Yazar "Eyduran, Ecevit" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    DETECTING THE RELATIONSHIP OF CALIFORNIA MASTITIS TEST (CMT) WITH ELECTRICAL CONDUCTIVITY, COMPOSITION AND QUALITY OF THE MILK IN HOLSTEIN-FRIESIAN AND BROWN SWISS CATTLE BREEDS USING CART ANALYSIS
    (PARLAR SCIENTIFIC PUBLICATIONS (P S P), 2018) Aytekin, Ibrahim; Eyduran, Ecevit; Keskin, Ismail
    The aim of this study was to describe the relationship between mastitis and electrical conductivity, milk composition, milk quality in dairy cattle. California mastitis test (CMT) was used to make a diagnosis of mastitis in the cows, and considered as a binary response variable i.e. healthy and unhealthy. Conductivity, color measurement (L* and a*), milk fat, calving month and freezing point were considered as independent variables in the model. All the animals were classified with overall accuracy of 89.6 (%) or the error of 10.4 (%) in diagnosis of mastitis by using Classification and Regression Tree (CART) data mining algorithm. CART algorithm correctly classified unhealthy cows with an accuracy of 77.2%. The algorithm correctly classified healthy cows with a marvelous accuracy of 95.7% and a marvelous area value under ROC curve of 0.924, P=0.000). It was concluded that some measurements i.e. CMT, electrical conductivity, milk color values, milk composition and quality may be used to accurately detect mastitis together with the help of the CART algorithm.
  • Küçük Resim Yok
    Öğe
    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
    (ZOOLOGICAL SOC PAKISTAN, 2018) Aytekin, İbrahim; Eyduran, Ecevit; Karadaş, Köksal; Akşahan, Rifat; Keskin, İsmail
    The aim of this investigation was to develop a prediction equation for fattening final live body weight from several body measurements and fattening period of native, crossbred and exotic breeds. For this aim, a total of 103 young bulls were used. In the prediction of fattening final live weight as an output variable, several continuous predictors evaluated in the current study were: withers height (WH), back height (BH), front rump height (FRH), back rump height (BRH), body length (BL), back rump width (BRW), chest depth (CD) and chest circumference (CC). Also, the breed factor was considered as a nominal predictor and fattening period (FP) was accepted as an ordinal predictor. To obtain the prediction equation, the results of Multivariate Adaptive Regression Splines (MARS) data mining algorithm as a non-parametric regression technique was implemented. To measure predictive accuracy of MARS, model evaluation criteria such as coefficient of determination (R-2), adjusted coefficient of determination (R-ADJ(2)), SDRATIO and Pearson coefficient (r) between actual and predicted values in fattening final live weight were calculated. To reveal the highest predictive ability in the MARS algorithm, numbers of terms and basis functions were set at 21 and 45 where order of interactions was three. Except for CD, other predictors were entered into MARS model. MARS showed very high predictive capability (R-2=0.9717, R-ADJ(2)=0.9643, SDRATIO=0.168 and r=0.986) for the data evaluated in the investigation. Also, GCV value of the MARS prediction equation was found as 409.83. In conclusion, it could be suggested that a very reliable prediction equation with the predictive accuracy of nearly 100 (%) was developed in practice by using MARS data mining algorithm, which a quite remarkable tool in the prediction of fattening final live weight with interaction effects of predictors and in description of breed standards, in the development of breeding strategies and especially in the detection of ideal fattening period for each breed under the condition.
  • Küçük Resim Yok
    Öğe
    Prediction of Fleece Weight from Wool Characteristics of Sheep Using Regression Tree Method (Chaid Algorithm)
    (ZOOLOGICAL SOC PAKISTAN, 2016) Eyduran, Ecevit; Keskin, İsmail; Ertürk, Yakup Erdal; Dağ, Birol; Tatlıyer, Adile; Tirink, Cem; Akşahan, Rifat
    The goal of the current investigation was to predict the fleece weight from some physical wool characteristics of Akkaraman (47 heads) and Awassi ewes (108 heads) by using CHAID algorithm to obtain more flexible prediction through tree-based decision. All of the ewes were 2 years of age. The wool characteristics evaluated for the study were fleece weight (FW), staple length (SL), fiber length (FL), average number of crimps over a length of 5 cm (ANC) and wool fineness (WF). Results of the visual analysis from decision tree diagram demonstrated on the basis of CHAID algorithm that i) the Awassi sheep with both SL > 13 and FL <= 15 produced the heaviest FW average, ii) Akkaraman sheep was the group that had the lightest FW average (1.904 kg), none of all the analyzed characteristics influenced FW trait of Akkaraman sheep, iv) FL influenced solely FW of Awassi sheep with SL > 13 (Adjusted P < 0.05). To conclude, use of CHAID algorithm for the high heritable wool characteristics of economic significance could give precious information for determining sheep with high yields.