Classification of behaviour in housed dairy cows using an accelerometer-based activity monitoring system

Animal Biotelemetry

Jorge A. Vázquez Diosdado³  Zoe E. Barker²  Holly R. Hodges²  Jonathan R. Amory²  Darren P. Croft⁴  Nick J. Bell¹  Edward A. Codling³ 

[1] Royal Veterinary College, Hawkshead Lane, North Mymms AL9 7TA, Hatfield, UK

[2] Writtle College, Chelmsford CM1 3RR, Essex, UK

[3] Department of Mathematical Sciences, University of Essex, Wivenhoe Park, Colchester, CO4 3SQ, UK

[4] Center for Research in Animal Behaviour, College of Life and Environmental Sciences, University of Exeter, Exeter EX4 4QG, UK

关键词: Reality mining;    Tri-axial accelerometer;    Precision livestock farming;    Decision-tree algorithm;    Behavioural classification;   

Others  :  1224657
DOI  :  10.1186/s40317-015-0045-8

 received in 2015-02-17, accepted in 2015-05-25,  发布年份 2015

【 摘 要 】

Background

Advances in bio-telemetry technology have made it possible to automatically monitor and classify behavioural activities in many animals, including domesticated species such as dairy cows. Automated behavioural classification has the potential to improve health and welfare monitoring processes as part of a Precision Livestock Farming approach. Recent studies have used accelerometers and pedometers to classify behavioural activities in dairy cows, but such approaches often cannot discriminate accurately between biologically important behaviours such as feeding, lying and standing or transition events between lying and standing. In this study we develop a decision-tree algorithm that uses tri-axial accelerometer data from a neck-mounted sensor to both classify biologically important behaviour in dairy cows and to detect transition events between lying and standing.

Results

Data were collected from six dairy cows that were monitored continuously for 36 h. Direct visual observations of each cow were used to validate the algorithm. Results show that the decision-tree algorithm is able to accurately classify three types of biologically relevant behaviours: lying (77.42 % sensitivity, 98.63 % precision), standing (88.00 % sensitivity, 55.00 % precision), and feeding (98.78 % sensitivity, 93.10 % precision). Transitions between standing and lying were also detected accurately with an average sensitivity of 96.45 % and an average precision of 87.50 %. The sensitivity and precision of the decision-tree algorithm matches the performance of more computationally intensive algorithms such as hidden Markov models and support vector machines.

Conclusions

Biologically important behavioural activities in housed dairy cows can be classified accurately using a simple decision-tree algorithm applied to data collected from a neck-mounted tri-axial accelerometer. The algorithm could form part of a real-time behavioural monitoring system in order to automatically detect dairy cow health and welfare status.

