Sensor data classification for the indication of lameness in sheep

Research output: Contribution to Book/Report typesChapterResearchpeer-review

Abstract

Lameness is a vital welfare issue in most sheep farming countries, including the UK. The pre-detection at the farm level could prevent the disease from becoming chronic. The development of wearable sensor technologies enables the idea of remotely monitoring the changes in animal movements which relate to lameness. In this study, 3D-acceleration, 3D-orientation, and 3D-linear acceleration sensor data were recorded at ten samples per second via the sensor attached to sheep neck collar. This research aimed to determine the best accuracy among various supervised machine learning techniques which can predict the early signs of lameness while the sheep are walking on a flat field. The most influencing predictors for lameness indication were also addressed here. The experimental results revealed that the Decision Tree classifier has the highest accuracy of 75.46%, and the orientation sensor data (angles) around the neck are the strongest predictors to differentiate among severely lame, mildly lame and sound classes of sheep.
Original languageEnglish
Title of host publicationCollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing
Place of PublicationEdinburgh
PublisherSpringer
Publication statusPublished - 11 Dec 2017

Fingerprint

Sensors
Decision trees
Farms
Learning systems
Animals
Classifiers
Acoustic waves
Monitoring
Wearable sensors

Keywords

  • Sensor data analysis
  • classification
  • sheep lameness detection

Cite this

Al-Rubaye, Z., Al-Sherbaz, A., McCormick, W. D., & Turner, S. J. (2017). Sensor data classification for the indication of lameness in sheep. In CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing Edinburgh: Springer.
Al-Rubaye, Zainab ; Al-Sherbaz, Ali ; McCormick, Wanda D ; Turner, Scott J. / Sensor data classification for the indication of lameness in sheep. CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing. Edinburgh : Springer, 2017.
@inbook{1c0a303978c84c35a81eb96c7a81e4d8,
title = "Sensor data classification for the indication of lameness in sheep",
abstract = "Lameness is a vital welfare issue in most sheep farming countries, including the UK. The pre-detection at the farm level could prevent the disease from becoming chronic. The development of wearable sensor technologies enables the idea of remotely monitoring the changes in animal movements which relate to lameness. In this study, 3D-acceleration, 3D-orientation, and 3D-linear acceleration sensor data were recorded at ten samples per second via the sensor attached to sheep neck collar. This research aimed to determine the best accuracy among various supervised machine learning techniques which can predict the early signs of lameness while the sheep are walking on a flat field. The most influencing predictors for lameness indication were also addressed here. The experimental results revealed that the Decision Tree classifier has the highest accuracy of 75.46{\%}, and the orientation sensor data (angles) around the neck are the strongest predictors to differentiate among severely lame, mildly lame and sound classes of sheep.",
keywords = "Sensor data analysis, classification, sheep lameness detection",
author = "Zainab Al-Rubaye and Ali Al-Sherbaz and McCormick, {Wanda D} and Turner, {Scott J}",
year = "2017",
month = "12",
day = "11",
language = "English",
booktitle = "CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing",
publisher = "Springer",

}

Al-Rubaye, Z, Al-Sherbaz, A, McCormick, WD & Turner, SJ 2017, Sensor data classification for the indication of lameness in sheep. in CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing. Springer, Edinburgh.

Sensor data classification for the indication of lameness in sheep. / Al-Rubaye, Zainab; Al-Sherbaz, Ali; McCormick, Wanda D; Turner, Scott J.

CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing. Edinburgh : Springer, 2017.

Research output: Contribution to Book/Report typesChapterResearchpeer-review

TY - CHAP

T1 - Sensor data classification for the indication of lameness in sheep

AU - Al-Rubaye, Zainab

AU - Al-Sherbaz, Ali

AU - McCormick, Wanda D

AU - Turner, Scott J

PY - 2017/12/11

Y1 - 2017/12/11

N2 - Lameness is a vital welfare issue in most sheep farming countries, including the UK. The pre-detection at the farm level could prevent the disease from becoming chronic. The development of wearable sensor technologies enables the idea of remotely monitoring the changes in animal movements which relate to lameness. In this study, 3D-acceleration, 3D-orientation, and 3D-linear acceleration sensor data were recorded at ten samples per second via the sensor attached to sheep neck collar. This research aimed to determine the best accuracy among various supervised machine learning techniques which can predict the early signs of lameness while the sheep are walking on a flat field. The most influencing predictors for lameness indication were also addressed here. The experimental results revealed that the Decision Tree classifier has the highest accuracy of 75.46%, and the orientation sensor data (angles) around the neck are the strongest predictors to differentiate among severely lame, mildly lame and sound classes of sheep.

AB - Lameness is a vital welfare issue in most sheep farming countries, including the UK. The pre-detection at the farm level could prevent the disease from becoming chronic. The development of wearable sensor technologies enables the idea of remotely monitoring the changes in animal movements which relate to lameness. In this study, 3D-acceleration, 3D-orientation, and 3D-linear acceleration sensor data were recorded at ten samples per second via the sensor attached to sheep neck collar. This research aimed to determine the best accuracy among various supervised machine learning techniques which can predict the early signs of lameness while the sheep are walking on a flat field. The most influencing predictors for lameness indication were also addressed here. The experimental results revealed that the Decision Tree classifier has the highest accuracy of 75.46%, and the orientation sensor data (angles) around the neck are the strongest predictors to differentiate among severely lame, mildly lame and sound classes of sheep.

KW - Sensor data analysis

KW - classification

KW - sheep lameness detection

M3 - Chapter

BT - CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing

PB - Springer

CY - Edinburgh

ER -

Al-Rubaye Z, Al-Sherbaz A, McCormick WD, Turner SJ. Sensor data classification for the indication of lameness in sheep. In CollaborateCom 2017 - 13th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing. Edinburgh: Springer. 2017