Hostname: page-component-7dd5485656-tbj44 Total loading time: 0 Render date: 2025-10-30T23:34:49.416Z Has data issue: false hasContentIssue false
  • English
  • Français

Using animal-mounted sensor technology and machine learning to predict time-to-calving in beef and dairy cows

Published online by Cambridge University Press:  13 January 2020

G. A. Miller Open the ORCID record for G. A. Miller [Opens in a new window] ,
M. Mitchell ,
Z. E. Barker ,
K. Giebel ,
E. A. Codling ,
J. R. Amory ,
C. Michie ,
C. Davison ,
C. Tachtatzis  and
I. Andonovic
...Show all authors
G. A. Miller*
Affiliation:
Department of Agriculture, Horticulture and Engineering Sciences, Scotland’s Rural College, Peter Wilson Building, West Mains Road, King’s Buildings, EdinburghEH9 3JG, UK
M. Mitchell
Affiliation:
Department of Animal and Veterinary Science, Scotland’s Rural College, Peter Wilson Building, West Mains Road, King’s Buildings, EdinburghEH9 3JG, UK
Z. E. Barker
Affiliation:
School of Animal and Human Sciences, Writtle University College, Lordship Road, Writtle, ChelmsfordCM1 3RR, UK
K. Giebel
Affiliation:
School of Animal and Human Sciences, Writtle University College, Lordship Road, Writtle, ChelmsfordCM1 3RR, UK
E. A. Codling
Affiliation:
Department of Mathematical Sciences, University of Essex, Wivenhoe Park, ColchesterCO4 3SQ, UK
J. R. Amory
Affiliation:
School of Animal and Human Sciences, Writtle University College, Lordship Road, Writtle, ChelmsfordCM1 3RR, UK
C. Michie
Affiliation:
Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Royal College Building, 204 George Street, GlasgowG1 1XW, UK
C. Davison
Affiliation:
Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Royal College Building, 204 George Street, GlasgowG1 1XW, UK
C. Tachtatzis
Affiliation:
Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Royal College Building, 204 George Street, GlasgowG1 1XW, UK
I. Andonovic
Affiliation:
Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Royal College Building, 204 George Street, GlasgowG1 1XW, UK
C.-A. Duthie
Affiliation:
Department of Agriculture, Horticulture and Engineering Sciences, Scotland’s Rural College, Peter Wilson Building, West Mains Road, King’s Buildings, EdinburghEH9 3JG, UK
*
†E-mail: gemma.miller@sruc.ac.uk
Get access

Abstract

Worldwide, there is a trend towards increased herd sizes, and the animal-to-stockman ratio is increasing within the beef and dairy sectors; thus, the time available to monitoring individual animals is reducing. The behaviour of cows is known to change in the hours prior to parturition, for example, less time ruminating and eating and increased activity level and tail-raise events. These behaviours can be monitored non-invasively using animal-mounted sensors. Thus, behavioural traits are ideal variables for the prediction of calving. This study explored the potential of two sensor technologies for their capabilities in predicting when calf expulsion should be expected. Two trials were conducted at separate locations: (i) beef cows (n = 144) and (ii) dairy cows (n = 110). Two sensors were deployed on each cow: (1) Afimilk Silent Herdsman (SHM) collars monitoring time spent ruminating (RUM), eating (EAT) and the relative activity level (ACT) of the cow, and (2) tail-mounted Axivity accelerometers to detect tail-raise events (TAIL). The exact time the calf was expelled from the cow was determined by viewing closed-circuit television camera footage. Machine learning random forest algorithms were developed to predict when calf expulsion should be expected using single-sensor variables and by integrating multiple-sensor data-streams. The performance of the models was tested using the Matthew’s correlation coefficient (MCC), the area under the curve, and the sensitivity and specificity of predictions. The TAIL model was slightly better at predicting calving within a 5-h window for beef cows (MCC = 0.31) than for dairy cows (MCC = 0.29). The TAIL + RUM + EAT models were equally as good at predicting calving within a 5-h window for beef and dairy cows (MCC = 0.32 for both models). Combining data-streams from SHM and tail sensors did not substantially improve model performance over tail sensors alone; therefore, hour-by-hour algorithms for the prediction of time of calf expulsion were developed using tail sensor data. Optimal classification occurred at 2 h prior to calving for both beef (MCC = 0.29) and dairy cows (MCC = 0.25). This study showed that tail sensors alone are adequate for the prediction of parturition and that the optimal time for prediction is 2 h before expulsion of the calf.

