Zobraziť v EDS Plný text ve formátu PDF

Comparison of the MARS and XGBoost algorithms for predicting body weight in Kalahari Red goats.

Uložené v:
Podrobná bibliografia
Názov: Comparison of the MARS and XGBoost algorithms for predicting body weight in Kalahari Red goats.
Autori: TYASI, Louis Thobela1, TIRINK, Cem2 cem.tirink@gmail.com, MOKOENA, Kwena1, ÖNDER, Hasan3, ŞEN, Uğur4, ÇANGA BOĞA, Demet5, TOLUN, Tolga6, GÖK, İsmail6, AKSOY, Yüksel7, BAYYURT, Lütfi8, YILMAZ, Ömer Faruk3
Zdroj: Turkish Journal of Veterinary & Animal Sciences. 2026, Vol. 50 Issue 1, p18-25. 8p.
Druh dokumentu: Article
Predmet: Machine learning, Goats, Goodness-of-fit tests, Body size, Livestock growth
Author-Supplied Keywords: body measurement
Kalahari Red goat
MARS
prediction
XGBoost
Abstrakt: Estimating goat body weight from morphometric traits is essential for growth monitoring, health management, and welfare. Accurate weight informs nutrition, clinical interventions, and mating decisions. In this study, the MARS and XGBoost algorithms were used to estimate the live weight of Kalahari Red goats based on body measurements. A dataset containing body length (BL), birth type (single, twin, or triplet), withers height (WH), rump height (RH), and heart girth (HG) information for 200 goats was used in the training and testing of the models. The performances of the models were evaluated with the goodness-of-fit criteria. XGBoost showed a performance of R² = 0.998, RMSE = 0.023, and MAPE = 0.039 in the training set and R² = 0.974, RMSE = 0.669, and MAPE = 0.927 in the test set. In addition, MARS achieved R² = 0.994, RMSE = 0.260, and MAPE = 0.447 in the training set and R² = 0.968, RMSE = 0.595, and MAPE = 0.771 in the test set. These results demonstrate that, although the R² values of XGBoost are higher than those of MARS, both algorithms were effective. XGBoost consistently yielded lower errors and slightly higher R² in estimating the live weight of Kalahari Red goats based on body measurements. [ABSTRACT FROM AUTHOR]
Copyright of Turkish Journal of Veterinary & Animal Sciences is the property of Scientific and Technical Research Council of Turkey and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Author Affiliations: 1Department of Agricultural Economics and Animal Production, Faculty of Science and Agriculture, University of Limpopo, Limpopo, South Africa.
2Department of Animal Science, Faculty of Agriculture, Iğdır University, Iğdır, Turkiye.
3Department of Animal Science, Faculty of Agriculture, Ondokuz Mayıs University, Samsun, Turkiye.
4Department of Agricultural Biotechnology, Faculty of Agriculture, Ondokuz Mayıs University, Samsun, Turkiye.
5Department of Numerical Methods, Faculty of Economics and Administrative Sciences, Niğde Ömer Halisdemir University, Niğde, Turkiye.
6Department of Bioengineering, Faculty of Agriculture, Kahramanmaraş Sütçü İmam University, Kahramanmaraş, Turkiye.
7Department of Animal Science, Faculty of Agriculture, Eskişehir Osmangazi University, Eskişehir, Turkiye.
8Department of Animal Science, Faculty of Agriculture, Gaziosmanpaşa University, Tokat, Turkiye.
ISSN: 1300-0128
DOI: 10.55730/1300-0128.4405
Prístupové číslo: 192162921
Databáza: Veterinary Source
FullText Links:
  – Type: pdflink
    Url: https://content.ebscohost.com/cds/retrieve?content=AQICAHj0k_4E0hTGH8RJwT4gCJyBsGNe_WN95AvKlDbXJGqwxwHm-YosJMCrxQtB8tkCkpVJAAAA4zCB4AYJKoZIhvcNAQcGoIHSMIHPAgEAMIHJBgkqhkiG9w0BBwEwHgYJYIZIAWUDBAEuMBEEDC6-3qBUfvRRzbT0ggIBEICBm4E-RhTn0Zxy_A6nSPqh7WO1vj20eg0-lnNRdWUY1i963xhXE8DXmMwRrRBwCv9kZ-btUeOTZC6z7spVHOdMO86AyPnnlQSVD1x1Qk27kUPZU3lkpVyZxAcSM6tp_yjryE600QzMHN2wLWWsk1Vbr7aTG4AQ_iExdE7LJTP-xYTDHsAOxefhWGXKbaU_Ltz6ZuDPGzr1hy3wGZtn
Text:
  Availability: 0
Header DbId: vft
DbLabel: Veterinary Source
An: 192162921
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Comparison of the MARS and XGBoost algorithms for predicting body weight in Kalahari Red goats.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22TYASI%2C+Louis+Thobela%22">TYASI, Louis Thobela</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22TIRINK%2C+Cem%22">TIRINK, Cem</searchLink><relatesTo>2</relatesTo><i> cem.tirink@gmail.com</i><br /><searchLink fieldCode="AR" term="%22MOKOENA%2C+Kwena%22">MOKOENA, Kwena</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22ÖNDER%2C+Hasan%22">ÖNDER, Hasan</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22ŞEN%2C+Uğur%22">ŞEN, Uğur</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22ÇANGA+BOĞA%2C+Demet%22">ÇANGA BOĞA, Demet</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22TOLUN%2C+Tolga%22">TOLUN, Tolga</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22GÖK%2C+İsmail%22">GÖK, İsmail</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22AKSOY%2C+Yüksel%22">AKSOY, Yüksel</searchLink><relatesTo>7</relatesTo><br /><searchLink fieldCode="AR" term="%22BAYYURT%2C+Lütfi%22">BAYYURT, Lütfi</searchLink><relatesTo>8</relatesTo><br /><searchLink fieldCode="AR" term="%22YILMAZ%2C+Ömer+Faruk%22">YILMAZ, Ömer Faruk</searchLink><relatesTo>3</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Turkish+Journal+of+Veterinary+%26+Animal+Sciences%22">Turkish Journal of Veterinary & Animal Sciences</searchLink>. 2026, Vol. 50 Issue 1, p18-25. 8p.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Article
