Burcu Kurnaz
Research Subjects
Burcu Kurnaz has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hasan Önder
Ondokuz Mayis Üniversitesi
4 shared publications - Cem Tırınk
Department of Animal Science, Faculty of Agriculture, Igdir University, Iğdır, Türkiye
2 shared publications - Beata Sitkowska
Department of Animal Biotechnology and Genetics, Faculty of Animal Breeding and Biology, Bydgoszcz University of Science and Technology, 85-084 Bydgoszcz, Poland
1 shared publication - Dariusz Piwczyński
Department of Animal Biotechnology and Genetics, Bydgoszcz University of Science and Technology, 85-084 Bydgoszcz, Poland
1 shared publication - Hüseyin Mert Yüksel
Department of Animal Science, Faculty of Agriculture, Erciyes University, Kayseri, Turkiye
1 shared publication - Magdalena Kolenda
Department of Animal Biotechnology and Genetic, Faculty of Animal Breeding and Biology, Bydgoszcz University of Science and Technology, 85-796 Bydgoszcz, Poland
1 shared publication
Latest Publications
- 15 July 2026
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 9 (4) , 1819-1831
XGBoost Algoritması ve Saanen Oğlaklarında Vücut Ölçüleri Kullanılarak Canlı Ağırlığın Tahmini Amacıyla Kullanılması
Değişkenler arasındaki ilişkiyi matematiksel olarak modelleyen regresyon yöntemleri, gelişen bilim dünyasında istatistiki yöntemlerden biri olarak modernleşmektedir. Bu doğrultuda makine öğrenmesi yöntemleri klasik yöntemlerden ayrılarak daha uygulanabilir analizler sağlayarak karşımıza çıkmaktadırlar. Bu çalışmada 157 adet oğlak verisine ait cidago yüksekliği (CY), sağrı yüksekliği (SY), göğüs derinliği (GD), doğum ağırlığı (DA) ve vücut uzunluğu (VU) değişkenleri kullanılarak canlı ağrlık (CA) tahmini XGBoost metodu kullanılarak analiz edilmiştir. Çoklu doğrusal bağıntının varlığını tespit etmek amacıyla Varyans Şişirme Faktörü analizi sonucunda tüm değişkenler için 5 eşiğinin altında değerler bulunmuştur. Çapraz Doğrulama Kat sayısının, Ortalama Hata Kareleri Kökü üzerine etkisini göstermek amacıyla XGBoost hiperparametre ayarlaması sonucunda 7 katlı çapraz doğrulamanın marjinale ulaştığı belirlenmiştir. Optimum model; eta=0,1, max_depth=5, min_child_weight=1, subsample=0,7, colsample_bytree=0,5, gamma=0 ve best_nrounds=240 parametreleri ile elde edilmiştir. Bu model test verisinde 0,283 RMSE, 0,115 MAE ve 0,988 R² değeri ile yüksek tahmin başarısı göstermiştir. Optimize edilmiş XGBoost modeli için öğrenme eğrisine bakıldığında seçilen modelin iyi dengelenmiş olduğu ve güçlü genelleme yeteneğini koruduğu gözlemlenmiştir. Hangi değişkenlerin önemli olduğunu ve aynı zamanda model tahminlerini nasıl ve hangi yönde etkilediklerini belirlemek amacıyla hem kazanç tabanlı değişken önemi hem de SHAP analizi çıktılarına göre C2 en etkili tahminleyici olarak belirlenmiştir. Elde edilen bulgular, XGBoost algoritmasının oğlaklarda canlı ağırlık tahmininde güvenilir, başarılı ve yorumlanabilir bir yöntem olduğunu göstermektedir.
