Determination of ewe behaviour around lambing time and prediction of parturition 7 days prior to lambing by tri-axial accelerometer sensors in an extensive farming system
Rajneet Sohi
A * , Fazel Almasi A , Hien Nguyen B , Alexandra Carroll A , Jason Trompf C , Maneka Weerasinghe D , Aidin Bervan D , Boris I. Godoy E , Awais Ahmed A , Michael J. Stear A , Aniruddha Desai D and Markandeya Jois A
A School of Life Sciences, La Trobe University, Bundoora, Vic. 3086, Australia.
B School of Mathematics and Physics, University of Queensland, St. Lucia, Qld 4072, Australia.
C Northgate Park, Glenrowan, Wangaratta, Vic. 3675, Australia.
D Centre for Technology Infusion, La Trobe University, Bundoora, Vic. 3086, Australia.
E Department of Mechanical Engineering, Boston University, Boston, MA 02215, USA.
Animal Production Science 62(17) 1729-1738 https://doi.org/10.1071/AN21460
Submitted: 7 September 2021 Accepted: 6 June 2022 Published: 8 July 2022
© 2022 The Author(s) (or their employer(s)). Published by CSIRO Publishing. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)
Abstract
Context: Lamb loss and dyctocia are two major challenges in extensive farming systems. While visual observation can be impractical due to the large sizes of paddocks, number of animals and high labour cost, wearable sensors can be used to monitor the behaviour of ewes as there might be changes in their activities prior to lambing. This provides sufficient time for the farm manager to nurse those ewes that are at risk of dyctocia.
Aim: The objective of this study was to determine whether the behaviour of a pregnant ewe could predict the time of parturition.
Methods: Two separate trials were conducted: the first trial (T1), with 32 ewes, included human/video observations, and the second trial (T2), with 165 ewes, conducted with no humans present, to emulate real extensive farming settings. The ewes were fitted with tri-axial accelerometer sensors by means of halters. Three-dimensional movement data were collected for a period of at least 7 and 14 days in T1 and T2 respectively. The sensor units were retrieved, and their data downloaded using ActiGraph software. Ewe behaviour was determined through support vector machine learning (SVM) algorithm, including licking, grazing, rumination, walking, and idling. The behaviours of ewes predicted by analysis of sensor data were compared with behaviours determined using visual observation (video recordings), with time synchronisation to validate the results. Deep learning and neural-network algorithms were used to predict lambing time.
Key results: The concordance percentages between visual observation and sensor data were 90 ± 11, 81 ± 15, 95 ± 10, 96 ± 6, and 93 ± 8% ± s.d. for grazing, licking, rumination, idling, and walking respectively. The deep-learning model predicted the time of lambing with 90% confidence via a quantile regression method, which can be interpereted as 90% prediction intervals, and shows that the time of lambing can be predicted with reasonable confidence approximately 240 h before the actual lambing events.
Conclusion: It was possible to predict the time of parturition up to 10 days before lambing.
Implications: The behaviour of ewes around lambing time has a direct effect on the survival of the lambs and therefore plays an important part in animal management. This knowledge could improve the productivity of sheep and considerably decrease lamb mortality rates.
Keywords: accelerometer sensors, extensive farming, lamb survival, lambing time, machine learning, parturition, quantile regression, sheep behaviour.
References
Abe S (1997) ‘Neural networks and fuzzy systems: theory and applications.’ (Springer US: Imprint: Springer: Boston, MA, USA)Abe S (2010) ‘Support vector machines for pattern classification.’ Advances in computer vision and pattern recognition. (Springer London: London, UK)
| Crossref |
Alvarenga FAP, Borges I, Palkovič L, Rodina J, Oddy VH, Dobos RC (2016) Using a three-axis accelerometer to identify and classify sheep behaviour at pasture. Applied Animal Behaviour Science 181, 91–99.
| Using a three-axis accelerometer to identify and classify sheep behaviour at pasture.Crossref | GoogleScholarGoogle Scholar |
Arun Kumar M, Gopal M (2011) Reduced one-against-all method for multiclass SVM classification. Expert Systems with Applications 38, 14238–14248.
| Reduced one-against-all method for multiclass SVM classification.Crossref | GoogleScholarGoogle Scholar |
Barwick J, Lamb DW, Dobos R, Welch M, Trotter M (2018) Categorising sheep activity using a tri-axial accelerometer. Computers and Electronics in Agriculture 145, 289–297.
