Prediction of Fattening Final Live Weight from some Body Measurements and Fattening Period in Young Bulls of Crossbred and Exotic Breeds using MARS Data Mining Algorithm

Aytekin, İ̇brahim; Eyduran, Ecevit; Karadaş, Köksal; Akşahan, Rifat; Keskin, İsmail

doi:10.17582/journal.pjz/2018.50.1.189.195

Cited by 39 publications

(27 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The values of RMSE and MAPE obtained from RF and SVM in this study are smaller than those obtained from CART, CHAID, RBF, and MLP methods reported by Eyduran et al [15]. However, the R 2 value of 0.9717 obtained from the MARS algorithm for prediction of the fattening final weight of bulls by Aytekin et al [16] is close to the R 2 values of the RF method of this study. We observed that the RF method not only achieved much higher predictive performance than other competing methods used in this study, but also then other machine learning methods used in similar studies.…”

Section: Discussionsupporting

confidence: 63%

“…Multivariate adaptive regression splines (MARS) algorithms along with CART were employed to estimate important variables for predicting the body weights of Turkish Tazi dogs [14]. The CART, CHAID, radial basis function (RBF), and multilayer perceptron (MLP) methods were used to find the best predictive model for body weight by means of various body measurements in the indigenous Beetal goat of Pakistan [15], whereas Aytekin et al [16] applied the MARS algorithm to the prediction of fattening final weight of bulls from some body measurements. These studies have reported the potential of data mining algorithms in accurately predicting the nonlinear relation between body weight and morphological and biometrical traits of animals.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Predicting the body weight of Balochi sheep using a machine learning approach

Huma¹,

Iqbal²

2019

Turk J Vet Anim Sci

View full text Add to dashboard Cite

In the socioeconomic life of the people of Balochistan, Pakistan, sheep occupy a strategic position. The Balochi sheep is an indigenous sheep breed of Balochistan primarily reared for mutton production; it makes a significant contribution to household income in rural areas. This breed, also found in the eastern parts of Iran, is well adapted to a wide range of harsh climate conditions. Balochi sheep generally have a white medium-sized body with a fat tail and black, brown, or spotted muzzle and legs.Body weight, an important measure of animal performance, not only provides an informative measure for feeding, health care, and breeding (selection) of animals, but has also been found to be very effective in evaluating reproductive efficacy in sheep. Reproductive performance of sheep is one of the key factors in profitability [1]. For fertility in sheep, testicular length and scrotal circumference and length, among other testicular characteristics, are considered important variables [2]. The growth and development of testicular characteristics have been reported to be closely related to the body size of animals [3].Predicting the body weight of farm animals from various body traits observed at different growth periods for sheep [4,5], goat [6,7], and cattle [8,9] has been studied in detail in the literature. Most past studies have employed multiple linear regression analysis for modelling the body weight (dependent variable) of animals based on various body and testicular traits (independent variables). However, it has been reported that the strong correlation among independent variables, also known as multicollinearity, generally exists; as a consequence, large standard errors of the parameters have been obtained, resulting in inaccurate estimates [10]. As a remedy, few studies have used alternative methods such as ridge regression and factor analysis scores in multiple regression [5,11]. These statistical tools have also been employed for predicting the body weight of Balochi sheep using various biometrical traits [10]. However, these traditional methods are inadequate for explaining complex relationships.Recently, a few researchers have successfully applied various data mining and machine algorithms for the prediction of live body weight of animals using morphological traits. These methods aim to map body weight from a collection to morphological measures of animals. Applied chi-square automatic interaction detector (CHAID), exhaustive CHAID (ECHAID), classification and regression tree (CART), and artificial Abstract: Various machine learning algorithms have been used to model and predict the body weight of rams of the Balochi sheep breed of Pakistan. The traditional generalized linear model along with regression trees, support vector machine, and random forests methods have been used to develop models for the prediction of the body weight of animals. The independent variables (inputs) include the body (body length, heart girth, withers height) and testicular (scrotal diameter, scrotal circumference, scrotal lengt...

show abstract

Section: Discussionsupporting

confidence: 63%

mentioning

confidence: 99%

Predicting the body weight of Balochi sheep using a machine learning approach

Huma¹,

Iqbal²

2019

Turk J Vet Anim Sci

View full text Add to dashboard Cite

show abstract

“…There are limited number of studies using the MARS method in agricultural sciences (Aytekin et al, 2018;Celik et al, 2018;Eyduran et al, 2017). In a previous study by Chavan et al (2016), path analysis was performed to determine the direct and indirect effects of various characters in soybean.…”

