Analysis by Data Mining Methods of Relationships among Egg Quality Characteristics in Japanese Quails

Abstract

This study examined the relationships between some egg quality characteristics in quails (shape index, shell thickness, shell weight, egg white index, egg white height, yolk index, yolk height and Haugh unit) and the yolk and white weights of eggs by using the CHAID (Chi-Squared Automatic Interaction Detection), Extended CHAID and CART (Classification and Regression Trees) algorithms. The CHAID, Extended CHAID and CART algorithms have significant advantages as they do not require assumptions such as normality, linearity and homogeneity. The methods were compared by using the criteria of coefficient of determination (R²), adjusted coefficient of determination () and Root Mean Square Error (RMSE). As a result, the most suitable method for determining the egg quality characteristics that are effective on the yolk weight of eggs was found to be the CHAID algorithm. With this method, the highest yolk weight was obtained from the group where egg weight was higher than 13.36 g, and the shape index was higher than 0.895. For determining the quality characteristics that affect egg white weight, the most suitable method was found to be the CART algorithm. With this method, the highest egg white weight was obtained from the group where egg weight was higher than 12.47 g, the egg white index was 0.326, and the shape index was 0.865. 

Keywords

• Quail
• CART
• CHAID
• Egg quality

Bıldırcınlarda Yumurta Kalite Özellikleri Arasındaki İlişkilerin Veri Madenciliği Yöntemleri ile İncelenmesi

Öz

Bu çalışmada, bıldırcınlarda bazı yumurta kalite özellikleri (şekil indeksi, kabuk kalınlığı, kabuk ağırlığı, ak indeksi, ak yüksekliği, sarı indeksi, sarı yüksekliği, özgül ağırlık ve Haugh birimi) ile yumurtanın sarı ve ak ağırlığı arasındaki ilişkiler CHAID (Chi-Squared Automatic Interaction Detection), Geniş CHAID ve CART (Classification and Regression Trees) algoritmaları kullanılarak incelenmiştir. CHAID, Geniş CHAID ve CART algoritmaları normallik, doğrusallık, homojenlik vb. varsayımları gerektirmediğinden önemli avantajlara sahiptirler. Yöntemlerin karşılaştırılmasında belirleme katsayısı (R²), düzeltilmiş belirleme katsayısı (), Hata Kareler Ortalamasının Karekökü (RMSE) ve Ortalama mutlak yüzde hata (MAPE) kriterleri kullanılmıştır. Sonuç olarak, yumurtaların sarı ağırlığı üzerine etkili olan yumurta kalite özelliklerinin belirlenmesinde en uygun yöntemin CHAID algoritması olduğu saptanmıştır. Bu yöntemle, en yüksek sarı ağırlığı, yumurta ağırlığının 13,36 g’dan fazla ve şekil indeksinin 0,895’ten daha yüksek olduğu gruptan elde edilmiştir. Ak ağırlığını etkileyen kalite özelliklerini belirlemede ise, en uygun yöntem CART algoritması olmuştur. Bu yönteme göre, en yüksek yumurta ak ağırlığı, yumurta ağırlığının 12.47 g’dan fazla, ak indeksinin 0,326 ve şekil indeksinin 0,865 olduğu gruptan elde edilmiştir. 

