Evaluating advanced computing techniques for predicting breeding values in Harnali sheep

Bangar, Yogesh C.; Magotra, Ankit; Malik, B S; Malik, Z. S.; Yadav, Abhay Singh

doi:10.1007/s11250-021-02763-7

Cited by 5 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…demonstrated that the model selection procedure could be replaced by ridge regression to improve the mean response to selection and to reduce the variability of selection response. da Silva et al (2021) used multiple Bayesian models for making genomic predictions higher correlation of 0.89 between BV and predicted BV, using ANN was observed for breeding values prediction in Harnali breed sheep byBangar et al (2021). Our results correlate well with the reports ofGhotbaldini et al (2019) for the breeding values prediction for body weight in Kermani sheep who used two ANN models to arrive at the correlation coe cients of 0.703 and 0.864 for them.…”

supporting

confidence: 83%

“…and among them, the Bayesian ridge regression model had the lowest mean error value which is different from the results obtained in this study. A higher correlation of 0.90 between BV and predicted BV, using the Bayesian technique was observed for the prediction of BVs in the Harnali breed of sheep byBangar et al (2021) Out of the models, model 12 had the highest correlation but a much higher correlation (0.92) was reported by Shahinfar et al (2012) for the breeding values prediction in dairy cattle. Lopes et al (2020) also showed that the ANNs performed well for the genomic prediction of genetic merit when compared with other machine learning techniques.A…”

mentioning

confidence: 64%

“…The gradient boost hyperparameters (grid search) were n estimators = 500,1000,2000, learning rate = 0.0001,.001,0.01,.1, max depth = 1,2,4, subsample = .5,.75,1, random state = 1. Hyperparameter tuning for XGBoost included learning rate = 0.001, 0.01, 0.05, 0.1, max depth = 3, 5, 7, 10, 20, min child weight = 1, 3, 5, subsample = 0.5, 0.7, colsample by tree = 0.5, 0.7, n estimators = 50, 100, 200, 500, 1000, objective = 'reg: squarederror'Grid search was employed for arriving at the best n-neighbors for KNN which were speci ed in a tuple as[2,3,4,5,6,7,8,9,11]. MARS was used to t the training data of all three datasets K fold cross-validation.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Evaluation of Artificial Intelligence Algorithms for the Prediction of Genetic Merit

Hamadani

Ganai

Andrabi

et al. 2022

Preprint

View full text Add to dashboard Cite

As the amount of data on farms grows, it is important to evaluate the potential of artificial intelligence for making farming predictions. Considering all this, this study was undertaken to evaluate various machine learning (ML) algorithms using 52-year data for sheep. Data preparation was done before analysis. Breeding values were estimated using Best Linear Unbiased Prediction. 13 ML algorithms were evaluated for their ability to predict the breeding values. The variance inflation factor for all features selected through PCA was 1. The correlation coefficients between true and predicted values for Artificial neural networks, Bayesian ridge regression, Classification and regression trees, Genetic Algorithms, Gradient boosting algorithm, K nearest neighbours, MARS algorithm, Polynomial regression, Principal component regression, Random forests, Support Vector Machines, XGBoost algorithm were 0.852, 0.742, 0.869, 0.762, 0.915, 0.781, 0.746, 0.742, 0.746, 0.917, 0.777, 0.915 respectively for breeding value prediction. Random forests had the highest correlation coefficients. A total of 13 machine learning models were developed from the prediction of breeding values in sheep in the present study. It may be said that machine learning techniques can perform predictions with reasonable accuracies and can thus be viable alternatives to conventional strategies for breeding value prediction.

show abstract

supporting

confidence: 83%

mentioning

confidence: 64%

mentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Artificial Intelligence Algorithms for the Prediction of Genetic Merit

Hamadani

Ganai

Andrabi

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…da Silva et al 17 used multiple Bayesian models for making genomic breeding values predictions and among them, the Bayesian ridge regression model had the lowest mean error value which is different from the results obtained in this study. A higher correlation of 0.90 between BV and predicted BV, using the Bayesian technique was observed for the prediction of BVs in the Harnali breed of sheep by Bangar et al 23 .…”

Section: Discussionmentioning

confidence: 75%

“…A higher correlation of 0.89 between BV and predicted BV, using ANN was observed for breeding values prediction in Harnali breed sheep by Bangar et al 23 . Our results correlate well with the reports of Ghotbaldini et al 26 for the breeding values prediction in Kermani sheep who used two ANN models to arrive at the correlation coefficients of 0.703 and 0.864 for them.…”

Section: Discussionmentioning

confidence: 77%

Comparison of artificial intelligence algorithms and their ranking for the prediction of genetic merit in sheep

Hamadani

Ganai

Ahmad

et al. 2022

Sci Rep

View full text Add to dashboard Cite

As the amount of data on farms grows, it is important to evaluate the potential of artificial intelligence for making farming predictions. Considering all this, this study was undertaken to evaluate various machine learning (ML) algorithms using 52-year data for sheep. Data preparation was done before analysis. Breeding values were estimated using Best Linear Unbiased Prediction. 12 ML algorithms were evaluated for their ability to predict the breeding values. The variance inflation factor for all features selected through principal component analysis (PCA) was 1. The correlation coefficients between true and predicted values for artificial neural networks, Bayesian ridge regression, classification and regression trees, gradient boosting algorithm, K nearest neighbours, multivariate adaptive regression splines (MARS) algorithm, polynomial regression, principal component regression (PCR), random forests, support vector machines, XGBoost algorithm were 0.852, 0.742, 0.869, 0.915, 0.781, 0.746, 0.742, 0.746, 0.917, 0.777, 0.915 respectively for breeding value prediction. Random forests had the highest correlation coefficients. Among the prediction equations generated using OLS, the highest coefficient of determination was 0.569. A total of 12 machine learning models were developed from the prediction of breeding values in sheep in the present study. It may be said that machine learning techniques can perform predictions with reasonable accuracies and can thus be viable alternatives to conventional strategies for breeding value prediction.

show abstract

Neural network and Bayesian-based prediction of breeding values in Beetal goat

Magotra

Bangar

Yadav

2022

Trop Anim Health Prod

View full text Add to dashboard Cite

Evaluating advanced computing techniques for predicting breeding values in Harnali sheep

Cited by 5 publications

References 17 publications

Evaluation of Artificial Intelligence Algorithms for the Prediction of Genetic Merit

Evaluation of Artificial Intelligence Algorithms for the Prediction of Genetic Merit

Comparison of artificial intelligence algorithms and their ranking for the prediction of genetic merit in sheep

Neural network and Bayesian-based prediction of breeding values in Beetal goat

Contact Info

Product

Resources

About