PSX-A-21 Late-Breaking: Predicting live weight using linear body measurements in growing dairy calves

2021 ◽  
Vol 99 (Supplement_3) ◽  
pp. 371-372
Author(s):  
Vanessa Rotondo ◽  
Vern R Osborne ◽  
Marlene Paibomesai ◽  
Katharine M Wood ◽  
Sophia Jantzi
Keyword(s):  
Machine Learning ◽  
Body Weight ◽  
Linear Models ◽  
Dairy Farm ◽  
Live Weight ◽  
Dairy Calves ◽  
Body Measurements ◽  
Linear Measurements ◽  
The Right ◽  
Linear Body

Abstract The objective of this study was to explore how linear body measurements are related to body weight and can be used to predict calf body weight using linear and machine learning models. To meet these objectives, a total of 69 Holstein calves from a commercial dairy farm were enrolled in the study from wk 2 – 8 of age. Calves were weighed and linear measurements were collected weekly. Nineteen linear measurements were obtained each week, including: poll to nose, width across the eyes, width across the right ear, neck length (NL), wither height (WH), heart girth (HG), midpiece height (MH), midpiece circumference (MC), midpiece width (MW), midpiece depth (MD), midpiece width across the 13th rib (MW13), hook height, hook width, pin height, top of pin bones width (PW), nose to tail body length, the length between the withers and pins (WPL), forearm to hoof, cannon bone to hoof. These measurements were taken using a commercial soft tape measure and calipers. Using a machine learning approach, models were generated to predict BW from calf linear measurements using Weka software 3.8.5 (University of Waikato, New Zealand) using a 10-fold cross-validation method. Both linear regression (LR) and random forest (RF) models were evaluated. Across all weeks the LR model derived 12 of the 19 traits to fit the BW model (r2 = 0.93). These included: PN, NL, WH, HG, MC, MW, MD, HW, PW, MW13, WPL. The RF model slightly reduced BW predictions (r2= 0.92). The results of this study suggest that linear models built on linear measurements can accurately estimate body weight in dairy calves. These data and models generated are important to further the development of visualized weighing systems for young dairy calves and may be used to accurately predict BW without a scale.

PSIII-5 Predicting live weight using linear body measurements in growing beef calves

2021 ◽  
Vol 99 (Supplement_3) ◽  
pp. 285-285
Author(s):  
Vanessa Rotondo ◽  
Dan Tulpan ◽  
Katharine M Wood ◽  
Marlene Paibomesai ◽  
Vern R Osborne
Keyword(s):  
Machine Learning ◽  
Body Weight ◽  
Linear Models ◽  
Live Weight ◽  
Body Measurements ◽  
Learning Models ◽  
Linear Measurements ◽  
Beef Calves ◽  
Machine Learning Models ◽  
Linear Body

Abstract The objective of this study is to investigate how linear body measurements relate to and can be used to predict calf body weight using linear and machine learning models. To meet these objectives, a total of 103 Angus cross calves were enrolled in the study from wk 2 - 8. Calves were weighed and linear measurements were collected weekly, such as: poll to nose, width across the eyes (WE), width across the right ear, neck length, wither height, heart girth (HG), midpiece height (MH), midpiece circumference, midpiece width (MW), midpiece depth (MD), hook height, hook width, pin height, top of pin bones width (PW), width across the ends of pin bones, nose to tail body length, the length between the withers and pins, forearm to hoof, cannon bone to hoof. These measurements were taken using a commercial soft tape measure and calipers. To assess relationships between traits and to fit a model to predict BW, data were analyzed using the Weka (The University of Waikato, New Zealand) software using both linear regression (LR) and random forest (RF) machine learning models. The models were trained using a 10-fold cross-validation approach. The automatically derived LR model used 11 traits to fit the data to weekly BW (r2 = 0.97), where the traits with the highest coefficients were HG, PW and WE. The RF model improved further the BW predictions (r2= 0.98). Additionally, sex differences were examined. Although the BW model continued to fit well (r2 0.97), some of the top linear traits differed. The results of this study suggest that linear models built on linear measurements can accurately estimate body weight in beef calves, and that machine learning can further improve the model fit.

