Body Weight Of Cattle Research Articles

Integration of Cocoa and Cattle Towards Production and Creation Body Weight of Cattle

Cocoa is one of the main plantation crops in North Kolaka, Southeast Sulawesi, and is a strategic plantation commodity that tends to be important for the national economy because it provides employment, a source of foreign exchange, and a source of income for farmers. Manure is a waste product from livestock manure, one of which is cattle, which can be used to add nutrients and improve the physical and biological properties of soil. Integrated agriculture (crop-livestock integration) is an agricultural system characterized by the interrelationship between crop and livestock components in a farming business or an area. This study was conducted to determine the effect of manure on cocoa crop production, and to find out that feed made from cocoa fruit peel waste can increase the body weight of cattle. To find out how cattle manure and cattle feed using cocoa shell waste can be integrated in increasing cocoa production and increasing body weight in cattle. Based on the results of the research conducted, it was found that the cattle manure treatment showed the best results for each parameter observed in cocoa production, while in the cattle parameter, the provision of additional cocoa peel feed gave the highest results.

Body Weight Estimation of Cattle in Standing and Lying Postures Using Point Clouds Derived from Unmanned Aerial Vehicle-Based LiDAR

This study aims to explore body weight estimation for cattle in both standing and lying postures, using 3D data. We apply a Unmanned Aerial Vehicle-based (UAV-based) LiDAR system to collect data during routine resting periods between feedings in the natural husbandry conditions of a commercial farm, which ensures minimal interruption to the animals. Ground truth data are obtained by weighing cattle as they voluntarily pass an environmentally embedded scale. We have developed separate models for standing and lying postures and trained them on features extracted from the segmented point clouds of cattle with unique identifiers (UIDs). The models for standing posture achieve high accuracy, with a best-performance model, Random Forest, obtaining an R2 of 0.94, an MAE of 4.72 kg, and an RMSE of 6.33 kg. Multiple linear regression models are trained to estimate body weight for the lying posture, using volume- and posture-wise characteristics. The model used 1 cm as the thickness of the slice-wise volume calculation, achieving an R2 of 0.71, an MAE of 7.71 kg, and an RMSE of 9.56 kg. These results highlight the potential of UAV-based LiDAR data for accurate and non-intrusive estimation of cattle body weight in lying and standing postures, which paves the way for improved management practices in precision livestock farming.

Heritability of docility and correlation with body weight and linear body measurements in cattle

Abstract This study aimed to estimate heritability of docility and its correlations with body weight and linear body measurements in cattle. The number of animals tested for docility was 132. Fixed factors such as breed, sex, hump status and age contemporary group were fitted in the models. The body parameters measured were body weight, body length, heart girth and height at withers. Docility was scored on a scale of 1 to 5. The data was analysed using restricted maximum likelihood method. The results indicate mean docility score of 2.82 ± 1.51. The heritability of docility was 0.23 ± 0.05 which implies that docility in the cattle population can respond to selection. The heritability of body weight (0.013 ± 0.004) and the linear body measurements (range: 0.001 ± 0.15 to 0.02 ± 0.20) were very low. The genetic and phenotypic correlation between docility and body weight was 0.48 ± 0.07 and 0.60 ± 0.04 respectively. The genetic and phenotypic correlations between docility and the linear body measurements ranged from -0.99 ± 0.18 to -0.14 ± 0.25 and from 0.09 ± 0.20 to 0.60 ± 0.04 respectively. It was concluded that improvement of docility in the cattle population is possible through mass selection.

Folic acid supplementation during fattening period affects growth and nutritional metabolism in Japanese Black beef cattle