- 15 July 2026
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 9 (4) , 1819-1831
XGBoost Algoritması ve Saanen Oğlaklarında Vücut Ölçüleri Kullanılarak Canlı Ağırlığın Tahmini Amacıyla Kullanılması
Değişkenler arasındaki ilişkiyi matematiksel olarak modelleyen regresyon yöntemleri, gelişen bilim dünyasında istatistiki yöntemlerden biri olarak modernleşmektedir. Bu doğrultuda makine öğrenmesi yöntemleri klasik yöntemlerden ayrılarak daha uygulanabilir analizler sağlayarak karşımıza çıkmaktadırlar. Bu çalışmada 157 adet oğlak verisine ait cidago yüksekliği (CY), sağrı yüksekliği (SY), göğüs derinliği (GD), doğum ağırlığı (DA) ve vücut uzunluğu (VU) değişkenleri kullanılarak canlı ağrlık (CA) tahmini XGBoost metodu kullanılarak analiz edilmiştir. Çoklu doğrusal bağıntının varlığını tespit etmek amacıyla Varyans Şişirme Faktörü analizi sonucunda tüm değişkenler için 5 eşiğinin altında değerler bulunmuştur. Çapraz Doğrulama Kat sayısının, Ortalama Hata Kareleri Kökü üzerine etkisini göstermek amacıyla XGBoost hiperparametre ayarlaması sonucunda 7 katlı çapraz doğrulamanın marjinale ulaştığı belirlenmiştir. Optimum model; eta=0,1, max_depth=5, min_child_weight=1, subsample=0,7, colsample_bytree=0,5, gamma=0 ve best_nrounds=240 parametreleri ile elde edilmiştir. Bu model test verisinde 0,283 RMSE, 0,115 MAE ve 0,988 R² değeri ile yüksek tahmin başarısı göstermiştir. Optimize edilmiş XGBoost modeli için öğrenme eğrisine bakıldığında seçilen modelin iyi dengelenmiş olduğu ve güçlü genelleme yeteneğini koruduğu gözlemlenmiştir. Hangi değişkenlerin önemli olduğunu ve aynı zamanda model tahminlerini nasıl ve hangi yönde etkilediklerini belirlemek amacıyla hem kazanç tabanlı değişken önemi hem de SHAP analizi çıktılarına göre C2 en etkili tahminleyici olarak belirlenmiştir. Elde edilen bulgular, XGBoost algoritmasının oğlaklarda canlı ağırlık tahmininde güvenilir, başarılı ve yorumlanabilir bir yöntem olduğunu göstermektedir.
- Open Access
- 15 March 2025
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 8 (2) , 354-362
Examination of Distance Based Regression Methods for Different Data Structures in Animal Science
Distance-based regression is an alternative method for parameter estimation in linear regression models when mixed-type explanatory variables are used. Distance-based regression is similar to classical linear regression, except that explanatory variables are measured by distance measures rather than raw values. In this study, datasets with sample sizes of 10, 25, 50, 100, 250 and 500 produced for Binomial, Normal, t, Chi-square and Poisson distributions of Euclidean, Gower and Manhattan distance measures and real data with discrete and continuous distribution that body weight at sixth months was used as outcome variable, body length and chest depth at sixth months of Saanen kids were used as explanatory variables as continuous data. Milk fat ratio was determined as the response variable, while the number of milking per day and the season of Polish Holstein Friesian cattle were determined as the explanatory variables as discrete data. It was aimed to determine the effect on the data sets (10, 50 and 100 sample sizes) by comparing the results obtained from the Linear Regression method. R packages "dbstats", "cluster" and "tidyverse" were used to perform the analysis. As a result, it has been determined that the use of Manhattan distance in data with Poisson distribution may produce unsuccessful results, especially in small sample sizes (n
- 15 March 2025
- Published by Black Sea Journal of Engineering and Science in Black Sea Journal of Engineering and Science
- Vol. 8 (2) , 354-362
Open AccessExamination of Distance Based Regression Methods for Different Data Structures in Animal Science
Distance-based regression is an alternative method for parameter estimation in linear regression models when mixed-type explanatory variables are used. Distance-based regression is similar to classical linear regression, except that explanatory variables are measured by distance measures rather than raw values. In this study, datasets with sample sizes of 10, 25, 50, 100, 250 and 500 produced for Binomial, Normal, t, Chi-square and Poisson distributions of Euclidean, Gower and Manhattan distance measures and real data with discrete and continuous distribution that body weight at sixth months was used as outcome variable, body length and chest depth at sixth months of Saanen kids were used as explanatory variables as continuous data. Milk fat ratio was determined as the response variable, while the number of milking per day and the season of Polish Holstein Friesian cattle were determined as the explanatory variables as discrete data. It was aimed to determine the effect on the data sets (10, 50 and 100 sample sizes) by comparing the results obtained from the Linear Regression method. R packages "dbstats", "cluster" and "tidyverse" were used to perform the analysis. As a result, it has been determined that the use of Manhattan distance in data with Poisson distribution may produce unsuccessful results, especially in small sample sizes (n
- 1 July 2022
- Published by Ondokuz Mayis University in Black Sea Journal of Agriculture
- Vol. 5 (3) , 311-313
3-D Classification of Agricultural Areas of Turkey using Mammalian Livestock Existence
Animal production is valuable importance for human being and countries in terms of both economic and human nutrition. To increase the value of benefits from the livestock sector, there are many attempts to make policies. In this study, 26 different agricultural areas of Turkey according to their agricultural properties were clustered by using mammalian livestock existence such as cattle, water buffalo, sheep, goat and horse. For this aim 3-D clustering was applied using R software with FactoMineR and factoextra packages. The results showed that the number of 26 agricultural areas were clustered in four clusters. TR83 area including Samsun, Tokat, Çorum and Amasya cities was formed in a cluster lonely. The second cluster included agricultural areas of TRA2, TRC2 and TRB2 that these areas consist of the cities Ağrı, Kars, Iğdır, Ardahan, Şanlıurfa, Diyarbakır, Van, Muş, Bitlis and Hakkari. TRC3, TR62 and TR61 agricultural areas formed the third cluster including the cities of Mardin, Batman, Şırnak, Siirt, Adana, Mersin, Antalya, Isparta and Burdur. The other agricultural areas were included in the fourth cluster. These results are also important for traders' financial and human capital and trading practices such as the use of brokers and regular suppliers and customers had varying effects on margins and costs of animal trade. It is also amenable to public policy to improve the market environment and marketing efficiency.