Prediction of body weight from linear body measurements in sheep

2017 ◽  
Author(s):  
Sandeep Kumar ◽  
S. P. Dahiya ◽  
Z. S. Dahiya ◽  
C. S. Patil
Keyword(s):  
Body Weight ◽  
Genetic Correlations ◽  
Body Height ◽  
Selection Criterion ◽  
Live Weight ◽  
Tail Length ◽  
Coefficient Of Determination ◽  
Body Measurements ◽  
Linear Type ◽  
Linear Body

Measurements of body conformation in sheep are of value in judging the quantitative characteristics of meat and also helpful in developing suitable selection criterion. Data on 349 Harnali sheep for body length (BL), body height (BH), heart girth (HG), paunch girth (PG), tail length (TL), head circumference (HC), ear length (EL), ear width (EW), face length (FL) and adult body weight (ABW) were analysed to study the relationship between linear body measurements and body weight. The mixed linear model with dam’s weight at lambing as covariate was used to study the effect of non-genetic factors on body measurements and body weight. High estimates of heritability were obtained for BL, BH, HG, TL, HC, EL, EW, FL and ABW while moderate estimate was obtained for PG. The phenotypic correlations of BL, BH, HG, PG, HC and FL with ABW were positive and significant (0.32±0.04 to 0.59±0.08). The genetic correlations of HG, PG, HC and FL with ABW were 0.51±0.13, 0.42±0.19, 0.44±0.13 and 0.43±0.15, respectively. Various combinations of linear type traits to predict ABW were found to have coefficient of determination as high as 0.92. It is concluded that heart girth is the most important trait for estimation of live weight in sheep and the prediction equation is Body weight = -63.72 + 1.23 HG with R2 = 0.87.

scholarly journals Morphometric characterization of Brahman crossbred cattle and prediction of live weight using linear body measurements

2016 ◽  
Vol 1 (3) ◽  
pp. 569-577
Author(s):  
Md Mahbubur Rashid ◽  
Md Azharul Hoque ◽  
Khan Shahidul Huque ◽  
Md Azharul Islam Talukder ◽  
AK Fazlul Huque Bhuiyan
Keyword(s):  
Body Weight ◽  
Correlation Coefficient ◽  
Live Weight ◽  
The Body ◽  
Regression Equations ◽  
Body Measurements ◽  
Crossbred Cattle ◽  
Bone Length ◽  
Bone Width ◽  
Linear Body

The present work was conducted to evaluate the variability in linear body measurements; to investigate the relationship between body linear measurements and live weight and to predict live weight of F1 Brahman crossbred cattle using body measurements. A total of 123 male and 87 female F1 Brahman crossbred cattle of 6-36 months age and weighing from 63 to 535 kg were used for the study over a period from 2010 to 2014. The study revealed that that most of the morphological measurements were linearly increased with the advances of age. The body weight had highest correlation coefficient with the heart girth around the chest (r=0.96, p<0.001) and lowest with canon bone length (r=0.49, p<0.001) compared with other body measurements. The correlations of body weight with tail length, ear length, canon bone length and canon bone width were at medium level (r=0.51-0.79). Grouping of data according to age indicated that heart girth in >24 months group had highest correlation coefficient (r=0.96) with body weight compared to ?12 months (r=0.92) and >12-24 months (r=0.95) group. The stepwise regression models revealed that heart girth singly accounted highest variation (93%) in body weight for all animals. Thus, the general equation for prediction of live weight of Brahman crossbred cattle was Y=4.07HG–356 (±6.96) where Y=live weight (Kg), HG=heart girth around the chest (cm). The regression equations for the live weight were Y=2.71HG–191 (±13.5), Y=4.05HG–357 (±9.77) and Y=4.87HG–471 (±23.0) for ?12, >12-24 and >24 months age groups. The best model for estimating body weight was obtained using HG and body length (BL) for all animals Y=2.83HG+1.80BL–392 (±6.69). These results suggested that prediction equations based on HG or in combination of HG and BL can be used efficiently in Brahman crossbred cattle to predict live weight.Asian J. Med. Biol. Res. December 2015, 1(3): 569-577

scholarly journals Use of Body Linear Measurements to Estimate Live Weight in Communal Beef Cattle

2021 ◽  
Vol 2 (2) ◽  
pp. 11-20
Author(s):  
Soul Washaya ◽  
Wesley Bvirwa ◽  
Godfrey Nyamushamba
Keyword(s):  
Body Weight ◽  
Principal Component Regression ◽  
Live Weight ◽  
Principal Component ◽  
Body Measurements ◽  
Linear Regression Models ◽  
Linear Measurements ◽  
Smallholder Farms ◽  
Accuracy Of Prediction ◽  
The Relationship

