیدمانی با پنج ورودی و یک لایه مخفی حاوی 4 نرون با تابع فعال‌سازی تانژانت هیپربولیک که با استفاده از الگوریتم یادگیری لونبرگ-مارکوارت و تعداد تکرار 1000 آموزش دیده بود، بهترین نتیجه را برای پیش‌بینی این ویژگی‌ها در مقایسه با شبکه‌ی تابع پایه‌ی شعاعی بدست داد. ضرایب تبیین اندازه ذرات تولیدی، ویسکوزیته، کشش سطحی و هدایت الکتریکی محلول به ترتیب برابر با 958/0، 991/0، 996/0 و 967/0 بودند. آنالیز حساسیت مقادیر پیش‌بینی شده توسط شبکه‌ی عصبی پرسپترون چند لایه در برابر مقادیر تجربی حاکی از قرار گرفتن داده‌ها به طور تصادفی در اطراف خط رگرسیونی با ضریب تبیین بالا بود که دلیلی بر دقت بالای شبکه‌ی عصبی در پیش‌بینی داده‌های خروجی می‌باشد. شایان ذکر است که اندازه ذرات تولیدی، ویسکوزیته و هدایت الکتریکی محلول پلیمری با بالا رفتن غلظت پلیمرهای به کار رفته افزایش یافت و تمامی سطوح اختلاف آماری معنی‌دار (05/0< P) داشتند. نتایج به دست آمده در این مطالعه، به منظور پیش‌بینی اثرات عوامل اشاره شده بر ویژگی‌های فیزیکی محلول هیدروکلوئیدی و ذرات تولیدی در جهت انتخاب مناسبترین ترکیب دیواره، با در نظر داشتن هدف از ریزپوشانی ترکیب زیست فعال، اهمیت کاربردی دارند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

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

نویسندگان [English]

  • Ali Alehosseini 1
  • Mahboobe Sarabi Jamab 2
  • Behrouz Ghorani 3
  • Rassoul Kadkhodaee 4
  • Saowakon Wongsasulak 5
1 PhD. Student of Food Materials and Process Design Engineering, Department of Food Nanotechnology, Research Institute of Food Science & Technology, Mashhad, Iran
2 Assistant Professor, Department of Food Biotechnology, Research Institute of Food Science & Technology (RIFST), Mashhad, Iran
3 Assitant Professor, Department of Food Nanotechnology, Research Institute of Food Science & Technology
4 Associate Professor, Department of Food Nanotechnology, Research Institute of Food Science & Technology
5 Assitant Professor, Department of Food Engineering, King Mongkut’s University of Technology Thonburi (KMUTT), Bangkok, Thailand
چکیده [English]

Electrohydrodynamic atomization has recently been introduced as a safe method for encapsulation of sensitive bioactive compounds. In this regard, the parameters affecting the size and morphology of particles, owing to their key role in the protection and controlled release of bioactive compounds, are of paramount importance. In this study the influence of whey protein concentrate (WPC), gum Arabic and skim milk concentration as well as the operating voltage on the size and morphology of electrosprayed particles was investigated and the experimental data were then used for simulation of the process using two feed-forward artificial neural networks: multilayer perceptron and radial basis function networks. These models along with different threshold functions were employed to predict the viscosity, surface tension, electrical conductivity of polymers solutions, and the size of particles. The results showed that multilayer perceptron network comprising a set of 5 inputs and a single hidden layer containing 4 neurons with hyperbolic tangent activation function which was trained by Levenberg-Marquardt (LM) learning algorithm at 1000 epochs predicted the desired outputs more accurately than the radial basis function network. The determination coefficients (R2) for particles size, viscosity, surface tension, and electrical conductivity of polymers solutions were found to be 0.958, 0.9991, 0.996 and 0.967, respectively. Examination of the sensitivity analysis diagram of the predicted values by multilayer perceptron neural network versus experimental data revealed random scattering of points in the close proximity of the regression line with a high determination coefficient which clearly verifies the high accuracy of the model in predicting the outputs. It should be noted that size of particles as well as viscosity and electrical conductivity of solutions significantly increased with the rise of polymers concentration (p < 0.05). The findings of this study may be of useful to predict the impact of the above-mentioned parameters on the physical properties of polymer solutions and the fabricated particles in order to select the most appropriate wall materiel based on the purpose of encapsulation of bioactive compounds.

