Identificador persistente para citar o vincular este elemento:
http://hdl.handle.net/10662/22097
Títulos: | Machine learning-enabled fatty acid quantification and classification of pork from autochthonous breeds using low-field 1H NMR spectroscopic data |
Autores/as: | Ramiro Alcobendas, José Luis Gómez Neo, Ana María Pérez Palacios, María Trinidad Antequera Rojas, María Teresa Fernández Marcos, Carlos María |
Palabras clave: | Lipidómica;Ácidos grasos;Modelos de regresión;Espectroscopía de Resonancia Magnética Nuclear;Cerdo ibérico;Cerdo celta;Lipidomics;Fatty acids;Regression models;Espectroscopia de resonancia magnética nuclear;Iberian pig;Celta pig |
Fecha de publicación: | 2024 |
Editor/a: | Elsevier |
Resumen: | Traditional pig breeds, known for their sustainability and superior meat quality, are experiencing growing consumer preference. The lipid fraction composition of these meats plays a fundamental role in their health benefits and excellent organoleptic properties. Accordingly, accurate characterisation of intramuscular fat is crucial for maintaining quality standards and combating fraudulent practices. This study employs benchtop nuclear magnetic resonance (NMR) spectroscopy to delineate the lipidic profiles of various cuts from two emblematic Spanish autochthonous pig breeds. The implementation of chemometric and machine learning models enabled the classification of pork samples based on cut and breed of origin. Moreover, this investigation pioneers the coupling of benchtop NMR with machine learning models for quantitative purposes, achieving precise quantification of polyunsaturated, monounsaturated and saturated fatty acids in intramuscular fat. This novel approach holds promise for enhancing the traceability and authentication of traditional pig products, fostering consumer confidence and promoting sustainable livestock practices. |
URI: | http://hdl.handle.net/10662/22097 |
DOI: | 10.1016/j.foodcont.2024.110753 |
Colección: | DQOIN - Artículos IProCar - Artículos |
Archivos
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
j_foodcont_2024_110753.pdf | 2,95 MB | Adobe PDF | Descargar |
Este elemento está sujeto a una licencia Licencia Creative Commons