Body measurements are important criteria in the selection of elite animals for breeding. The objective of this study was to determine the relationship, accuracy of prediction of body weight from body measurements, and identifying multicollinearity from three beef breeds.  Four classes of stock (bull, cows, steers, and heifers) were considered. Correlation, simple, and multiple linear regression models were fitted with body weight (BW) as the dependent variable and body length (BL), heart girth (HG), height at wither (HW), muzzle circumference (MC), and shank circumference (SC) as the independent variables. The BW of the animals ranged from 218 to 630 kg, the least being heifers and bulls were the heaviest. The pairwise phenotypic correlations showed a high and significant positive relationship between BW and body dimensions (r = 0.751- 0.96; P<0.01). However, negative correlations were observed between BW with BL and MC of r = -0.733 and -0.703 and -0.660, -0.650, for cows and heifers, respectively. Regressing BW on BL, HG, and HW measurements gave statistically significant (P<0.01) equations with R2 ranging from 0.60 to 0.79. Collinearity, as portrayed by high variance inflation factors (VIFs), tolerance values, and low eigenvalues, was evident in four of the variables. It was concluded that the regression model was useful in BW prediction for smallholder farms and the relationship between BW and other body measurements was influenced by breed and class of stock. It is recommended that ridge regression or principal component regression be used in cases where multicollinearity exisists.

scholarly journals Statistical models based on morphometric traits for live body weight estimation in goats

2021 ◽  
Vol 13 (Volume 13, Issue 2) ◽  
pp. 134-140
Author(s):  
N.A. Ouchene-Khelifi ◽  
N. Ouchene
Keyword(s):  
Body Weight ◽  
Statistical Models ◽  
Live Weight ◽  
Abdominal Circumference ◽  
Body Measurements ◽  
Morphometric Traits ◽  
Linear Measurements ◽  
Strategic Plans ◽  
P 75 ◽  
Simple Regression Analysis

Abstract. The objective of this study was to develop statistical models to predict body weight from goat’s body measurements. Data on 1702 goats for circumferences of chest (CG), abdominal circumference (AC) and spiral circumference (SC), height at withers (WH), body length (BL), and body weight (BW) were analysed to study the relationship between linear body measurements and body weight. The present study revealed that in the goats from all breeds studied (Arabia, Makatia, Kabyle, M’zabite, Saanen and Alpine), the weight evolved in the same direction and at the same rate as the linear measurements chosen. The linear measurements were all significantly correlated with animal weight (p<0.001). Results indicated that Arabia goats had the highest WH (71.07 cm) and CG (17.72 cm). The highest measurements were reported in Alpine goats for AC (97.73 cm), BL (78.05 cm), SC (106.29 cm) and BW (41.60 kg). The Kabyle breed were recorded with the lowest values for the WH (64.95 cm), BL (67.58 cm) and BW (29.52 kg). The average live weight was 38.15±10.90 kg with differences according to age, sex and breed (Arabia, Makatia, Kabyle and M’Zabite). Positive and highly significant (p<0.001) correlations were observed between BW and the majority of independent variables. The highest relationship was illustrated between CG with BW (r=0.922). Linear regression analyses were performed to develop the models. The simple regression analysis found all parameters to be significant (p<0.001) (WH, BL, CG, AC and CS) and CG gave more precision on the weight when using a single measurement parameter (R2 varied between 0.950 and 0.967). Therefore, the following formula can be used to estimate the live weight of the animals using only the chest circumference (P=75*CG). The development of these equations would enable producers and researchers to predict the animal body weight and develop strategic plans for the relevant goat herds.

Effect of Breed and Sex on Body Weight and Linear Body Measurements of Turkeys (Meleagris gallopavo)

2019 ◽  
pp. 1-5
Author(s):  
I. M. Chana ◽  
M. Kabir ◽  
O. Orunmuyi ◽  
A. A. Musa
Keyword(s):  
Body Weight ◽  
Wing Length ◽  
Meleagris Gallopavo ◽  
The Body ◽  
Body Measurements ◽  
Neck Length ◽  
Linear Measurements ◽  
Randomized Design ◽  
Chest Girth ◽  
Linear Body

Aim: The aim of this study was to investigate the effect of breed and sex on body weight and linear body measurements of 100 Turkeys which included 50 Norfolk and 50 Mammoth breeds each. Study Design and Duration: The experiment lasted for 20 weeks during which the performance parameters were monitored in 100 Turkeys using completely randomized design. Methodology: The body weight and linear measurements were taken at an interval of two weeks (i.e. day 1, 2, 4, 6, 8, 10, 12, 14, 16, 18 and 20 weeks). Parameters monitored were shank length (cm), back length (cm), chest girth (cm), neck length (cm), thigh length, and wing length and body weight. Results: Result obtained showed that there where significant differences (P<0.05) in body weight across the breed with Norfolk having 2.70±0.04 and Mammoth 2.55±0.04. The linear measurements studied (body length, neck length, back length, shank length, thigh length, wing length, and chest girth) showed that the Norfolk had superiority over the Mammoth breed. Conclusion: Result showed remarkable and better growth performance of male turkeys than their female counterparts for all traits and ages. Also, higher values in linear body parameters noted in males.

scholarly journals Nonlinear modeling growth body weight of Mangalarga Marchador horses