- 1 July 2022
- Published by Ondokuz Mayis University in Black Sea Journal of Agriculture
- Vol. 5 (3) , 311-313
3-D Classification of Agricultural Areas of Turkey using Mammalian Livestock Existence
Animal production is valuable importance for human being and countries in terms of both economic and human nutrition. To increase the value of benefits from the livestock sector, there are many attempts to make policies. In this study, 26 different agricultural areas of Turkey according to their agricultural properties were clustered by using mammalian livestock existence such as cattle, water buffalo, sheep, goat and horse. For this aim 3-D clustering was applied using R software with FactoMineR and factoextra packages. The results showed that the number of 26 agricultural areas were clustered in four clusters. TR83 area including Samsun, Tokat, Çorum and Amasya cities was formed in a cluster lonely. The second cluster included agricultural areas of TRA2, TRC2 and TRB2 that these areas consist of the cities Ağrı, Kars, Iğdır, Ardahan, Şanlıurfa, Diyarbakır, Van, Muş, Bitlis and Hakkari. TRC3, TR62 and TR61 agricultural areas formed the third cluster including the cities of Mardin, Batman, Şırnak, Siirt, Adana, Mersin, Antalya, Isparta and Burdur. The other agricultural areas were included in the fourth cluster. These results are also important for traders' financial and human capital and trading practices such as the use of brokers and regular suppliers and customers had varying effects on margins and costs of animal trade. It is also amenable to public policy to improve the market environment and marketing efficiency.
- Open Access
- 14 March 2022
- Published by West Pomeranian University of Technology, Szczecin in Acta Scientiarum Polonorum Zootechnica
- Vol. 20 (3) , 41-44
Determination of the Best Model to Predict Milk Dry Matter in High Milk Yielding Dairy Cattle
This study was aimed to determinate the best model to predict milk dry matter in high milk yielding dairy cattle. Level of milk dry matter (MDM) (%) is of great importance. The material of this study consisted of 2208 milking records of dairy cattle yielding more than 40 l per day from Polish Holstein Friesian population. In this study to estimate the milk dry matter, regression of daily milk yield (MY) (l), milk urea (MU), milk protein (MP) (%) and milk fat (MF) (%) as explanatory variables were used. To estimate the best fitting, curve estimation was used. Estimation of the curves showed that milk urea was cubic, milk yield, milk protein and milk fat were quadratic. To avoid multicollinearity where VIF value greater than 10, stepwise variable selection procedure was used. After variable selection the regression equation was obtained as MDM=2.879+1.290*MF+2.395*MP-0.039*MF^2–0.225*MP^2 with 0.946 coefficient of determination. Our results showed that milk fat (%) and milk protein (%) can be used to estimate the milk dry matter (%) with a great achievement in high milk yielding dairy cattle.
- 14 March 2022
- Published by West Pomeranian University of Technology, Szczecin in Acta Scientiarum Polonorum Zootechnica
- Vol. 20 (3) , 41-44
Open AccessDetermination of the Best Model to Predict Milk Dry Matter in High Milk Yielding Dairy Cattle
This study was aimed to determinate the best model to predict milk dry matter in high milk yielding dairy cattle. Level of milk dry matter (MDM) (%) is of great importance. The material of this study consisted of 2208 milking records of dairy cattle yielding more than 40 l per day from Polish Holstein Friesian population. In this study to estimate the milk dry matter, regression of daily milk yield (MY) (l), milk urea (MU), milk protein (MP) (%) and milk fat (MF) (%) as explanatory variables were used. To estimate the best fitting, curve estimation was used. Estimation of the curves showed that milk urea was cubic, milk yield, milk protein and milk fat were quadratic. To avoid multicollinearity where VIF value greater than 10, stepwise variable selection procedure was used. After variable selection the regression equation was obtained as MDM=2.879+1.290*MF+2.395*MP-0.039*MF^2–0.225*MP^2 with 0.946 coefficient of determination. Our results showed that milk fat (%) and milk protein (%) can be used to estimate the milk dry matter (%) with a great achievement in high milk yielding dairy cattle.