Yumurta Verimi Üzerine Bazı Özelliklerin Etkisinin Regresyon Analiz Yöntemlerinden Bagging Mars ile Belirlenmesi ve R Uygulaması

Çalışmada, BAGGING ile MARS birleştirilerek elde edilen hibrid bir yaklaşımın yumurta tavuklarından elde edilen bir veri setinde sıcaklık ve nemin yumurta verimi, kırık/çatlak yumurta, ölen hayvan sayısı ve yem tüketimi üzerine etkisinin olup olmadığı test edilmiştir. Çalışmada Adana ili Çukurova Bölgesinde bulunan özel bir hayvancılık işletmesinden 2018 yılına ait yumurta üretim işletmesinden elde edilen veriler kullanılmıştır. Araştırmada, ortalama 60 haftalık yaşta olan Lohman ırkı tavuklardan elde edilen veri seti kullanılmıştır. Oluşan MARS ve Bagging MARS algoritmasında regresyon problemlerinin daha güçlü bir çözümünü sunmak için R STUDIO programındaki earth (enhanced adaptive regression through hinges) ve caret (classification and regression training), mda (Mixture Discriminant Analysis) paketleri kullanılmıştır. Bagging MARS tekniğinin tahmin performansı, bootstrap örnek sayısı olan B değeri 3 alınarak uyum iyiliği kriterleri ile değerlendirilmiştir. Çalışmada, MARS ve bagging MARS analizi kullanarak sıcaklık ve nemin yumurta verimi, kırık/çatlak yumurta, ölen hayvan sayısı ve yem tüketimi üzerine etkisi araştırılmıştır. Yumurta verimi üzerine, akşam sıcaklığının(t3) etkisinin olduğu fakat sabah(t1) ve öğle(t2) sıcaklıklarının ise etkisinin olmadığı belirtilmiştir. Kırık/çatlak yumurta ve ölen hayvan hayvan sayısı 5 den az/ hafta olmasından dolayı, MARS ve Bagging MARS modellerinde bu değişkenlere tahmin denkleminde yer verilmemiştir. Yem tüketiminin ise, her iki modelde de pozitif bir katkısının olduğu görülmüştür.

Determination of the Effect of Some Properties on Egg Yield with Regression Analysis Met-hod Bagging Mars and R Application

In the study, it has been demonstrated its use for a data set obtained from layer hens in a hybrid approach obtained by combining BAGGING and MARS. In the study, the data of 2018 of the egg production enterprise in a private livestock enterprise in the Çukurova Region of Adana province were used. In the research, a data set obtained from Lohman breed chickens, who are at an average age of 60 weeks, was used. Earth (enhanced adaptive regression through hinges) and caret (classification and regression training), mda (Mixture Discriminant Analysis) packages were used in R STUDIO program to provide a stronger solution of regression problems in the created MARS and Bagging MARS algorithm. The estimation performance of the bagging MARS technique was evaluated with the goodness of fit criteria by taking the B value of the bootstrap sample number 3. In the study, the effect of temperature and humidity on egg yield, broken / cracked eggs, number of dead animals and feed consumption was investigated using MARS and bagging MARS analysis. While the effect of evening temperature(t3) on egg yield was found to be significant, it was not included in the estimation equation since morning (t1) and noon(t2) temperatures did not have a significant effect. Since the number of broken / cracked eggs and dead animals is less than 5 weeks, these variables are not included in the estimation equation in MARS and Bagging MARS models. It has been observed that feed consumption has a positive contribution in both models.