The folate requirements for beef cattle have not been established. Therefore, we investigated whether rumen-unprotected folic acid supplementation during the fattening period affects carcass traits and nutritional metabolism in Japanese Black beef cattle. Eighteen Beef cattle aged 16 months were divided into three groups: control, low folic acid supplementation (0.43 g DM/day), and high folic acid supplementation (0.86 g DM/day). Treatment was administered for 12 months. Folic acid supplementation dose-dependently increased serum folate levels, suggesting that supplemental folic acid can be absorbed into the body. Folic acid supplementation dose-dependently decreased serum vitamin B12 levels, while plasma total homocysteine and methylmalonic acid levels—markers for deficiency of folate and/or vitamin B12—were unaffected. Thus, the treatment did not clearly affect the nutritional status of these vitamins. Supplementation increased body weight, with no negative effects on other carcass traits. The levels of insulin-like growth factor 1, retinol, albumin, and some amino acids in serum or plasma were affected by supplementation. These results suggest that rumen-unprotected folic acid supplementation during the fattening period could increase the body weight of Japanese Black beef cattle and the mechanism of action may be related to growth-related hormones and/or the metabolism of some nutrients, including folate.

Machine Learning-based Prediction of Cattle Body Weight Using Muzzle Morphometrics

Body weight measurement of cattle is a tedious farm operation but is essential for their health maintenance at farm. This study proposes a novel and easier approach for cattle body weight prediction using muzzle morphometrics. Vrindavani crossbred cattle of different age groups were considered for the study. The muzzle images were collected and analyzed in MATLAB for determination of muzzle dimensions followed by mapping the dimensions to the body weight of the cattle using artificial neural network with varying network parameters. The results of the showed that all muzzle parameters had good correlation with the body weight of the cattle. Further, it was also observed that the combination of Levenberg-Marquardt training algorithm with logsigmoidal transfer function performed the best with model simulation accuracy of 78.07%. The study concludes that muzzle morphometrics may be used for body weight measurements, however, newer or diverse muzzle parameters may be considered in future works to further improve the model accuracy for a more practical application.

Relationship between parasitism with milk yield and body weight of Mafriwal cattle

Mafriwal cattle have good characteristics, but parasitism effects on their production have never been explored. This study aimed to determine the relationship between phenotypic markers of parasitism, namely packed cell volume (PCV), peripheral eosinophils count (PEC), nematode eggs (EPG), and coccidia oocyst (OPG) with the milk yield and body weight of Mafriwal cattle. Fecal and blood samples were collected from 242 cattle between 2021 and 2022. PCV and PEC were obtained from blood samples, while EPG and OPG were obtained from fecal samples. PCR was conducted to identify haemoparasite species. Milk yield data and the body weight of calves were also recorded. Spearman’s rank correlation showed that body weight has a negative correlation with PCV (r=-0.4; P<0.01) and a positive correlation with PEC (r=0.39; P<0.01) in 2022. Multiple linear regression models were used to determine the effect of phenotypic markers and year of sampling on milk yield and body weight. The best models were selected based on the lowest Akaike Information Criterion. Milk yield decreased significantly (P<0.001) from 2021 to 2022. An increase in PEC led to a significant reduction (P<0.001) in milk yield. Conversely, body weight increased significantly (P<0.001) from 2021 to 2022 and an increase in PCV caused a significant (P<0.001) reduction in body weight. Elevated EPG and OPG led to significant (P<0.01) reductions in body weight but the interaction between EPG and OPG has a significant positive (P<0.001) impact on body weight. Overall, the findings suggest that milk yield and body weight of Mafriwal cattle were significantly affected by parasitism thus necessitating the implementation of parasite control approaches.

Early Detection of Candidate Genes for Body Weight in Indonesian Cattle Breeds with Genome-Wide Association Study (GWAS)

Abstract Genome-wide association study (GWAS) was used to detect candidate genes affecting economic traits in livestock. GWAS can detect single nucleotide polymorphisms (SNPs) in all chromosome regions. This study aimed to determine the genetic markers for body weight by GWAS in native cattle breeds of Indonesia. The Illumina Bovine 50K BeadChip was used to determine the candidate genes in three mixed-sex Indonesian cattle breeds of Bali (16 animals), Madura (16 animals), and Ongole grade (13 animals). All animals were raised at the Pasuruan Regency, East Java, Indonesia breeding station. The GWAS was performed in pooled sample of animals (45 animals) with the general linear model (GLM) method using SNP markers with minimum allele frequency (MAF) values more than 0.05 by TASSEL 5.0. software. Therefore, the body weight of cattle at 1 to 3 years of age was collected for each animal for computing Manhattan plot graphics. This research found that SUGT1, SF3A3, and DSCAM genes were detected as potential genetic markers for body weight in cattle breeds of Indonesia. The SUGT1 and DSCAM genes were monomorphic in Bali cattle (Bos javanicus). In addition, both genes were significantly associated (P<0.05) with the body weight of Ongole-grade cattle (Bos indicus) at three years of age. However, the SF3A3 gene was significantly (P<0.05) associated with body weight of Madura cattle (Bos indicus) at 2 and 3 years of age. In conclusion, the GWAS of pool animals reveals three candidate genes significantly associated with body weight in many cattle breeds of Indonesia. Further study to detect SNPs in candidate genes with sequencing method is essential to apply these findings practically.

