Intelligent Modeling of Bread texture Acoustic Measurement Method and Artificial Neural Network (Case Study: Enriched Bread with Chia)

Document Type : Research Article

Authors

1 Department of Food Science & Technology, Agricultural Sciences and Natural Resources University of Khuzestan, Iran

2 Department of Food Science & Technology, Faculty of Animal Science and Food Technology, Khuzestan Ramin University of Agricultural & Natural Resources, Mollasani, Iran

3 Assistant professor of Khuzestan Agricultural Sciences and Natural Resources University

4 Food Science and Technology, Agricultural Sciences and Natural Resources University of Khuzestan

Abstract

The purpose of this study is to model the bread texture by acoustical- mechanical method, non- destructively. To do so, bread texture enriched with 3 different levels of modified chia (2.5%, 5% and 7.5%) was evaluated by texture analyzer at a test speed of 3 mm. s-1 to 30% compression, while the microphone was located at 5 cm from the samples at a 45° angle to the horizon. From the sound recorded during loading mean sound intensity, maximum of sound, variance, standard deviation, root mean absolute value, root mean square value, skewness, kurtosis, fifth moment, sixth moment, energy, entropy in time domain, and spectral entropy and natural frequency in the frequency domain were extracted. After selecting the most suitable features (maximum sound, variance, standard deviation, root mean absolute value, energy, entropy and natural frequency), based on statistical analysis, artificial neural network with 3 algorithms ( Marquardt, scaled conjugate gradient, gradient descent) was trained and tested with 7 neurons in the input layer (in accordance with the selected features) and 3 neurons in the output layer (hardness, gumminess, chewiness). Based on the results, the training error in the Levenberg - Marquardt algorithm was lower than the other algorithms, and the root mean squared error of the test stage of this algorithm to predict hardness, gumminess and chewiness were 0.14, 0.23, and 0.33, respectively. This shows the ability of the proposed method in predicting the quality of bread.

Graphical Abstract

Intelligent Modeling of Bread texture Acoustic Measurement Method and Artificial Neural Network (Case Study: Enriched Bread with Chia)

Highlights

  • Chia seed modification by roasting method.
  • Determination of bread quality enriched with modified chia flour using acoustical-mechanical testing method during storage.
  • Three different learning algorithms (Levenberg-Marquardt, scaled conjugate gradient, gradient descent) were used to train artificial neural network.  
  • Levenberg-Marquardt (the best learning algorithm) predicted hardness, chewiness and gumminess with (R2 = 0.97), (R2 = 0.95) and (R2 = 0.93), respectively.

