schliessen

Filtern

 

Bibliotheken

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-... Full description

Journal Title: Asian-Australasian Journal of Animal Sciences 01 November 2018, Vol.31(11), pp.1700-1713
Main Author: Daniel Zaborski
Other Authors: Witold S. Proskura , Wilhelm Grzesiak
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 1011-2367 ; E-ISSN: 1976-5517 ; DOI: 10.5713/ajas.17.0780
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: doaj_soai_doaj_org_article_a1cb888883d94847b0599ccf71429e94
title: The use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
format: Article
creator:
  • Daniel Zaborski
  • Witold S. Proskura
  • Wilhelm Grzesiak
subjects:
  • Dystocia
  • Prediction
  • Statistical Analysis
  • Dairy Cattle
  • Agriculture
ispartof: Asian-Australasian Journal of Animal Sciences, 01 November 2018, Vol.31(11), pp.1700-1713
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.
language: eng
source:
identifier: ISSN: 1011-2367 ; E-ISSN: 1976-5517 ; DOI: 10.5713/ajas.17.0780
fulltext: fulltext_linktorsrc
issn:
  • 1011-2367
  • 10112367
  • 1976-5517
  • 19765517
url: Link


@attributes
ID1524683329
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordidoai_doaj_org_article_a1cb888883d94847b0599ccf71429e94
sourceiddoaj_s
recordidTN_doaj_soai_doaj_org_article_a1cb888883d94847b0599ccf71429e94
sourcesystemOther
dbidDOA
pqid2024475975
galeid568371288
display
typearticle
titleThe use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
creatorDaniel Zaborski ; Witold S. Proskura ; Wilhelm Grzesiak
ispartofAsian-Australasian Journal of Animal Sciences, 01 November 2018, Vol.31(11), pp.1700-1713
identifier
subjectDystocia ; Prediction ; Statistical Analysis ; Dairy Cattle ; Agriculture
descriptionObjective 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.
languageeng
oafree_for_read
source
version6
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
linktorsrc$$Uhttps://doaj.org/article/a1cb888883d94847b0599ccf71429e94$$EView_full_text_in_DOAJ
search
creatorcontrib
0Daniel Zaborski
1Witold S. Proskura
2Wilhelm Grzesiak
titleThe use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
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.

subject
0Dystocia
1Prediction
2Statistical Analysis
3Dairy Cattle
4Agriculture
general
0English
1Asian-Australasian Association of Animal Production Societies
210.5713/ajas.17.0780
3Directory of Open Access Journals (DOAJ)
sourceiddoaj_s
recordiddoaj_soai_doaj_org_article_a1cb888883d94847b0599ccf71429e94
issn
01011-2367
110112367
21976-5517
319765517
rsrctypearticle
creationdate2018
addtitleAsian-Australasian Journal of Animal Sciences
searchscope
0doaj_full
1doaj1
scope
0doaj_full
1doaj1
lsr45$$EView_full_text_in_DOAJ
tmp01Directory of Open Access Journals (DOAJ)
tmp02DOA
startdate20181101
enddate20181101
lsr40Asian-Australasian Journal of Animal Sciences, 01 November 2018, Vol.31 (11), pp.1700-1713
doi10.5713/ajas.17.0780
citationpf 1700 pt 1713 vol 31 issue 11
lsr30VSR-Enriched:[pqid, galeid]
sort
titleThe use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
authorDaniel Zaborski ; Witold S. Proskura ; Wilhelm Grzesiak
creationdate20181101
lso0120181101
facets
frbrgroupid1745195313833331251
frbrtype5
newrecords20190714
languageeng
topic
0Dystocia
1Prediction
2Statistical Analysis
3Dairy Cattle
4Agriculture
collectionDirectory of Open Access Journals (DOAJ)
prefilterarticles
rsrctypearticles
creatorcontrib
0Daniel Zaborski
1Witold S. Proskura
2Wilhelm Grzesiak
jtitleAsian-Australasian Journal of Animal Sciences
creationdate2018
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext_linktorsrc
addata
au
0Daniel Zaborski
1Witold S. Proskura
2Wilhelm Grzesiak
atitleThe use of data mining methods for dystocia detection in Polish Holstein-Friesian Black-and-White cattle
jtitleAsian-Australasian Journal of Animal Sciences
risdate20181101
volume31
issue11
spage1700
epage1713
pages1700-1713
issn1011-2367
eissn1976-5517
formatjournal
genrearticle
ristypeJOUR
abstract

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.

pubAsian-Australasian Association of Animal Production Societies
doi10.5713/ajas.17.0780
urlhttps://doaj.org/article/a1cb888883d94847b0599ccf71429e94
oafree_for_read
date2018-11-01