Anahtar Kelimeler

• Bıldırcın
• Yumurta kalitesi
• CHAID
• CART

References

1. Ali, M., Eyduran, E., Tariq, MM., Tirink, C., Abbas, F., Bajwa, M. A., Baloch, M. H., Nizamani, A. H., Waheed, A., Awan, M. A., Shah, S. H., Ahmad, Z. & Jan, S. (2015). Comparison of artificial neural network and decision tree algorithms used for predicting live weight at post weaning period from some biometrical characteristics in Harnai sheep. Pakistan J. Zool. 47(6), 1579-1585.
2. Balta, B. & Topal, M. (2018). Regression tree approach for assessing the effects of non-genetic factors on birth weight of Hemşin lamb. Alınteri Journal of Agricultural Science, 33(1), 65-73.
3. Csuka, J. & Ledec, M. (1981). Egg Quality Evaluation by Selected Physical Markers. Rocz. Zoot. T. 8(2), 45-58.
4. Çelik, Ş., Şengül, T., İnci, H., Söğüt, B. & Şengül, A. Y. (2017). Estimation of egg weight from some external and internal quality characteristics in quail by using various data mining algorithms. Indian Journal of Animal Sciences, 87(12), 1524–1530.
5. Çelik, Ş. & Yılmaz, O. (2018). Prediction of body weight of Turkish Tazi Dogs using Data Mining techniques: Classification and Regression Tree (CART) and Multivariate Adaptive Regression Splines (MARS). Pakistan Journal of Zoology, 50(2), 575-583.
6. Doğan, İ. (2003). Holştayn ırkı ineklerde süt verimine etki eden faktörlerin CHAID analizi ile incelenmesi. Ankara Üniversitesi Veteriner Fakültesi Dergisi, 50, 65-70.
7. Duru, M., Duru, A. A., Karadaş, K., Eyduran, E., Cinli, H. & Tariq, M. M. (2017). Effect of Carrot (Daucus carota) leaf powder on external and internal egg characteristics of Hy-Line White Laying hens. Pakistan J. Zool., 49(1), 125-132.
8. Eyduran, E., Akın, M. & Eyduran, S. P. (2019). Application of Multivariate Adaptive Regression Splines in Agricultural Sciences through R Software. Nobel Bilimsel Eserler Sertifika No: 20779, Ankara. ISBN: 978-605-2149-81-2.

9. Eyduran, E., Yılmaz, İ., Kaygısız, A. & Aktaş, Z. M. (2013). An investigation on relationship between lactation milk yield, somatic cell count and udder traits in first lactation Turkish Saanen goat using different statistical techniques. The Journal Animal Plant Science, 23(4), 956-963.
10. Eyduran, E., Zaborski, D., Waheed, A., Celik, S., Karadas, K. & Grzesiak, W. (2017). Comparison of the Predictive Capabilities of Several Data Mining Algorithms and Multiple Linear Regression in the Prediction of Body Weight by Means of Body Measurements in the Indigenous Beetal Goat of Pakistan. Pakistan Journal of Zoology, 49(1), 273-282.
11. Gevrekçi, Y. & Takma, Ç. (2018). A Comparative Study for Egg Production in Layers by Decision Tree Analysis. Pakistan J. Zool., 50(2), 437-444.
12. Grzesiak, W. & Zaborski, D. (2012). Examples of the use of data mining methods in animal breeding. (Book) ISBN 978-953-51-0720-0. Additional information is available at the end of the chapter. http://dx.doi.org/10.5772/50893.
13. Khan, M. A., Tariq, M. M., Eyduran, E., Tatlıyer, A., Rafeeq, M., Abbas, F., Rashid, N., Awan, M. A., Javed, K. (2014). Estimating body weight from several body measurements in Harnai sheep without multicollinearity problem. Journal of Animal Plant Science, 24(1), 120-126.
14. Koyuncugil, A. S. (2007). Borsa şirketlerinin sektörel risk profillerinin veri madenciliğiyle belirlenmesi. Sermaye Piyasası Kurulu Araştırma Raporu, Araştırma Dairesi, Ankara.
15. Mendeş, M. & Akkartal, E. (2009). Regression tree analysis for predicting slaughter weight in broilers. Italian Journal of Animal Science, 8, 615-624.
16. Nisbet, R., Elder, J. & Miner, G. (2009). Handbook of statistical analysis and data mining applications. Canada.
17. Oguntunji, A. O. (2017). Regression tree analysis for predicting body weight of Nigerian Muscovy duck (Cairina moschata). Genetika, 49(2), 743-753.
18. Orhan, H., Eyduran, E., Tatlıyer, A. & Saygıcı, H. (2016). Prediction of egg weight from egg quality characteristics via ridge regression and regression tree methods. Revista Brasileira de Zootecnia, 45(7), 380-385.
19. Takma, C., Atıl, H. & Aksakal, V. (2012). Comparison of Multiple Linear Regression and Artificial Neural Network Models Goodness of Fit to Lactation Milk Yields. Kafkas Üniversitesi Veteriner Fakültesi Dergisi, 18, 941-944.