Keywords

Main Subjects

References

[1] Soleimani Fard, M., Alami, M., Maghsoud loo, Y.,& Najafian, G. (2013). The effect of Arabic gel as improving the rheological properties of wheat flour dough and anti-stagnation agent of Barbari bread.J. Innov. Food Sci. Technol., 5, 1-11. [In Persian]
[2] Hejri Zarifi, S., Hadad- Khoda-Parast, M., Sheikh al-Islami, Z., Shfafi Znozian, M.,& Pourferzad, A. (2014). Investigation of the effect of date kernel germ on dough rheology and sensory properties of Barbari bread. J. Innov. Food Sci. Technol., 6, 25-32. [In Persian]
[3] Majzoobi, M.,  Mortazavi, S. H., Asadi-Yousofabad, S. H., &  Farahnaky, A. (2013). Effects of acorn flour on the properties of dough and Barbari bread. J. Food Ind. Res., 23, 271-280. [In Persian]
[4] Jalini, M., ghiafeh davoodi, M.,& Sheikh al-Islami, Z.( 2017). The Effect of Adding Your Seed to the Nutritional and Shelf Life of Barberry bread. J. Innov. Food Sci. Technol., 9, 1-11. [In Persian]
[5] Moazeni, M., Zarringhalami, S., & Ganjloo, A. (2018) . Effect of Barbari dough enrichment with quinoa whole flour on farinograph characteristics and bread quality. J. Food Ind. Res., 28, 103- 112. [In Persian]
 [6] Costantini, L., Lukšič, L., Molinari, R., Kreft, I., Bonafaccia, G., Manzi, L.,& Merendino, N. (2014). Development of gluten-free bread using tartary buckwheat and chia flour rich in flavonoids and omega-3 fatty acids as ingredients. Food chem., 165, 232-240.
[7] Alfredo, V. O., Gabriel, R. R., Luis, C. G.,& David, B. A. (2009). Physicochemical properties of a fibrous fraction from chia (Salvia hispanica L.). LWT., 42, 168-173.
[8] Lazaro, H., Puente, L., Zúñiga, M. C.,& Muñoz, L. A. (2018). Assessment of rheological and microstructural changes of soluble fiber from chia seeds during an in vitro micro-digestion. LWT., 95, 58-64.
[9] Muñoz, L. A., Cobos, A., Diaz, O.,& Aguilera, J. M. (2012). Chia seeds: Microstructure, mucilage extraction and hydration. J. Food Eng., 108, 216-224
[10] Jogihalli, P., Singh, L.,& Sharanagat, V. S. (2017). Effect of microwave roasting parameters on functional and antioxidant properties of chickpea (Cicer arietinum). LWT., 79, 223-233.
[11] Gholami, Z., & Ansari, S. (2018). Modeling the effect of microwave roasting on physicochemical properties of watermelon seeds and its optimization. Innov. Food Sci. Technol. (Food Sci. Technol.)., 10, 71-85. [In Persian]
[12] Chen, J., Karlsson, C.,& Povey, M. (2005). Acoustic envelope detector for crispness assessment of biscuits. J. Texture Stud., 36, 139-156.
[13] Jakubczyk, E., Gondek, E.,& Tryzno, E. (2017). Application of novel acoustic measurement techniques for texture analysis of co-extruded snacks. LWT., 75, 582-589.
[14] Çarşanba, E., Duerrschmid, K.,& Schleining, G. (2018). Assessment of acoustic-mechanical measurements for crispness of wafer products. J. Food Eng., 229, 93-101
[15] Huerta, K., Soquetta, M., Alves, J., Stefanello, R., Kubota, E.,& Rosa, C. S. (2018). Effect of flour chia (Salvia hispanica L.) as a partial substitute gum in gluten free breads. Int. Food Res. J., 25, 755-766.
[16] Abdanan Mehdizadeh, M., & Amraee, S. (2017). Computational estimation of L*a*b* units from RGB using machine vision. Iran. J. Food Sci. Ind. Res., 13, 53-64. [In Persian]  
 [17] Arimi, J. M., Duggan, E., O’sullivan, M., Lyng, J. G.,& O’riordan, E. D. (2010). Effect of water activity on the crispiness of a biscuit (Crackerbread): mechanical and acoustic evaluation. Food Res. Int., 43, 1650-1655.
[18] Błońska, A., Marzec, A.,& Błaszczyk, A. (2014). Instrumental evaluation of acoustic and mechanical texture properties of short‐dough biscuits with different content of fat and inulin. J. Texture Stud., 45, 226-234.
[19] Nouri, M., Nasehi, B., Mehdizadeh, S. A.,& Goudarzi, M. (2017). A novel application of vibration technique for non-destructive evaluation of bread staling. J. Food Eng., 197, 44-47.
[20] Salehifar, M., Shahedi, M., & Kabir, Gh. (2006). Investigating the effects of using different percentages of oatmeal and excess fat in bread preparation formulation on sensory and stale properties of bread texture. Agric. Sci. Technol. Nat. Resour.,  10, 233-244.[In Persian]
 [21] Romankiewicz, D., Hassoon, W. H., Cacak-Pietrzak, G., Sobczyk, M., Wirkowska-Wojdyła, M., Ceglińska, A.,& Dziki, D. (2017). The effect of chia seeds (Salvia hispanica L.) addition on quality and nutritional value of wheat bread. J.Food Qual., 2017, 1-7.
[22] Zhang, W., Cui, D.,& Ying, Y. (2014). Nondestructive measurement of pear texture by acoustic vibration method. Postharvest Biol. Technol., 96, 99-105.
[23] Zdunek, A., Cybulska, J., Konopacka, D.,& Rutkowski, K. (2011). Evaluation of apple texture with contact acoustic emission detector: A study on performance of calibration models. J. Food Eng., 106, 80-87.
[24] Różyło, R.,& Laskowski, J. (2011). Predicting bread quality (bread loaf volume and crumb texture). Pol. J.Food Nutr.Sci., 61, 61-67.
Innovative Food Technologies
Volume 7, Issue 4
August 2020
Pages 517-534

Files

History

  • Receive Date: 28 July 2019
  • Revise Date: 07 October 2019
  • Accept Date: 14 June 2020

Share

How to cite

Statistics