Multiple regression and machine learning based methods for carcass traits and saleable meat cuts prediction using non-invasive in vivo measurements in commercial lambs
| Autor: | Eloisa Helena Mendes Vieira, Rebeka Magalhães da Costa, Michelle Santos da Silva, Raimundo Nonato Braga Lôbo, Vinícius de Sena Sales Viana, Anderson Antonio Carvalho Alves, Ingrid Barbosa de Mendonça, Andrés Chaparro Pinzon |
|---|---|
| Přispěvatelé: | Universidade Estadual Paulista (Unesp), Federal University of Ceará (UFC), Empresa Brasileira de Pesquisa Agropecuária (EMBRAPA) |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
Mean squared error business.industry Non invasive Bayesian network Feature selection Machine learning computer.software_genre Breed Carcass weight Hot dressing percentage Support vector regression Food Animals Linear regression Trait In vivo measurements Animal Science and Zoology Artificial intelligence business computer Mathematics |
| Zdroj: | Scopus Repositório Institucional da UNESP Universidade Estadual Paulista (UNESP) instacron:UNESP |
| Popis: | Made available in DSpace on 2019-10-06T16:11:48Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-02-01 The aim of this study is to investigate the performance of multiple linear regression and machine learning methods to predict carcass traits and commercial meat cuts in lambs using non-invasive in vivo measurements. Bayesian networks were also investigated as an alternative method for feature selection. Phenotypes from 74 nondescript breed lambs were measured. A leave-one-out cross-validation strategy was performed and predictive ability statistics (R2, RMSE) were assessed. Moderate to high prediction accuracies were observed, with R2 values across models ranging, from 0.36 to 0.88 for carcass traits and 0.65 to 0.84 for meat cuts predictions. Results suggest that support vector machine algorithm is a potential alternative to the traditional multiple linear regression model. Further, the results of this study suggest that both stepwise and Bayesian network procedures could be useful as pre-selection tools of the input variables in non-parametric approaches and the best method for feature selection may be trait and model dependent. Departament of Animal Science State University of São Paulo (FCAV-UNESP) Rodovia de Acesso Prof. PauloDonato Castellane, S/N Department of Animal Science Federal University of Ceará (UFC), Av. Mister Hull, S/N Embrapa Caprinos e Ovinos Estrada Sobral/Groaíras, km 04, Caixa postal 71 Departament of Animal Science State University of São Paulo (FCAV-UNESP) Rodovia de Acesso Prof. PauloDonato Castellane, S/N |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|