Use of Multivariate Adaptive Regression Splines Algorithm to Predict Body Weight from Body Measurements of Anatolian buffaloes in Türkiye

• Published in: Animals (Basel) Vol. 12; no. 21; p. 2923
• Main Authors: Ağyar, Oğuz, Tırınk, Cem, Önder, Hasan, Şen, Uğur, Piwczyński, Dariusz, Yavuz, Esra
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 25.10.2022; MDPI
• Subjects: Adaptive algorithms; Algorithms; biometric properties; Birth weight; Body length; Body measurements; Body weight; Chest; Circumferences; Criteria; Datasets; Feeds; Height; MARS; Meat; Meat production; Multivariate analysis; Performance evaluation; prediction; Rural development; Shoulder; Software; Tails; Test sets; Variables; water buffalo
• ISSN: 2076-2615; 2076-2615
• DOI: 10.3390/ani12212923

Anatolian buffalo is an important breed reared for meat and milk in various regions of Türkiye. The present study was performed to estimate body weight (BW) from several body measurements, such as tail length (TL), shoulder height (SH), withers height (WH), body length (BL), chest circumference (CC), shank diameter (SD) and birth weight (BiW). The data set was taken from Muş Province of Türkiye. In this respect, 171 Anatolian buffaloes were used. To estimate the BW, different proportions of the training and test sets were used with the MARS algorithm. The optimal MARS was determined at a proportion of 70–30%. The MARS model displays the heaviest BW that can be produced by Anatolian buffalo according to tail length, body length, chest circumference and shoulder height. In conclusion, it could be suggested that the MARS algorithm may allow animal breeders to obtain an elite population and to determine the body measurements affecting BW as indirect selection criteria for describing the breed description of Anatolian buffalo and aiding sustainable meat production and rural development in Türkiye.