Sınıfl andırma Ağacı Algoritmaları ve Çok Değişkenli Uyarlanabilir Regresyon Uzanımları (MARS) Kullanılarak Kıl ve Honamlı Keçilerinin Fenotipik Karakterizasyonu

Hayvanları bilimsel olarak tanımlamak ve ırkları birbirinden ayırt etmek için bazı morfolojik ve fizyolojik verilere ihtiyaç vardır. Alanında uzman olmayanlar dışında keçi ırklarını birbirinden ayırt etmek güçtür. Bu çalışma, veri madenciliği algoritmaları kullanılarak bazı vücut özellikleri üzerinden Honamlı ve Kıl keçileri için yeni bir fenotipik karakterizasyon geliştirmeyi amaçlamıştır. Çalışmada, Kıl keçisi (65 hayvan) ve Honamlı keçisinin (83 hayvan) bazı vücut özellikleri bağımsız değişkenler olarak kullanılmıştır. Veri madenciliği algoritmalarının bağımlı değişkeni ise Honamlı ve Kıl ırkları ikili yanıt değişkeni olarak tanımlanmıştır. CHAID, Exhaustive CHAID, CART, QUEST ve MARS algoritmalarının ırk ayrımındaki başarısı sırasıyla %87.80, %85.80, %87.80, %77.00 ve %88.51 iken, ROC eğrisi altında kalan alan ise sırasıyla 0.880, 0.853, 0.868, 0.784 ve 0.942 ve Cohen’s Kappa katsayıları (κ) 0.755, 0.711, 0.749, 0.549 ve 0.739 olduğu tespit edilmiştir. Sonuç olarak, morfolojik ayrımları tam olarak yapılamayan Honamlı ve Kıl keçilerinin MARS ve CHAID algoritmalarında fenotip karakterizasyonu diğer yöntemlere göre yüksek başarı ile gerçekleşmiştir. Bu çalışma, Honamlı ve Kıl keçilerinin morfolojik verilere dayalı uygun istatistiksel algoritmalarla ayırt edilebileceğini ve damızlık hayvanların kökenini tespit etmek için keçi ıslahı çalışmaları ile entegre edilebileceğini göstermiştir.

Phenotypic Characterization of Hair and Honamli Goats Using Classification Tree Algorithms and Multivariate Adaptive Regression Spline (MARS)

Some morphological and physiological data are needed to scientifically describe animals and distinguish breeds from one another. Except for those who are not experts in the field, it is difficult to distinguish goat breeds from each other. Using data mining algorithms, this study aimed to develop a new phenotypic characterization for Honamli and Hair goats via some body measurement characteristics. In the study, some body characteristics of the Hair goat (65 animals) and the Honamli goat (83 animals) were used as independent variables. Th e dependent variable of the data mining algorithms, on the other hand, was defined as the binary response variable of Honamli and Hair breeds. Th e success of the CHAID, Exhaustive CHAID, CART, QUEST, and MARS algorithms in breed discrimination was determined at 87.80%, 85.80%, 87.80%, 77.00%, and 88.51%, respectively, while the area under the ROC curve was detected 0.880, 0.853, 0.868, 0.784, and 0.942, respectively, and Cohen’s Kappa coefficient (κ) 0.755, 0.711, 0.749, 0.549 and 0.739, respectively. As a result, the phenotype characterization of Honamli and Hair goats, whose morphological distinctions could not be made exactly, in MARS and CHAID algorithms, achieved with high success compared to other methods. Th e present study showed that Honamli and Hair goats may be distinguished by suitable statistical algorithms based on morphological data, which can be integrated with goat breeding studies to detect the origin of breeding animals.