2017 ◽  
Vol 47 (4) ◽  
Author(s):  
Felipe Amorim Caetano Souza ◽  
Tales Jesus Fernandes ◽  
Raquel Silva de Moura ◽  
Sarah Laguna Conceição Meirelles ◽  
Rafaela Aparecida Ribeiro ◽  
...  
Keyword(s):  
Body Weight ◽  
Linear Models ◽  
Nonlinear Modeling ◽  
Growth Curves ◽  
Live Weight ◽  
Information Criterion ◽  
Coefficient Of Determination ◽  
Cross Sectional ◽  
Adult Body Weight ◽  
The Cross

ABSTRACT: The analysis of the growth and development of various species has been done using the growth curves of the specific animal based on non-linear models. The objective of the current study was to evaluate the fit of the Brody, Gompertz, Logistic and von Bertalanffy models to the cross-sectional data of the live weight of the MangalargaMarchador horses to identify the best model and make accurate predictions regarding the growth and maturity in the males and females of this breed. The study involved recording the weight of 214 horses, of which 94 were males and 120 were non-pregnant females, between 6 and 153 months of age. The parameters of the model were estimated by employing the method of least squares, using the iteratively regularized Gauss-Newton method and the R software package. Comparison of the models was done based on the following criteria: coefficient of determination (R²); Residual Standard Deviation (RSD); corrected Akaike Information Criterion (AICc). The estimated weight of the adult horses by the models ranged between 431kg and 439kg for males and between 416kg and 420kg for females. The growth curves were studied using the cross-sectional data collection method. For males the von Bertalanffymodel was found to be the most effective in expressing growth, while in females the Brody model was more suitable. The MangalargaMarchador females achieve adult body weight earlier than the males.

INFLUENCE OF BREED, BIRTH DATE, AGE AND BODY WEIGHT ON LINEAR BODY MEASUREMENTS OF GROWING RAMS MAINTAINED IN A CONTROLLED ENVIRONMENT

1984 ◽  
Vol 64 (2) ◽  
pp. 279-291 ◽  
Author(s):  
J. N. B. SHRESTHA ◽  
D. P. HEANEY ◽  
P. S. FISER ◽  
G. A. LANGFORD
Keyword(s):  
Body Weight ◽  
Key Words ◽  
Litter Size ◽  
Body Length ◽  
Birth Date ◽  
Controlled Environment ◽  
Body Measurements ◽  
Leg Length ◽  
The Relationship ◽  
Linear Body

Heart girth (HG), body length (BL), leg length (LL), metacarpal circumference (MC), withers height (WH) and hook width (HW) of 233 growing rams of three synthetic strains, Suffolk and Finnsheep breeds were measured at 6, 8 and 10 mo of age. Thereafter, subsequent measurements were taken at 11–13 mo, 18–21 mo and 23–25 mo of age. Breed, birth period (hysterectomy derived birth date), age of ram and body weight (BW) had important effects (P < 0.05) on linear body measurements, whereas age of dam did not (P > 0.05). Significant effects of litter size on HG and BL were observed at 6 and 8 mo of age, respectively. All linear body measurements increased from 6 to 21 mo of age, whereas BL, WH and HW continued to increase to 25 mo. Rams of Strain 1, developed as a synthetic sire strain, with a large proportion of Suffolk background were generally similar to the Suffolk rams in all body measurements except for HG which was significantly larger than in Suffolk rams. The Finnsheep rams had smaller HG, BL, MC and HW than the synthetic strains and Suffolk rams, whereas LL and WH of the Finnsheep and Suffolk rams were similar. Rams of Strains 2 and 3, developed as synthetic dam strains with 50 percent Finnsheep background, were similar in body measurements. The synthetic dam strains did not differ from Strain 1 and/or Suffolk with respect to HG, BL, WH and HW. However, Suffolk rams had larger MC and shorter LL compared to those of the Strain 2 and 3 rams. Birth period had a significant effect on HG, BL, LL and MC, but no consistent trend with age of ram was apparent. Linear body measurements were positively correlated with each other and with body weight; however, the relationship varied as rams progressed in age. The importance of breed, birth date, age of ram and body weight on body measurements and the requirements for appropriate adjustments is emphasized. Key words: Sheep, body measurements, breed, birth date, age of ram

Prediction of body weight using linear body measurements in farm-bred rabbits Prediction of body weight in rabbits

2013 ◽  
Author(s):  
Karu. Pasupathi ◽  
M. Sakthivel ◽  
D. Balasubramanyam ◽  
M. Babu ◽  
P. Kumarasamy
Keyword(s):  
Body Weight ◽  
Body Measurements ◽  
Linear Body
Sign in / Sign up

Export Citation Format

Share Document