Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms

Kaitlynn M. Abell, Miles E. Theurer, Robert L. Larson, Brad J. White, David K. Hardin, Richard F Randle

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Parentage data from beef calves has shown that in multiple-sire pastures a disproportionate number of calves are born from a single bull. Investigating and accurately quantifying bull behavior within multiple-sire pastures will begin to determine reason(s) for the variability in the number of calves sired. The study objective was to assess accelerometer data and various classification algorithms to accurately predict bull behavior events in a multiple-sire pasture. Behavior events of interest in this study included lying, standing, walking, and mounting. Two bulls and ten estrous synchronized cows were used. True behavior events were determined during daylight hours with video analysis, and matched with accelerometer data. Accelerometers were attached to both ears, withers, and neck of both bulls. Accelerometer data were recorded for every second over 3 days. Accelerometer data were used to generate algorithms and accuracy was evaluated compared to known video behavioral data. The prevalence based on the raw video data for lying was 32.6%, standing was 59.4%, walking was 7.4%, and mounting was 0.6%. The random forest classifier had the highest accuracy compared to other classifiers (random tree and decision tree) for each tag location and behavior of interest. The accuracies from the random forest algorithms ranged from 92 to 99% for lying, 85 to 90% for standing, 73 to 77% for walking, and 74% to 80% for mounting. The classification algorithm was able to accurately predict a lying and standing event, and predict a walking and mounting event with a lower accuracy. Further research is needed to determine how behaviors between bulls affects overall parentage data.

Original languageEnglish (US)
Pages (from-to)221-227
Number of pages7
JournalComputers and Electronics in Agriculture
Volume136
DOIs
StatePublished - Apr 15 2017

Fingerprint

accelerometer
Accelerometers
sires
bulls
pasture
Mountings
pastures
taxonomy
walking
parentage
calves
Classifiers
Beef
Decision trees
withers
neck
video
analysis
ears
beef

Keywords

  • Beef bull
  • Behavior
  • Cattle
  • Machine learning
  • Multiple-sire pasture

ASJC Scopus subject areas

  • Forestry
  • Animal Science and Zoology
  • Agronomy and Crop Science
  • Computer Science Applications
  • Horticulture

Cite this

Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms. / Abell, Kaitlynn M.; Theurer, Miles E.; Larson, Robert L.; White, Brad J.; Hardin, David K.; Randle, Richard F.

In: Computers and Electronics in Agriculture, Vol. 136, 15.04.2017, p. 221-227.

Research output: Contribution to journalArticle

Abell, Kaitlynn M. ; Theurer, Miles E. ; Larson, Robert L. ; White, Brad J. ; Hardin, David K. ; Randle, Richard F. / Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms. In: Computers and Electronics in Agriculture. 2017 ; Vol. 136. pp. 221-227.
@article{09ff5d18c14c418ab4c51da185dccac6,
title = "Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms",
abstract = "Parentage data from beef calves has shown that in multiple-sire pastures a disproportionate number of calves are born from a single bull. Investigating and accurately quantifying bull behavior within multiple-sire pastures will begin to determine reason(s) for the variability in the number of calves sired. The study objective was to assess accelerometer data and various classification algorithms to accurately predict bull behavior events in a multiple-sire pasture. Behavior events of interest in this study included lying, standing, walking, and mounting. Two bulls and ten estrous synchronized cows were used. True behavior events were determined during daylight hours with video analysis, and matched with accelerometer data. Accelerometers were attached to both ears, withers, and neck of both bulls. Accelerometer data were recorded for every second over 3 days. Accelerometer data were used to generate algorithms and accuracy was evaluated compared to known video behavioral data. The prevalence based on the raw video data for lying was 32.6{\%}, standing was 59.4{\%}, walking was 7.4{\%}, and mounting was 0.6{\%}. The random forest classifier had the highest accuracy compared to other classifiers (random tree and decision tree) for each tag location and behavior of interest. The accuracies from the random forest algorithms ranged from 92 to 99{\%} for lying, 85 to 90{\%} for standing, 73 to 77{\%} for walking, and 74{\%} to 80{\%} for mounting. The classification algorithm was able to accurately predict a lying and standing event, and predict a walking and mounting event with a lower accuracy. Further research is needed to determine how behaviors between bulls affects overall parentage data.",
keywords = "Beef bull, Behavior, Cattle, Machine learning, Multiple-sire pasture",
author = "Abell, {Kaitlynn M.} and Theurer, {Miles E.} and Larson, {Robert L.} and White, {Brad J.} and Hardin, {David K.} and Randle, {Richard F}",
year = "2017",
month = "4",
day = "15",
doi = "10.1016/j.compag.2017.01.030",
language = "English (US)",
volume = "136",
pages = "221--227",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

