Multivariate Adaptive Regression Splines Data Mining Algorithm for Prediction of Body Weight of Hy-Line Silver Brown Commercial Layer Chicken Breed

Tyasi, Thobela Louis; Makgowo, Kgotlelelo Maaposo; Mokoena, Kwena; Rashijane, Lebo Trudy; Mathapo, Madumetja Cyril; Danguru, Lebogang William; Molabe, Kagisho Madikadike; Bopape, Paul Mogowe; Mathye, Nhlakanipho Divine; Maluleke, Dannis

doi:10.17582/journal.aavs/2020/8.8.794.799

Cited by 7 publications

(5 citation statements)

References 1 publication

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Body weight was individually weighted weekly (BW2, BW4, BW6, BW8, BW10 and BW12) using a digital balance with a sensitivity 0.1 g. Other body measurements were taken using a measuring tape (cm) biweekly which included shank length(SL), keel length (KL), chest circumference (CC) and back length (BL) according to ( Tyasi et al, 2020).…”

Section: Data Collectingmentioning

confidence: 99%

Prediction of Body weight and other linear Body Weight Measurements of Leghorn Versus Two Egyptian Strains of Chicken

Habashy

Enab

El-Tahawy

2021

Journal of Animal and Poultry Production

View full text Add to dashboard Cite

The aim of this study was to undertake the relationship between body weight and linear body measurement traits in three different chicks' strains, as well as to develop some regression equations to estimate body weight from linear body measurement. A total of 600 chicks (200 each from Fayomi (F), Golden Sabahia (GS) and White Leghorn (WL)) were used for this research. Result showed that males of the three strains were significantly higher body weight (bw) and other body measurements. Comparison of three strains also showed that GS bird was significantly better than F and WL birds for all traits under study. Lower correlation value was obtained between BW and back length (BL) and significant in male WL strain at 8 weeks old. At 12 weeks old, high, positive and significant values were observed between BW and circumference breast (CB) in female WL strain. A stepwise multiple regression analysis revealed that BW was best predicted using shank length (SL), keel length (KL), CB, BL for male WL, SL, CB, BL for female WL, GS and male F. Meanwhile, BW was best predicted using SL and CB for male GS. It was concluded that breed differences do exist between the strains under study and some of body measurements can be used as accurate indicators to improve body weight. Therefore, breeding programs designed for genetic improvement of body weight in the population of Leghorn, Golden Sabahia and Fayoumi chicks can use selection of different body measurements as selection criteria.

show abstract

Section: Data Collectingmentioning

confidence: 99%

Prediction of Body weight and other linear Body Weight Measurements of Leghorn Versus Two Egyptian Strains of Chicken

Habashy

Enab

El-Tahawy

2021

Journal of Animal and Poultry Production

View full text Add to dashboard Cite

show abstract

“…The authors used morphometric measurements in the analysis. The multivariate adaptive regression splines (MARS) algorithm was used to evaluate body weight in the Hy-line Silver Brown chicken breed (Tyasi et al, 2020). In goats, the MARS, CART, CHAID, and exhaustive CHAID algorithms were used to determine factors affecting body weight (Altay, 2022).…”

Section: Introductionmentioning

confidence: 99%

Evaluating the prediction performances of artificial neural network, nearest neighbor, and CART algorithms for body weight in Sujiang pigs using morphological measurements

Ergin,

Koskan

2024

Preprint

View full text Add to dashboard Cite

The objective of this study was to evaluate machine learning algorithms for predicting body weight in Sujiang pigs. Sujiang pigs originated from the Duroc and Jiangquhai blood lines to improve both the growth rate and lean percentage of native breeds. K nearest neighbor, decision tree (CART), and artificial neural network algorithms were used to predict body weight (BW) using morphological traits such as body length (BL), body height (BH), chest circumference (CC), hip width (HW), and backfat thickness (BFT). The age of the pigs (180±5) was also included as a nominal predictor. For this purpose, all morphological measurements taken from 365 Sujiang pigs in a previous study were used. In total, 219 individual measurements were obtained after data preprocessing. In the Sujiang pig dataset, BW had a significantly positive and high linear relationship with BH (0.66), BL (0.72), CW (0.81), HW (0.84), and CC (0.88) (p < 0.01). Overall, the ANN algorithm outperformed the KNN and DT algorithms in this pig dataset according to the goodness of fit criteria of R2 = 0.91 and RMSE = 3.1. Nevertheless, the KNN algorithm also demonstrated good predictions on the test dataset (R2 = 0.86 and RMSE = 3.57). In the ANN algorithm, several training algorithms were compared, such as the Levenberg‒Marquardt algorithm, Bayesian regularization, and scaled conjugate gradient. In addition, the number of neurons in the hidden layer was manipulated to 2, 3, or 4. All training algorithms yielded similar results. However, when the predictor variables were CC, HW, BL, and BH, the Levenberg–Marquardt network had a superior ability to predict body weight in Sujiang pigs, with R2 = 0.89 and RMSE = 3.05. Furthermore, when BL measurements were not included in the model, the model’s predictive ability decreased by approximately 6%. According to the results, the use of Levenberg‒Marquardt and Bayesian Regularization in the ANN algorithm could help to improve breeding strategies. The traits determined to be the best predictors of BW in Sujiang pigs via the ANN algorithm can be used as indirect selection criteria in the future. However, this study suggested that different age stages, breeds, and traits should be considered in the model to accurately predict BW.

