Prediction of Body Weight by Using PCA-Supported Gradient Boosting and Random Forest Algorithms in Water Buffaloes (Bubalus bubalis) Reared in South-Eastern Mexico.

This study aims to use advanced machine learning techniques supported by Principal Component Analysis (PCA) to estimate body weight (BW) in buffalos raised in southeastern Mexico and compare their performance. The first stage of the current study consists of body measurements and the process of determining the most informative variables using PCA, a dimension reduction method. This process reduces the data size by eliminating the complex structure of the model and provides a faster and more effective learning process. As a second stage, two separate prediction models were developed with Gradient Boosting and Random Forest algorithms, using the principal components obtained from the data set reduced by PCA. The performances of both models were compared using R2, RMSE and MAE metrics, and showed that the Gradient Boosting model achieved a better prediction performance with a higher R2 value and lower error rates than the Random Forest model. In conclusion, PCA-supported modeling applications can provide more reliable results, and the Gradient Boosting algorithm is superior to Random Forest in this context. The current study demonstrates the potential use of machine learning approaches in estimating body weight in water buffalos, and will support sustainable animal husbandry by contributing to decision making processes in the field of animal science.

Multi-Trait Single-Step Genomic Prediction for Milk Yield and Milk Components for Polish Holstein Population.

The objective of our study was to evaluate the predictive ability of a multi-trait genomic prediction model that accounts for interactions between marker effects to estimate heritability and genetic correlations of traits including 305-day milk yield, milk fat percentage, milk protein percentage, milk lactose percentage, and milk dry matter percentage in the Polish Holstein Friesian cow population. For this aim, 14,742 SNP genotype records for 586 Polish Holstein Friesian dairy cows from Poland were used. Single-Trait-ssGBLUP (ST) and Multi-Trait-ssGBLUP (MT) methods were used for estimation. We examined 305-day milk yield (MY, kg), milk fat percentage (MF, %), milk protein percentage (MP, %), milk lactose percentage (ML, %), and milk dry matter percentage (MDM, %). The results showed that the highest marker effect rank correlation was found between milk fat percentage and milk dry matter. The weakest marker effect rank correlation was found between ML and all other traits. Obtained accuracies of this study were between 0.770 and 0.882, and 0.773 and 0.876 for MT and ST, respectively, which were acceptable values. All estimated bias values were positive, which is proof of underestimation. The highest heritability value was obtained for MP (0.3029) and the lowest heritability value was calculated for ML (0.2171). Estimated heritability values were low for milk yield and milk composition as expected. The strongest genetic correlation was estimated between MDM and MF (0.4990) and the weakest genetic correlation was estimated between MY and ML (0.001). The genetic relations with milk yield were negative and can be ignored as they were not significant. In conclusion, multi-trait genomic prediction can be more beneficial than single-trait genomic prediction.

Predicting carcass tissue composition in Blackbelly sheep using ultrasound measurements and machine learning methods.

This study aimed to predict Blackbelly sheep carcass tissue composition using ultrasound measurements and machine learning models. The models evaluated were decision trees, random forests, support vector machines, and multi-layer perceptrons and were used to predict the total carcass bone (TCB), total carcass fat (TCF), and total carcass muscle (TCM). The best model for predicting the three parameters, TCB, TCF, and TCM was random forests, with mean squared error (MSE) of 0.31, 0.33, and 0.53; mean absolute error (MAE) of 0.26, 0.29, and 0.53; and the coefficient of determination (R2) of 0.67, 0.69, and 0.76, respectively. The results showed that machine learning methods from in vivo ultrasound measurements can be used as determinants of carcass tissue composition, resulting in reliable results.

Predicting body weight through biometric measurements in growing hair sheep using data mining and machine learning algorithms.

