Predicting In Vitro Rumen VFA Production Using CNCPS Carbohydrate Fractions with Multiple Linear Models and Artificial Neural Networks

Abstract

The objectives of this trial were to develop multiple linear regression (MLR) models and three-layer Levenberg-Marquardt back propagation (BP3) neural network models using the Cornell Net Carbohydrate and Protein System (CNCPS) carbohydrate fractions as dietary variables for predicting in vitro rumen volatile fatty acid (VFA) production and further compare MLR and BP3 models. Two datasets were established for the trial, of which the first dataset containing 45 feed mixtures with concentrate/roughage ratios of 10∶90, 20∶80, 30∶70, 40∶60, and 50∶50 were used for establishing the models and the second dataset containing 10 feed mixtures with the same concentrate/roughage ratios with the first dataset were used for testing the models. The VFA production of feed samples was determined using an in vitro incubation technique. The CNCPS carbohydrate fractions (g), i.e. CA (sugars), CB1 (starch and pectin), CB2 (available cell wall) of feed samples were calculated based on chemical analysis. The performance of MLR models and BP3 models were compared using a paired t-test, the determination coefficient (R2) and the root mean square prediction error (RMSPE) between observed and predicted values. Statistical analysis indicated that VFA production (mmol) was significantly correlated with CNCPS carbohydrate fractions (g) CA, CB1, and CB2 in a multiple linear pattern. Compared with MLR models, BP3 models were more accurate in predicting acetate, propionate, and total VFA production while similar in predicting butyrate production. The trial indicated that both MLR and BP3 models were suitable for predicting in vitro rumen VFA production of feed mixtures using CNCPS carbohydrate fractions CA, CB1, and CB2 as input dietary variables while BP3 models showed greater accuracy for prediction.

Comparison of Diagnosis Accuracy between a Backpropagation Artificial Neural Network Model and Linear Regression in Digestive Disease Patients: an Empirical Research

“…Other researchers [ 63 – 66 ] identically demonstrated that the BP-ANN model had great abilities in information processing, high parallelism related to nonlinearity input variables, generalization, and the fault-tolerant capabilities as the nonparametric algorithm, which is widely used for classification, clustering, regression, and dimensionality reduction in several disease fields. The BP-ANN model was superior to linear regression because of its extraordinary processing ability for dealing with the hidden nonlinear relationship between input markers and the clinical outcome, which might be ignored by linear regression and statisticians [ 67 – 70 ].…”

“…relationship between input markers and the clinical outcome, which might be ignored by linear regression and statisticians [67][68][69][70].…”

Estimation of Individual Glucose Reserves in High-Yielding Dairy Cows

“…Subsequently, the NPA of the digestive precursors were assessed according to Loncke et al [21] and Martineau et al [28]. These models exhibited higher R 2 and lower standard deviation of the residuals compared with other published models of VFA production and absorption [65][66][67][68]. Nonetheless, regression-induced deviations, which over-or underestimate values in specific ranges of the data, have to be considered.…”

“…GLUT1, which is a non-insulin Dairy 2022, 3 dependent glucose transporter on the apical and basal membrane of bovine mammary epithelial cells [112] is a major factor contributing to a constant rate of glucose uptake to the mammary glands of dairy cows. GLUT1 expression is regulated through local concentrations of growth hormone (GH) releasing factor and local hypoxia in response to the high metabolic activity of the mammary gland [68,113]. Therefore, the rate of glucose uptake to the bovine mammary gland remains fairly constant across a wide range of plasma glucose concentrations [114].…”