Optimizing Ongole Grade Cattle weight prediction through Principal Component Analysis

Abstract Ongole Grade (OG) cattle are commonly raised by many farmers in Indonesia, particularly in rural and remote areas where weighing scales are not readily available. The weight of these OG cattle can be estimated by utilizing their body measurements through the application of Principal Component Analysis (PCA). This research aimed to predict the body weight (BW) of OG cattle, which are primarily kept by smallholder farmers, using PCA based on various body measurements such as body length (BL), chest girth (CG), shoulder height (SH), and chest width (CW). Additionally, the effectiveness of PCA-based predictions was compared with a multiple linear regression model. This study involved a total of 120 OG cattle, comprising 26 males and 94 females. The PCA of the body measurements, as well as the correlation and regression between these measurements (BL, CG, SH, and CW) and BW, were analyzed using the R programming language. The selection criteria for identifying the best-fit model for BW prediction were based on statistical indicators including coefficient of determination (R2), Adjusted R2, residual standard error (RSE), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC). The findings of this investigation revealed that the primary factors representing body measurements were PC1 for both male (accounting for 89.21% variance) and female OG cattle (accounting for 85.71% variance). In comparison to the regression models, those generated from three PCs for males and two PCs for females demonstrated greater precision and simplicity in estimating the BW of OG cattle, without encountering multicollinearity issues. Consequently, the outcomes of this study have practical applications, serving as a means to predict the BW of OG cattle and contributing to selection programs within this cattle breed.

Analysis of the influence of the birth period on the body weight of Nelore cattle

This study aimed to present the relationship between the birth period of beef cattle and the weaning weight of Nelore calves. A total of 260,832 Nelore animals from the database of the National Association of Breeders and Researchers (ANCP) were used. Out of this total, 130,001 were males (49.84%) and 130,831 were females (50.16%) of the Nelore breed conceived via artificial insemination. The animals used were born between the years 2014 and 2017 in the Southeast and Midwest regions in different months of birth. The evaluated characteristic was the weaning weight, and the assessment of these weights was defined at 210 days (standard weaning age). It was observed that there were no significant differences (P>0.05) in weaning weight between the years of birth. However, among the birth months, significant differences (P<0.05) in weaning weight were observed, with animals born between July and October (dry season) showing higher average weights. Therefore, it was concluded that the month of birth of Nelore calves can influence the weaning weight at 210 days of age, emphasizing that the weaning month is directly related to the weight gain of the animals. Therefore, a well-defined breeding season is necessary to control the ideal months for weaning heavier animals.

The meta-analysis of beef cattle body weight prediction using body measurement approach with breed, sex, and age categories.

The aim of the study was to use a meta-analysis to identify the correlation between linear body measurements, including body length (BL), wither height (WH), heart girth (HG), and body volume (BV), and body weight in beef cattle by breed, sex, and age as categories. These results can be used as a method for predicting beef cattle body weight. This study used systematic review and meta-analysis guidelines to create a checklist. The first stage was searching for papers relevant to the study objectives. The second stage was searching using the keywords beef cattle, body weight, body measurement, and correlation. The third stage was reviewing the title and abstract. The fourth stage was abstracting information from selected papers, and the last stage was tabulating data. The results from this study were obtained, and 32 papers were eligible for the meta-analysis stage. The correlation between linear body measurement and body weight of beef cattle showed that HG (r = 0.88) and BV (r = 0.97) were significantly (p < 0.05) different compared to BL (r = 0.74) and WH (r = 0.72). The correlation between HG and body weight, and the categorization of cattle breeds showed significantly (p < 0.05) different results. The correlation between BV and body weight of cattle according to breed categories showed results that were not significantly (p > 0.05) different, while age was significantly (p < 0.05). In conclusion, to predict beef cattle body weight, it is necessary to use HG or BV, with breed, sex, and age of cattle as categories.