PDF

___

1. Atay O, Gökdal Ö, Eren V: Reproductive characteristics and kid marketing weights of hair goat flocks in rural conditions in Turkey. Cuba J Agric Sci, 44 (4): 353-358, 2010.
2. Karadag O: A study on the investigation of Honamli through some morphological characteristics fertility and casein genes polymorphism. PhD Thesis. Namık Kemal University Graduate School of Natural and Applied Sciences, 2016.
3. Varol M: Definition of morphological traits of Hair goats in Denizli province. MSc Thesis, Adnan Menderes University Graduate School of Natural and Applied Sciences, 2014.
4. Akbas AA, Saatci M: Growth, slaughter, and carcass characteristics of Honamlı, Hair, and Honamlı x Hair (F1) male goat kids bred under extensive conditions. Turk J Vet Anim Sci, 40 (4): 459-467, 2016. DOI: 10.3906/vet-1511-5
5. Taskaya H, Kale M: Investigation of Caprine Arthritis Encephalitis Virus (CAEV) infection in Honamlı goat breed. MAE Vet Fak Derg, 5 (2): 58-63, 2020. DOI: 10.24880/maeuvfd.682590
6. Elmaz Ö, Akbaş AA, Saatcı M: Effects of birth type on growth, fattening performance and carcass characteristics in Honamlı male kids. Kafkas Univ Vet Fak Derg, 23 (5): 749-755, 2017. DOI: 10.9775/kvfd.2017.17703
7. Bulut Z, Kurar E, Ozsensoy Y, Altunok V, Nizamlioglu M: Genetic diversity of eight domestic goat populations raised in Turkey. BioMed Res Int, 2016:2830394, 2016. DOI: 10.1155/2016/2830394
8. Karsli T, Demir E, Fidan HG, Aslan M, Karsli BA, Arik IZ, Semerci ES, Karabag K, Balcioglu MS: Determination of genetic variability, population structure and genetic differentiation of indigenous Turkish goat breeds based on SSR loci. Small Ruminant Res, 190:106147, 2020. DOI: 10.1016/j. smallrumres.2020.106147
9. Aytekin I: Effects of two different rearing systems on kid growth in Honamli goat. In, Proceedings of International Human and Nature Sciences: Problems and Solution Seeking Congress, 7-9 October, Sarajevo, Bosnia and Herzegovina, 2016.
10. Nsoso SJ, Podisi B, Otsogie E, Mokhutshwane BS, Ahmadu B: Phenotypic characterization of indigenous Tswana goats and sheep in Botswana: Continuous traits. Trop Anim Health Prod, 36 (8): 789-800, 2004. DOI: 10.1023/B:TR OP.0000045979.52357.61
11. Jordana J, Ribo O, Pelegrin M: Analysis of genetic relationships from morphological characters in Spanish goat breeds. Small Ruminant Res, 12, 301- 314, 1993. DOI: 10.1016/0921-4488(93)90065-P
12. Herrera M, Rodero E, Gutierrez MJ, Peña F, Rodero JM: Application of multifactorial discriminant analysis in the morphostructural differentiation of Andalusian caprine breeds. Small Ruminant Res, 22, 39-47, 1996. DOI: 10.1016/0921-4488(96)00863-2
13. Capote J, Delgado JV, Fresno M, Camacho ME, Molina A: Morphological variability in the Canary goat population. Small Ruminant Res, 27, 167-172, 1998. DOI: 10.1016/S0921-4488(97)00047-3
14. Herrera PSJI, Rodero E, Sànchez MD, Luque M: Raza caprina Moncaina. 1. Caracteres cuantitativos morfoestructurales. In, Proceedings of Actas XXVIII Congreso de la SEOC, 8-10 October, Granada, Spain, 2003.
15. Alpar C: Uygulamalı Çok Değişkenli Istatistiksel Yöntemler. 4th Ed., Detay Yayıncılık, Ankara, Turkey, 2017.
16. Maimon OZ, Rokach L: Data mining with decision trees: Theory and applications. In, Rocach L, Maimon O (Eds): Series In Machine Perception and Artificial Intelligence 2nd ed., World Scientific, Danvers, USA, 2014.
17. Akın M, Eyduran SP, Eyduran E: Mars algorithm in solving regression and classification type problems in agricultural sciences with R software. 1-264, Nobel Academic Publishing, Ankara, Turkey, 2020.
18. Ertugrul M: Ovine Breeding Practices. 2nd ed., Ankara University Faculty of Agriculture Publications Number: 1446, Ankara, Turkey, 1996.
19. Eyduran E, Keskin I, Erturk YE, Dag B, Tatliyer A, Tirink C, Aksahan R, Tariq MM: Prediction of fleece weight from wool characteristics of sheep using regression tree method (Chaid Algorithm). Pak J Zool, 48 (4): 957-960, 2016.
20. Orucoglu O: Determination of environmental factors affecting 305-day milk yield of Holstein cows by regression tree method. MSc Thesis. Suleyman Demirel University, Graduate School of Natural and Applied Sciences, 2011.
21. Aksahan R, Keskin I: Determination of the some body measurements effecting fattening final live weight of cattle by the regression tree analysis. Selcuk J Agr Food Sci, 2 (1): 53-59, 2015.