PDF

___

Ağaoğlu YS, Eyduran SP, Eyduran E. 2007. Comparison of Some Pomological Characteristics of Blackberry Cultivars Growth in Ayaş Conditions. Ankara Universitesi Tarım Bilimleri Dergisi, 13(1): 69-74.
Akın M, Hand C, Eyduran E, Reed BM.2018. Predicting minor nutrient requirements of hazelnut shoot cultures using regression trees. Pl. Cell Tissu. Organ Cult., 132: 545-559. https://doi.org/10.1007/s11240-017-1353-x
Akın ME, Eyduran E, Reed BM. 2016. Using the CHAID data mining algorithm for tissue culture medium optimization. In: In vitro cellular and developmental biology-animal. 52, Spring ST, New York, NY 10013, USA, pp. 233.
Akın M, Eyduran E, Reed BM. 2017. Use of RSM and CHAID data mining algorithm for predicting mineral nutrition of hazelnut. Plant Cell Tissue Organ Cult. 128: 303-316.
Akın M, Eyduran SP, Eyduran E, Reed BM. 2020. Analysis of macro nutrient related growth responses using multivariate adaptive regression splines. Plant Cell, Tissue and Organ Culture (PCTOC), 140: 661–670. https://doi.org/10.1007/ s11240-019-01763-8
Aksoy A, Ertürk, YE, Eyduran E, Tariq MM. 2018: Comparing predictive performances of MARS and CHAID algorithms for defining factors affecting final fattening live weight in cultural beef cattle enterprises. Pakistan Journal of Zoology, 50(6), 2279-2286.
Aytekin I, Eyduran E, Koksal K, Akşahan R, Keskin I. 2018. Prediction of fattening final live weight from some body measurements and fattening period in young bulls of crossbred and exotic breeds using MARS data mining algorithm. Pakistan J. Zoology, 50(1): 189-195.
Breiman L. 1994. Bagging Predictor. Technical report No. 421. Departement of Statistics University of California.
Craven P, Wahba G. 1979. Smoothing noisy data with spline functions. Estimating the correct degree of smoothing by the method of generalized crossvalidation. Numb. Mathem., 31: 317-403.
Çanga D, Boga M. 2019. Hayvancılıkta Mars Kullanımı ve Bır Uygulama. III. International Scientific and Vocational Studies Congress – Science and Health (Tam Metin Bildiri/Sözlü Sunum) (Yayın No:5583178).
Çanga D, Yavuz E, Efe E. 2019. Use of MARS Data Mining Algorithm for Egg Weight Estimation presented at the International Congress on Domestic Animal Breeding Genetics and Husbandry-19 (ICABGEH-19).
Çelik S, Eyduran E, Karadas K, Tariq MM.2017. Comparison of predictive performance of data mining algorithms in predicting body weight in Mengali rams of Pakistan. Revista Brasileira de Zootecnia, 46(11): 863-872.
Çelik S, Yilmaz 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). doi:10.17582/journal.pjz/2018.50.2.575.583.
Çelik S, Boydak E. 2020.Descrıptıon Of The Relatıonshıps Between Dıfferent Plant Characterıstıcs In Soybean Usıng Multıvarıate Adaptıve Regressıon Splınes (Mars) Algorıthm, The Journal of Animal & Plant Sciences,30(2): 2020, Page:431-441ISSN: 1018-708.
Ekinci M. 2010. Yumurtlama Periyodunun Sonunda Olan ve Yumurtadan Kesilmiş Yumurta Tavuklarında L-Dopa Kullanımının Yumurtlama Süresi, Yumurta Verimi ve Yumurta Kalitesi Üzerine Etkisi. Doktora tezi. http://libratez.cu.edu.tr/tezler/8043.pdf
Eyduran SP, Ağaoğlu YS, Eyduran E, Özdemir T.2007a. Comparison of some raspberry cultivars’ herbal features by repeated random complete design statistic technique. Pakistan J. Biological Sciences, 10(8): 1270-1275.
Eyduran SP, Özdemir T, Ağaoğlu YS. 2007b. Ankara (Ayaş) koşullarında yetiştirilen böğürtlen çeşitlerinin bazı bitkisel özellikleri. Alatarım. 6 (1): 18-25.
Eyduran E, Akkus O, Kara MK, Tirink C, Tariq MM(2017a). Use of Multivariate Adaptive Regression Splines (Mars) in predicting body weight from body measurements in Mengali rams. International Conference on Agriculture, Forest, Food, Sciences and Technologies, ICAFOF, 15-17 May 2017, Cappadocia-Turkey.
Eyduran E, Tirink C, Karahan AE, Türkoğlu M, Tariq MM. 2017b. Comparison of predictive performances of MARS and CART algorithms through R software. International Conference on Computational ans Statistical Methods in Applied Sciences, Samsun Turkey, 181.