A first meta-analysis study on body weight prediction method for beef cattle based on digital image processing

Objective: This study aimed to develop a method for predicting the body weight of beef cattle using meta-analysis based on digital image processing. Materials and Methods: The meta-analysis process commenced by collecting studies with the keywords “beef cattle,” “correlation,” “digital image,” and “body weight” from Google Scholar and Science Direct. The obtained studies were reviewed papers based on their titles, abstracts, and content, and then categorized by authors, year, country, sample size, and correlation coefficient. A digital image of body measurements used included wither and hip height, chest depth, heart girth, body length, and top view. The statistical analysis was conducted by calculating effect sizes using the correlation coefficient and sample sizes. Results: The results of the meta-analysis, based on 3,017 cattle from 13 selected studies, showed the highest and lowest correlation coefficients for the top view variable and hip height. Based on cattle breed, significant differences (p &lt; 0.05) were observed in the wither height variable with correlation coefficients of 0.94, 0.79, and 0.66 for Hanwoo, Holstein, and Simmental, respectively. Based on sex, significant differences (p &lt; 0.05) were seen in the wither height variable, with correlation coefficients of 0.73 for males and 0.90 for females, while for hip height, the values were 0.70 and 0.87, respectively. Conclusion: In conclusion, to achieve the best accuracy in predicting the body weight of beef cattle based on a digital image, the top view variable can be used. However, for ease of field experimentation, body length or chest depth can also be used while taking breed and sex categories into the model.

Single Nucleotide Polymorphism R25C and R25H on Leptin gene and their association with body weight and measurements of Pasundan cattle

Abstract. Hilmia N, Ramdani D, Hidayat R, Widyastuti R, Hernaman I, Dudi, Edianingsih P, Arifin J. 2023. Single Nucleotide Polymorphism R25C and R25H on Leptin gene and their association with body weight and measurements of Pasundan cattle. Biodiversitas 24: 6310-6315. The Leptin gene is a potential candidate for genetic selection in livestock. Nonsynonimous Single Nucleotide Polymorphisms (SNP) Arg25Cys/R25C in Leptin gene associated with fat deposition mainly. This study aimed to identify polymorphism of Leptin Gene based on SNPs of Pasundan cattle and their association with body weight and measurements. This research used 64 DNA samples along with the corresponding body weight and measurement data from Pasundan cattle. About 9 and 7 DNA samples from Bali and Ongole cross (PO) cattle respectively, were also collected as comparisons. The DNA along 620 bp was multiplied by PCR. The SNPs in the Leptin gene on exon two were identified, followed by direct sequencing of the PCR product. The sequencing results were analyzed by BioEdit and Molecular Evolutionary Genetic Analysis (MEGA) 4.0. The General Linear Model analyzed the association between SNPs and body weight and measurements. The results showed there were two nonsynonymous SNP in the Leptin gene on exon two, i.e. g.1047C&gt;T/Arg25Cys/R25C (T allele) that changed amino acid Arginine to Cysteine and g.1048G&gt;A/Arg25His/R25H (A allele) which changed Arginine to Histidine. The frequency of the C allele in the Leptin gene on Pasundan cattle (0.54) was higher than mutation alleles, i.e. T ( 0.29) and A allele (0.17). There were six genotypes: CC (0.266), CT (0.390), CA (0.156), TT, TA, and AA 0.063 respectively. The Leptin gene mutation at the 25th position of amino acids, which changed Arginin to Cystein or Histidin (R25C and R25H), did not affect body weight and measurement in Pasundan Cattle. Therefore, nonsynonymous SNP R25C and R25H could not be used as marker genetic selection in Pasundan cattle.