【 授权许可】

   
2015 Vázquez Diosdado et al.

【 图 表 】

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

【 参考文献 】

• [1]Tomkiewicz SM, Fuller MR, Kie JG, Bates KK: Global positioning system and associated technologies in animal behaviour and ecological research. Philos Trans R Soc B 2010, 365:2163-76.
• [2]Baratchi M, Meratnia N, Havinga PJM, Skidmore AK, Toxopeus BAG: Sensing solutions for collecting spatio-temporal data for wildlife monitoring applications: a review. Sensors 2013, 13:6054-88.
• [3]Mannini A, Sabatini AM: Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors 2010, 10:1154-75.
• [4]Bourke AK, O’Brien JV, Lyons GM: Evaluation of threshold-based tri-axial accelerometer fall detection algorithm. Gait Posture 2007, 26:194-9.
• [5]Nathan R, Spiegel O, Formann-Roe S, Harel R, Wikelski M, Getz WM: Using tri-axial acceleration data to identify behavioural modes of free-ranging animals: general concepts and tools illustrated for griffon vultures. J Exp Biol 2012, 215:986-96.
• [6]Resheff YS, Rotics S, Harel R, Spiegel O, Nathan R: AcceleRater: a web application for supervised learning of behavioural modes from acceleration measurements. Mov Ecol 2014, 2:27. BioMed Central Full Text
• [7]Moreau M, Siebert S, Buerket A, Schlecht E: Use of tri-axial accelerometer for automated recording and classification of goats’ grazing behaviour. Appl Anim Behav Sci 2009, 119:158-70.
• [8]Martiskainen P, Jӓrvinen M, Skön JP, Tiirikainen J, Kolehmainen M, Mononen J: Cow behaviour pattern recognition using a three- dimensional accelerometer and support vector machines. Appl Anim Behav Sci 2009, 119:32-8.
• [9]Robert B, White BJ, Renter DG, Larson RL: Evaluation of three-dimensional accelerometers to monitor and classify behaviour patterns in cattle. Compu Electron Agric 2009, 67:80-4.
• [10]Shamoun-Baranes J, Bom R, van Loon EE, Ens BJ, Oosterbeek K, Bouten W: From sensor data to animal behaviour: an oystercatcher example. PLoS One 2012., 7Article ID e37997
• [11]Bidder OR, Campbell HA, Gómez–Laich A, Urgé P, Walker J, Cai Y, et al.: Love thy neighbour: automatic animal behavioural classification of acceleration data using the k-nearest neighbour algorithm. PLoS One 2014., 9Article ID e88609
• [12]Chen KY, Bassett DR Jr: The technology of accelerometry-based activity monitors: current and future. Med Sci Sports Exer 2005, 37:490-500.
• [13]Sakamato KQ, Sato K, Ishizuka M, Watanuki Y, Takahashi A, Daunt F, et al.: Can ethograms be automatically generated using body acceleration data from free-ranging birds? PLoS One 2009., 4Article ID e5379
• [14]Brown DD, Kays R, Wikelski M, Wilson R, Klimley AP: Observing the unwatchable through acceleration logging of animal behaviour. Animal Biotelem 2013, 1(1):20. BioMed Central Full Text
• [15]Shepard ELC, Wilson RP, Quintana F, Gomez LA, Liebsch N, Albareda DA, et al.: Identification of animal movement patterns using tri-axial accelerometry. Endang Species Res 2010, 10:47-60.
• [16]Yoda K, Naito Y, Sato K, Takahashi A, Nishikawa J, Ropert-Coudert Y, et al.: A new technique for monitoring the behaviours of free-ranging Adélie penguins. J Exp Biol 2001, 204:685-90.
• [17]Krause J, Krause S, Arlinghaus R, Psorakis I, Roberts S, Rutz C: Reality mining of animal social systems. Trends Ecol Evol 2013, 28:541-51.
• [18]Banarjee D, Diagle CL, Dong B, Wurtz K, Newberry RC, Siegford JM, et al.: Detection of jumping and landing force in laying hens using wireless wearable sensors. Poult Sci 2014, 93:2724-33.
• [19]Liikavainio T, Bragfge T, Hakkarainen M, Jurvelin JS, Karjalainen PA, Arokoski JP: Reproducibility of loading measurements with skin-mounted accelerometers during walking. Arch Phys Med Rehabil 2007, 88:907-15.
• [20]Chen S, Amiyaal L, White BJ, Sanderson MW, Lanzas C. Spatial-temporal dynamics of high-resolution animal social networks: what we can learn from domestic animals. q-bio PE. 2014. arXiv: 1407.6074.
• [21]Yoda K, Sato K, Niizuma Y, Kurita M, Bost CA, Le Maho Y, et al.: Precise monitoring of proposing behaviour of Adélie penguins determined using acceleration data loggers. J Exp Biol 1999, 202:3121-6.
• [22]Mclune DW, Marks NJ, Wilson RP, Houghton JDR, Montgomery IW, McGowan NE, et al.: Tri-axial accelerometers quantify behaviour in the Eurasian badger (Meles meles): towards an automated interpretation of field data. Animal Biotelem 2014, 2:5. BioMed Central Full Text
• [23]Langrock R, King R, Mathiopoulus J, Thomas L, Fortin D, Morales JM: Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions. Ecology 2012, 93:2336-42.
• [24]Guo Y, Poulton G, Corke P, Bishop-Hurley GJ, Wark T, Swain DL: Using accelerometer, high sample rate GPS and magnetometer data to develop a cattle movement and behaviour model. Ecol Model 2009, 220:2068-75.
• [25]Yin L, Hong T, Liu C: Estrus detection in dairy cows from acceleration data using self-learning classification models. J Comput 2013, 8:2590-7.
• [26]Morttram T. Wireless technologies for managing grazing animals. In. Profitable and sustainable grazing systems—moving forward with science. Worcester, UK. 2013.
• [27]González LA, Tolkamp BJ, Coffrey MP, Ferret A, Kyriazakis I: Changes in feeding behaviour for the automatic monitoring of health disorders in dairy cows. J Dairy Sci 2008, 91:1017-28.
• [28]Palmer MA, Law R, O’Connell NE: Relationships between lameness and feeding behaviour in cubicle-housed Holstein-Friesian dairy cows. Appl Anim Behav Sci 2012, 140:121-7.
• [29]Medrano-Galarza C, Gibbons J, Wagner S, de Passillé AM, Rushen J: Behavioural changes in dairy cows with mastitis. J Dairy Sci 2012, 95:6994-7002.
• [30]Blackie N, Amory JR, Bleach ECL, Scafie J: The effect of lameness on lying behaviour of zero grazed Holstein dairy cattle. Appl Anim Behav Sci 2011, 14:124-37.
• [31]Spence AJ, Tan H, Wilson A: Accuracy of the TurfTrax racing data system for determination of equine speed and position. Equine Vet J l 2010, 40:680-3.
• [32]Homburger H, Schneider MK, Hilfiker S, Lüscher A: Inferring behavioral states of grazing livestock from high-frequency position data alone. PLoS One 2014., 9Article ID e114522
• [33]Bailey DW, Van Wagoner HC, Weinmeister R: Individual animal selection has the potential to improve uniformity of grazing on foothill rangeland. Rangl Ecol Manag 2006, 59:351-8.
• [34]Qasem L, Cardew A, Wilson A, Griffiths I, Halsey LG, Shepard ELC, et al.: Tri-axial dynamic acceleration as a proxy for animal energy expenditure; should we summing values or calculating the vector? PLoS One 2012., 7Article ID e31187
• [35]Gleiss AC, Wilson RP, Shepard ELC: Making overall dynamic body acceleration work: on the theory of acceleration as a proxy for energy expenditure. Methods Ecol Evol 2011, 2:23-33.
• [36]Matlab release 2014a. Natick, Massachusetts: The MathWorks, Inc.; 2014
• [37]Rezek I, Roberts SJ. Ensemble hidden Markov models for biosignal analysis. In. 14th International Conference on Digital Signal Processing. Santori, Greece. 2002.
• [38]Murphy KP: Machine learning: a probabilistic perspective. MIT Press, Cambridge, Massachusetts; 2012.
• [39]Rabiner L: Tutorial on hidden Markov models and selected applications on speech recognition. Proc IEEE 1989, 77:257-86.
• [40]Cortes C, Vapnik V: Support-vector networks. Mach Learn 1995, 20:273-97.
• [41]Duan KB, Keerthi SS: Which is the best multiclass SVM method? Lect Notes Comput Sc 2005, 3541:278-85.
• [42]Hsu CW, Lin CJ: A comparison of methods of multiclass support vector machines. IEEE Trans Neural Netw 2002, 13:415-25.