| Categorising sheep activity using a tri-axial accelerometer.Crossref | GoogleScholarGoogle Scholar |
Barwick J, Lamb DW, Dobos R, Welch M, Schneider D, Trotter M (2020) Identifying sheep activity from tri-axial acceleration signals using a moving window classification model. Remote Sensing 12, 646
| Identifying sheep activity from tri-axial acceleration signals using a moving window classification model.Crossref | GoogleScholarGoogle Scholar |
Bezdek JC, Keller J, Krisnapuram R, Pal NR (1999) ‘Fuzzy models and algorithms for pattern recognition and image processing.’ Handbooks of fuzzy sets series. (Kluwer Academic Publ.: Boston, MA, USA)
Borchers MR, Chang YM, Proudfoot KL, Wadsworth BA, Stone AE, Bewley JM (2017) Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle. Journal of Dairy Science 100, 5664–5674.
| Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle.Crossref | GoogleScholarGoogle Scholar | 28501398PubMed |
Borghart GM, O’Grady LE, Somers JR (2021) Prediction of lameness using automatically recorded activity, behavior and production data in post-parturient Irish dairy cows. Irish Veterinary Journal 74, 4
| Prediction of lameness using automatically recorded activity, behavior and production data in post-parturient Irish dairy cows.Crossref | GoogleScholarGoogle Scholar | 33549140PubMed |
Box GEP, Jenkins GM, Reinsel GC (2008) ‘Time series analysis: forecasting and control.’ 4th edn. Wiley series in probability and statistics. (John Wiley: Hoboken, NJ, USA)
Bruce M, Young JM, Masters DG, Refshauge G, Thompson AN, Kenyon PR, Behrendt R, Lockwood A, Miller DW, Jacobson C (2021) The impact of lamb and ewe mortality associated with dystocia on Australian and New Zealand sheep farms: a systematic review, meta-analysis and bio-economic model. Preventive Veterinary Medicine 196, 105478
| The impact of lamb and ewe mortality associated with dystocia on Australian and New Zealand sheep farms: a systematic review, meta-analysis and bio-economic model.Crossref | GoogleScholarGoogle Scholar | 34487918PubMed |
Byun H, Lee S-W (2003) A survey on pattern recognition applications of support vector machines. International Journal of Pattern Recognition and Artificial Intelligence 17, 459–486.
| A survey on pattern recognition applications of support vector machines.Crossref | GoogleScholarGoogle Scholar |
Charlier I, Paindaveine D, Saracco J (2015a) Quantifquantile: an R package for performing quantile regression through optimal quantization. The R Journal 7, 65–80.
| Quantifquantile: an R package for performing quantile regression through optimal quantization.Crossref | GoogleScholarGoogle Scholar |
Charlier I, Paindaveine D, Saracco J (2015b) Conditional quantile estimation through optimal quantization. Journal of Statistical Planning and Inference 156, 14–30.
| Conditional quantile estimation through optimal quantization.Crossref | GoogleScholarGoogle Scholar |
Chollet F, Allaire JJ (2018) Deep learning with R.
Dozat T (2016) Incorporating Nesterov Momentum into Adam.
Fogarty ES, Swain DL, Cronin GM, Moraes LE, Bailey DW, Trotter MG (2020a) Potential for autonomous detection of lambing using global navigation satellite system technology. Animal Production Science 60, 1217–1226.
| Potential for autonomous detection of lambing using global navigation satellite system technology.Crossref | GoogleScholarGoogle Scholar |
Fogarty ES, Swain DL, Cronin GM, Moraes LE, Trotter M (2020b) Can accelerometer ear tags identify behavioural changes in sheep associated with parturition? Animal Reproduction Science 216, 106345
| Can accelerometer ear tags identify behavioural changes in sheep associated with parturition?Crossref | GoogleScholarGoogle Scholar | 32414471PubMed |
Gurule SC, Tobin CT, Bailey DW, Hernandez Gifford JA (2021) Evaluation of the tri-axial accelerometer to identify and predict parturition-related activities of Debouillet ewes in an intensive setting. Applied Animal Behaviour Science 237, 105296
| Evaluation of the tri-axial accelerometer to identify and predict parturition-related activities of Debouillet ewes in an intensive setting.Crossref | GoogleScholarGoogle Scholar |
Hahnloser RHR, Seung HS (2001) Permitted and forbidden sets in symmetric threshold-linear networks. In ‘Advances in Neural Information Processing Systems 13 - Proceedings of the 2000 Conference, NIPS 2000 (Advances in Neural Information Processing Systems)’. (Neural Information Processing Systems Foundation)
Hinch GN, Brien F (2014) Lamb survival in Australian flocks: a review. Animal Production Science 54, 656–666.
