Examinando por Autor "Woerner, Dale"

Mostrando 1 - 2 de 2
  • Miniatura
    Ítem
    Predicting Cattle Meat Types through Machine Learning Models Trained on Rapid Evaporative Ionization Mass Spectrometry (REIMS) Data
    (Zamorano: Escuela Agrícola Panamericana, 2023) Reyes L., Esther A.; Acosta, Adela; Woerner, Dale
    Currently, the meat industry faces several problems, one of them being consumer fraud, which has arised the need to guarantee to the consumer that the product offered for sale is what it says on the label. This leads to the main objective of this study, which was to use data obtained by Rapid Evaporative Ionization Mass Spectrometry (REIMS) analysis for the training of 12 predictive models in three different dimensional reduction methods in order to train these models for the quick and accurate identification of the bovine breed from which the meat is obtained. Steaks from the Loggisimus dorsi muscle in the USDA classification as "Prime" from the Angus breed and the Wagyu breed were used. Each method's five best predictive models were selected for analysis and discussion. The best dimensional reduction method was Feature Selection (FS), which showed accuracies ranging from 73.6 to 91.8% in the different predictive models, being the best predictive model SVM Poly, which obtained the highest percentages in the performance metrics in the three dimensional reduction methods. Thus, demonstrating the effectiveness of using REIMS data for predicting the bovine breed from which the Longissimus dorsi steaks derive.
  • Miniatura
    Ítem
    Prediction of beef carcass composition using linear measurements obtained by DXA scan.
    (Zamorano: Escuela Agrícola Panamericana, 2023) Lopez G., Ariel A.; Acosta, Adela; Woerner, Dale; Mendizabal, Andres
    The third most popular meat in the world, behind chicken and veal, is beef. This emphasizes how important it is to precisely determine your market value to ensure that producers are paid fairly. There is a need for more precise methodologies to analyze the composition of the carcass because the USDA's current method for determining yield has its limitations. In this study, lineal measurements were taken using DXA scans, and models were developed to predict sub primal performance as well as fat and bone percentage. The highlighted model for subprime yield achieved an R2 of 0.97 using just five predictors. Using three predictors, the model for fat content recorded an R2 of 0.94, whilst the prediction for bone content was established at an R2 of 0.81. Although 11 potential predictors were identified, the models were refined to only use the five most significant predictors. The study indicates a promising path for improving the assessment of the carcass composition by multiple linear regression in order to obtain more accurate valuations in the beef industry.