کلیدواژه‌ها [English]

  • Electrohydrodynamic Atomization
  • Artificial neural network
  • Multilayer Perceptron Model
  • Radial Basis Function Model
  • Physical Properties
 

[1]  Biesalski, H.-K., Dragsted, L.O., Elmadfa, I., Grossklaus, R., Müller, M., Schrenk, D., Walter, P., and Weber, P. 2009. Bioactive compounds: definition and assessment of activity. Nutrition (Burbank, Los Angeles County, Calif.), 25: 1202-5.

[2]  Laelorspoen, N., Wongsasulak, S., Yoovidhya, T., and Devahastin, S. 2014. Microencapsulation of Lactobacillus acidophilus in zein–alginate core–shell microcapsules via electrospraying. Journal of Functional Foods, 7: 342-349.

[3]  Krasaekoopt, W., Bhandari, B., and Deeth, H. 2003. Evaluation of encapsulation techniques of probiotics for yoghurt. International Dairy Journal, 13: 3-13.

[4]  Ghorani, B., Alehosseini, A., and Tucker, N. 2016. Electrospinning as a novel delivery vehicle for bioactive compounds in food nanotechnology, in Innovative processing technologies for foods with bioactive compounds, J.J. Moreno, Editor. CRC Press. p. 259- 292.

[5]  Ghorani, B., Kadkhodai, R., and Alehosseini, A. 2017. The effect of biopolymer type, temperature and relative humidity on the physicochemical characteristics and stability of Microencapsulated bioactive compounds of saffron. Food Science and Technology Iran Journal, 14: 127-142 (In Persian).

[6]  Solanki, H.K., Pawar, D.D., Shah, D.A., Prajapati, V.D., Jani, G.K., Mulla, A.M., and Thakar, P.M. 2013. Development of microencapsulation delivery system for long-term preservation of probiotics as biotherapeutics agent. BioMed research international, 2013: 620719.

[7]  López-Rubio, A. and Lagaron, J.M. 2012. Whey protein capsules obtained through electrospraying for the encapsulation of bioactives. Innovative Food Science & Emerging Technologies, 13: 200-206.

[8]  Doherty, S.B., Gee, V.L., Ross, R.P., Stanton, C., Fitzgerald, G.F., and Brodkorb, A. 2011. Development and characterisation of whey protein micro-beads as potential matrices for probiotic protection. Food Hydrocolloids, 25: 1604-1617.

[9]  Gilbert, V., Rouabhia, M., Wang, H., Arnould, A.-L., Remondetto, G., and Subirade, M. 2005. Characterization and evaluation of whey protein-based biofilms as substrates for in vitro cell cultures. Biomaterials, 26: 7471-7480.

[10]  Gunasekaran, S., Ko, S., and Xiao, L. 2007. Use of whey proteins for encapsulation and controlled delivery applications. Journal of Food Engineering, 83: 31-40.

[11]  Desmond, C., Ross, R.P., O'Callaghan, E., Fitzgerald, G., and Stanton, C. 2002. Improved survival of Lactobacillus paracasei NFBC 338 in spray-dried powders containing gum acacia. Journal of Applied Microbiology, 93: 1003-1011.

[12]  McNamee, B.F., O’Riordan, E.D., and O’Sullivan, M. 2001. Effect of partial replacement of gum arabic with carbohydrates on its microencapsulation properties. Journal of Agriculture and Food Chemistry, 49: 3385-3388.

[13]  López-Rubio, A., Sanchez, E., Wilkanowicz, S., Sanz, Y., and Lagaron, J.M. 2012. Electrospinning as a useful technique for the encapsulation of living bifidobacteria in food hydrocolloids. Food Hydrocolloids, 28: 159-167.

[14]  Philips, G., Ogasawara, T., and Ushida, K. 2008. The regulatory and scientific approach to defining gum Arabic as a diatery fiber. Food Hydrocolloids, 22: 24-35.

[15]  Chavarri, M., Maranon, I., and Carmen, M. 2012. Encapsulation technology to protect probiotic bacteria. Probiotics. InTech. 501-540.

[16]  Hernández-Rodríguez, L., Lobato-Calleros, C., Pimentel-González, D.J., and Vernon-Carter, E.J. 2014. Lactobacillus plantarum protection by entrapment in whey protein isolate: κ-carrageenan complex coacervates. Food Hydrocolloids, 36: 181-188.

[17]  López-Rubio, A. and Lagaron, J.M. 2011. Improved incorporation and stabilisation of β-carotene in hydrocolloids using glycerol. Food Chemistry, 125: 997-1004.

