The effect of different time epoch settings on the classification of sheep behaviour using tri-axial accelerometry

Abstract Monitoring behaviour of grazing animals is important for the management of grazing systems. A study was run to discriminate between the main behaviours (grazing, ruminating and other activities) of sheep at pasture wearing a halter equipped with an accelerometer (BEHARUM device), and to identify the epoch setting (5, 10, 30, 60, 120, 180 and 300 s) with the best performance. The BEHARUM device includes a three-axial accelerometer sensor and a force sensor positioned under the lower jaw of the animal. The halter was fitted to eight Sarda dairy sheep that rotationally grazed either a spatial association (mixture) or a time association of berseem clover ( Trifolium alexandrinum L.) and Italian ryegrass ( Lolium multiflorum Lam.) for 6 h day −1 . The behaviour of the animals was also video-recorded. The raw acceleration and force data were processed for each epoch setting to create 15 variables: the mean, variance and inverse coefficient of variation (ICV; mean/standard deviation) per minute for the X-, Y-, Z-axis and force, and the resultant. Multivariate statistical techniques were used to discriminate between the three behavioural activities: canonical discriminant analysis (CDA), and discriminant analysis (DA). To validate the derived discriminant functions, a bootstrap procedure was run. To evaluate the performance of DA in discriminating between the three activities, the sensitivity, specificity, precision, accuracy and Coehn’s k coefficient were calculated, based on the error distribution in assignment. Results show that a discriminant analysis can accurately classify important behaviours such as grazing, ruminating and other activities in sheep at pasture. The prediction model has demonstrated a better performance in classifying grazing behaviour than ruminating and other activities for all epochs. The 30 s epoch length yielded the most accurate classification in terms of accuracy and Coehn’s k coefficient. Nevertheless, 60 and 120 s may increase the potential recording time without causing serious lack of accuracy.

[1]  V. H. Oddy,et al.  Using a three-axis accelerometer to identify and classify sheep behaviour at pasture , 2016 .

[2]  M. Pastell,et al.  Predicting Sleep and Lying Time of Calves with a Support Vector Machine Classifier Using Accelerometer Data , 2011 .

[3]  P. Carvalho.  Memorial Lecture : Can grazing behavior support innovations in grassland management ? , 2015 .

[4]  Mark Trotter,et al.  Categorising sheep activity using a tri-axial accelerometer , 2018, Comput. Electron. Agric..

[5]  C. Arcidiacono,et al.  Development of a threshold-based classifier for real-time recognition of cow feeding and standing behavioural activities from accelerometer data , 2017, Comput. Electron. Agric..

[6]  Esmaeil S. Nadimi,et al.  Monitoring and classifying animal behavior using ZigBee-based mobile ad hoc wireless sensor networks and artificial neural networks , 2012 .

[7]  Roland Kays,et al.  Observing the unwatchable through acceleration logging of animal behavior , 2013, Animal Biotelemetry.

[8]  Per Peetz Nielsen,et al.  Automatic registration of grazing behaviour in dairy cows using 3D activity loggers , 2013 .

[9]  Corrado Dimauro,et al.  Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer , 2017 .

[10]  B. Efron.  Bootstrap Methods: Another Look at the Jackknife , 1979 .

[11]  T. Komatsu,et al.  The use of accelerometer to measure sleeping posture of beef cows. , 2018, Animal science journal = Nihon chikusan Gakkaiho.

[12]  G. Piccione,et al.  Effect of different farming management on daily total locomotor activity in sheep , 2011 .

[13]  F. Bookstein,et al.  Statistical assessment of bilateral symmetry of shapes , 2000 .

[14]  J. P. Holland,et al.  An automated sensor-based method of simple behavioural classification of sheep in extensive systems , 2008 .

[15]  J. Fleiss,et al.  The measurement of interrater agreement , 2004 .

[16]  Greg Bishop-Hurley,et al.  Behavioral classification of data from collars containing motion sensors in grazing cattle , 2015, Comput. Electron. Agric..

[17]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[18]  Esmaeil S. Nadimi,et al.  Observer Kalman filter identification and multiple-model adaptive estimation technique for classifying animal behaviour using wireless sensor networks , 2009 .

[19]  Andreas Buerkert,et al.  Use of a tri-axial accelerometer for automated recording and classification of goats' grazing behaviour , 2009 .

[20]  G. Piccione,et al.  Evaluation of total locomotor activity and oxidative markers daily rhythms in sheep , 2010 .

[21]  Kensuke Kawamura,et al.  Development of an automatic classification system for eating, ruminating and resting behavior of cattle using an accelerometer , 2008 .

[22]  Edward A. Codling,et al.  Classification of behaviour in housed dairy cows using an accelerometer-based activity monitoring system , 2015, Animal Biotelemetry.

[23]  Y Ueda,et al.  Technical note: the use of a physical activity monitor to estimate the eating time of cows in pasture. , 2011, Journal of dairy science.