T he objective was to implement a semolina percentage recognition system using near-infrared spectroscopy (NIR) and multivariate data analysis. For this purpose, 6 samples were an aly zed with different percentages of semolina (20, 4 0, 6 0, 80 an d 100 %) . Samples were repeated 20 times. T he observed NI R sp ect r um was absorbance in the range of 1100 and 2500 nm. In order to reduce the data, the analysis of main components was used by testing 24 classification models, from which the one that reached the highest level of precision was the Linear Support Vector Machine (SVM) algorithm, reaching 98.8%, achieving fairly satisfactory discriminatio n with values of PC1 (99.7%), PC2 (0.3%) and PC3 (0.1%), reachin g a total cumulative variation of the contribution of th e f ir st 3 P Cs of 99.9%. Partial Least Regression (PLS) models applied to NIR-spectra showed R2 between 0.9388. T hese values demonstrated that NIR spectroscopy can be used for the identification and quantif ication of fiber added to semolina.

In this research, the whey potential for optimization of biogas production by anaerobic codigestion with cow dung was studied. It used a two-component multifactorialdesign, where it was studied four batch typebiodigesters of 4 liters on a laboratory scale with different whey concentrations (0%, 10%, 30%, 50%) and dilute cow dung in relation 1:1.5, each one in three replications. The experimentation was performed under temperature control of 35°C±2°C; and pH control between 6.4 to 6.9 by the addition of NaOH 3N; with an average of 7% of total solids and a holding time of 35 days. Below these conditions, the 2 nd biodigester with 10% of whey, it was the one which generate the largest amount of biogas with 37.9 liters in total; the 3 rd biodigester, with 30% of whey generates 24.2 liters of biogas;and the 4 th biodigester, with 50% of whey generates 14.5 liters. The reduction of total solids in biodigesters were 38.5%, 43.4%, 40.2% and 27.6% respectively. We used the Gompertz model, which allowed us to find high correlation grades oscillating between 86.295% y 94.268%. Therefore, it can be established, that the use of whey duplicates the biogas production until 52% and sets a limit of 30% (v/v) to obtain a good biogas production in batch-type biodigesters.

No abstract

The objective of this research was to compare the best structure of a Neural Network (ANN) with a multivariate nonlinear regression model (MNLR) to predict the physicochemical quality parameters of milk. To create a predictor model for the livestock sector, 3 input and 6 output variables were used. To achieve this, a Feedforward ANN with Backpropagation training algorithms was applied. For the models, the Matlab 2020a software was used. The lowest mean absolute deviation (MAD) was found to be 0.00715952, corresponding to a Neural Network with 2 hidden layers (18 and 19), with Tansig and log sig type function, respectively. MNLR models had R2values greater than 0.9. Cross-Validation with 10 interactions was used for this purpose. For comparison, a Duncan test was used where it was found that there are no statistically significant differences between the real sample, the MNLR, and the ANN, with a 95.0% confidence level.

No abstract