[18]  Pérez-Masiá, R., López-Nicolás, R., Periago, M.J., Ros, G., Lagaron, J.M., and López-Rubio, A. 2015. Encapsulation of folic acid in food hydrocolloids through nanospray drying and electrospraying for nutraceutical applications. Food chemistry, 168: 124-33.

[19]  Pérez-Masiá, R., Lagaron, J.M., and Lopez-Rubio, A. 2015. Morphology and stability of edible lycopene-containing micro-and nanocapsules produced through electrospraying and spray drying. Food and Bioprocess Technology, 8: 459-470.

[20]  Rayleigh, L. 1882. XX. On the equilibrium of liquid conducting masses charged with electricity. Philosophical Magazine Series 5, 14: 184-186.

[21]  Jaworek, A. 2007. Micro- and nanoparticle production by electrospraying. Powder Technology, 176: 18-35.

[22]  Ghorani, B. and Tucker, N. 2015. Fundamentals of electrospinning as a novel delivery vehicle for bioactive compounds in food nanotechnology. Food Hydrocolloids, 51: 227-240.

[23]  Jaworek, A. and Sobczyk, A.T. 2008. Electrospraying route to nanotechnology: An overview. Journal of Electrostatics, 66: 197-219.

[24]  Anu Bhushani, J. and Anandharamakrishnan, C. 2014. Electrospinning and electrospraying techniques: Potential food based applications. Trends in Food Science & Technology, 38: 21-33.

[25]  Pérez-Masiá, R., Lagaron, J.M., and López-Rubio, A. 2014. Development and optimization of novel encapsulation structures of interest in functional foods through electrospraying. Food and Bioprocess Technology, 7: 3236-3245.

[26]  Nieuwland, M., Geerdink, P., Brier, P., van den Eijnden, P., Henket, J.T.M.M., Langelaan, M.L.P., Stroeks, N., van Deventer, H.C., and Martin, A.H. 2013. Food-grade electrospinning of proteins. Innovative Food Science & Emerging Technologies, 20: 269-275.

[27]  Wongsasulak, S., Kit, K.M., McClements, D.J., Yoovidhya, T., and Weiss, J. 2007. The effect of solution properties on the morphology of ultrafine electrospun egg albumen–PEO composite fibers. Polymer, 48: 448-457.

[28]  Gomez-Mascaraque, L.G., Morfin, R.C., Pérez-Masiá, R., Sanchez, G., and Lopez-Rubio, A. 2016. Optimization of electrospraying conditions for the microencapsulation of probiotics and evaluation of their resistance during storage and in-vitro digestion. LWT - Food Science and Technology, 69: 438-446.

[29]  Xie, J., Lim, L.K., Phua, Y., Hua, J., and Wang, C.-H. 2006. Electrohydrodynamic atomization for biodegradable polymeric particle production. Journal of Colloid and Interface Science, 302: 103-112.

[30]  Bakhshi, P.K., Nangrejo, M.R., Stride, E., and Edirisinghe, M. 2012. Application of electrohydrodynamic technology for folic acid encapsulation. Food and Bioprocess Technology, 6: 1837-1846.

[31]  Haykin, S. and Lippmann, R. 1994. Neural networks, a comprehensive foundation. International journal of neural systems, 5(4): 363-364.

[32]  Sajikumar, N. and Thandaveswara, B. 1999. A non-linear rainfall–runoff model using an artificial neural network. Journal of Hydrology, 216(1): 32-55.

[33]  Wesolowski, M. and Suchacz, B. 2012. Artificial neural networks: theoretical background and pharmaceutical applications: a review. Journal of AOAC International, 95(3): 652-668.

[34]  Chatterjee, S.P. and Pandya, A.S. 2015. Artificial Neural Networks in Drug Transport Modeling and SimulationeII. Artificial Neural Network for Drug Design, Delivery and Disposition: 243.

[35]  Amiri Chaijan, R., Khosh Taghaza, M., Montazer, G., Minaee, S., and Alizadeh, M. 2009. Estimation of head rice yield using artificial neural networks for fluidized bed drying of rough rice. JWSS-Isfahan University of Technology, 13(48): 285-298.

[36]  Mokhtarian, M. and Zenoozian, M.S. 2011. Predicting of osmotic dehydration kinetics of pumpkin by means of intelligent artificial neural network in static situation. J. Food Sci. Technol, 3: 61-73.