Determination of live weight, which is one of the most important features that determine meat production, is a very important issue for herd management and sustainable livestock. In this context, the necessity of finding alternative methods has emerged, especially in rural conditions, due to the difficulties to be experienced in finding the weighing tool. Especially for conditions with no weighing tool, it has been tried to establish relations between the information obtained from body measurements and live weight. Since these studies will differ from species to species and breed to breed, the need for new studies is extremely high. For this aim, it is to evaluate the body measurement information obtained with the present study using several statistical approaches. To implement this aim, several data mining and machine learning algorithms such as multivariate adaptive regression splines (MARS), classification and regression tree (CART), and support vector machine regression (SVR) algorithms were used for training (70%) and test (30%) sets. To predict final body weight, 280 hair sheep breeds (162 female and 118 male) ranging from 2 months to 3 years were used with different data mining and machine learning approaches. Various goodness-of-fit criteria were used to evaluate the performances of the aforementioned algorithms. Although the MARS and SVR algorithms gave the same and highest results in terms of R2 and r values for both the train and the test sets, the SVR algorithm is one of the methods to be recommended as a result of this study, especially when other goodness-of-fit criteria are evaluated. In conclusion, the usage of SVR algorithms may be a useful tool of machine learning approaches for detecting the hair sheep breed standards and may contribute to increasing the sheep meat quality in Mexico.

Comparison of the data mining and machine learning algorithms for predicting the final body weight for Romane sheep breed.

The current study aimed to predict final body weight (weight of fourth months of age to select the future reproducers) by using birth weight, birth type, sex, suckling weight, age at suckling weight, weaning weight, age at weaning weight, and age of final body weight for the Romane sheep breed. For this purpose, classification and regression tree (CART), multivariate adaptive regression splines (MARS), and support vector machine regression (SVR) algorithms were used for training (80%) and testing (20%) sets. Different data mining and machine learning algorithms were used to predict final body weight of 393 Romane sheep (238 female and 155 male animals) were used with different artificial intelligence algorithms. The best prediction model was obtained by CART model, both training and testing set. Constructed CART models indicated that sex, suckling weight, weaning weight, age of weaning weight, and age of final weight could be used as an indirect selection measure to get a superior sheep flock on the final body weight of Romane sheep. If genetically established, the Romane sheep whose sex is female, age of final weight is over 142 days, and weaning weight is over 28 kg could be chosen for affording genetic improvement in final body weight. In conclusion, the usage of CART procedure may be worthy of reflection for identifying breed standards and choosing superior sheep for meat yield in France.

Usage of the XGBoost and MARS algorithms for predicting body weight in Kajli sheep breed.

This study aimed to utilize the XGBoost and MARS algorithms to predict present weight from body measurements. The algorithms have the potential to model nonlinear relationships between body measurements and weight, and this study attempted to find a model that provided the most accurate predictions of present weight. The current study was conducted with 152 animals in order to achieve a certain goal. To compare the model performances, goodness-of-fit criteria such as R2, r, RMSE, CV, SDratio, PI, MAPE, AIC were used. According to the results of this study, the XGBoost algorithm was the most reliable model for predicting present weight from body measurement. Even if the XGBoost algorithm was the most accurate model, the MARS algorithm was the reliable model for the same aim. In addition, it is hoped that the results of this study will help researchers and breeders better understand the relationship between body measurements and weight and ultimately be able to help individuals better manage their weight. As a conclusion, in the current study, the XGBoost algorithm is an effective, efficient, and reliable tool for accurately estimating present weight from body measurements. This makes it an invaluable tool in rural areas, where traditional weighing scales may not be available or reliable.

Estimation of Body Weight Based on Biometric Measurements by Using Random Forest Regression, Support Vector Regression and CART Algorithms.

The study's main goal was to compare several data mining and machine learning algorithms to estimate body weight based on body measurements at a different share of Polish Merino in the genotype of crossbreds (share of Suffolk and Polish Merino genotypes). The study estimated the capabilities of CART, support vector regression and random forest regression algorithms. To compare the estimation performances of the evaluated algorithms and determine the best model for estimating body weight, various body measurements and sex and birth type characteristics were assessed. Data from 344 sheep were used to estimate the body weights. The root means square error, standard deviation ratio, Pearson's correlation coefficient, mean absolute percentage error, coefficient of determination and Akaike's information criterion were used to assess the algorithms. A random forest regression algorithm may help breeders obtain a unique Polish Merino Suffolk cross population that would increase meat production.