| Lamb survival in Australian flocks: a review.Crossref | GoogleScholarGoogle Scholar |
Ikurior SJ, Pomroy WE, Scott I, Corner-Thomas R, Marquetoux N, Leu ST (2020) Gastrointestinal nematode infection affects overall activity in young sheep monitored with tri-axial accelerometers. Veterinary Parasitology 283, 109188
| Gastrointestinal nematode infection affects overall activity in young sheep monitored with tri-axial accelerometers.Crossref | GoogleScholarGoogle Scholar | 32693323PubMed |
Jacobson C, Bruce M, Kenyon PR, Lockwood A, Miller D, Refshauge G, Masters DG (2020) A review of dystocia in sheep. Small Ruminant Research 192, 106209
| A review of dystocia in sheep.Crossref | GoogleScholarGoogle Scholar |
Jolliffe IT, Cadima J (2016) Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374, 20150202
| Principal component analysis: a review and recent developments.Crossref | GoogleScholarGoogle Scholar |
Kamphuis C, DelaRue B, Burke CR, Jago J (2012) Field evaluation of 2 collar-mounted activity meters for detecting cows in estrus on a large pasture-grazed dairy farm. Journal of Dairy Science 95, 3045–3056.
| Field evaluation of 2 collar-mounted activity meters for detecting cows in estrus on a large pasture-grazed dairy farm.Crossref | GoogleScholarGoogle Scholar | 22612940PubMed |
Kenward MG, Roger JH (1997) Small sample inference for fixed effects from restricted maximum likelihood. Biometrics 53, 983–997.
| Small sample inference for fixed effects from restricted maximum likelihood.Crossref | GoogleScholarGoogle Scholar | 9333350PubMed |
Knerr S, Personnaz L, Dreyfus G (1990) Single-layer learning revisited: a stepwise procedure for building and training a neural network. In ‘Neurocomputing’. (Eds FF Soulié, J Hérault) pp. 41–50. (Springer: Cham, Switzerland)
| Crossref |
Martiskainen P, Järvinen M, Skön J-P, Tiirikainen J, Kolehmainen M, Mononen J (2009) Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines. Applied Animal Behaviour Science 119, 32–38.
| Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines.Crossref | GoogleScholarGoogle Scholar |
National Health and Medical Research Council (2013) ‘Australian code for the care and use of animals for scientific purposes.’ 8th edn. (National Health and Medical Research Council: Canberra)
O’Neill CJ, Bishop-Hurley GJ, Williams PJ, Reid DJ, Swain DL (2014) Using UHF proximity loggers to quantify male–female interactions: a scoping study of estrous activity in cattle. Animal Reproduction Science 151, 1–8.
| Using UHF proximity loggers to quantify male–female interactions: a scoping study of estrous activity in cattle.Crossref | GoogleScholarGoogle Scholar | 25449547PubMed |
Smith D, McNally J, Little B, Ingham A, Schmoelzl S (2020) Automatic detection of parturition in pregnant ewes using a three-axis accelerometer. Computers and Electronics in Agriculture 173, 105392
| Automatic detection of parturition in pregnant ewes using a three-axis accelerometer.Crossref | GoogleScholarGoogle Scholar |
Sohi R, Trompf J, Marriott H, Bervan A, Godoy BI, Weerasinghe M, Desai A, Jois M (2017) Determination of maternal pedigree and ewe–lamb spatial relationships by application of bluetooth technology in extensive farming systems. Journal of Animal Science 95, 5145–5150.
| Determination of maternal pedigree and ewe–lamb spatial relationships by application of bluetooth technology in extensive farming systems.Crossref | GoogleScholarGoogle Scholar | 29293717PubMed |
Vapnik VN (1998) ‘Statistical learning theory, adaptive and learning systems for signal processing, communications, and control.’ (Wiley: New York, NY, USA)
Walton E, Casey C, Mitsch J, Vázquez-Diosdado JA, Yan J, Dottorini T, Ellis KA, Winterlich A, Kaler J (2018) Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour. Royal Society Open Science 5, 171442
| Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour.Crossref | GoogleScholarGoogle Scholar | 29515862PubMed |
Yang ZR (2004) Biological applications of support vector machines. Briefings in Bioinformatics 5, 328–338.
| Biological applications of support vector machines.Crossref | GoogleScholarGoogle Scholar | 15606969PubMed |
