arrow
返回

Dynamic cattle behavioural classification using supervised ensemble classifiers

delete2015-02-01
delete130
PRE
AI
R
Ritaban Dutta *
D
Daniel Smith
R
Rawnsley, Richard
G
Greg Bishop-Hurley
J
James Hills
G
Greg Timms
D
D. Henry
DOI:10.1016/j.compag.2014.12.002delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
In this paper various supervised machine learning techniques were applied to classify cattle behaviour patterns recorded using collar systems with 3-axis accelerometer and magnetometer, fitted to individual dairy cows to infer their physical behaviours. Cattle collar data was collected at the Tasmanian Institute of Agriculture (TIA) Dairy Research Facility in Tasmania. In the first stage of analysis a novel hybrid unsupervised clustering framework, comprised of probabilistic principal component analysis, Fuzzy C Means, and Self Organizing Map network algorithms was developed and used to study the natural structure of the sensor data. Findings from this unsupervised clustering were used to guide the next stage of supervised machine learning. Five major behaviour classes, namely, Grazing, Ruminating, Resting, Walking, and other behaviour were identified for the classification trials. An ensemble of classifiers approach was used to learn models of cow behaviour using sensor data and ground truth behaviour observations acquired from the field. Ensemble classification using bagging, Random Subspace and AdaBoost methods along with conventional supervised classification methods, namely, Binary Tree, Linear Discriminant Analysis classifier, Naive Bayes classifier, k-Nearest Neighbour classifier, and Adaptive Neuro Fuzzy Inference System classifier were compared. The highest average correct classification accuracy of 96% was achieved using the bagging ensemble classification with Tree learner, which had 97% sensitivity, 89% specificity, 89% F1 score and 9% false discovery rate. This study has shown that cattle behaviours can be classified with a high accuracy using supervised machine learning technique. As dairy and beef systems become more intensive, the ability to identify the changes in the behaviours of individual livestock becomes increasingly difficult. Accurate behavioural monitoring through sensors provides a significant potential in providing a mechanism for the early detection and quantitative assessment of animal health issues such a lameness, informing key management events such as the identification of oestrus, or informing changes in supplementary feeding requirements. Crown Copyright (C) 2014 Published by Elsevier B.V. All rights reserved.
Keyword:
Cattle tag data analysis
Cattle behavioural classification
Ensemble machine learning
Unsupervised data clustering
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Computers and Electronics in Agriculture 封面图
Computers and Electronics in Agriculture
IF:
8.9
论文数:
1.0W
被引数:
6.8W

机构

U
University of Tasmania
学者数:
507
论文数: 241
被引数: 9.0K
引用论文

引用论文

err分享
err收藏
On the Function of Cilia in the Female Reproductive Tract
err1978-01-01
err0
PREAI
errBjörn A. Afzelius; Per Camner; Björn Mossberg
err分享
err收藏
Age differences in rereading
err2004-07-01
err0
errOAAI
errElizabeth A. L. Stine-Morrow; Danielle D. Gagne; Daniel G. Morrow; Barbara Herman DeWall
err分享
err收藏
Nanoimprinting — a Key Enabling Technology for BioM EMS and Biomedical Applications
err2004-01-01
err0
PREAI
errR. Eichinger-Heue; T. Glinsner; P. Kettner; P. Lindner; C. Schaefer; S. Dwyer; B. Vratzov
err分享
err收藏
Electronic-Nose Technology Using Sputum Samples in Diagnosis of Patients with Tuberculosis
err2010-11-01
err66
errOAAI
errKolk, Arend; Hoelscher, Michael; Maboko, Leonard; Jung, Jutta; Kuijper, Sjoukje; Cauchi, Michael; Bessant, Conrad; van Beers, Stella; Dutta, Ritaban; Gibson, Tim; Reither, Klaus
err分享
err收藏
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
学者 查看更多内容