Keywords

precision livestock farmingparturitionbovinerandom forestanimal-mounted sensors

Information

Type
Research Article
Information
animal , Volume 14 , Issue 6 , June 2020 , pp. 1304 - 1312
Copyright
© The Animal Consortium 2020

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Agjee, NH, Mutanga, O, Peerbhay, K and Ismail, R 2018. The impact of simulated spectral noise on random forest and oblique random forest classification performance. Journal of Spectroscopy, https://doi.org//10.1155/2018/8316918, Published online by Hindawi 13 March 2018.CrossRefGoogle Scholar
Agriculture and Horticulture Development Board (AHDB), Beef and Lamb 2018. AHDB UK cattle yearbook 2018. AHDB Beef and Lamb, Kenilworth, UK.Google Scholar
Barrier, AC, Haskell, MJ, Birch, S, Bagnall, A, Bell, DJ, Dickinson, J, Macrae, AI and Dwyer, CM 2013. The impact of dystocia on dairy calf health, welfare, performance and survival. The Veterinary Journal 195, 86–90.CrossRefGoogle ScholarPubMed
Borchers, MR, Chang, YM, Proudfoot, KL, Wadsworth, BA, Stone, AE and Bewley, JM 2017. Machine-learning-based calving prediction from activity, lying, and ruminating behaviors in dairy cattle. Journal of Dairy Science 100, 664–5674.CrossRefGoogle ScholarPubMed
Braun, U, Tschoner, T and Hässig, M 2014. Evaluation of eating and rumination behaviour using a noseband pressure sensor in cows during the peripartum period. BMC Veterinary Research 10, 195 doi: 10.1186/s12917-014-0195-6.CrossRefGoogle ScholarPubMed
Büchel, S and Sundrum, A 2014. Decrease in rumination time as an indicator of the onset of calving. Journal of Dairy Science 97, 3120–3127.CrossRefGoogle ScholarPubMed
Calamari, L, Soriani, N, Panella, G, Petrera, F, Minuti, A and Trevisi, E 2014. Rumination time around calving: an early signal to detect cows at greater risk of disease. Journal of Dairy Science 97, 3635–3647.CrossRefGoogle ScholarPubMed
Clark, CEF, Lyons, NA, Millapan, L, Talukder, S, Cronin, GM, Kerrisk, KL and Garcia, SC 2015. Rumination and activity levels as predictors of calving for dairy cows. Animal 9, 91–695.CrossRefGoogle ScholarPubMed
De Amicis, I, Veronesi, MC, Robbe, D, Gloria, A and Carluccio, A 2018. Prevalence, causes, resolution and consequences of bovine dystocia in Italy. Theriogenology 1007, 104–108.CrossRefGoogle Scholar
Eriksson, S, Näsholm, A, Johansson, K and Philipsson, J 2004. Genetic parameters for calving difficulty, stillbirth, and birth weight for Hereford and Charolais at first and later parities. Journal of Animal Science 82, 375–383.CrossRefGoogle ScholarPubMed
Gaafar, HMA, Shamiah, M, Abu El-Hamd, MA, Shitta, AA and Tag El-Din, MA 2011. Dystocia in Friesian cows and its effects on postpartum reproductive performance and milk production. Tropical Animal Health and Production 43, 229–234.CrossRefGoogle ScholarPubMed
Huzzey, JM, von Keyserlingk, MAG and Weary, DM 2005. Changes in feeding, drinking and standing behaviour of dairy cows during the transition period. Journal of Dairy Science 88, 2454–2461.CrossRefGoogle ScholarPubMed
Jensen, MB 2012. Behaviour around the time of calving in dairy cows. Applied Animal Behaviour Science 139, 195–202.CrossRefGoogle Scholar
Konka, J, Michie, C and Andonovic, I 2014. Automatic classification of eating and ruminating in cattle using a collar mounted accelerometer. Paper presented at the 39th ICAR Session, 19–23 May 2014, Berlin, Germany.Google Scholar
Kovács, L, Kézér, FL, Ruff, F and Szenci, O 2016. Rumination time and reticuloruminal temperature as possible predictors of dystocia in dairy cows. Journal of Dairy Science 100, 1568–1579.CrossRefGoogle ScholarPubMed
Krieger, S, Sattlecker, G, Kickinger, F, Auer, W, Drillich, M and Iwersen, M 2018. Prediction of calving in dairy cows using a tail-mounted tri-axial accelerometer: a pilot study. Biosystems Engineering 173, 79–84.CrossRefGoogle Scholar
Kuhn, M, Contributions from Wing J, Weston S, Williams A, Keefer C, Engelhardt A, Cooper T, Mayer Z, Kenkel B, the R Core Team, Benesty M, Lescarbeau R, Ziem A, Scrucca L, Tang Y, Candan C and Hunt T 2018. caret: classification and regression training. R package version 6.0-80.Google Scholar
Lombard, JE, Garry, FB, Tomlinson, SM and Garber, LP 2007. Impacts of dystocia on health and survival of dairy calves. Journal of Dairy Science 90, 1751–1760.CrossRefGoogle ScholarPubMed