Eyduran E, Sevgenler H, Akın M, Eyduran BM. 2018. Usage multivariate adaptive regression splines for predicting continuous responses. Animal and Plant Sciences. International Agricultural Science Congress. 9-12May, Van, Turkey.
Eyduran E, Akin M, Eyduran SP. 2019a. 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.
Eyduran E, Çanga D, Sevgenler H, Çelik AE. 2019b. Use of Bootstrap Aggregating Bagging MARS to Improve Predictive Accuracy for Regression Type Problems. presented at the 11. Uluslararası İstatistik Kongresi.
Friedman JH. 1991. Multivariate adaptive regression splines. Annls. Stat., 19: 1-141. https://doi. org/10.1214/aos/ 117634796.
Gecer MK, Akin M, Gundogdu M, Eyduran SP. 2016. Organic Acids, Sugars, Phenolic Compounds, and Some Horticultural Characteristics of Black And White Mulberry Accessions from Eastern Anatolia. Can J Plant Sci. 96(1): 27-33.
Grzesiak W, Zaborski D, Sablik P, Żukiewicz A, Dybus A and Szatkowska I. 2010. Detection of cows with insemination problems using selected classification models. Comput. Electron. Agric., 74: 265-273. https://doi.org/ 10.1016/j.compag.2010.09.001
Hasibuan MJA, Rusgiyono A, Safitri D. 2020. Pemodelan Produk Domestık Regıonal Bruto (Pdrb) Dı Provınsı Jawa Tengah Menggunakan Bootstrap Aggregatıng Multıvarıate Adaptıve Regressıon Splınes (Baggıng Mars). Jurnal Gaussian, 8(1): 139-148.
Hastie T, Tibshirani R, Friedman J. 2009. The elements of statistical learning: Data mining, inference and prediction, second ed. Springer. https://doi.org/10.1007/978-0-387- 84858-7.
Karadas K, Tariq M, Tariq MM, Eyduran E. 2017. Measuring predictive performance of data mining and artificial neural network algorithms for predicting lactation milk yield in indigenous Akkaraman sheep. Pakistan Journal of Zoology, 49(1): 1-7.
Kibet CE. 2012. A Multıvarıate Adaptıve Regressıon Splınes Approach To Predıct The Treatment Outcomes Of Tuberculosıs Patıents In Kenya. Yüksek Lisans Tezi, Science in Biometry to The University of Nairobi, Kenya.
Koç Y, Eyduran E, Akbulut O. 2017. Application of Regression Tree Method for Different Data from Animal Science. Pakistan Journal of Zoology, 49(2): 599-607.
Kutlu HR, Görgülü M, Baykal L. 1996. Tavukçulukta beslemeçevre sıcaklığı ilişkisi. Ulusal Kümes Hayvanları Semp.`96, 18-21 Kasım, s: 228-249, Adana.
Kutlu HR. 2009. Tavukların Beslenmesi (M.Türkoğlu ve M.Sarıca Editörler) Tavukçuluk Bilimi, Yetiştirme, Besleme, Hastalıklar, 3. Baskı, Bey Ofset Matbaacılık, Ankara, S:437,438.
Mendeş M, Akkartal E. 2009. Regression tree analysis for predicting slaughter weight in broilers. Italian Journal of Animal Science, 8, 615-624.
Milborrow S. 2018. Derived from mda: mars by T. Hastie and R. Tibshirani. İnternet url: https://CRAN.R-project.org/ package=earth (10.10.2018).
R Core Team. 2014. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, 2014. http://www.R-project.org.
Sevgenler H. 2019. Keçilere Ait Kimi Özelliklerin Canlı Ağırlık Üzerindeki Etkilerini Belirlemek Amacıyla Kullanılan Veri Madenciliği Algoritmalarının (Cart, Chaıd Ve Mars) Karşılaştırılması. Yüksek Lisans Tezi, Iğdır Üniversitesi Fen Bilimleri Enstitüsü. Iğdır.
Steinberg D. 2001. An alternative to neural networks: Multivariate adaptive regression splines (MARS), PC AI, January/February, pp. 38 -41.
Storlie CB, Swiler LP, Helton JC, Sallaberry CJ. 2009. Implementation and evaluation of nonparametric regression procedures for sensitivity analysis of computation all demanding models Reliab. Engin. Syst. Safe., 94: 1735-1763. https://doi.org/10.1016/j.ress.2009.05.007
Zaborski D, Grzesiak W, Szewczuk M, Eyduran E, Tariq MM, Ali M. 2018. The use of MARS method for predicting daily body weight gains in Harnai sheep. IX International Scientific Agriculture Symposium “Agrosym 2018”, Jahorina Bosnia Herzegovina.