NEURAL NETWORK ANALYSIS OF SILAGE FORAGE QUALITY BASED ON THE BIOCONSOLIDATION INDEX OF LACTIC ACID BACTERIA BIOSYSTEMS

In this study, using the original neural network information technology, it was possible to perform an intelligent analysis of molecular genetic data of silage microflora and evaluate the influence of silage starters and preservatives on the directionality of microbiological biochemical processes in silage biomass. The output product of the intelligent analysis of fractal profiles of silage microflora was the CSIgaZ and CSImU indices, chosen to represent quantitatively, in terms of microbiological data, the intensity of silage outgassing and the amount of lactic and acetic acids in silage. According to the CSImU index it was possible to evaluate the increase of lactic acid and decrease of acetic acid in silage, which signals the slowing down of development of putrefactive microorganisms in silage, and according to the CSIgaZ index - the decrease of silage gas emissions, which indicates favourable anaerobic conditions in which microbiological biochemical processes in silage take place. The laboratory experiment on silage of hedgehog silage conducted in the molecular genetic laboratory of ‘Biotrof’ Ltd. showed that ‘Biotrof-111’ (based on Bacillus subtilis, produced by ‘Biotrof’ Ltd.) creates the best anaerobic conditions in the silaged plant biomass, where the microflora of silage bioconsolidates in the biosystem of lactic acid bacteria. LLC ‘Biotrof’) creates the best anaerobic conditions in the silage plant biomass, in which the silage microflora bioconsolidates into a biosystem of lactic acid bacteria with a minimum value of CSIgaZ index = 3.1 and a maximum value of CSImU index = 6.8, that is, in this variant of silage silage hedgehog silage microflora of silage manages to group in such a way, that simultaneously provides a relatively low intensity of silage gas emissions, accelerated formation of lactic acid and slow formation of acetic acid in silage, and thus in these conditions the processes will be completed with the best quality nutritional indicators of silage.

1. Zenkova N.N. Practical guide to the use of fodder resources in fodder production: a practical guide / Zenkova N.N., Ganushchenko O.F.; Shloma T.M.; Kovaleva I.V. // Vitebsk: VGAVM. 2021. 176 p. (In Russ.)

2. Laptev G.Yu. Promilk leaven will ensure the quality of silage and grain slage / Laptev G.Yu., Yildirim E.A., Ilyina L.A., Novikova N.I., Tyurina D.G., Markman I.L. // Livestock of Russia. 2023. 4: 50-55. (In Russ.)

3. Laptev G.Y. Prevent secondary fermentation and aerobic spoilage of silage / Yildirim E.A., Tyurina D.G., Novikova N.I., Ilyina L.A., Chervatenko D.Y. // Livestock of Russia. 2024. 4: 52-54. (In Russ.)

4. Laptev G.Y. Effectiveness of the preparation ‘Biotrof-600’ to combat undesirable microflora in the storage of conditioned grain. / Collection ‘Actual problems of preparation, storage and rational use of forages’ of the international scientific-practical conference devoted to the 100th anniversary of the birth of Doctor of Agricultural Sciences, Professor S.Y. Zafren // M.: 2009. 41-45. (In Russ.)

5. Yildirim E.A., Biotrof-111: all possible does at once / Yildirim E.A., Tyurina D.G. // Livestock of Russia. 2021. 4: 48-51 (In Russ.)

6. Pobednov Yu.A. Effectiveness of corn and grass silage with the preparation Biorof 111 (recommendations) / Pobednov Yu.A., Mamaev A.A., Khudokormov VV, Shchukin NN, Gorkin AM, Borodulya V.I., Laptev GY, Soldatova VV // M.: FSU RCSC, 2010. 17 p. (In Russ.)

7. Bikonya S.N. Increase of nutritive value of silage and haylage with the use of bioconservatives / Dissertation of Candidate of Agricultural Sciences // Volgograd: Volgograd GAU. 2023. 128 p. (In Russ.)

