دورية أكاديمية
ESTIMATION OF BODY WEIGHT FROM MORPHOLOGICAL MEASUREMENTS IN BOER GOATS WITH THE APPLICATION OF ARTIFICIAL NEURAL NETWORKS AND SOME REGRESSION MODELS.
| العنوان: | ESTIMATION OF BODY WEIGHT FROM MORPHOLOGICAL MEASUREMENTS IN BOER GOATS WITH THE APPLICATION OF ARTIFICIAL NEURAL NETWORKS AND SOME REGRESSION MODELS. |
|---|---|
| Alternate Title: | PROCENA TELESNE TEŽINE IZ MORFOLOŠKIH MERENJA KOD BOER KOZA PRIMENOM VEŠTAČKIH NEURALNIH MREŽA I NEKIH REGRESIJSKIH MODELA. (Slovenian) |
| المؤلفون: | TYASI, T. L., ÇELIK, Ş. |
| المصدر: | Genetika (0534-0012); 2023, Vol. 55 Issue 3, p929-949, 21p |
| مصطلحات موضوعية: | BODY weight, GOATS, AFRIKANERS, MACHINE learning, REGRESSION analysis, ARTIFICIAL neural networks |
| Abstract (English): | In this study, examination of the characteristics of body measurements affecting the body weight of Boer goats and the estimation of the body weight were investigated. To examine their body morphological features, 400 live animals were taken into consideration. The morphological measurements taken from the goats in the study were body weight (BW), body length (BL), heart girth (HG), withers height (WH), rump height (RH), rump length (RL), ear length (EL) and head with (HW) respectively. These animals were between 1-6 years old; 112 of them were male and 288 of them were female. Multiple regression, ridge regression and artificial neural networks (ANN) methods were applied to estimate the body weight. In the prediction of body weight as a dependent variable, the ANNs predictive model produced high predictive performance. Mean square error (MSE), mean absolute error (MAD) and mean absolute percent error (MAPE) statistics were used to determine model performance. Using the Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN) learning algorithm, the body features that had the greatest impact on body weight were determined. Comparison of the predictive performance of the put forward model against both multiple regression and state of the ridge regression methods showed that the artificial neural networks outperformed both competing models by achieving the least values for MAD, MSE and MAPE in both training and testing data sets. The results of artificial neural networks were promising and accurate in the prediction of the body weight of goats. [ABSTRACT FROM AUTHOR] |
| Abstract (Slovenian): | U ovoj studiji ispitivane su karakteristike telesnih merenja koje utiču na telesnu težinu burskih koza i procena telesne težine. Za ispitivanje morfoloških karakteristika uzeto je u obzir 400 živih životinja. Morfološka merenja bila su telesna težina (BV), dužina tela (BL), obim srca (HG), visina grebena (VH), visina stražnjice (RH), dužina ostatka (RL), dužina uha ( EL) i glava sa (HV) respektivno. Ove životinje su bile stare između 1-6 godina. Njih 112 bili su muškog pola, a 288 ženskog. Za procenu telesne težine primenjene su metode višestruke regresije, regresije grebena i veštačkih neuronskih mreža (ANN). U predviđanju telesne težine kao zavisne varijable, prediktivni model ANN je proizveo visoke prediktivne performanse. Statistika srednje kvadratne greške (MSE), srednje apsolutne greške (MAD) i prosečne apsolutne greške procenta (MAPE) korišćena je za određivanje performansi modela. Koristeći algoritam učenja višeslojnog perceptrona (MLP) veštačke neuronske mreže (ANN), određene su karakteristike tela koje su imale najveći uticaj na telesnu težinu. Poređenje prediktivnih performansi predloženog modela u odnosu na metode višestruke regresije i stanja grebenske regresije pokazalo je da su veštačke neuronske mreže nadmašile oba konkurentska modela postižući najmanje vrednosti za MAD, MSE i MAPE u skupovima podataka za obuku i testiranje. Rezultati veštačkih neuronskih mreža bili su obećavajući i tačni u predviđanju telesne težine koza. [ABSTRACT FROM AUTHOR] |
| Copyright of Genetika (0534-0012) is the property of Serbian Genetics Society and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| قاعدة البيانات: | Complementary Index |
Full Text Finder كن أول من يترك تعليقا!