22. Kim SH, Kim CY, Seol DH, Choi JE, Hong SJ: Machine learning-based process-level fault detection and part-level fault classification in semiconductor etch equipment. IEEE Trans Semicond Manuf, 35, 174-185, 2022. DOI: 10.1109/ TSM.2022.3161512
23. Breiman L, Friedman JH, Olshen RA, Stone CJ: Classification and regression trees. 1-368, Chapman & Hall/CRC, Wadsworth, New York, USA, 1984.
24. Kass GV: An exploratory technique for investigating large quantities of categorical data. J R Stat Soc Ser C Appl Stat, 29 (2): 119-127, 1980. DOI: 10.2307/2986296
25. Karakaya E, Çelik Ş, Taysi MR: CHAID algoritması ile balıketi tüketimini etkileyen faktörlerin incelenmesi. JAFAG, 35 (2): 85-93, 2018. DOI: 10.13002/ jafag4381
26. Biggs D, De Ville B, Suen E: A method of choosing multiway partitions for classification and decision trees. J Appl Stat, 18 (1): 49-62, 1991. DOI: 10.1080/ 02664769100000005
27. Loh WY, Shih YS: Split selection methods for classification trees. Stat Sin, 7, 815-840, 1997.
28. Friedman JH: Multivariate adaptive regression splines. Ann Statist, 19, 1-67, 1991. DOI: 10.1214/aos/1176347963
29. Tırınk C, Eyduran E, Faraz A, Waheed A, Tauqir NA, Nabeel MS, Tariq MM, Sheikh IS: Use of multivariate adaptive regression splines for prediction of body weight from body measurements in Marecha (Camelus dromedaries) camels in Pakistan. Trop Anim Health Prod, 53 (3): 1-10, 2021. DOI: 10.1007/ s11250-021-02788-y
30. Huma ZE, Iqbal F: Predicting the body weight of Balochi sheep using a machine learning approach. Turk J Vet Anim Sci, 43 (4): 500-506, 2019. DOI: 10.3906/vet-1812-23
31. Hanley JA, McNeil BJ: The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143, 29-36, 1982. DOI: 10.1148/ radiology.143.1.7063747
32. IBM Corp. Released: IBM SPSS Statistics for Windows, Version 23.0. Armonk, NY: IBM Corp., 2015.
33. Eyduran E, Akin M, Eyduran SP: Application of multivariate adaptive regression splines in agricultural sciences through R software. 1-112, Nobel Academic Publishing, Ankara, Turkey, 2019.
34. Kuhn M: Caret: Classification and regression training. Retrieved from. https://CRAN.R-project.org/package=caret; Accessed: 07.12.2020.
35. R Core Team: R: A language and environment for statistical computing. R foundation for statistical computing, Vienna, Austria. https://www.Rproject. org/; Accessed: 05.07.2020.
36. Altay Y, Boztepe S, Eyduran E, Keskin İ, Tariq MM, Bukhari FA, Ali I: Description of factors affecting wool fineness in Karacabey Merino sheep using chaid and mars algorithms. Pak J Zool, 53 (2): 691, 2021. DOI: 10.17582/journal. pjz/20190329150359
37. Olfaz M, Tırınk C, Önder H: Use of CART and CHAID algorithms in Karayaka sheep breeding. Kafkas Univ Vet Fak Derg, 25 (1): 105-110, 2019. DOI: 10.9775/kvfd.2018.20388
38. FAO: Phenotypic Characterization of Animal Genetic Resources. FAO Animal Production and Health Guidelines No: 11. Rome, Italy, 2012.
39. Mukeherjee DK, Singh CSP, Mishra HR: Anote on some phenotypic parameters in grey and brown Bengal goats. Indian J Anim Sci, 49, 671-671, 1979.
40. Gonzalez-Martinez A, Herrera M, Luque M, Rodero E: Influence of farming system and production purpose on the morphostructure of Spanish goat breeds. Span J Agric Res, 12 (1): 117-124, 2014. DOI: 10.5424/sjar/2014121-4673
41. Zaitoun IS, Tabbaa MJ, Bdour S: Differentiation of native goat breeds of Jordan on the basis of morphostructural characteristics. Small Ruminant Res, 56, 173-182, 2005. DOI: 10.1016/j.smallrumres.2004.06.011
42. Bourzat D, Souvenir Zafindrajoana P, Lauvergne JJ, Zeuh V: Comparaison morpho-biometrique de chevres au Nord Cameroun et au Tchad (Morphological and biometric comparison of goats in Northern Cameroon and Chad). Rev Élev Méd Vét Pays Trop, 46, 667- 674, 1993.
43. Dossa LH, Wollny C, Gauly M: Spatial variation in goat populations from Benin as revealed by multivariate analysis of morphological traits. Small Ruminant Res, 73, 150-159, 2007. DOI: 10.1016/j.smallrumres.2007.01.003
44. Chacón E, Macedo F, Velázquez F, Paiva SR, Pineda E, McManus C: Morphological measurements and body indices for Cuban Creole goats and their crossbreds. R Bras Zootec, 40, 1671-1679, 2011. DOI: 10.1590/S1516- 35982011000800007
45. El Moutchou N, González Martínez AM, Chentouf M, Lairini K, Rodero E: Approach to morphological characterization of northern Morocco goat population. Cah Options Mediterr, 108, 427-432, 2014.
46. Orhan I, Duzler A, Alan A, Elmaz O, Ozgel O: Morphological investigations on the hairs of the Honamli and the Hair goat (Black goat). Kocatepe Vet J, 11 (2): 173-179, 2018. DOI: 10.30607/kvj.407473