8. Chagarovskiĭ V., Chagarovskiĭ A. Study of the biological activity of direct ferments of the Christian Hansen company used in the production of lactic acid milk products/Ukraine Mikrobiolohichnyĭ Zhurnal . 2003. 5(1): 78 – 83.

9. Driehuis F. Fermentation characteristics and aerobic stability of grass silage inoculated with Lactobacillus buchneri, with or without homofermentative lactis acid bacteria/Driehuis F., Oude Elferink S.J.W.H., Van Wikselaar P.G. // Grass Forage Sci., 2001, 56(4): 330-343 (doi: 10.1046/j.1365-2494.2001.00282.x).

10. Tabacco E. Dry matter and nutritional losses during aerobic deterioration of corn and sorghum silages as influenced by different lactic acid bacteria inocula / Tabacco E., Righi F., Quarantelli A., Borreani G. // J. Dairy Sci., 2011, 94: 1409-1419 (doi: 10.3168/jds.2010-3538).

11. Rigу E. Ensiling alfalfa with hydrolyzed corn meal additive and bacterial inoculant / Rigу E., Zsédely E., Tóth T., Schmidt J. // Acta Agronomica Óvariensis, 2011, 53(2): 15-23.

12. Laptev G.Yu. Analysis of mycotoxin accumulation in fodder plant raw materials and silage / Laptev G.Yu., Novikova N.I., Dubrovina E.G., Ilyina L.A., Yildirim E.A., Nikonov I.N., Filippova V.A., Brazhnik E.A. // Fodder production. 2014. 10: 36-39. (In Russ.)

13. Pobednov Yu.A., Kosolapov V.M. Biological basis of alfalfa silage with preparations of lactic acid bacteria (review) / Agricultural Biology. 2018. 53(2): 258-269. (In Russ.)

14. Osipyan B.A., Mamaev A.A. Efficiency of application of preparations ‘Biotroph 600’ and ‘Biotroph 700’ at ensiling of plant raw materials provided with sugar / Fodder production. 2014. 11: 35-39. (In Russ.)

15. Netrusov A.I., Bonch-Osmolovskaya E.A., Gorlenko V.M. Ecology of microorganisms / M.: Akademiya, 2004. 272 p. (In Russ.)

16. Chubenko G.I. Methods of bacterial identification: method. manual / Blagoveshchensk: Amurskaya GMA, 2018. 44 p. (In Russ.)

17. Gafarov F.M., Galimyanov A.F. Artificial neural networks and applications: textbook. - Kazan: Izd-vo Kazan. un-sta, 2018. 121 p. (In Russ.)

18. Kruglov V.V., Borisov V.V. Artificial neural networks. Theory and practice / M.: Hotline Telkom, 2002. 382 p. (In Russ.)

19. Vorobyov N.I., Selina M.V., Guselnikova A.A. Neural network programme for the analysis of the state of animal microbiota / Certificate of state registration of computer program No. 2024614895 from 29.02.2024 Application of K.I. Skryabin MBA No. 2024613194 from 16.02.2024. (In Russ.)

20. Witten I.H., Frank E., Hall M.A., Kaufmann M. Data Mining: Practical Machine Learning Tools and Techniques. 3rd ed. / Witten I.H., Frank E., Hall M.A., Kaufmann M. // Elsevier, 2011. 629 p.

21. Ben-Jacob E. Bacterial self-organization: coenhancement of complexication and adaptability in a dynamic environment / Phil. Trans. R. Soc. Lond. A. 2003. 361: 1283-1312.

22. Young I.M., Crawford J.W. Interactions and self-organization in the soil-microbe complex / Science, 2004, 304(5677): 1634-1637.

23. Crawford J.W., Deacon L., Grinev D., Harris J.A., Ritz K., Singh B.K., Young I. Microbial diversity affects self-organization of the soil-microbe system with consequences for function / Journal of the Royal Society Interface. 2012, 9(71): 1302-1310.

