Volume 18, Issue 113 (2021)                   FSCT 2021, 18(113): 77-90 | Back to browse issues page


XML Persian Abstract Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Alehosseini E, Jafari S M, Shahiri Tabarestani H. Evaluating the performance of artificial neural networks (ANNs) for predicting the physical, rheological, and colorimetric properties of chitosan nanoparticles (CSNPs). FSCT 2021; 18 (113) :77-90
URL: http://fsct.modares.ac.ir/article-7-48586-en.html
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 , Smjafari@gau.ac.ir
3- Assistant Professor, Department of Food Chemistry, Faculty of Food Science and Technology, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran
Abstract:   (1591 Views)
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.
Full-Text [PDF 2414 kb]   (1236 Downloads)    
Article Type: Original Research | Subject: Nanotechnology in the food industry (nanoparticles, nanocapsulations, nanomolies, etc.)
Received: 2020/12/23 | Accepted: 2021/02/6 | Published: 2021/07/1

Add your comments about this article : Your username or Email:
CAPTCHA

Send email to the article author


Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.