Detection of correct pregnancy status in lactating dairy cattle using MARS data mining algorithm
نویسندگان
چکیده
In this study, it is aimed to determine pregnancy outcomes by using multivariate adaptive regression splines (MARS) algorithm for classification type problems. For purpose, data obtained from a private dairy farm in the Konya region of Türkiye 2020 were used Holstein cattle. It has been determined how perform statistical analyses on solving classification-type problems with MARS and use R packages (caret earth) creating an script file. After analysis, estimation equation was created finding probability being pregnant: While lactation period, cow age, number lactations, insemination number, total milk yield variables are important, seen that 7-day mean last not significant. Using train function caret package, terms produce highest accuracy degree interaction determined. Goodness-of-fit tests optimum model calculated. Within scope evaluation generalization ability model, training test sets created, success graph algorithm, building phase summarized, established measured. When status taken as positive reference, correct rate (sensitivity) animal found be 0.9574. The (specificity) pregnant animals 0.8370. overall ratio set (accuracy) 0.8777. area under ROC curve (AUC) 0.947, which indicates specificity value close 1.
منابع مشابه
Conventional and extended intramammary therapy of persistent subclinical mastitis using nafcillin-penicillindihydrostreptomycin in lactating dairy cattle
The objective of the present study was to compare the efficacy of conventional and extendedintramammary (IMM) therapy of persistent subclinical mastitis in lactating dairy cattle using nafcillinpenicillin-dihydrostreptomycin combination (NPD). Sixty-five dairy cows with 126 infected quarters were enrolled in the study. Infected cows were allocated randomly to 1 of 3 different treatment regimens...
متن کاملmetrics for the detection of changed buildings in 3d old vector maps using als data (case study: isfahan city)
هدف از این تحقیق، ارزیابی و بهبود متریک های موجود جهت تایید صحت نقشه های قدیمی سه بعدی برداری با استفاده از ابر نقطه حاصل از لیزر اسکن جدید شهر اصفهان می باشد . بنابراین ابر نقطه حاصل از لیزر اسکنر با چگالی حدودا سه نقطه در هر متر مربع جهت شناسایی عوارض تغییر کرده در نقشه های قدیمی سه بعدی استفاده شده است. تمرکز ما در این تحقیق بر روی ساختمان به عنوان یکی از اصلی ترین عارضه های شهری می باشد. من...
Plasma and milk urea nitrogen in relation to pregnancy rate in lactating dairy cattle.
The objectives of this study were to relate concentrations of plasma (PUN) and milk (MUN) urea nitrogen to pregnancy rate in dairy cows and compare various methods of analysis and preparation of milk for measuring MUN. In two experiments, blood or milk samples were collected on the day of AI from Holstein cows (n = 160 and n = 155, respectively). Three methods of MUN analysis were compared. Two...
متن کاملthe clustering and classification data mining techniques in insurance fraud detection:the case of iranian car insurance
با توجه به گسترش روز افزون تقلب در حوزه بیمه به خصوص در بخش بیمه اتومبیل و تبعات منفی آن برای شرکت های بیمه، به کارگیری روش های مناسب و کارآمد به منظور شناسایی و کشف تقلب در این حوزه امری ضروری است. درک الگوی موجود در داده های مربوط به مطالبات گزارش شده گذشته می تواند در کشف واقعی یا غیرواقعی بودن ادعای خسارت، مفید باشد. یکی از متداول ترین و پرکاربردترین راه های کشف الگوی داده ها استفاده از ر...
ذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Turkish Journal of Veterinary & Animal Sciences
سال: 2022
ISSN: ['1300-0128', '1303-6181']
DOI: https://doi.org/10.55730/1300-0128.4257