24. Vorobyov N.I. Biosystem selforganisation and fractal structure of frequency-taxonomic profiles of microbiota of broiler intestine under the influence of feed probiotics / Vorobyev N.I., Egorov I.A., Kochish I.I., Nikonov I.N., Lenkova T.N. // Agricultural Biology. 2021. 56(2): 400-410. (In Russ.)

25. Kochish I.I. Neural network modelling of fractal self-organization of microbialorganism biosystems in the intestines of birds / Kochish I.I., Vorobiev N.I., Nikonov I.N., Selina M.V. // Veterinary and Zootechnia. 2022. 12: 57-65. (In Russ.)

26. Manfred Schroeder. Fractals, Chaos, Power Laws: Minutes from an Infinite Paradise / NY: 2009. Dover Publications. 448 p.

27. Sutrop U. List Task and a Cognitive Salience Index / Field metods. 2001. 13(3): 263-276.

28. Zagoruiko N.G. Cognitive data analysis / Novosibirsk: Academic Publishing House GEO. 2013. 183 p. (In Russ.)

29. Kim J.-O. Factor, discriminant and cluster analysis / Kim J.-O., Mueller C.W., Klecka W.R., Oldenderfer M.S., Blashfield R.K. // M., 1989. 216 p.

30. Zaikina A.S. Neural network analysis of compliance of microbial-organism biosystem of broiler intestine fractal-stochastic model / Zaikina A.S., Buryakov N.P., Vorobyev N.I., Nikonov I.N. // Perm agrarian bulletin, 4(40). 2022: 98-106. (In Russ.)

31. Jürgen Schmidhuber. Deep learning in neural networks: an overview / Neural Netw. 2015. Jan:61:85-117 (doi: 10.1016/j.neunet.2014.09.003)

32. Pogodaev, A.K. Application of neural network models for building the production rules of expert systems / Pogodaev, A.K.; Habibullina, E.L.; Inyutin, D.M. // Applied mathematics and control issues. 2021. 2: 73-92. (In Russ.)

33. Kulakov, K.A.; Dimitrov, V.M. Fundamentals of software testing / Petrozavodsk: PetrSU Publishing House, 2018. 57 p. (In Russ.)

34. Widrow, Bernard; et al. The no-prop algorithm: A new learning algorithm for multilayer neural networks / Neural Networks. 2013. 37: 182–188.

35. Mascarenhas, WF. Fast and accurate normalization of vectors and quaternions / Comp. Appl. Math. 2018. 37: 4649–4660.

36. Nikolić, D. Scaled correlation analysis: a better way to compute a cross-correlogram / Nikolić, D; Muresan, RC; Feng, W; Singer, W. // European Journal of Neuroscience. 2012. 35(5): 1–21.

37. Everitt, BS. Cluster Analysis / Everitt, BS, Landau S, Leese M, Stahl D. // John Wiley & Sons, 2011. 352 p.

38. Markova L.V., Korchevskaya E.A. Numerical methods of finding eigenvectors and eigenvalues of matrices / Vitebsk: P.M. Masherov State University, 2011. 47 p. (In Russ.)

39. Yildirim E.A. Study of epiphytic microflora as a source of silage microbiocenosis formation by NGS-sequencing method / Yildirim E.A., Laptev G.Y., Ilyina L.A., Nikonov I.N., Filippova V.A., Soldatova V.V., Brazhnik E.A., Novikova N.I., Gagkaeva T.Y. // Agricultural Biology. 2015. Т. 50(6): 832-838. (In Russ.)

40. Duke V. A., Flegontov A. V. V., Fomina I. K. Application of data mining technologies in natural science, technical and humanitarian fields // Izvestiya RGPU named after A.I. Herzen. 2011. 138: 77-84. (In Russ.)