Utility of MARS Algorithm for Describing Non-Genetic Factors Affecting Pasture Revenue of Morkaraman Breed and Romanov × Morkaraman F1 Crossbred Sheep under Semi Intensive Conditions

Aksoy, Adem; Ertürk, Yakup Erdal; Eyduran, Ecevit; Tariq, Mohammad Masood

doi:10.17582/journal.pjz/2019.51.1.235.240

Cited by 5 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In solving regression-type problems, there is no need for any assumptions about both the distribution of variables and the relationships between response and explanatory variables in this algorithm [ 16 , 17 ]. The algorithm has various slopes in the training data set, splitting up the individual segmented linear segments (splines) [ 16 ]. The splines relate without problems and form connection points called “knots”.…”

Section: Methodsmentioning

confidence: 99%

Use of Multivariate Adaptive Regression Splines Algorithm to Predict Body Weight from Body Measurements of Anatolian buffaloes in Türkiye

Ağyar

Tirink

Önder

et al. 2022

Animals

View full text Add to dashboard Cite

Anatolian buffalo is an important breed reared for meat and milk in various regions of Türkiye. The present study was performed to estimate body weight (BW) from several body measurements, such as tail length (TL), shoulder height (SH), withers height (WH), body length (BL), chest circumference (CC), shank diameter (SD) and birth weight (BiW). The data set was taken from Muş Province of Türkiye. In this respect, 171 Anatolian buffaloes were used. To estimate the BW, different proportions of the training and test sets were used with the MARS algorithm. The optimal MARS was determined at a proportion of %70-%30. The MARS model displays the heaviest BW that can be produced by Anatolian buffalo according to tail length, body length, chest circumference and shoulder height. In conclusion, it could be suggested that the MARS algorithm may allow animal breeders to obtain an elite population and to determine the body measurements affecting BW as indirect selection criteria for describing the breed description of Anatolian buffalo and aiding sustainable meat production and rural development in Türkiye.

show abstract

Section: Methodsmentioning

confidence: 99%

Use of Multivariate Adaptive Regression Splines Algorithm to Predict Body Weight from Body Measurements of Anatolian buffaloes in Türkiye

Ağyar

Tirink

Önder

et al. 2022

Animals

View full text Add to dashboard Cite

show abstract

“…The K nearest neighbors’ algorithm was able to predict the breeding values with a correlation of 0.781 with the test dataset. The correlation coefficient between the predicted and true values was found to be 0.75 with a coefficient of determination of 0.557 while Aksoy et al 37 reported a much higher coefficient of determination of 0.968. They also reported that the MARS algorithm had greater predictive accuracy compared to the multiple regression analysis.…”

Section: Discussionmentioning

confidence: 88%

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

“…Moreover, these algorithms obtaining homogenous subgroups in a little while are not affected by the problem of multicollinearity, missing data and outliers [29]. Also, the supremacy of multivariate adaptive regression splines (MARS) is reported for the prediction of BW in sheep [21,[30][31][32], goat [28], camel [33] and cattle [34]. These algorithms are non-parametric methods that are commonly used for nominal, ordinal and scale variables [14,22].…”

Section: Methodsmentioning

confidence: 99%

Body Weight Prediction of Thalli Sheep Reared in Southern Punjab Using Different Data Mining Algorithms

Abbas¹,

Ullah

Waheed

2021

PPASA

View full text Add to dashboard Cite

This study is conducted to predict the body weight (BW) for Thalli sheep of southern Punjab from different body measurements. In the BW prediction, several body measurements viz., withers height, body length, head length, head width, ear length, ear width, neck length, neck width, heart girth, rump length, rump width, tail length, barrel depth and sacral pelvic width are used as predictors. The data mining algorithms such as Chi-square Automatic Interaction Detector (CHAID), Exhaustive CHAID, Classification and Regression Tree (CART) and Artificial Neural Network (ANN) are used to predict the BW for a total of 85 female Thalli sheep. The data set is partitioned into training (80 %) and test (20 %) sets before the algorithms are used. The minimum number of parent (4) and child nodes (2) are set in order to ensure their predictive ability. The R2 % and RMSE values for CHAID, Exhaustive CHAID, ANN and CART algorithms are 67.38(1.003), 64.37(1.049), 61.45(1.093) and 59.02(1.125), respectively. The mostsignificant predictor is BL in the BW prediction of Thalli sheep. The heaviest BW average of 9.596 kg is obtained from the subgroup of those having BL > 25.000 inches. On behalf of the several goodness of fit criteria, we conclude that the CHAID algorithm performance is better in order to predict the BW of Thalli sheep and more suitable decision tree diagram visually. Also, the obtained CHAID results may help to determine body measurements positively associated with BW for developing better selection strategies with the scope of indirect selection criteria.

show abstract

Utility of MARS Algorithm for Describing Non-Genetic Factors Affecting Pasture Revenue of Morkaraman Breed and Romanov × Morkaraman F1 Crossbred Sheep under Semi Intensive Conditions

Cited by 5 publications

References 11 publications

Use of Multivariate Adaptive Regression Splines Algorithm to Predict Body Weight from Body Measurements of Anatolian buffaloes in Türkiye

Use of Multivariate Adaptive Regression Splines Algorithm to Predict Body Weight from Body Measurements of Anatolian buffaloes in Türkiye

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

Body Weight Prediction of Thalli Sheep Reared in Southern Punjab Using Different Data Mining Algorithms

Contact Info

Product

Resources

About