ANALISIS DAMPAK PAKAN FERMENTATIF TERHADAP PENGGEMUKAN SAPI POTONG

In the cattle fattening business, feed is the main factor determining cattle growth. Providing quality feed is a challenge for ruminant breeders, both large ruminants and small ruminants, especially during the dry season where availability is very limited. Therefore, breeders are required to create other alternatives for providing quality feed, with good shelf life, at lower costs. One application of simple technology that could be a solution is through feed fermentation. This research aims to analyze: the effect of fermented feed on cattle fattening performance. The material used was 15 cows, consisting of 8 imported/foreign crossbreed cattle and 7 local cattle. The location of this fattening process is carried out at the Ibnu Hikam Tani Farmer's Cage, Kulur Sindangkasih Village, Majalengka. The method used is Operational Research (RO). The results of the research showed that by using fermented feed, the increase in body weight (ADG) of foreign breed cattle was 0.5-0.7 kg per day, while the growth of local cattle was 0.5 kg per day. Meanwhile, the average daily feed cost is IDR 20,000-25,000 per day per head. Farmers' perceptions vary regarding the price of feed and feed ingredients. Even though this self-mixed fermented feed is still below SNI standards, it does not reduce the nutritional quality for the nutritional intake needed by ruminants. This research concluded that by using fermented feed, foreign-breed cattle absorb more nutrients than local cattle. So it is recommended to improve feed quality by adding or changing the feed formula currently used.

Feature extraction using multi-view video analytics for dairy cattle body weight estimation

Accurate body weight (BW) estimation of livestock provides valuable information about animal health and welfare and can be used to assess changes in nutrient status of individuals or groups of animals. To obtain BW information regularly, automated low-cost methods that do not intrude upon normal farm operation are essential. Measurements of BW from 196 lactating, Holstein dairy cattle were collected across 5 days (655 +/- 77.1 kg; range 458 - 876 kg). This population of animals was used to develop a BW estimation system for dairy cattle using a synchronized two-camera system. The system applies deep-learning models and domain knowledge to both camera views to estimate BW of dairy cattle despite challenges such as occluding fences and crowded backgrounds. Videos from side and front-view were used to extract features about the anatomical locations and shape of the individual cows, and a regression model was applied to the features for BW prediction. We demonstrate that each view provides valuable information for BW estimation, where combining two views outperforms either view separately. This is despite the side view having distractors such as occluding fences and crowded backgrounds. The experimental results, applied to videos captured within the constraints of an operating dairy farm, demonstrate a root-mean-squared prediction error of 34 kg and a mean absolute percentage error of 4.1%, when a Random Forest is trained on four days of data and tested on the fifth unseen day. This model enabled 57% of cattle BW to be estimated within 25 kg of their measured BW. In addition, we demonstrated that linear regression generalized well to unseen data.

PSVIII-27 Beef Cattle Body Weight Forecast Monitored on Pasture Through Artificial Intelligence

Abstract The use of artificial intelligence through forecasting models for the weight of beef cattle allows decision-making regarding the production chain, which makes it more efficient and respects social, environmental and economic aspects, with ever-increasing predictions. Approaches adopting separately stochastic and deterministic components were adopted. Thus, this work, based on deterministic dynamic systems, aims to forecast the body weight of cattle simultaneously with the variables temperature, atmospheric pressure and global radiation, for the first time being monitored on pasture. Data were collected on a commercial farm located in Britânia/GO/Brazil, 158 male animals of crossbread origin,kept in 101 hectares of pasture, in a rotational system, receiving 0.3% BW day-1 of protein supplement and water ad libitum were weighed. Based on Takens' embedding theorem, it was possible to represent the phase spaces and facilitate data entry into the regression model. The models used were Multi-Layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), LightGBM, Support Vector Machine (SVM), Long Short-Term Memory (LSTM) and Echo State Network (ESN). To fit the models, the dataset was separated into 110 animals for K-fold cross-validation with 5 subsets and 48 animals for validation. Bayesian optimization was implemented to find the best hyperparameter values for each model. Three scenarios were evaluated: 7, 14 and 28 days of forecast horizon (fp), respectively. The evaluation metric used was the mean squared error (MSE), which verifies the accuracy of the models. As result, we verified according to Table 1 that the SVM presented the least MSE values for the 3 scenarios. After this step, the best model was selected, and the model was adjusted with the 110 animals and validated with the validation data. The result obtained from the MSE was 0.000071 kg². 0.000176 kg² and 0.000478 kg² for 7, 14 and 28 days of fh, respectively. According to Figure 1, the predicted values in relation to the observed values showed good results for the 3 scenarios; however, for the scenarios of 14 and 28 days, a small overestimation was observed for the body weights with the greatest values. The adjusted SMV model demonstrated that it was possible to predict meat production with deterministic models. Thus, the use of artificial intelligence methods is efficient to assist in decision making on the beef cattle production chain.