Using the artificial bee colony technique to optimize machine learning algorithms in estimating the mature weight of camels.

This paper aims to predict male and female camels' mature weight (MW) through various morphological traits using hybrid machine learning (ML) algorithms. For this aim, biometrical measurements such as birth weight (BW), length of face (FL), length of the neck (NL), a girth of the heart (HG), body length (BL), withers height (WH), and hind leg length (HLL) were used to estimate the mature weight for eight camel breeds of Pakistan. In this study, multivariate adaptive regression splines (MARS), random forest (RF), and support vector machine (SVM) were applied to develop prediction models. Furthermore, the artificial bee colony (ABC) algorithm is employed to optimize ML models' internal parameters and improve prediction accuracy. The predictive performance of ML and hybrid models was evaluated on a testing dataset using goodness-of-fit measures such as mean absolute deviation (MAD), mean absolute percentage error (MAPE), coefficient of determination (R2), and root mean square error (RMSE). The results of the study revealed the ABC-SVM model was the best predictive model. The experimental results of this study showed that the proposed ABC-SVM method could effectively improve the accuracy for MW prediction of camels, thus having a research and practical value.

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

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 Mus 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.

Use of multivariate adaptive regression splines for prediction of body weight from body measurements in Marecha (Camelus dromedaries) camels in Pakistan.

The aim of the present work was to predict live body weight by means of some body measurements, i.e., SH, CG, and BG in indigenous Marecha camel breed. For this purpose, multivariate adaptive regression splines (MARS) algorithm was used at proportions of various training and test sets, i.e., 65:35, 70:30, and 80:20 in V-tenfold cross-validation. In prediction of live body weight of the Marecha camels (160 female and 145 male animals) in the MARS predictive models, pairs of sex-SH (model 1), sex-CG (model 2), and sex-BG (model 3) as potential predictors. The best MARS model in LW prediction was obtained using sex and SH independent variables for 80:20 training and test set. Sex was determined to be an important source of variation in SH, CG, and BG as a result of sexual dimorphism in camels (P < 0.01). MARS results indicated that SH could be used as an indirect selection criterion to obtain elite camel herds on LW of Marecha camels. If genetically confirmed, the Marecha camels whose SH is taller than 165.1 cm could be selected for providing genetic progress in LW. In conclusion, use of MARS algorithm may be worthy of consideration for better identification of camel breed standards and selection of superior Marecha camels for meat productivity in Pakistan.

Prediction of live body weight based on body measurements in Thalli sheep under tropical conditions of Pakistan using cart and mars.

Thalli sheep is a significant breed reared under tropical region of Punjab province of Pakistan. The present study was conducted to predict live body weight (LBW) by means of from some body measurements, i.e., chest girth (CG), belly girth (BG), rump height (RH), withers height (WH), neck girth (NG), and body length (BL) taken from 155 Thalli indigenous sheep of Pakistan. Age factor is determined to be a significant source of variation for BL, BG, CG, BG, WH, and NG (p < 0.05). LBW is correlated significantly with BL (0.850), CG (0.825), BG (0.849), RH (0.579), WH (0.547), and NG (0.7760), respectively (p < 0.01). For LBW prediction, CART and MARS data mining algorithms were comparatively used based on ten cross-validation method. Among 185 candidate MARS models with 1-5 degrees of interaction and 2-38 terms, the MARS model with 7 terms and no interaction effect in R software was the best model for LBW prediction on the basis of the smallest cross-validated RMSE value. Also, the optimal CART tree structure was obtained with 9 terminal nodes for the smallest cross-validated RMSE value. MARS algorithm outperformed CART in LBW prediction and explained 90.3 (%) of variability in LBW of Thalli sheep. Results of the optimal CART structure reflected that Thalli sheep with BL > 75 cm, RH > 83 cm, and NG > 55 cm has the heaviest LBW of 72 kg. The optimal MARS model displays that the heaviest LBW can be produced by Thalli sheep with BL > 71.12 cm, BG > 106.68 cm, WH > 76.2 cm, NG > 50.8 cm in 5th age group. In conclusion, it coud be recommended that MARS predictive modeling may enable animal breeders to obtain elite Thalli sheep population and to detect body measurement positively influencing LBW as indirect selection criteria for not only describing breed characterization and developing flock management standards, but also ensuring sustainable meat production and rural development in Pakistan.

