ISSN 2074-9414 (Print),
ISSN 2313-1748 (Online)

ARTIFICIAL NEURAL NETWORKS FOR THE ASSESSMENT OF QUALITY INDICES OF LOW-ALLERGY FERMENTED MILK DRINKS

Abstract
The use of β-lactoglobulin hydrolysate produced with the use of Flavorpro 750MDP and Promod 439L enzyme preparations to obtain fermented milk drinks having reduced residual antigenicity has been suggested. It is necessary to provide normalized physical-chemical and acceptable organoleptic characteristics of resulting fermented milk drink. The purpose of the research is to study the possibility of applying the method of artificial neural networks for prediction of properties, quality indices and safety factors of normalized dairy mixes used to obtain low-allergenic fermented milk drinks. Organoleptic characteristics, physical and chemical properties of the normalized mixes have been studied with sensorymetric method. The method of evaluation of quality indices of normalized mixes and fermented milk drinks has been adapted using the method of artificial neural networks. Three-layer neural network with 6 neurons in the input layer, 12 neurons in the inner layer and 4 neurons in the output layer according to the number of output parameters has been used. The algorithm of back-propagation errors has been applied for training the network. The research results confirm that the obtained neural network predicts the main characteristics of normalized mixes with β-lactoglobulin hydrolysate almost accurately; the relative error does not exceed 2.6% when predicting β-lactoglobulin content, 3.9% when predicting residual antigenicity and 3.1% when predicting titratable acidity and organoleptic characteristics. This method is applicable for assessing the quality of finished goods and can replace the routine methods of analysis in force at the enterprises of dairy industry.
Keywords
Artificial neural networks, quality index evaluation, low-allergy fermented milk drinks
REFERENCES
  1. Ponomareva, N.V. Biokonversiya molochnyh belkov dlya snizheniya ostatochnoy allergennosti / N.V. Ponomareva, E.I. Mel'nikova, E.V. Bogdanova // Biotehnologiya. - 2015. - № 1. - S. 70 - 74.
  2. Mel'nikova, E.I. Mikropartikulyaty syvorotochnyh belkov kak imitatory molochnogo zhira v proizvodstve produktov pitaniya / E.I. Mel'nikova, E.B. Stanislavskaya // Fundamental'nye issledovaniya. - 2009. - № 57. - S. 23.
  3. Izuchenie hranimosposobnosti molokosoderzhaschego produkta smetannogo tipa / L.V. Golubeva, O.I. Dolmatova, E.I. Bocharova, Zh.S. Dolmatova // Vestnik Voronezhskogo gosudarstvennogo universiteta inzhenernyh tehnologiy. - 2012. - № 4 (54). - S. 90-91.
  4. Himicheskie sensory i ih sistemy / Yu.G. Vlasov, Yu.E. Ermolenko, A.V. Legin, A.M. Rudnickaya [i dr.] // Zhurnal analiticheskoy himii. - 2012. - T. 65. - № 9. - S. 900-919.
  5. Vlasov, Yu.G. Elektronnyy yazyk - sistemy himicheskih sensorov dlya analiza vodnyh sred / Yu.G. Vlasov, A.V. Legin, A.M. Rudnickaya // Rossiyskiy himicheskiy zhurnal (Zhurnal Rossiyskogo himicheskogo obschestva im. D.I. Mendeleeva). - 2008. - T. LII. - № 2. - S. 101-112.
  6. Kuchmenko, T.A. Innovacionnye resheniya v analiticheskom kontrole / T.A. Kuchmenko. - Voronezh: VGTA, 2009. -252 s.
  7. Perspektivy ispol'zovaniya «elektronnogo yazyka» v kontrole brodil'nyh proizvodstv / R.A. Enikeeva, P.S. Nikanorov, A.V. Nasonenko, V.A. Sergeeva [i dr.] // Izvestiya SPbGTI(TU). - 2015. - № 29. - S. 76-79.
  8. System of piezosensors for prognostication of the storage life of food products / Ya.I. Korenman, E.I. Mel'Nikova, S.I. Niftaliev, S.E. Boeva, A.A. Selivanova, E.S. Rudnichenko, E.V. Bogdanova // Russian Journal of Applied Chemistry. - 2009. - Vol. 82. - no. 8. - P. 1380-1383. DOI: 10.1134/S1070427209080114.
  9. Tang, Kea-Tiong. A Local Weighted Nearest Neighbor Algorithm and a Weighted and Constrained Least-Squared Method for Mixed Odor Analysis by Electronic Nose Systems / Kea-Tiong Tang, Yi-Shan Lin, Jyuo-Min Shyu // Sensors. - 2010. - No. 10. - P. 10467-10483; DOI: 10.3390/s101110467.
  10. Rassel, S. Iskusstvennyy intellekt. Sovremennyy podhod / S. Rassel, P. Norvig. - M.: Vil'yams, 2007. - 1410 s.
  11. Korotcenkov, G. Chemical sensors: comprehensive sensor technologies [Text] / G. Korotcenkov.-Momentum Press, LLC, 2012. - 77 p.
  12. Haykin, S. Neyronnye seti: polnyy kurs / S. Haykin. - M.: Vil'yams, 2016. - 1104 s.
  13. Sensorometricheskiy analiz i neyrosetevye tehnologii v ocenke kachestva molokosoderzhaschih produktov / E.I. Mel'nikova, Ya.I. Korenman, S.I. Niftaliev, S.E. Boeva. - Voronezh: VGTA, 2009. - 202 s.
  14. Patent № 2288468 RF. Universal'naya p'ezosorbcionnaya yacheyka detektirovaniya / A.A. Kiselev, S.I. Niftaliev, Ya.I. Korenman, E.I. Mel'nikova, S.E. Svetolunova // Izobreteniya. - 2006. - № 33. - Ch. I. - S. 318.
  15. Parts, Ya.A. Mnogochastotnye p'ezorezonansnye datchiki: princip deystviya, sposoby postroeniya, reshaemye zadachi / Ya.A. Parts // Nelineynyy mir. - 2009. - № 5. - S. 17-23.
  16. Eremin, N.I. Nemetallicheskie poleznye iskopaemye / N.I. Eremin. - M.: Izd-vo MGU, 2007. - 464 s.
  17. Boeva, S.E. Analiz i ocenka kachestva nekotoryh molokosoderzhaschih produktov / S.E. Boeva. - Dis.. kand. him. nauk: spec. 02.00.02 - Analiticheskaya himiya. - Voronezh, 2007. - 163 s.
  18. Sanina, M.Yu. Primenenie ekspress- i test-metodov v analize prirodnyh ob'ektov / M.Yu. Sanina // Izvestiya VGPU. - 2013. - T. 260. - № 1. - S. 258-262.
How to quote?
About journal

Download
Contents
Abstract
Keywords
References