65 Machine and Deep Learning Modelling Strategies for Body Weight Prediction of Cattle and Swine

Abstract Machine Learning (ML) and Deep Learning (DL) are two sub-fields of that focus on creating predictive models from data. The algorithms used in ML and DL have been widely used in various livestock science studies, but it is uncommon for both ML and DL to be applied to the same problem. This talk presents examples where both ML and DL algorithms were successfully applied for prediction of body weight of cattle and swine. Often referred to as data-driven modelling, ML uses algorithms such as linear regression, Decision Trees, Artificial Neural Networks (ANNs) and Random Forests to generate predictive models from data. These models are then used to make predictions based on new input data. On the other hand, DL is a more advanced sub-field of AI that uses deep neural networks (a larger version of traditional ANNs) to make predictions. While the domain of application of DL is somewhat restricted to problems where datapoints have stronger relationships among them (e.g., digital images, text) DL algorithms can handle more complex relationships between input data and the target variable, making them ideal for solving more challenging problems. In the case of body weight prediction of cattle and swine, both ML and DL algorithms have been successfully used to make predictions. For example, ML algorithms have been used to predict body weight based on factors such as age, gender, and morphometric measurements. On the other hand, DL algorithms have been successfully for either direct predictions based on the relationship between body weight and other physiological parameters, such as feed intake or growth rate, or as an assistive technology for decluttering and segmentation of animal subjects from digital images with variable backgrounds. In conclusion, both ML and DL are useful tools in the field of livestock science, and both have been successfully used in the prediction of body weight of cattle and swine. However, the choice of which approach to use and its success rate will depend on the specific problem at hand and the complexity of the relationships between the input data and the target variable.

Candidate genes for longitudinal traits under sequential sampling in beef cattle.

Both the measurement age of a longitudinal trait and the common pre-sampling procedures used in beef cattle herds may affect the identification of a functional candidate gene (FCG) that is potentially associated with a trait. To identify the FCG that takes part in the genetic control of body weight at five different ages in a beef cattle population with and without sequential sampling, the animals were weighed at different measurement events, around 330, 385, 440, 495 and 550 days old. Genetic parameters were estimated for body weight at each age using a single trait (STM) and a random regression model (RRM). In addition, two different databases were used to estimate the genetic parameters: the first (DB100) was formed by all animals that were weighed in the five measurement events, and the second (DB70) has records of the same population, considering that 70% of the heaviest animals were selected after each measurement event. For DB100, genome-wide association studies (GWAS) were performed with 21,667 SNP markers to identify genomic windows that explained at least 1% of the genetic variance. Additionally, prioritization analyses were performed and FCGs were selected. We associated seven different FCGs with body weight at different ages. Among them, the gene DUSP10 was suggested as FCG in all five ages evaluated. Genetic parameters estimated for body weight using DB100 were similar when STM and RRM were applied. However, when DB70 was used as phenotypic data, there were differences between the two models. When the STM was applied, there were differences between the genetic parameters estimated for body weight when DB100 or DB70 were used as sources of phenotypes, but not for the estimates obtained with RRM. The importance of each gene for animal growth can change at different ages, and different genes may be more relevant to body weight at each different growth stage for beef cattle. Besides, sequential sampling can affect the GWAS results of a longitudinal trait. The age of the animal when a longitudinal trait is measured and pre-sampling can also contribute to inconsistencies in GWAS results for body weight in beef cattle, depending on the time when that data were collected, and consequently on the identification of FCG between studies, even when models that consider a covariance structure are used.