López de Maturana, E, Legarra, A, Varona, L and Ugarte, E 2007. Analysis of fertility and dystocia in Holsteins using recursive models to handle censored and categorical data. Journal of Dairy Science 90, 2012–2024.CrossRefGoogle ScholarPubMed
Lowman, BG, Scott, N and Somerville, S 1976. Condition scoring of cattle. Bulletin No. 6. East of Scotland College of Agriculture, Edinburgh, UK.Google Scholar
McGuirk, BJ, Forsyth, R and Dobson, H 2007. Economic cost of difficult calvings in the United Kingdom dairy herd. Veterinary Record 161, 685–687.CrossRefGoogle ScholarPubMed
Mee, JF 2008. Prevalence and risk for dystocia in dairy cattle: a review. The Veterinary Journal 176, 93–101.CrossRefGoogle ScholarPubMed
Miedema, HM, Cockram, MS, Dwyer, CM and Macrae, AI 2011a. Changes in the behaviour of dairy cows during the 24h before normal calving compared to behaviour during late pregnancy. Applied Animal Behaviour Science 131, 8–14.CrossRefGoogle Scholar
Miedema, HM, Cockram, MS, Dwyer, CM and Macrae, AI 2011b. Behavioural predictors of the start of normal and dystocic calving in dairy cows and heifers. Applied Animal Behaviour Science 132, 14–19.CrossRefGoogle Scholar
Miller, GA, Mitchell, MA, Barker, Z, Giebel, K, Codling, E, Amory, J and Duthie, C-A 2019. Animal-mounted sensor technology to predict ‘time to calving’ in beef and dairy cows. In Proceedings of the British Society of Animal Science BSAS 75th Annual Conference 2019 held at the Edinburgh International Conference Centre (EICC), 9–11 April 2019, p. 149.CrossRefGoogle Scholar
Nix, JM, Spitzer, JC, Grimes, LW, Burns, GL and Plyler, BB 1998. A retrospective analysis of factors contributing to calf mortality and dystocia in beef cattle. Theriogenology 49, 1515–1523.CrossRefGoogle ScholarPubMed
Ouellet, V, Vasseur, E, Heuwieser, W, Burfeind, O, Maldague, X and Charbonneau, E 2016. Evaluation of calving indicators measured by automated monitoring devices to predict the onset of calving in Holstein dairy cows. Journal of Dairy Science 99, 1539–1548.CrossRefGoogle ScholarPubMed
Pahl, C, Hartung, E, Grothmann, A and Mahlkow-Nerge, K 2014. Rumination activity of dairy cows in the 24 hours before and after calving. Journal of Dairy Science 97, 6935–6941.CrossRefGoogle ScholarPubMed
Phocas, F and Laloë, D 2003. Evaluation of genetic parameters for calving difficulty in beef cattle. Journal of Animal Science 81, 933–938.CrossRefGoogle ScholarPubMed
R Core Team 2017. R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria.Google Scholar
Robin, X, Turck, N, Hainard, A, Tiberti, N, Lisacek, F, Sanchez, J and Muller, M 2011. pROC: an open-source package for R and S+ to analyse and compare ROC curves. BMC Bioinformatics 12, 77. doi: 10.1186/1471-2105-12-77.CrossRefGoogle Scholar
Rumph, JM and Faust, MA 2006. Genetic analysis of calving ease in Holsteins in the U.K. based on data from heifers and cows. In Proceedings of the 8th World Congress on Genetics Applied to Livestock Production, 13–18 August 2006, Belo Horizonte, Brazil, p. 11.Google Scholar
Rutten, CJ, Kamphuis, C, Hogeveen, H, Huijps, K, Nielen, M and Steeneveld, W 2017. Sensor data on cow activity, rumination, and ear temperature improve prediction of the start of calving in dairy cows. Computers and Electronics in Agriculture 132, 108–118.CrossRefGoogle Scholar
Saint-Dizier, M and Chastant-Maillard, S 2015. Methods and on-farm devices to predict calving time in cattle. The Veterinary Journal 205, 349–356.CrossRefGoogle ScholarPubMed
Shah, KD, Nakao, T and Kubota, H 2006. Plasma estrone sulphate (E1S) and estradiol-17β (E2β) profiles during pregnancy and their relationship with the relaxation of sacrosciatic ligament, and prediction of calving time in Holstein-Fresian cattle. Animal Reproduction Science 95, 38–53.CrossRefGoogle Scholar
Soriani, N, Trevisi, E and Calamari, L 2012. Relationships between rumination time, metabolic conditions, and health status in dairy cows during the transition period. Journal of Animal Science 90, 4544–4554.CrossRefGoogle ScholarPubMed
Titler, M, Maquivar, MG, Bas, S, Rajala-Schultz, PJ, Gordon, E, McCullough, K and Federico, P 2015. Prediction of parturition in Holstein dairy cattle using electronic data loggers. Journal of Dairy Science 98, 5304–5312.CrossRefGoogle ScholarPubMed
Supplementary material: File

Miller et al. supplementary material

Table S1

Download Miller et al. supplementary material(File)
File 14.4 KB