Uso de técnicas de machine learning na análise da relação da composição do leite bovino com a contagem de células somáticas
Gardado en:
| Autor Principal: | |
|---|---|
| Data de Publicación: | 2025 |
| Formato: | Bachelor thesis |
| Idioma: | por |
| Fonte: | Repositório Institucional da UPF |
| Download full: | https://repositorio.upf.br/handle/123456789/9537 |
Summary: | This work investigates the relationship between some milk components — protein, lactose, and fat — and the somatic cell count (SCC), one of the main indicators of the health of dairy cows. Machine learning techniques were used to perform a statistical analysis, aiming to assess the potential of these components for detecting diseases such as mastitis. The algorithms Simple and Multiple Linear Regression, Random Forest, and XGBoost were trained for predictive modeling, and their performances were evaluated based on metrics such as the coefficient of determination (R2), mean squared error (MSE), and the relative importance of the predictor variables. The results indicate that lactose was the most influential factor in the prediction of SCC, standing out as a marker for monitoring the udder health of dairy cows. Linear models showed an R2 performance of 0.14, and non-linear machine learning models showed an R2 performance of 0.17, reflecting the biological complexity of the studied phenomenon. |
Sexa o primeiro en deixar un comentario!