Prediction of marbling score and carcass traits in Korean Hanwoo beef cattle using machine learning methods and synthetic minority oversampling technique

Saleh Shahinfar; Hawlader A Al-Mamun; Byoungho Park; Sidong Kim; Cedric Gondro

doi:10.1016/j.meatsci.2019.107997

Prediction of marbling score and carcass traits in Korean Hanwoo beef cattle using machine learning methods and synthetic minority oversampling technique

Meat Sci. 2020 Mar:161:107997. doi: 10.1016/j.meatsci.2019.107997. Epub 2019 Nov 12.

Authors

Saleh Shahinfar¹, Hawlader A Al-Mamun², Byoungho Park³, Sidong Kim³, Cedric Gondro⁴

Affiliations

¹ Department of Computer Science, School of Science and Technology, University of New England, Armidale, NSW, Australia. Electronic address: shahinfar@uwalumni.com.
² CSIRO Data61, Canberra, Australian Capital Territory, Australia.
³ Animal Breeding and Genetics Division, National Institute of Animal Science, RDA, Republic of Korea.
⁴ CSIRO Data61, Canberra, Australian Capital Territory, Australia; College of Agriculture and Natural Resources, Michigan State University, East Lansing, MI, USA.

PMID: 31812939
DOI: 10.1016/j.meatsci.2019.107997

Abstract

Pricing of Hanwoo beef in the Korean market is primarily based on meat quality, and particularly on marbling score. The ability to accurately predict marbling score early in the life of an animal is extremely valuable for producers to meet the requirements of their target market, and for genetic selection. A total of 3989 Korean Hanwoo cattle (2108 with 50 k SNP genotypes) and 45 phenotypic features were available for this study. Four machine learning (ML) algorithms were applied to predict six carcass traits and compared against linear regression prediction models. In most scenarios, SMO was the best performing algorithm. The most and least accurately predicted traits were carcass weight and marbling score with correlation of 0.95 and 0.64 respectively. Additionally, the value of using a synthetic minority over-sampling technique (SMOTE) was evaluated and results showed a slight improvement in the prediction error of marbling score. Machine Learning approaches can be useful tools to predict important carcass traits in beef cattle.

Keywords: Carcass traits; GWAS; Genetic algorithm; Hanwoo Beef Cattle; Machine learning; Marbling score; SMOTE.

MeSH terms

Animals
Cattle
Food Quality*
Image Processing, Computer-Assisted / methods*
Machine Learning / statistics & numerical data*
Red Meat / analysis*
Red Meat / standards*
Reproducibility of Results
Republic of Korea
Ultrasonography / methods*