تشخیص صفت فاصله زایش با استفاده از روشهای درخت تصمیم و ماشین بردار پشتیبان در گاوهای شیری هلشتاین

نوع مقاله : مقاله کامل

نویسندگان

1 دانشکده کشاورزی،دانشگاه یاسوج، ایران

2 گروه علوم دامی،دانشکده کشاورزی،دانشگاه یاسوج، ایران

چکیده

کاهش خصوصیات تولیدمثلی در گاوهای شیری هلشتاین یک مشکل عمده در رابطه با پرورش گاوهای شیری است. رابطه منفی بین میزان تولید شیر و عملکرد تولید‌مثلی در نژادهای مختلف وجود دارد. با تمرکز بر روی صفات تولیدمثلی مانند صفت فاصله زایش، تولید نیز در نسل‌های بعدی بهبود خواهد یافت. زیرا فاصله زایش یکی از فاکتورهایی است که میزان کارآمدی و کفایت تولیدمثل را نشان می‌دهد. استفاده از الگوریتم‌های هوشمند روش‌های یادگیری ماشین در بررسی سامانه‌های پیچیده رو به افزایش است و این روش‌ها نیز می‌توانند رهیافت مناسبی برای تحلیل داده‌های صنعت گاو شیری به‌حساب آیند. در پژوهش حاضر، بررسی امکان دسته‌بندی فاصله زایش در گاوهای شیری هلشتاین با استفاده از دو روش درخت تصمیم (الگوریتم‌های برجسته، جنگل تصادفی و بیز ساده) و ماشین بردار پشتیبان انجام شد. برای بررسی کارایی روش‌ها، از معیارهای صحت و جذر میانگین مربعات خطا استفاده شد. نتایج حاصل از این پژوهش نشان داد که روش‌های مختلف درخت تصمیم (برجسته) نسبت به روش ماشین بردار پشتیبان عملکرد بالاتری در امکان دسته‌بندی فاصله زایش داشت. سن مادر و تولید شیر، بیشترین ارتباط را با فاصله زایش داشتند. پژوهش حاضر اولین مطالعه با هدف تشخیص فاصله زایش با استفاده از روش‌های درخت تصمیم و ماشین بردار پشتیبان است که ممکن است اطلاعات در جهت درک بیشتر مدیریت فاصله زایش را بهبود دهد. عدم نیاز به برقراری هیچ پیش‌فرضی برای مدل‌سازی و تفسیر آسان نتایج مدل‌های درختی، دو مزیت اساسی آن است که به همین دلیل به‌نظر می‌رسد برای تحقیقات اصلاح نژاد دام مفید باشند.
 

کلیدواژه‌ها

عنوان مقاله [English]

Detection of Calving interval trait using decision tree and support vector machine methods in Holstein dairy cows

نویسندگان [English]

  • M. Montazeri Najafabadi 1
  • M. R. Bahreini Behzadi 2
1 Faculty of Agriculture, Yasouj University,Yasouj, Iran
2 Faculty of Agriculture, Yasouj University,Yasouj, Iran.
چکیده [English]

Decreased reproductive traits in cows are a major problem in raising dairy cows. There has been a negative relationship between milk production and reproductive performance in different breeds of dairy cows. By focusing on reproductive traits such as calving interval, production in later generations will be improved. Because calving interval is one of the factors that indicate the efficiency and adequacy of reproduction. Using intellectual algorithms of machine learning methods to investigate complex systems are growing and these algorithms could be assumed as right approach to analysis dairy cattle industry data. In the present work, was carried out to investigate the possibility of calving interval classification in Holstein dairy cattle using two methods of decision tree (algorithms of j48, random forest and Naive Bayes) and support vector machine. Were used accuracy and root mean square error to investigate the efficiency of methods. The results of this study showed that decision tree methods (j48) have a higher performance than support vector machine in classification of as calving interval. Calving age and milk production showed high amount of correlation with calving interval. The present work is the first study to detection of calving interval using decision tree and support vector machine methods that may provide information to greater understanding on calving interval management. Tree models don’t require the establishment of no default for making model and feasibility of tree models results interpretation are two essential beneficiary of these models which for this reason seem to be useful for bovine breeding researches.

کلیدواژه‌ها [English]

  • Decision Tree
  • Classification
  • Calving interval
  • Dairy cow
  • Support Vector Machine

