Resumen
The document presents the results of the evaluation of the milk sample classification process through the modeling of
machine learning techniques, with random forest being the most accurate according to its accuracy percentage of
96%. The paper presents the results of the evaluation of the milk sample classification process through the modeling
of machine learning techniques. This research aimed to discriminate the presence or absence of adulterants, which
allows the obtaining of dairy products suitable for human consumption. Also, accelerate and specify the inspection
process of these samples. The relevance of the present study can be understood from the product under analysis:
milk. This is mass consumption, especially in children. Therefore, it is considered relevant to demonstrate efficiently
that quality products are provided to the population and this document is a contribution to the credibility of the integrity
of dairy products.
machine learning techniques, with random forest being the most accurate according to its accuracy percentage of
96%. The paper presents the results of the evaluation of the milk sample classification process through the modeling
of machine learning techniques. This research aimed to discriminate the presence or absence of adulterants, which
allows the obtaining of dairy products suitable for human consumption. Also, accelerate and specify the inspection
process of these samples. The relevance of the present study can be understood from the product under analysis:
milk. This is mass consumption, especially in children. Therefore, it is considered relevant to demonstrate efficiently
that quality products are provided to the population and this document is a contribution to the credibility of the integrity
of dairy products.
Idioma original | Inglés estadounidense |
---|---|
Título de la publicación alojada | Machine Learning Applied to Milk Sample Classification |
Lugar de publicación | Australia |
Editorial | IEOM Society International |
Capítulo | 1 |
Número de páginas | 9 |
ISBN (versión digital) | 979-8-3507-0542-3 |
Estado | Publicada - 15 mar. 2023 |