The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
Objective The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Asian-Australasian Association of Animal Production Societies
2018-11-01
|
Series: | Asian-Australasian Journal of Animal Sciences |
Subjects: | |
Online Access: | http://www.ajas.info/upload/pdf/ajas-17-0780.pdf |
id |
doaj-a1cb888883d94847b0599ccf71429e94 |
---|---|
record_format |
Article |
spelling |
doaj-a1cb888883d94847b0599ccf71429e942020-11-24T23:21:22ZengAsian-Australasian Association of Animal Production SocietiesAsian-Australasian Journal of Animal Sciences1011-23671976-55172018-11-0131111700171310.5713/ajas.17.078023972The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattleDaniel Zaborski0Witold S. Proskura1Wilhelm Grzesiak2 Department of Ruminants Science, West Pomeranian University of Technology, Szczecin 71-270, Poland Department of Ruminants Science, West Pomeranian University of Technology, Szczecin 71-270, Poland Department of Ruminants Science, West Pomeranian University of Technology, Szczecin 71-270, PolandObjective The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-and-White heifers and cows and to indicate the most influential predictors of calving difficulty. Methods A total of 1,342 and 1,699 calving records including six categorical and four continuous predictors were used. Calving category (difficult vs easy or difficult, moderate and easy) was the dependent variable. Results The maximum sensitivity, specificity and accuracy achieved for heifers on the independent test set were 0.855 (for ANN), 0.969 (for NBC), and 0.813 (for GDA), respectively, whereas the values for cows were 0.600 (for ANN), 1.000 and 0.965 (for NBC, GDA, and LR), respectively. With the three categories of calving difficulty, the maximum overall accuracy for heifers and cows was 0.589 (for MARS) and 0.649 (for ANN), respectively. The most influential predictors for heifers were an average calving difficulty score for the dam’s sire, calving age and the mean yield of the farm, where the heifer was kept, whereas for cows, these additionally included: calf sex, the difficulty of the preceding calving, and the mean daily milk yield for the preceding lactation. Conclusion The potential application of the investigated models in dairy cattle farming requires, however, their further improvement in order to reduce the rate of dystocia misdiagnosis and to increase detection reliability.http://www.ajas.info/upload/pdf/ajas-17-0780.pdfDystociaPredictionStatistical AnalysisDairy Cattle |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Daniel Zaborski Witold S. Proskura Wilhelm Grzesiak |
spellingShingle |
Daniel Zaborski Witold S. Proskura Wilhelm Grzesiak The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle Asian-Australasian Journal of Animal Sciences Dystocia Prediction Statistical Analysis Dairy Cattle |
author_facet |
Daniel Zaborski Witold S. Proskura Wilhelm Grzesiak |
author_sort |
Daniel Zaborski |
title |
The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle |
title_short |
The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle |
title_full |
The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle |
title_fullStr |
The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle |
title_full_unstemmed |
The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle |
title_sort |
use of data mining methods for dystocia detection in polish holstein-friesian black-and-white cattle |
publisher |
Asian-Australasian Association of Animal Production Societies |
series |
Asian-Australasian Journal of Animal Sciences |
issn |
1011-2367 1976-5517 |
publishDate |
2018-11-01 |
description |
Objective The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-and-White heifers and cows and to indicate the most influential predictors of calving difficulty. Methods A total of 1,342 and 1,699 calving records including six categorical and four continuous predictors were used. Calving category (difficult vs easy or difficult, moderate and easy) was the dependent variable. Results The maximum sensitivity, specificity and accuracy achieved for heifers on the independent test set were 0.855 (for ANN), 0.969 (for NBC), and 0.813 (for GDA), respectively, whereas the values for cows were 0.600 (for ANN), 1.000 and 0.965 (for NBC, GDA, and LR), respectively. With the three categories of calving difficulty, the maximum overall accuracy for heifers and cows was 0.589 (for MARS) and 0.649 (for ANN), respectively. The most influential predictors for heifers were an average calving difficulty score for the dam’s sire, calving age and the mean yield of the farm, where the heifer was kept, whereas for cows, these additionally included: calf sex, the difficulty of the preceding calving, and the mean daily milk yield for the preceding lactation. Conclusion The potential application of the investigated models in dairy cattle farming requires, however, their further improvement in order to reduce the rate of dystocia misdiagnosis and to increase detection reliability. |
topic |
Dystocia Prediction Statistical Analysis Dairy Cattle |
url |
http://www.ajas.info/upload/pdf/ajas-17-0780.pdf |
work_keys_str_mv |
AT danielzaborski theuseofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle AT witoldsproskura theuseofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle AT wilhelmgrzesiak theuseofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle AT danielzaborski useofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle AT witoldsproskura useofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle AT wilhelmgrzesiak useofdataminingmethodsfordystociadetectioninpolishholsteinfriesianblackandwhitecattle |
_version_ |
1725571769020973056 |