267 Efficacy of Using the Elastic net Regularized Regression Method to Predict Body Weight of Beef Heifers Using Body Measurements and Calculated Frame Score

Abstract Several methods to estimate the body weight (BW) of cattle have been proposed. Body measurements have proved to be useful in estimating the BW of cattle. However, there are multicollinearities between body measurements which could affect the accuracy of prediction models. Least absolute shrinkage and selection operator (LASSO regression), ridge regression, and more recently elastic net (EN) regularization has been suggested to handle multicollinearity better than simple regression. Elastic net is a regularization technique that combines LASSO and ridge regression. In this study, we modelled BW against some body measurements [calculated: volume (VL) 218 to 503 liters; frame score (FS) 2.1 to 7.5; surface area (SA) 4.02 to 7.1 m2], and direct body measurements [body length (BL) 89 to 136 cm; hip height (HH) 96 to 136 cm; hip width (HW) 33 to 52 cm; heart girth (HG) 149 to 191 cm; mid girth (MG) 177 to 234 cm; flank girth (FG) 156 to 239 cm] to examine which variable(s) predicts BW more accurately. Data from 300 heifers (9 breeds) collected over 4 years were used with year as a random effect to account for differences between years. We ran the EN model using the glmnet function of the R caret package. Ten-fold cross validation was used with 5 repeats. The EN model was trained using 206 observations and validated with 94 observations. The best model was selected based on the minimum root mean square error and median R-square (R2) values. Including FS in the prediction model resulted in the highest R2 (0.5754) and was a better predictor for BW compared with other models: VL (0.4271), SA (0.4130) and direct body measurements (0.4861). This suggests that calculated FS could be a better estimate for BW than direct body measurements and indicates that FS still accurately predicts size of heifers.

Estimation of Bali Cattle Body Weight Based on Morphological Measurements by Machine Learning Algorithms: Random Forest, Support Vector, K-Neighbors, and Extra Tree Regression

In order to forecast and model the weight of cattle a number of techniques have been used. Nonetheless, no machine algorithm has been utilized to estimate the weight of Bali cattle. This article examines the use of machine learning regression to create models for Bali cattle's body weight prediction. The response variables consist of body weight as the dependent variable and body length, girth circumference, height at wither of 228 male and 211 female cattle of similar ages (285 days). The descriptive statistics of female Bali cattle in our investigation revealed that the morphological measurements were similar to those documented by other researchers. To predict body weight on the basis of different characteristics, machine learning models such as Random Forest, Support Vector, K-Neighbors, and Extra Tree regressions have been used. Additionally, linear regression was utilized to estimate the body weight for comparison with the traditional approach. The assessment standards used included the determination coefficient, the root mean square error, the average absolute error, and the average absolute percentage error as measures of evaluation efficiency. We found that Linear Regression performs the best among all the regressors for female cattle. Similarly for male, it is about the same as extra tree regression. The machine learning algorithm (MLA) was discovered to furnish more precise estimate of the weight of the body cattle, surpassing the conventional algorithm.

Predicting body weight of South African Sussex cattle at weaning using multivariate adaptive regression splines and classification and regression tree data mining algorithms

ABSTRACT The use of multivariate adaptive regression splines (MARS) and classification and regression tree (CART) to estimate the live body weight at weaning age of the Sussex cattle breed remain poorly understood in South Africa. This study was conducted to examine the effect of linear body measurements on body weight at weaning using MARS and CART algorithms. The body weight and linear body measurements included sternum height, withers height, heart girth, hip height, body length, rump length and rump width were collected from 101 Sussex cattle (female = 57 and male = 44) at weaning. Goodness of fit criterions was used to select the best data mining algorithms. The results showed that MARS showed higher predictive performance in the criteria as compared to CART algorithm. The findings of the study suggest that MARS algorithm can be used to estimate the BW at weaning age in Sussex cattle breed. These findings might be helpful to cattle farmers in the selection criterions of breeding stock at weaning age.