Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors

Andrew Hamilton*, Chris Davison, Christos Tachtatzis, Ivan Andonovic, Craig Michie, HJ Ferguson, Laura Somerville, Nicholas N Jonsson

*Corresponding author for this work

Research output: Contribution to journal › Article

5 Downloads (Pure)

Abstract

The reticuloruminal function is central to the digestive efficiency in ruminants. For cattle, collar- and ear tag-based accelerometer monitors have been developed to assess the time spent ruminating on an individual animal. Cattle that are ill feed less and so ruminate less, thus, the estimation of the time spent ruminating provides insights into the health of individual animals. pH boluses directly provide information on the reticuloruminal function within the rumen and extended (three hours or more) periods during which the ruminal pH value remains below 5.6 is an indicator that dysfunction and poor welfare are likely. Accelerometers, incorporated into the pH boluses, have been used to indicate changes in behaviour patterns (high/low activity), utilised to detect the onset of oestrus. The paper demonstrates for the first time that by processing the reticuloruminal motion, it is possible to recover rumination periods. Reticuloruminal motion energy and the time between reticuloruminal contractions are used as inputs to a Support Vector Machine (SVM) to identify rumination periods with an overall accuracy of 86.1%, corroborated by neck mounted rumination collars.
Original languageEnglish
Article number1165
JournalSensors
Volume19
Issue number5
Early online date7 Mar 2019
DOIs
Publication statusPrint publication - 7 Mar 2019

Fingerprint

rumination
sensors (equipment)
collars
cattle
ear tags
neck
estrus
ruminants
rumen
animals
monitoring
energy
support vector machines

Keywords

  • Cattle
  • Bolus sensors
  • Accelerometers
  • Behaviour
  • Rumination

Cite this

Hamilton, A., Davison, C., Tachtatzis, C., Andonovic, I., Michie, C., Ferguson, HJ., ... Jonsson, N. N. (2019). Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors. Sensors, 19(5), [1165]. https://doi.org/10.3390/s19051165
Hamilton, Andrew ; Davison, Chris ; Tachtatzis, Christos ; Andonovic, Ivan ; Michie, Craig ; Ferguson, HJ ; Somerville, Laura ; Jonsson, Nicholas N. / Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors. In: Sensors. 2019 ; Vol. 19, No. 5.
@article{3b7afc8ec2ea43ea8daf36bb9886e358,
title = "Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors",
abstract = "The reticuloruminal function is central to the digestive efficiency in ruminants. For cattle, collar- and ear tag-based accelerometer monitors have been developed to assess the time spent ruminating on an individual animal. Cattle that are ill feed less and so ruminate less, thus, the estimation of the time spent ruminating provides insights into the health of individual animals. pH boluses directly provide information on the reticuloruminal function within the rumen and extended (three hours or more) periods during which the ruminal pH value remains below 5.6 is an indicator that dysfunction and poor welfare are likely. Accelerometers, incorporated into the pH boluses, have been used to indicate changes in behaviour patterns (high/low activity), utilised to detect the onset of oestrus. The paper demonstrates for the first time that by processing the reticuloruminal motion, it is possible to recover rumination periods. Reticuloruminal motion energy and the time between reticuloruminal contractions are used as inputs to a Support Vector Machine (SVM) to identify rumination periods with an overall accuracy of 86.1{\%}, corroborated by neck mounted rumination collars.",
keywords = "Cattle, Bolus sensors, Accelerometers, Behaviour, Rumination",
author = "Andrew Hamilton and Chris Davison and Christos Tachtatzis and Ivan Andonovic and Craig Michie and HJ Ferguson and Laura Somerville and Jonsson, {Nicholas N}",
year = "2019",
month = "3",
day = "7",
doi = "10.3390/s19051165",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-3210",
publisher = "MDPI",
number = "5",

}

Hamilton, A, Davison, C, Tachtatzis, C, Andonovic, I, Michie, C, Ferguson, HJ, Somerville, L & Jonsson, NN 2019, 'Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors', Sensors, vol. 19, no. 5, 1165. https://doi.org/10.3390/s19051165

Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors. / Hamilton, Andrew; Davison, Chris; Tachtatzis, Christos; Andonovic, Ivan; Michie, Craig; Ferguson, HJ; Somerville, Laura; Jonsson, Nicholas N.

In: Sensors, Vol. 19, No. 5, 1165, 07.03.2019.

Research output: Contribution to journal › Article

TY - JOUR

T1 - Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors

AU - Hamilton, Andrew

AU - Davison, Chris

AU - Tachtatzis, Christos

AU - Andonovic, Ivan

AU - Michie, Craig

AU - Ferguson, HJ

AU - Somerville, Laura

AU - Jonsson, Nicholas N

PY - 2019/3/7

Y1 - 2019/3/7

N2 - The reticuloruminal function is central to the digestive efficiency in ruminants. For cattle, collar- and ear tag-based accelerometer monitors have been developed to assess the time spent ruminating on an individual animal. Cattle that are ill feed less and so ruminate less, thus, the estimation of the time spent ruminating provides insights into the health of individual animals. pH boluses directly provide information on the reticuloruminal function within the rumen and extended (three hours or more) periods during which the ruminal pH value remains below 5.6 is an indicator that dysfunction and poor welfare are likely. Accelerometers, incorporated into the pH boluses, have been used to indicate changes in behaviour patterns (high/low activity), utilised to detect the onset of oestrus. The paper demonstrates for the first time that by processing the reticuloruminal motion, it is possible to recover rumination periods. Reticuloruminal motion energy and the time between reticuloruminal contractions are used as inputs to a Support Vector Machine (SVM) to identify rumination periods with an overall accuracy of 86.1%, corroborated by neck mounted rumination collars.

AB - The reticuloruminal function is central to the digestive efficiency in ruminants. For cattle, collar- and ear tag-based accelerometer monitors have been developed to assess the time spent ruminating on an individual animal. Cattle that are ill feed less and so ruminate less, thus, the estimation of the time spent ruminating provides insights into the health of individual animals. pH boluses directly provide information on the reticuloruminal function within the rumen and extended (three hours or more) periods during which the ruminal pH value remains below 5.6 is an indicator that dysfunction and poor welfare are likely. Accelerometers, incorporated into the pH boluses, have been used to indicate changes in behaviour patterns (high/low activity), utilised to detect the onset of oestrus. The paper demonstrates for the first time that by processing the reticuloruminal motion, it is possible to recover rumination periods. Reticuloruminal motion energy and the time between reticuloruminal contractions are used as inputs to a Support Vector Machine (SVM) to identify rumination periods with an overall accuracy of 86.1%, corroborated by neck mounted rumination collars.

KW - Cattle

KW - Bolus sensors

KW - Accelerometers

KW - Behaviour

KW - Rumination

U2 - 10.3390/s19051165

DO - 10.3390/s19051165

M3 - Article

C2 - 30866541

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 5

M1 - 1165

ER -

Hamilton A, Davison C, Tachtatzis C, Andonovic I, Michie C, Ferguson HJ et al. Identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors. Sensors. 2019 Mar 7;19(5). 1165. https://doi.org/10.3390/s19051165

Access to Document