scholarly journals DESCRIBING FACTORS AFFECTING BIRTH WEIGHT AND GROWTH TRAITS IN HEMSIN LAMBS USING DECISION TREE METHODS

2011 ◽  
Vol 50 (No. 1) ◽  
pp. 14-21 ◽  
Author(s):  
E. Krupa ◽  
M. Oravcová ◽  
P. Polák ◽  
J. Huba ◽  
Z. Krupová

Growth traits of purebred calves of six beef breeds (Aberdeen Angus – AA, Blonde d’Aquitaine – BA, Charolais – CH,Hereford – HE, Limousine – LI and Beef Simmental – BS) born from 1998 to 2002 were analysed. Traits under study were birth weight (BW), weight at 120 days (W120), weight at 210 days – weaning weight (WW), weight at 365 days – yearling weight (YW) and average daily gains from birth to 120 days (ADG1), from birth to 210 days (ADG2), from birth to 365 days (ADG3), from 120 to 210 days (ADG4). General linear model with class effects of breed, dam’s age at calving, sex, herd-year-season (HYS) and covariation of age at weighing was used for analyses. All effects significantly affected both weight and gain traits except for dam’s age that was significant for BW, W120, YW and ADG3, and age at weighing that was significant for W120, WW, YW, ADG2, ADG3, ADG4. Estimated least squares means of growth traits were compared using Scheffe’s multiple-range tests. Highest BW (40.57 kg) and W120 (172.43 kg) were found for BA calves. BS calves had highest WW (260.30 kg), YW (424.07 kg), ADG1 (1 154 g), ADG2 (1 053 g), ADG3 (1 054 g) and ADG4 (1 098 g). Highest BW, YW, ADG3 and ADG4 were found for males-singles. Males-twins had highest W120, WW, ADG1 and ADG2. Calves descending from 5–7 years old dams had highest BW, W120, WW, ADG1, ADG2 and ADG4. The proportion of variability of growth traits explained by HYS effect (42.96–71.69%) was high, whereas proportions of variability explained by SEX effect (2.03–5.77%), age of dam (1.02–2.24%) and breed (1.05–2.21%) were low. Residuals accounted for 23.71 up to 53.79% of total variance.  


2016 ◽  
Vol 46 (4) ◽  
pp. 2924-2934 ◽  
Author(s):  
Muhammad Azam ◽  
Muhammad Aslam ◽  
Khushnoor Khan ◽  
Anwar Mughal ◽  
Awais Inayat

Author(s):  
Faiza Charfi ◽  
Ali Kraiem

A new automated approach for Electrocardiogram (ECG) arrhythmias characterization and classification with the combination of Wavelet transform and Decision tree classification is presented. The approach is based on two key steps. In the first step, the authors adopt the wavelet transform to extract the ECG signals wavelet coefficients as first features and utilize the combination of Principal Component Analysis (PCA) and Fast Independent Component Analysis (FastICA) to transform the first features into uncorrelated and mutually independent new features. In the second step, they utilize some decision tree methods currently in use: C4.5, Improved C4.5, CHAID (Chi - Square Automatic Interaction Detection) and Improved CHAID for the classification of ECG signals, which are taken, from the MIT-BIH database, including normal subjects and subjects affected by arrhythmia. The authors’ results suggest the high reliability and high classification accuracy of C4.5 algorithm with the bootstrap aggregation.


Sign in / Sign up

Export Citation Format

Share Document