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Goats%22">Goats</searchLink><br /><searchLink fieldCode="DE" term="%22Goodness-of-fit+tests%22">Goodness-of-fit tests</searchLink><br /><searchLink fieldCode="DE" term="%22Body+size%22">Body size</searchLink><br /><searchLink fieldCode="DE" term="%22Livestock+growth%22">Livestock growth</searchLink>
– Name: Keyword
  Label: Author-Supplied Keywords
  Group: Kw
  Data: <searchLink fieldCode="DE" term="%22body+measurement%22">body measurement</searchLink><br /><searchLink fieldCode="DE" term="%22Kalahari+Red+goat%22">Kalahari Red goat</searchLink><br /><searchLink fieldCode="DE" term="%22MARS%22">MARS</searchLink><br /><searchLink fieldCode="DE" term="%22prediction%22">prediction</searchLink><br /><searchLink fieldCode="DE" term="%22XGBoost%22">XGBoost</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Estimating goat body weight from morphometric traits is essential for growth monitoring, health management, and welfare. Accurate weight informs nutrition, clinical interventions, and mating decisions. In this study, the MARS and XGBoost algorithms were used to estimate the live weight of Kalahari Red goats based on body measurements. A dataset containing body length (BL), birth type (single, twin, or triplet), withers height (WH), rump height (RH), and heart girth (HG) information for 200 goats was used in the training and testing of the models. The performances of the models were evaluated with the goodness-of-fit criteria. XGBoost showed a performance of R² = 0.998, RMSE = 0.023, and MAPE = 0.039 in the training set and R² = 0.974, RMSE = 0.669, and MAPE = 0.927 in the test set. In addition, MARS achieved R² = 0.994, RMSE = 0.260, and MAPE = 0.447 in the training set and R² = 0.968, RMSE = 0.595, and MAPE = 0.771 in the test set. These results demonstrate that, although the R² values of XGBoost are higher than those of MARS, both algorithms were effective. XGBoost consistently yielded lower errors and slightly higher R² in estimating the live weight of Kalahari Red goats based on body measurements. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group:
  Data: <i>Copyright of Turkish Journal of Veterinary & Animal Sciences is the property of Scientific and Technical Research Council of Turkey and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
– Name: AffiliationAuthor
  Label: Author Affiliations
  Group: AuInfo
  Data: <relatesTo>1</relatesTo>Department of Agricultural Economics and Animal Production, Faculty of Science and Agriculture, University of Limpopo, Limpopo, South Africa.<br /><relatesTo>2</relatesTo>Department of Animal Science, Faculty of Agriculture, Iğdır University, Iğdır, Turkiye.<br /><relatesTo>3</relatesTo>Department of Animal Science, Faculty of Agriculture, Ondokuz Mayıs University, Samsun, Turkiye.<br /><relatesTo>4</relatesTo>Department of Agricultural Biotechnology, Faculty of Agriculture, Ondokuz Mayıs University, Samsun, Turkiye.<br /><relatesTo>5</relatesTo>Department of Numerical Methods, Faculty of Economics and Administrative Sciences, Niğde Ömer Halisdemir University, Niğde, Turkiye.<br /><relatesTo>6</relatesTo>Department of Bioengineering, Faculty of Agriculture, Kahramanmaraş Sütçü İmam University, Kahramanmaraş, Turkiye.<br /><relatesTo>7</relatesTo>Department of Animal Science, Faculty of Agriculture, Eskişehir Osmangazi University, Eskişehir, Turkiye.<br /><relatesTo>8</relatesTo>Department of Animal Science, Faculty of Agriculture, Gaziosmanpaşa University, Tokat, Turkiye.
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1300-0128
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.55730/1300-0128.4405
– Name: AN
  Label: Accession Number
  Group: ID
  Data: 192162921
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=vft&AN=192162921
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.55730/1300-0128.4405
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 18
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Goats
        Type: general
      – SubjectFull: Goodness-of-fit tests
        Type: general
      – SubjectFull: Body size
        Type: general
      – SubjectFull: Livestock growth
        Type: general
    Titles:
      – TitleFull: Comparison of the MARS and XGBoost algorithms for predicting body weight in Kalahari Red goats.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: TYASI, Louis Thobela
      – PersonEntity:
          Name:
            NameFull: TIRINK, Cem
      – PersonEntity:
          Name:
            NameFull: MOKOENA, Kwena
      – PersonEntity:
          Name:
            NameFull: ÖNDER, Hasan
      – PersonEntity:
          Name:
            NameFull: ŞEN, Uğur
      – PersonEntity:
          Name:
            NameFull: ÇANGA BOĞA, Demet
      – PersonEntity:
          Name:
            NameFull: TOLUN, Tolga
      – PersonEntity:
          Name:
            NameFull: GÖK, İsmail
      – PersonEntity:
          Name:
            NameFull: AKSOY, Yüksel
      – PersonEntity:
          Name:
            NameFull: BAYYURT, Lütfi
      – PersonEntity:
          Name:
            NameFull: YILMAZ, Ömer Faruk
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 13000128
          Numbering:
            – Type: volume
              Value: 50
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Turkish Journal of Veterinary & Animal Sciences
              Type: main
ResultId 1