Section: Discussionmentioning

confidence: 99%

“…Among those, MARS is a statistically valuable tool that can capture relationship between sets of dependent and independent variables. There are other studies on MARS algorithm in agricultural sciences (Celik et al, 2017;Eyduran et al, 2017;Aytekin et al, 2018;Aksoy et al, 2018). MARS is an algorithm that can produce a powerful prediction equation in the response variable.…”

Section: Introductionmentioning

confidence: 99%

Description of the Relationships Between Different Plant Characteristics in Soybean Using Multivariate Adaptive Regression Splines (Mars) Algorithm

2020

THE JAPS

View full text Add to dashboard Cite

The aim of this study was to reveal the relationships between several morphological characteristics of the soybean (Glycine max (L.) Merr.) plants in the year 2014. For this aim, plant height (PH), first pod height (FPH), branch number (BN), number of nodes (NN), pod number per plant (PNP), seed number per pod (SNP), 1000-seed weight (1000SW), yield per decare (YD) and harvest index (HI) were measured. Five different MARS models were developed for the plant height, first pod height, pod number, harvest index and yield per decare characteristics. The constructed models were evaluated based on the criteria of minimum generalized cross-validation (GCV), SDratio, RMSE, AIC, AICc and maximum coefficient of determination (R 2) in predictive performance. The R 2 values of the MARS models were determined to be 0.902, 0.924, 0.949, 0.987 and 0.998, respectively. For the prediction of PH, FPH and HI, the second degree interaction model was determined to be the most suitable model. For predicting PNP and YD, the third degree interaction MARS model was determined to be the best model. The dependent variables considered here was predicted with a high accuracy by all models established with the MARS algorithm. As a result, application of the MARS algorithm may allow plant breeders to obtain influential clues in selecting promising soybean varieties.

show abstract

“…In the backward procedure, unnecessary basic functions are deleted. This sustainability process is known as "pruning" and the optimal number of nodes can be found using general cross validation (GCV) (Kibet 2012, Zhang and Goh, 2016, Aytekin et al 2018, Celik and Yılmaz 2018, Eyduran et al 2017c, Sevgenler 2019, Eyduran et al 2019a, Canga and Boga 2019. In general, more basic functions (selected from a set of possible basic functions) are added to the model to maximize the goodness of fit criteria for the least squares.…”

Section: Methodsmentioning

confidence: 99%

Prediction of Egg Weight Using MARS data mining Algorithm through R

Çanga

Yavuz

Efe

2021

Kahramanmaraş Sütçü İmam Üniversitesi Tarım Ve Doğa Dergisi

View full text Add to dashboard Cite

Internal and external quality characters of poultry eggs are quitely important to determine egg weight. Also, the quality of eggs is important for both hatching and egg production. The purpose of this study was modelling of egg weight with the MARS (Multivariate Adaptive Regression Splines) method using inner and outsider quality characters of egg in Lohmann LSL Classic white hybrit flock. For this purpose, the eggs of the Lohmann LSL Classic white hybrid flock (n=60) were used. Weekly egg yields were evaluated from the 22nd week to the 62nd week. In the research, for the prediction of dependent and continuous variable egg weight; shape index (SI), shell breaking resistance (SBS), shell weight (SW), shell thickness (ST), yolk diameter (YD), yolk width (YW), yolk height (YH), color (YC ), albumen length (AW), albumen height (AL) and albumen height (AH) were used. In order to obtain perfect goodness of fit, in the "earth" package of the R program, the definitions of penalty -1, degree = 2, nprune = 10 and nk = 60. The research, the mars prediction model was determined such as EW = 63.1-0.906 * max (0,75-SI)-0.32 * max (0, SI-75) -62.4 * max (0,0.57-ST) -354 * max (0, ST-0.57) + 1.13 * Groupa2 * max (0, 75-SI) + 1.49 * (0.0.57-ST) max * YD + 8.2*max(0, ST 0.57) * YD-0.02*(0 YD-38.5)max* YC-0.0366*YH * max(0,13-YC). As a result, some quality variables were found to be important in determining egg weight. Variables such as group a2, SI, YC, ST, YD, YH to estimate the weight of the egg determined as the dependent variable were used. Other variables are not included in this equation. In the poultry, the MARS prediction model may be a better alternative to classical nonlinear models in predicting egg weight since that it is easier and has higher accuracy.

show abstract

Prediction of Fattening Final Live Weight from some Body Measurements and Fattening Period in Young Bulls of Crossbred and Exotic Breeds using MARS Data Mining Algorithm

Cited by 39 publications

References 11 publications

Predicting the body weight of Balochi sheep using a machine learning approach

Predicting the body weight of Balochi sheep using a machine learning approach

Description of the Relationships Between Different Plant Characteristics in Soybean Using Multivariate Adaptive Regression Splines (Mars) Algorithm

Prediction of Egg Weight Using MARS data mining Algorithm through R

Contact Info

Product

Resources

About