Lambing event detection using deep learning from accelerometer data

Kirk Turner; Ferdous A Sohel; Ian Harris; Mark B Ferguson; Andrew N Thompson

doi:10.1016/j.compag.2023.107787

Back

Lambing event detection using deep learning from accelerometer data

Journal article

Open access

Peer reviewed

Lambing event detection using deep learning from accelerometer data

Kirk Turner, Ferdous A Sohel, Ian Harris, Mark B Ferguson and Andrew N Thompson

Computers and electronics in agriculture, Vol.208, Art. 107787

2023

DOI: https://doi.org/10.1016/j.compag.2023.107787

Appears in Open Access via Read & Publish Agreements

Files and links (1)

pdf

Published5.23 MBDownload View

CC BY-NC-ND V4.0, Open Access

Abstract

Behaviour classification

Machine learning

On-animal sensors

Parturition

Sheep

Newborn lamb mortality is a major economic and welfare concern for the sheep industry globally, which can potentially be reduced through automated monitoring of lambing difficulties and quantifying time of birth. This study investigated the identification of lambing ewes’ behaviours during labour and post-partum licking, by applying deep learning algorithms to halter-mounted accelerometer sensor data. 101 lambing ewes from two experiments and 29 non-pregnant ewes from three other experiments, were fitted with the sensors. Ground truth behaviour labels, 5 s long, were obtained based on video recordings of the study sheep. Classification using a Long Short-Term Memory (LSTM) model, was performed for different ethograms: labour behaviours, phases of labour, licking only, and labour and licking in the context of broader grazing behaviours. The model was fine-tuned with data of six sheep where the first birth fell within the observation period. A combined grazing and lambing behaviour ethogram achieved the best performance (accuracy: 81%) with recall of 0.85 for the licking behaviour. Fine-tuning increased performance further (average accuracy: 86.3%), with a best case recall of 0.88 for labour and 0.94 for licking. The licking only ethogram demonstrated strong recall for licking (0.9) when the epoch length was increased to 60 s. Isolation of the labour and licking behaviours achieved 84.8% accuracy, with a weighted F1-score of 0.85, demonstrating the ability to separate the labour phases. The study presents a strong foundation for the development of systems to detect lambing events and prolonged labour.

Details

Title: Lambing event detection using deep learning from accelerometer data
Authors/Creators: Kirk Turner - School of Information Technology, Murdoch University, Murdoch, WA 6150, Australia
Ferdous A Sohel
Ian Harris - neXtgen Agri, Saint Martins, Christchurch 8022, New Zealand
Mark B Ferguson - neXtgen Agri, Saint Martins, Christchurch 8022, New Zealand
Andrew N Thompson - School of Agricultural Sciences, Murdoch University, Murdoch, WA 6150, Australia
Publication Details: Computers and electronics in agriculture, Vol.208, Art. 107787
Publisher: Elsevier B.V
Identifiers: 991005567870107891
Murdoch Affiliation: Centre for Crop and Food Innovation; School of Information Technology
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Metrics

12 File views/ downloads

133 Record Views

20 Times Cited - Web of Science

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: International collaboration
Citation topics: 3 Agriculture, Environment & Ecology; 3.51 Dairy & Animal Sciences; 3.51.799 Farm Animal Welfare
Web Of Science research areas: Agriculture, Multidisciplinary; Computer Science, Interdisciplinary Applications
ESI research areas: Computer Science