检索结果-南通市图书馆

Deep learning based classification of sheep behaviour from accelerometer data with imbalance

Information Processing in Agriculture 2023年第3期10卷 377-390页

作者： Kirk E.Turner Andrew Thompson Ian Harris Mark Ferguson Ferdous Sohel Discipline of Information Technology Murdoch UniversityMurdochWA 6150Australia Centre for Crop and Food Innovation Food Futures InstituteMurdoch UniversityMurdochWA 6150Australia College of Science HealthEngineering and EducationMurdoch UniversityMurdochWA 6150Australia neXtgen Agri Saint MartinsChristchurch 8022New Zealand

classification of sheep behaviour from a sequence of tri-axial accelerometer data has the potential to enhance sheep *** behaviour is inherently imbalanced(e.g.,more ruminating than walking)resulting in underperforming classification for the minority activities which hold *** works have not addressed class imbalance and use traditional machine learning techniques,e.g.,Random Forest(RF).We investigated Deep Learning(DL)models,namely,Long Short Term Memory(LSTM)and Bidirectional LSTM(BLSTM),appropriate for sequential data,from imbalanced *** data sets were collected in normal grazing conditions using jaw-mounted and earmounted *** to this study,alongside typical single classes,e.g.,walking,depending on the behaviours,data samples were labelled with compound classes,e.g.,walking_-*** number of steps a sheep performed in the observed 10 s time window was also recorded and incorporated in the *** designed several multi-class classification studies with imbalance being addressed using synthetic *** models achieved superior performance to traditional ML models,especially with augmented data(e.g.,4-Class+Steps:LSTM 88.0%,RF 82.5%).DL methods showed superior generalisability on unseen sheep(i.e.,F1-score:BLSTM 0.84,LSTM 0.83,RF 0.65).LSTM,BLSTM and RF achieved sub-millisecond average inference time,making them suitable for real-time *** results demonstrate the effectiveness of DL models for sheep behaviour classification in grazing *** results also demonstrate the DL techniques can generalise across different *** study presents a strong foundation of the development of such models for real-time animal monitoring.

关键词： sheep behaviour classification Data synthesis Class imbalance Grazing sheep

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：