Applicability of machine learning methods for classifying lightweight pigs in commercial conditions
Pau Salgado-López, Joaquim Casellas, Iara Solar Diaz, Thomas Rathje, Josep Gasa, David Solà-Oriol · 2024
Read Applicability of machine learning methods for classifying lightweight pigs in commercial conditions by Pau Salgado-López, Joaquim Casellas, Iara Solar Diaz, Thomas Rathje, Josep Gasa, David Solà-Oriol (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11652721.txt.
Description
Pau Salgado-López and co-authors test whether learning algorithms can flag slow-growing pigs on commercial farms, in a 2024 study. Pigs in one batch grow at uneven rates, which strains systems that move whole groups at once. Spotting light pigs early could ease that strain. The team drew on records for tens of thousands of crossbred pigs raised under real farm conditions.
Data covered weaning, the end of the nursery stage, and slaughter. Light pigs were defined at three cut points, the lowest ten, twenty, and thirty percent by weight. A standard statistical model faced three machine learning methods on training and test splits. The setup shows whether the algorithms beat the classic approach at each growth stage. The authors frame the work as a test of fit for farm use, not just lab accuracy.
Catalog record
| CREATOR | Pau Salgado-López, Joaquim Casellas, Iara Solar Diaz, Thomas Rathje, Josep Gasa, David Solà-Oriol |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |