Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors

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...

Full description

Bibliographic Details
Main Authors: Andrew W. Hamilton, Chris Davison, Christos Tachtatzis, Ivan Andonovic, Craig Michie, Holly J. Ferguson, Laura Somerville, Nicholas N. Jonsson
Format: Article
Language:English
Published: MDPI AG 2019-03-01
Series:Sensors
Subjects:
Online Access:http://www.mdpi.com/1424-8220/19/5/1165
id doaj-87ce4d5883b6431ea9f492de9e395014
record_format Article
spelling doaj-87ce4d5883b6431ea9f492de9e3950142020-11-24T22:06:26ZengMDPI AGSensors1424-82202019-03-01195116510.3390/s19051165s19051165Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus SensorsAndrew W. Hamilton0Chris Davison1Christos Tachtatzis2Ivan Andonovic3Craig Michie4Holly J. Ferguson5Laura Somerville6Nicholas N. Jonsson7Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UKDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UKDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UKDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UKDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1RD, UKDairy Research and Innovation Centre, Scotland’s Rural College DG1 4TA, UKSchool of Veterinary Medicine, University of Glasgow, Glasgow G61 1QH, UKBiodiversity, Animal Health and Comparative Medicine, University of Glasgow, Glasgow G61 1QH, UKThe 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.http://www.mdpi.com/1424-8220/19/5/1165cattlebolus sensorsaccelerometersbehaviourrumination
collection DOAJ
language English
format Article
sources DOAJ
author Andrew W. Hamilton
Chris Davison
Christos Tachtatzis
Ivan Andonovic
Craig Michie
Holly J. Ferguson
Laura Somerville
Nicholas N. Jonsson
spellingShingle Andrew W. Hamilton
Chris Davison
Christos Tachtatzis
Ivan Andonovic
Craig Michie
Holly J. Ferguson
Laura Somerville
Nicholas N. Jonsson
Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
Sensors
cattle
bolus sensors
accelerometers
behaviour
rumination
author_facet Andrew W. Hamilton
Chris Davison
Christos Tachtatzis
Ivan Andonovic
Craig Michie
Holly J. Ferguson
Laura Somerville
Nicholas N. Jonsson
author_sort Andrew W. Hamilton
title Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
title_short Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
title_full Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
title_fullStr Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
title_full_unstemmed Identification of the Rumination in Cattle Using Support Vector Machines with Motion-Sensitive Bolus Sensors
title_sort identification of the rumination in cattle using support vector machines with motion-sensitive bolus sensors
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2019-03-01
description 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.
topic cattle
bolus sensors
accelerometers
behaviour
rumination
url http://www.mdpi.com/1424-8220/19/5/1165
work_keys_str_mv AT andrewwhamilton identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT chrisdavison identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT christostachtatzis identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT ivanandonovic identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT craigmichie identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT hollyjferguson identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT laurasomerville identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
AT nicholasnjonsson identificationoftheruminationincattleusingsupportvectormachineswithmotionsensitivebolussensors
_version_ 1725823789638352896