TY - JOUR

T1 - Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms

AU - Abell, Kaitlynn M.

AU - Theurer, Miles E.

AU - Larson, Robert L.

AU - White, Brad J.

AU - Hardin, David K.

AU - Randle, Richard F

PY - 2017/4/15

Y1 - 2017/4/15

N2 - Parentage data from beef calves has shown that in multiple-sire pastures a disproportionate number of calves are born from a single bull. Investigating and accurately quantifying bull behavior within multiple-sire pastures will begin to determine reason(s) for the variability in the number of calves sired. The study objective was to assess accelerometer data and various classification algorithms to accurately predict bull behavior events in a multiple-sire pasture. Behavior events of interest in this study included lying, standing, walking, and mounting. Two bulls and ten estrous synchronized cows were used. True behavior events were determined during daylight hours with video analysis, and matched with accelerometer data. Accelerometers were attached to both ears, withers, and neck of both bulls. Accelerometer data were recorded for every second over 3 days. Accelerometer data were used to generate algorithms and accuracy was evaluated compared to known video behavioral data. The prevalence based on the raw video data for lying was 32.6%, standing was 59.4%, walking was 7.4%, and mounting was 0.6%. The random forest classifier had the highest accuracy compared to other classifiers (random tree and decision tree) for each tag location and behavior of interest. The accuracies from the random forest algorithms ranged from 92 to 99% for lying, 85 to 90% for standing, 73 to 77% for walking, and 74% to 80% for mounting. The classification algorithm was able to accurately predict a lying and standing event, and predict a walking and mounting event with a lower accuracy. Further research is needed to determine how behaviors between bulls affects overall parentage data.

AB - Parentage data from beef calves has shown that in multiple-sire pastures a disproportionate number of calves are born from a single bull. Investigating and accurately quantifying bull behavior within multiple-sire pastures will begin to determine reason(s) for the variability in the number of calves sired. The study objective was to assess accelerometer data and various classification algorithms to accurately predict bull behavior events in a multiple-sire pasture. Behavior events of interest in this study included lying, standing, walking, and mounting. Two bulls and ten estrous synchronized cows were used. True behavior events were determined during daylight hours with video analysis, and matched with accelerometer data. Accelerometers were attached to both ears, withers, and neck of both bulls. Accelerometer data were recorded for every second over 3 days. Accelerometer data were used to generate algorithms and accuracy was evaluated compared to known video behavioral data. The prevalence based on the raw video data for lying was 32.6%, standing was 59.4%, walking was 7.4%, and mounting was 0.6%. The random forest classifier had the highest accuracy compared to other classifiers (random tree and decision tree) for each tag location and behavior of interest. The accuracies from the random forest algorithms ranged from 92 to 99% for lying, 85 to 90% for standing, 73 to 77% for walking, and 74% to 80% for mounting. The classification algorithm was able to accurately predict a lying and standing event, and predict a walking and mounting event with a lower accuracy. Further research is needed to determine how behaviors between bulls affects overall parentage data.

KW - Beef bull

KW - Behavior

KW - Cattle

KW - Machine learning

KW - Multiple-sire pasture

UR - http://www.scopus.com/inward/record.url?scp=85015836120&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015836120&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2017.01.030

DO - 10.1016/j.compag.2017.01.030

M3 - Article

VL - 136

SP - 221

EP - 227

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

ER -