مراجع

1.Adamczyk, K., D. Zaborski, W. Grzesiak, J. Makulska and W. Jagusiak. 2016. Recognition of culling reasons in Polish dairy cows using data mining methods. Computers and Electronics in Agriculture, 127: 26-37.
2. Arbel, R., Y. Bigun, E. Ezra, H. Sturman and D. Hojman. 2001. The effect of extended calving intervals in high lactating cows on milk production and profitability. Journal of Dairy Science, 84: 600–608.
3.Bahreini Behzadi, M., R. M. Montazeri NajafAbadi. 2018. Detection of dystocia trait using support vector machine and decision tree methods in Holstein dairy cows. In: Proceeding of 8th International Animal Science. Iran, Kordestan. 4-6. (In Farsi).
4.Berry, D., B. Harris, A.Winkelman and W. Montgomerie. 2005. Phenotypic associations between traits other than production and longevity in New Zealand dairy cattle. Journal of Dairy Science, 8: 2962-2974.  
5.Dalcq, A., C. Y. Beckers P. Mayeres, E. Reding, B. Wyzen, F. Colinet, ... and H. Soyeurt. 2018. The feeding system impacts relationships between calving interval and economic results of dairy farms. Journal animal Science, 12(8): 1662-1671.
6.Dash, M. and H. Liu. 2003. Consistency-based search in feature selection. Artificial Intelligence, 151: 155–176.
7.Dematawewa C. and P. Berger. 1998. Genetic and Phenotypic Parameters for 305-Day Yield, Fertility, and Survival in Holsteins1. Journal of Dairy Science, 10: 2700-2709.
8.Dulyala, R., S. Kuankid, T. Rattanawong and A. Aurasopon. 2014. Classification system for estrus behavior of cow using an accelerometer. In Signal and Information Processing Association Annual Summit and Conference (APSIPA), Asia-Pacific, 14-15.
9.Ghavi Hossein- Zadeh, N. 2014. Effect of dystocia on the productive performance and calf stillbirth in Iranian Holsteins. Journal of Agricultural Science and Technology, 1: 69-78.
10.Gonzalez, L. A., G. J. Bishop, R. N. Hurley Handcock and C. Crossman. 2015. Behavioral classification of data from collars containing motion sensors in grazing cattle. Computers and Electronics in Agriculture, 110: 91-102.
11.Groenendaal, H., D.T. Galligan and H. A. Mulder. 2004. An economic spreadsheet model to determine optimal breeding and replacement decisions for dairy cattle. Journal of Dairy Science, 87: 2146–2157.
12.Hall, M. A. 1998. Correlation-based Feature Subset Selection for Machine Learning. Thesis submitted in partial fulfillment of the requirements of the degree of Doctor of Philosophy at the University of Waikato Hamilton, New Zealand.
13.Hare, E. H. D. N., H. D. Norman and J. R. Wright. 2006. Trends in calving ages and calving intervals for dairy cattle breeds in the United States. Journal of dairy science, 89(1): 365-370.
14.Hempstalk, K., S. McParland and D. P. Berry. 2015. Machine learning algorithms for the prediction of conception success to a given insemination in lactating dairy cows. Journal of dairy science, 98(8): 5262-5273.
15.Inchaisri, C., R. Jorritsma, P. L. A. M. Vos, G.C. van der Weijden and  H. Hogeveen. 2011. Analysis of the economically optimal voluntary waiting period for first insemination. Journal of dairy science, 74: 835–846.
16.Kargar, S. and M. Mokarram. 2016. Use of feature selection algorithm to determine the most important factors affecting milk fat percentage of Holstein cows.  Iranian Journal of Ruminant Research, 4(4): 154-166. (In Farsi).
17.Kim, T and C. W. Heald. 1999. Inducing inference rules for the classification of bovine mastitis. Computers and Electronics in Agriculture, 23(1): 27-42.
18.Lehmann, J. O., J. G. Fadel, L. Mogensen, T. Kristensen, C. Gaillard and E. Kebreab. 2016. Effect of calving interval and parity on milk yield per feeding day in Danish commercial dairy herds. Journal of dairy science, 99(1): 621-633.
19.Maizon, D., P. Oltenacu, Y. Grohn, R. Strawderman and U. Emanuelson. 2004. Effects of diseases on reproductive performance in Swedish Red and White dairy cattle. Preventive veterinary medicine, 1: 113-126.
20.Martiskainenو P., M. Jarvinen, J. P. Skon, J. Tiirikainen, M. Kolehmainen and J. Mononen. 2009. Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines. Applied animal behaviour science, 119(1-2): 32-38.
21.Poldaru, R., J. Roots and A. H. Viira. 2005. The estimation of the econometric model of milk yield per cow: a support vector machine regression approach.Congress on it in Agriculture Operations Research, 166-167.
22.Qin, Z and J. Lawry. 2005. Decision tree learning with fuzzy labels. Information Sciences, 172: 91 129.
23.Royal, M. D., J. E. Pryce, J. A. Woolliams and A. P. F. Flint. 2002. The genetic relationship between commencement of luteal activity and calving interval, body condition score, production, and linear type traits in Holstein-Friesian dairy cattle. Journal of dairy science, 85(11): 3071-3080.
24.Sewalem, A., F. Miglior, G. Kistemaker, P. Sullivan and B. Van Doormaal. 2008. Relationship between reproduction traits and functional longevity in Canadian dairy cattle. Journal of Dairy Science, 91:1660–1668.
25.Shahriar, M. S., D. Smith, A. Rahman, M. Freeman, J. Hills, R. Rawnsley, ... and G. Bishop Hurley. 2016. Detecting heat events in dairy cows using accelerometers and unsupervised learning. Computers and Electronics in Agriculture 128: 20-26.
26.Silva, H. M., C. J. Wilcox, W. W. Thatcher, R. B. Becker and D. Morse. 1992. Factors Affecting Days Open, Gestation Length and Calving Interval in Florida Dairy Cattle1. Journal of Dairy Science, 75(1): 288-293.
27.Toghiani, S., A. A. Shadparvar, M. Moradi Shahrbabak and M. Dadpasand Taromsari. 2009. Genetic analysis of reproduction traits and their relationship with conformation traits in Holstein cows. Livestock Production Science, 125: 84-87.
28.Zaborski, D., W .Grzesiak, K. Kotarska, I. Szatkowska and M. Jedrzejczak. 2014. Detection of difficult calvings in dairy cows using boosted classification trees. Indian Journal of Animal Research, 48(5): 452-458.
29.Zaborski, D., W. Grzesiak and R. Pilarczyk. 2016. Detection of difficult calvings in the Polish Holstein-Friesian Black-and-White heifers.  Journal of applied animal research, 44(1): 42-53.
تحقیقات دامپزشکی و فرآورده‌های بیولوژیک
دوره 34، شماره 3
مهر 1400
صفحه 99-106

فایل ها

سابقه مقاله

  • تاریخ دریافت: 10 اسفند 1398
  • تاریخ بازنگری: 03 اردیبهشت 1399
  • تاریخ پذیرش: 09 اردیبهشت 1399

هم رسانی

ارجاع به این مقاله

آمار