Modeling and predicting the growth of indigenous Harnai sheep in Pakistan: non-linear functions and MARS algorithm.

Five non-linear functions, i.e. Gompertz, Logistic, Negative exponential, Brody and Bertalanffy, and multivariate adaptive regression splines (MARS) data mining algorithm were implemented with the objective to describe the body weight-age relationship of Harnai sheep of Balochistan, Pakistan. The data comprised of 1317 records of body weight from birth to 1 year were provided from Multi-Purpose Sheep Research Station Loralai, Balochistan. Each non-linear function and MARS algorithm were fitted to the data of male and female, single and twin and all lambs. Comparison among different non-linear models was based using the adjusted coefficient of determination ([Formula: see text]), Durbin-Watson statistic (DW), root mean square error (RMSE), Akaike's and Bayesian information criteria (AIC and BIC) and the coefficient of correlation (r) between observed and fitted live body weight. The best fit was provided by the Brody model in terms of the highest [Formula: see text] and r values and lowest RMSE, AIC and BIC values in male and female, single and twin and all lambs followed by Bertalanffy, Gompertz, Negative exponential and Logistic model in order of their goodness. The negative correlation between asymptotic weight and maturing rate inferred that animals with smaller mature weight mature fast. Though males and singles were found heavier at mature weight than females and twins, respectively, they mature more slowly. The results of the study suggested the use of the Brody model to accurately describe the weight-age relationship of Harnai sheep. The present study also showed a very high predictive performance of the MARS data mining algorithm for describing the growth of sheep. In conclusion, MARS algorithm may be a good alternative for breeders aiming at describing the weight-age relationship of Harnai sheep.

Use of MARS algorithm for predicting mature weight of different camel (Camelus dromedarius) breeds reared in Pakistan and morphological characterization via cluster analysis.

Mature weight is a significant trait that can be influenced by age, sex, breed, production system, and climate conditions in camels. In camel breeding, it is essential to describe breed standards of the studied camel breeds as part of morphological characterization and to determine morphological traits positively influencing mature weight within the scope of indirect selection criteria. This study was to find the best one among candidate models in prediction of mature weight from several morphological traits measured for eight camel breeds (Bravhi, Kachi, Kharani, Kohi, Lassi, Makrani, Pishin, and Rodbari) raised under Pakistan conditions. The morphological measurements taken from the camels in the study were birth weight (BW), weaning weight (WW), mature weight (MW), age of ridding (ARD), face length (FL), face width (FW), head length (HL), head width (HW), ear length (EL), ear width (EW), neck length (NL), neck width (NW), hump length (HL), hump width (HuW), heart girth (HG), withers height (WH), body length (BL), fore leg length (FLL), and hind leg length (HLL), respectively. In the prediction of mature body weight as a response variable, the optimal MARS predictive model with 15 terms selected by train function of the caret package produced very high predictive performance without encountering overfitting problem. Goodness of fit criteria were estimated to measure predictive quality of the MARS model using ehaGoF package available in R environment. Morphological characterization of the camel breeds was performed with hierarchical cluster analysis (HCA) on the basis of Euclidean distance-Single linkage. At the first step of hierarchical cluster analysis, the similarity level of Bravhi and Kachi camel breeds was the highest with 85.3569 (%). At the second step, Makrani joined to new cluster of Bravhi and Kachi camels found at the first step, and the similarity level of the new cluster comprising Bravhi, Kachi, and Makrani breeds was found as 84.5562 (%). MW was significantly correlated with BW (0.677), WW (0.536), HL (0.524), HuW (0.529), and ARD (0.375) at P < 0.01, and there was the highest correlation of 0.994 between HHL and FLL (P < 0.01). As a result, it could be suggested that results of MARS modeling may help camel breeders to reproduce the elite camel populations and to describe characteristics associated positively with MW within the scope of indirect selection criteria.