show abstract

“…In commu-nal areas, where there is a lack of resources, predicting body weight from biometric traits is the easiest and affordable procedure that may greatly assist prediction (Hlokoe and Tyasi, 2021). Body weight is an economic significant trait in livestock, and it assists greatly during farm management when feeding, vaccinating, marketing animals and when measuring growth performance (Haq et al, 2020), while biometric traits play a significant role in the prediction of body weight during breeding (Yakubu et al, 2015;Tyasi et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Previous studies were performed to show the significance of biometric traits in the estimation of body weight in Girolando cattle (Weber et al, 2020), in Botswana indigenous goats and sheep (Temoso et al, 2017), and in Batur sheep (Ibrahim et al, 2021). Tyasi et al (2020) estimated the body weight of Nguni cattle using path analysis. However, based on the knowledge acquired, there is limited documentation on the prediction of body weight using biometric traits with regression method in Nguni cattle.…”

Section: Introductionmentioning

confidence: 99%

Nguni Cattle Body Weight Estimation using Regression Analysis

Tyasi¹,

Hlokoe²

2022

JAHP

View full text Add to dashboard Cite

Regression analysis is used for estimating the relationship between the dependent variable and one or more independent variables. The current study was carried out to determine the relationship among measured body measurement traits such as heart girth (HG), body weight (BW), rump width (RW), body length (BL), head length (HL), withers height (WH), ear length (EL), rump height (RH), head width (HW) and sternum height (SH), and to detect the best-fitted regression model for the prediction of BW of Nguni cattle. A total of 70 Nguni cattle (59 females and 11 males) aged 2-4 years were employed in the current study. Pearson's correlation and stepwise regression techniques were employed for the analysis of data. The association findings showed that BW had a positively high significant association (P < 0.01) with WH (r = 0.94), HG (r = 0.91), RH (r = 0.88), SH (r = 0.90), RW (r = 0.73), and a positive statistical significant correlation (P < 0.05) with EL (r = 0.47), and BL (r = 0.46) in males. On the other hand, BW had a positively high remarkable relationship (P < 0.01) with HG (r = 0.75), RH (r = 0.69) and WH (r = 0.57), and a positive statistical significant correlation (P < 0.05) with BL (r = 0.43), SH (r = 0.38) and HW (r = 0.28) in females. Stepwise regression results showed that the model, including WH, HG, SH, RH, RW, HL, EL, and BL was the best-fitted model (R 2 = 0.95, MSE = 817.51) for the estimation of BW in males, and the model with parameters of HG, RH and WH was the best-fitted model (R 2 = 0.62, MSE = 4887.31) for the estimation of BW in female Nguni cattle. Correlation outcomes suggest that enhancement of WH, HG, SH, RH, RW, EL, BL, and HW might improve the BW of Nguni cattle. The regression results suggested that BW could be estimated accurately by the combination of two or more biometric traits. The findings might help cattle farmers to predict body weight using biometric traits.

show abstract

Multivariate Adaptive Regression Splines Data Mining Algorithm for Prediction of Body Weight of Hy-Line Silver Brown Commercial Layer Chicken Breed

Cited by 7 publications

References 1 publication

Prediction of Body weight and other linear Body Weight Measurements of Leghorn Versus Two Egyptian Strains of Chicken

Prediction of Body weight and other linear Body Weight Measurements of Leghorn Versus Two Egyptian Strains of Chicken

Evaluating the prediction performances of artificial neural network, nearest neighbor, and CART algorithms for body weight in Sujiang pigs using morphological measurements

Nguni Cattle Body Weight Estimation using Regression Analysis

Contact Info

Product

Resources

About