An IMU-based machine learning approach for daily behavior pattern recognition in dairy cows

IF 6.3 Q1 AGRICULTURAL ENGINEERING Smart agricultural technology Pub Date : 2024-08-18 DOI:10.1016/j.atech.2024.100539
{"title":"An IMU-based machine learning approach for daily behavior pattern recognition in dairy cows","authors":"","doi":"10.1016/j.atech.2024.100539","DOIUrl":null,"url":null,"abstract":"<div><p>Technological advancements have revolutionized livestock farming, notably in health monitoring. Traditional methods, which have been criticized for subjectivity and treatment delays, can be replaced with efficient health monitoring systems, thereby reducing costs and workload. Implementing cow behavior recognition allows for effective dairy cow health monitoring. In this research, we propose an integrated system using inertial measurement unit (IMU) devices and machine learning techniques for dairy cow behavior recognition. Six main dairy cow behaviors were studied: lying, standing, walking, drinking, feeding, and ruminating. All behavior types were manually labeled into the IMU data by reviewing the recorded footage. The labeled IMU data underwent four processing steps: selecting different window sizes, feature extraction, feature selection, and normalization. These processed data were then used to build the behavior recognition model. Various model structures, including SVM, Random Forest, and XGBoost, were tested. The top-performing model, XGBoost, with its proposed 58 features achieved an F1-score of 0.87, with specific scores of 0.93 for lying, 0.85 for walking, 0.94 for ruminating, 0.89 for feeding, 0.86 for standing, 0.93 for drinking, and 0.59 for other activities. During our online testing, we observed similar patterns for each healthy cow. The cumulative time spent on each behavior also matched the statistics from previous surveys. Additionally, our backend optimization approach resulted in a final overall percentage error of 1.55 % per day during online testing. In conclusion, our study presents an IMU-based system capable of accurately recognizing dairy cow behavior. Feature design and appropriate models are proposed herein. A functional optimization method was introduced indicating that our system has the potential with applications for estrus detection and other reproductive management practices in the dairy industry.</p></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":null,"pages":null},"PeriodicalIF":6.3000,"publicationDate":"2024-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772375524001448/pdfft?md5=f2fe1f7350786c4ff6118c741fa2d254&pid=1-s2.0-S2772375524001448-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Smart agricultural technology","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772375524001448","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

Technological advancements have revolutionized livestock farming, notably in health monitoring. Traditional methods, which have been criticized for subjectivity and treatment delays, can be replaced with efficient health monitoring systems, thereby reducing costs and workload. Implementing cow behavior recognition allows for effective dairy cow health monitoring. In this research, we propose an integrated system using inertial measurement unit (IMU) devices and machine learning techniques for dairy cow behavior recognition. Six main dairy cow behaviors were studied: lying, standing, walking, drinking, feeding, and ruminating. All behavior types were manually labeled into the IMU data by reviewing the recorded footage. The labeled IMU data underwent four processing steps: selecting different window sizes, feature extraction, feature selection, and normalization. These processed data were then used to build the behavior recognition model. Various model structures, including SVM, Random Forest, and XGBoost, were tested. The top-performing model, XGBoost, with its proposed 58 features achieved an F1-score of 0.87, with specific scores of 0.93 for lying, 0.85 for walking, 0.94 for ruminating, 0.89 for feeding, 0.86 for standing, 0.93 for drinking, and 0.59 for other activities. During our online testing, we observed similar patterns for each healthy cow. The cumulative time spent on each behavior also matched the statistics from previous surveys. Additionally, our backend optimization approach resulted in a final overall percentage error of 1.55 % per day during online testing. In conclusion, our study presents an IMU-based system capable of accurately recognizing dairy cow behavior. Feature design and appropriate models are proposed herein. A functional optimization method was introduced indicating that our system has the potential with applications for estrus detection and other reproductive management practices in the dairy industry.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于 IMU 的奶牛日常行为模式识别机器学习方法
技术进步给畜牧业带来了革命性的变化,尤其是在健康监测方面。传统方法因主观性和治疗延误而饱受诟病,而高效的健康监测系统可取代传统方法,从而降低成本和工作量。实施奶牛行为识别可实现有效的奶牛健康监测。在这项研究中,我们提出了一种利用惯性测量单元(IMU)设备和机器学习技术进行奶牛行为识别的集成系统。我们研究了奶牛的六种主要行为:躺卧、站立、行走、饮水、采食和反刍。所有行为类型都是通过查看记录的片段手动标记到 IMU 数据中的。标注的 IMU 数据经过四个处理步骤:选择不同的窗口大小、特征提取、特征选择和归一化。这些经过处理的数据随后被用于建立行为识别模型。测试了各种模型结构,包括 SVM、随机森林和 XGBoost。表现最好的 XGBoost 模型利用其提出的 58 个特征达到了 0.87 的 F1 分数,其中躺卧的具体分数为 0.93,行走为 0.85,反刍为 0.94,进食为 0.89,站立为 0.86,喝水为 0.93,其他活动为 0.59。在在线测试中,我们观察到每头健康奶牛都有类似的模式。每种行为花费的累计时间也与之前调查的统计数据相吻合。此外,我们的后台优化方法使在线测试期间每天的最终总体百分比误差为 1.55%。总之,我们的研究提出了一种基于 IMU 的系统,能够准确识别奶牛的行为。本文提出了特征设计和适当的模型。引入的功能优化方法表明,我们的系统具有应用于发情检测和奶牛业其他繁殖管理实践的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
4.20
自引率
0.00%
发文量
0
期刊最新文献
Development of a low-cost smart irrigation system for sustainable water management in the Mediterranean region Cover crop impacts on soil organic matter dynamics and its quantification using UAV and proximal sensing Design and development of machine vision robotic arm for vegetable crops in hydroponics Cybersecurity threats and mitigation measures in agriculture 4.0 and 5.0 Farmer's attitudes towards GHG emissions and adoption to low-cost sensor-driven smart farming for mitigation: The case of Ireland tillage and horticultural farmers
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1