التفاصيل البيبلوغرافية
| العنوان: |
Evaluation of in vitro ruminal fermentation kinetics of diet mixed with mineral organic additive using artificial neural network. |
| المؤلفون: |
Sofyan, A., Herdian, H., Sakti, A. A., Anggraeni, A. S., Amri, A. F., Kurniawan, T., Darma, I. N. G., Febrisiantosa, A. |
| المصدر: |
AIP Conference Proceedings; 2023, Vol. 2628 Issue 1, p1-9, 9p |
| مصطلحات موضوعية: |
RUMEN fermentation, INULIN, STANDARD deviations, DIET |
| مستخلص: |
In vitro gas production techniques can provide information about the kinetics of gas production as a result of the degradation of feed by rumen microbes. Response of rumen microbial degradation process is described by a number of mathematical equations which are generally non-linear models. On the other hand, the use of artificial neural network (ANN) methods has been widely used to characterize and predict microbial growth. This study was to evaluate the use of the ANN method to characterize gas production from basal cattle feed supplemented (in dry matter base) by: 2% organic mineral and probiotic mix (B), 2% B+I% inulin (C), A+ 2% B+I% protected amino acid (D); 2% B+I% inulin +I% protected amino acid (E), which incubated in buffering ruminal fluid using in vitro gas production methods. The multi-layer perception of the ANN model was compiled and compared with the non-linear model (NLM) of the gas production kinetics equation. The evaluation was carried out using the parameters consisting of mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and visual evaluation of the observation vs. prediction graph and residuals. The Gas accumulation production was not different for all diets at 48 hours of incubation time revealed by both methods. The residual dispersion showed the differences at 0-5 h incubation time for the diet determined by NLM while the NN model reveal no differences. Both models resulting non-negative values for the initial incubation period. The NL model shows smaller values for MSE, RMSE, MAE compared to the ANN model. Meanwhile, the R2 value of the ANN and NL models shows the same value. Both models showed the highest accuracy in the predictions for diet B. [ABSTRACT FROM AUTHOR] |
|
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
Find this article in full text from Scitation.