[Home ] [Archive]    
:: Main :: Current Issue :: Archive :: Search :: Submit :: Contact ::
:: Volume 2, Number 3 (Jul-Sep 2015) ::
Nutr Food Sci Res 2015, 2(3): 29-38 Back to browse issues page
Comparison of Trial and Error and Genetic Algorithm in Neural Network Development for Estimating Farinograph Properties of Wheat-flour Dough
Hajar Abbasi , Seyyed Mahdi Seyedain Ardabili, Mohammad Amin Mohammadifar, Zahra Emam-Djomeh
Assistant Professor Department of Food Science and Technology, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
Abstract:   (2466 Views)
Background and Objectives: Rheological characteristics of dough are important for achieving useful information about raw-material quality, dough behavior during mechanical handling, and textural characteristics of products. Our purpose in the present research is to apply soft computation tools for predicting the rheological properties of dough out of simple measurable factors. Materials and Methods: One hundred samples of white flour were collected from different provinces of Iran. Seven physic-chemical properties of flour and Farinogram parameters of dough were selected as neural network’s inputs and outputs, respectively. Trial-and-error and genetic algorithm (GA) were applied for developing an artificial neural network (ANN) with an optimized structure. Feed-forward neural networks with a back-propagation learning algorithm were employed. Sensitivity analyses were conducted to explore the ability of inputs in changing the Farinograph properties of dough. Results: The optimal neural network is an ANN-GA that evolves a four-layer network with eight nodes in the first hidden layer and seven neurons in the second hidden layer. The average of normalized mean square error, mean absolute error and correlation coefficient in estimating the test data set was 0.222, 0.124 and 0.953, respectively. According to the results of sensitivity analysis, gluten index was selected as the most important physicochemical parameter of flour in characterization of dough’s Farinograph properties. Conclusions: An ANN is a powerful method for predicting the Farinograph properties of dough. Taking advantages of performance criteria proved that the GA is more powerful than trial-and-error in determining the critical parameters of ANN’s structure, and improving its performance. Keywords: Artificial neural network, Genetic algorithm, Rheological characterization, Wheat-flour dough
Keywords: Artificial neural network, Genetic algorithm, Rheological characterization, Wheat-flour dough
Full-Text [PDF 515 kb]   (1667 Downloads)    
Type of Study: Research | Subject: Special
Received: 2015/04/7 | Accepted: 2015/06/27 | Published: 2015/06/27
Send email to the article author

Add your comments about this article
Your username or email:

Write the security code in the box >



XML     Print


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

Abbasi H, Seyedain Ardabili S M, Mohammadifar M A, Emam-Djomeh Z. Comparison of Trial and Error and Genetic Algorithm in Neural Network Development for Estimating Farinograph Properties of Wheat-flour Dough. Nutr Food Sci Res. 2015; 2 (3) :29-38
URL: http://nfsr.sbmu.ac.ir/article-1-89-en.html
Volume 2, Number 3 (Jul-Sep 2015) Back to browse issues page
Nutrition and Food Sciences Research
Persian site map - English site map - Created in 0.048 seconds with 799 queries by yektaweb 3506