[37]  Koç, M.L., Özdemir, Ü., and İmren, D. 2008. Prediction of the pH and the temperature-dependent swelling behavior of Ca2+-alginate hydrogels by artificial neural networks. Chemical engineering science, 63(11): 2913-2919.

[38]  Shahsavari, S., Shirmard, L.R., Amini, M., and Dokoosh, F.A. 2016. Application of Artificial Neural Networks in the Design and Optimization of a Nanoparticulate Fingolimod Delivery System Based on Biodegradable Poly (3-Hydroxybutyrate-Co-3-Hydroxyvalerate). Journal of Pharmaceutical Sciences.

[39]  Hashad, R.A., Ishak, R.A., Fahmy, S., Mansour, S., and Geneidi, A.S. 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.

[40]  Jeong, C.G., Francisco, A.T., Niu, Z., Mancino, R.L., Craig, S.L., and Setton, L.A. 2014. Screening of hyaluronic acid–poly (ethylene glycol) composite hydrogels to support intervertebral disc cell biosynthesis using artificial neural network analysis. Acta biomaterialia, 10(8): 3421-3430.

[41]  Thirugnanaselvam, M., Gobi, N., and Arun Karthick, S. 2013. SPI/PEO blended electrospun martrix for wound healing. Fibers and Polymers, 14: 965-969.

[42]  Moomand, K. and Lim, L.-T. 2015. Effects of solvent and n-3 rich fish oil on physicochemical properties of electrospun zein fibres. Food Hydrocolloids, 46: 191-200.

[43]  Kriegel, C., Kit, K.M., McClements, D.J., and Weiss, J. 2009. Electrospinning of chitosan–poly(ethylene oxide) blend nanofibers in the presence of micellar surfactant solutions. Polymer, 50: 189-200.

[44]  Bocanegra, R., Gaonkar, A.G., Barrero, A., Loscertales, I.G., Pechack, D., and Marquez, M. 2005. Production of cocoa butter microcapsules using an electrospray process. Journal of Food Science, 70: e492-e497.

[45]  Mokhtarian, M., Shafafi Zenoozian, M., Armin, M., and Kooshki, F. 2012. Application of response surface methodology coupled with artificial neural network to predict kinetic of food product under different drying conditions. Journal of Innovation in Food Science and Technology, 3(4): 51-66 (In Persian).

[46]  Alehosseini, E., Jafari, S.M., motamedzadegan, A., and Alehosseini, A. 1395. 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 (Agricultral Science): (In Persian).

[47]  Alehosseini, E., Jafari, S.M., motamedzadegan, A., and Alehosseini, A. 1394. Evaluate the performance of two type Artificial Neural Networks multi-layer perceptron (MLP) and radial basis function (RBF) to Prediction's Effects of Cleaning, Moisture, Temperature and Time on the chemical properties of wheat grain. Journal of science and technology - Tarbiat Modares University: (In Persian).

[48]  Kashaninejad, M., Dehghani, A., and Kashiri, M. 2009. Modeling of wheat soaking using two artificial neural networks (MLP and RBF). Journal of Food Engineering, 91(4): 602-607.

[49]  Sablani, S.S., Baik, O.-D., and Marcotte, M. 2002. Neural networks for predicting thermal conductivity of bakery products. Journal of Food Engineering, 52(3): 299-304.

[50]  Sablani, S.S. and Rahman, M.S. 2003. Using neural networks to predict thermal conductivity of food as a function of moisture content, temperature and apparent porosity. Food Research International, 36(6): 617-623.

[51]  Bock, N., Dargaville, T.R., and Woodruff, M.A. 2012. Electrospraying of polymers with therapeutic molecules: State of the art. Progress in Polymer Science, 37: 1510-1551.

[52]  Ding, L., Lee, T., and Wang, C.-H. 2005. Fabrication of monodispersed Taxol-loaded particles using electrohydrodynamic atomization. Journal of Controlled Release, 102(2): 395-413.

[53]  Wongsasulak, S., Patapeejumruswong, M., Weiss, J., Supaphol, P., and Yoovidhya, T. 2010. Electrospinning of food-grade nanofibers from cellulose acetate and egg albumen blends. Journal of Food Engineering, 98: 370-376.

[54]  Fong, H., Chun, I., and Reneker, D.H. 1999. Beaded nanofibers formed during electrospinning. Polymer, 40: 4585-4592.