hrcak mascot   Srce   HID

Izvorni znanstveni članak

Usporedno ispitivanje metode odzivnih površina, umjetne neuralne mreže i genetskog algoritma radi optimiranja hidratacije zrna soje

Tushar Gulati ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India
Mainak Chakrabarti ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India
Anshu Sing ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India
Anshu Sing ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India
Muralidhar Duvuuri ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India
Rintu Banerjee ; Microbial Biotechnology and Downstream Processing Laboratory, Agricultural and Food Engineering Department, Indian Institute of Technology, IN-721302 Kharagpur, India

Puni tekst: engleski, pdf (301 KB) str. 11-18 preuzimanja: 786* citiraj
APA 6th Edition
Gulati, T., Chakrabarti, M., Sing, A., Sing, A., Duvuuri, M. i Banerjee, R. (2010). Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration. Food Technology and Biotechnology, 48 (1), 11-18. Preuzeto s https://hrcak.srce.hr/48430
MLA 8th Edition
Gulati, Tushar, et al. "Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration." Food Technology and Biotechnology, vol. 48, br. 1, 2010, str. 11-18. https://hrcak.srce.hr/48430. Citirano 06.06.2020.
Chicago 17th Edition
Gulati, Tushar, Mainak Chakrabarti, Anshu Sing, Anshu Sing, Muralidhar Duvuuri i Rintu Banerjee. "Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration." Food Technology and Biotechnology 48, br. 1 (2010): 11-18. https://hrcak.srce.hr/48430
Harvard
Gulati, T., et al. (2010). 'Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration', Food Technology and Biotechnology, 48(1), str. 11-18. Preuzeto s: https://hrcak.srce.hr/48430 (Datum pristupa: 06.06.2020.)
Vancouver
Gulati T, Chakrabarti M, Sing A, Sing A, Duvuuri M, Banerjee R. Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration. Food Technology and Biotechnology [Internet]. 2010 [pristupljeno 06.06.2020.];48(1):11-18. Dostupno na: https://hrcak.srce.hr/48430
IEEE
T. Gulati, M. Chakrabarti, A. Sing, A. Sing, M. Duvuuri i R. Banerjee, "Comparative Study of Response Surface Methodology, Artificial Neural Network and Genetic Algorithms for Optimization of Soybean Hydration", Food Technology and Biotechnology, vol.48, br. 1, str. 11-18, 2010. [Online]. Dostupno na: https://hrcak.srce.hr/48430. [Citirano: 06.06.2020.]

Sažetak
U radu je modelirana i optimirana hidratacija zrna radi ubrzavanja prerade soje, pri čemu se pokušao ostvariti maksimalni prinos mase, usvajanje vode i retencija proteina. Metodom odzivnih površina te umjetnom neuralnom mrežom i genetskim algoritmom optimirane su sljedeće varijable procesa: omjer zrna soje i vode (optimalni omjer od 1:2,48 i 1:1,19), vrijeme (2 odnosno 8 sati) i temperatura (40 i 45, 1 °C). Tako je pronađena bolja alternativa klasičnom postupku namakanja zrna soje koji se učestalo koristi u industriji, a zahtijeva veliki utrošak vremena. Na osnovi rezultata razvijen je vrlo precizan model neuralne mreže (koeficijent regresije od 0,9443). Genetskim su algoritmom predviđeni optimalni uvjeti prerade, a učinkovitost je modela umjetne neuralne mreže i genetskog algoritma potvrđena ispitivanjem (koeficijent determinacije R2=0,938 i srednja kvadratna pogreška MSE=5,9299). Metodom odzivnih površina također je razvijen točan model procjene prinosa mase, usvajanja vode i retencije proteina (R2=0,8890–0,9297 i MSE=0,80–4,94).

Ključne riječi
metoda odzivnih površina; umjetna neuralna mreža; genetski algoritam; namakanje zrna soje

Hrčak ID: 48430

URI
https://hrcak.srce.hr/48430

[engleski]

Posjeta: 1.249 *