Volkan SEVİNÇ, Özge AKKUŞ, Çiğdem TAKMA, Öznur İŞÇİ GÜNERİ

Bayesian Network Analysis for the Factors Affecting the 305-day Milk Productivity of Holstein Friesians

The variables affecting the milk productivity have been discussedin various articles through different methods. A recent studyusing path analysis shows that three variables significantly affectthe 305-day milk yield of Holstein Friesian cows. These variablesare parity, first calving year and lactation length. Calving seasonis another variable which appears to be significant in a differentstudy. The aim of this study is to provide a simultaneousmultilateral analysis among the milk yield, these three variablesand a new variable calving season. The analysis was realizedthrough a Bayesian network built over the findings of the pathanalysis. 17,109 records of Holstein Friesian cows calvedbetween 2001-2011 years were analyzed. The estimatedBayesian network showed that younger cows produced moremilk. Lactation length and parity do not depend on each other.Cows reached their highest amount of milk yield on their 4thparities. Milk yield is mostly affected by lactation length. Finally,first calving year, parity, lactation length and calving seasonshould be considered as criteria in a selection study to increasethe milk yield.

PDF

___

Aktürk D, Bayramoğlu Z, Savran F & Tatlıdil F F (2010). The factors affecting milk production and milk production cost: Çanakkale case-Biga. Kafkas Üniversitesi Veterinerlik Fakültesi Dergisi 16(2): 329-335
Cheng J, Greiner R, Kelly J, Bell D A & Liu W (2002). Learning Bayesian networks from data: An information-theory based approach. Artificial Intelligence 137: 43-90
Chickering D M (2002). Learning equivalence classes of Bayesian-network structures. Journal of Machine Learning Research 2: 445-498
Cooper G & Herskovits E (1991). A Bayesian method for constructing Bayesian belief networks from databases. In: Proceedings of the 7th Conference on Uncertainty in Artificial Intelligence, 13-15 July, Los Angeles, California, USA, pp. 86-94
de Campos L M & Huete J F (2000). A new approach for learning belief networks using independence criteria. International Journal of Approximate Reasoning 24: 11-37
Eastham N T, Coates A, Cripps P, Richardson H, Smith R & Oikonomou G (2018). Associations between age at first calving and subsequent lactation performance in UK Holstein and Holstein-Friesian dairy cows. PLoS One 13(6): 1-13
Eetvelde M V, Kamal M M, Vandaele L & Opsomer G (2017). Season of birth is associated with first-lactation milk yield in Holstein Friesian cattle. Animal 11(12): 2252-2259
GeNIe (2019). BayesFusion, LLC. Retrieved in January, 15, 2019 from http://www.bayesfusion.com/
Heckerman D (1998). A tutorial on learning with Bayesian networks. In: M I Jordan (Eds), Learning in Graphical Models, NATO ASI Series (Series D: Behavioral and Social Sciences), Springer, Dordrecht, pp. 301-354
Hugin (2019). Hugin Expert. Retrieved in January, 15, 2019 from https://www.hugin.com/
Iqbal A, Fukuda O, Hiroshi O, Endo K, Arai K & Yamashita K (2016). Japanese dairy cattle productivity analysis using Bayesian network model (BNM). International Journal of Advanced Computer Science and Applications 7(11): 31-37
İnci S, Kaygısız A, Efe E & Baş S (2007). Milk yield and reproductive traits in Brown Swiss cattle raised at Altınova State Farm. Tarım Bilimleri Dergisi 13(3): 203-212
İşçi Ö, Takma Ç & Akbaş Y (2015). Siyah alaca sığırlarda 305 günlük süt verimini etkileyen faktörlerin path (iz) analizi ile belirlenmesi. Kafkas Üniversitesi Veterinerlik Fakültesi Dergisi 21(2): 219-224
Jensen F V (2001). Bayesian Networks and Decision Graphs. Springer-Verlag New York Inc., Secaucus, New Jersey
Kaya A, Yaylak E & Önenç A (1998). Süt sığırcılığında düzenli üreme ve önemi. Hayvansal Üretim Dergisi 38: 8-17
Marcot B G (2012). Metrics for evaluating performance and uncertainty of Bayesian network models. Ecological Modelling 230: 50-62
Mote S S, Chauhan D S & Ghost N (2016). Effect of environment factors on milk production and lactation length under different seasons in crossbred cattle. Indian Journal of Animal Research 50(2): 175-180
Natori K, Uto M, Nishiyama Y, Kawano S & Ueno M (2015). Constraint-based learning Bayesian networks using Bayes factor. In: J Suzuki & M Ueno (Eds), Advanced Methodologies for Bayesian Networks, Springer, Switzerland, pp. 15-31
Netica (2019). Norsys Software Corp. Retrieved in January, 15, 2019 from https://www.norsys.com/netica.html
Pearl J (1991). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco, California, pp. 321
Perochon L, Coulon J B & Lescourret F (1996). Modelling lactation curves of dairy cows with emphasis on individual variability. Journal of Animal Science 63: 189-200
Spirtes P, Glymour C & Scheines R (1993). Causation, Prediction and Search. Lecture Notes in Statistics 81, Springer-Verlag, New York
Şekerden Ö & Özkütük K (2000). Büyükbaş Hayvan Yetiştirme. Ç. Ü. Ziraat Fakültesi Ders Kitabı, No: C-122 s, Adana
Tahtalı Y, Şahin A, Ulutaş Z, Şirin E & Abacı S H (2011). Esmer ırkı sığırlarda süt verimi üzerine etkili faktörlerin path analizi ile belirlenmesi. Kafkas Üniversitesi Veterinerlik Fakültesi Dergisi 17(5): 859-864
Tümer S (2001). Süt Sığırı Yetiştirmede Döl Verimi ve Sürü Yönetimi. Kurs Notları, İzmir
Verma T S & Pearl J (1991). Equivalence and synthesis of causal models. Uncertain Artificial Intelligence 6: 255-268
Verma M K, Sachdeva G K, Yadav A K, Gautam S, Ali M M & Kumar S (2017). Effect of genetic and non-genetic factors on milk yield and milk constituents in Murrah buffalo. Indian Journal Animal Research 51(2): 387-390
Yüksel A N, Soysal İ, Kocaman İ & Soysal S İ (2000). Süt Sığırcılığı Temel Kitabı. Hasad Yayıncılık, İstanbul