Automatic classification system for grazing, ruminating and resting behaviour of dairy sheep using a tri-axial accelerometer

Abstract A device based on a tri-axial accelerometer was used to measure behavioural parameters of dairy sheep at pasture. Short tests were performed in grazing conditions to collect accelerometer data simultaneously with video recordings of sheep behavioural activities (grazing, ruminating and resting). The raw acceleration data was processed to create 12 variables: mean, variance and inverse coefficient of variation (ICV; mean/standard deviation) for the X-, Y- and Z-axis and the resultant at 1-min intervals. A database inclusive of the 12 acceleration variables and the three behavioural activities detected for each minute was then created. Three multivariate statistical techniques were used to discriminate the behavioural activities using the acceleration data: stepwise discriminant analysis (SDA), canonical discriminant analysis (CDA), and discriminant analysis (DA). Based on the acceleration variables selected by SDA, the subsequent CDA significantly discriminated the three behaviours by extracting two canonical functions. The first canonical function (CAN1) discriminated the grazing activity from the resting and ruminating, whereas the second (CAN2) differentiated the grazing from the ruminating behaviour. After bootstrap resampling, the DA correctly assigned 93.0% of minutes to behavioural activities. Stepwise regression analysis was used to estimate the rate of biting(total number of bites/min) using a subset of acceleration data that contained only minutes in which sheep were grazing. In this case, 15 variables were tested and out of them, only one was selected, the sum of X-axis value per minute (SX), which explained 65% of the total variation of the rate of biting .

[1]  F. Nydegger,et al.  Validation of a new health monitoring system (RumiWatch) for combined automatic measurement of rumination, feed intake, water intake and locomotion in dairy cows. , 2012 .

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

[3]  Albert Sundrum,et al.  Technical note: Evaluation of a new system for measuring feeding behavior of dairy cows , 2014 .

[4]  Laca,et al.  Acoustic measurement of intake and grazing behaviour of cattle , 2000 .

[5]  S. M. Rutter,et al.  An automatic system to record foraging behaviour in free-ranging ruminants , 1997 .

[6]  Emilio A. Laca,et al.  An integrated methodology for studying short-term grazing behaviour of cattle , 1992 .

[7]  Nils Zehner,et al.  Validation of a pressure sensor-based system for measuring eating, rumination and drinking behaviour of dairy cattle , 2016 .

[8]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[9]  Emilio A. Laca,et al.  Acoustic monitoring of chewing and intake of fresh and dry forages in steers , 2006 .

[10]  Peter I. Corke,et al.  Transforming Agriculture through Pervasive Wireless Sensor Networks , 2007, IEEE Pervasive Computing.

[11]  J. Newman,et al.  A Mechanistic Model of Some Physical Determinants of Intake Rate and Diet Selection in a Two-Species Temperate Grassland Sward , 1994 .

[12]  Remy Delagarde,et al.  Development of an automatic bitemeter for grazing cattle , 1999 .

[13]  Rory P. Wilson,et al.  Acceleration versus heart rate for estimating energy expenditure and speed during locomotion in animals: tests with an easy model species, Homo sapiens. , 2008, Zoology.

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

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

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

[17]  Technical note: Monitoring grazing bites and walking activity with pedometers. , 2013, Journal of dairy science.

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

[19]  Noman Islam,et al.  A review of wireless sensors and networks' applications in agriculture , 2014, Comput. Stand. Interfaces.

[20]  P. D. Penning,et al.  A technique to record automatically some aspects of grazing and ruminating behaviour in sheep , 1983 .

[21]  David G. Renter,et al.  Evaluation of three-dimensional accelerometers to monitor and classify behavior patterns in cattle , 2009 .

[22]  Kazato Oishi,et al.  Application of Overall Dynamic Body Acceleration as a Proxy for Estimating the Energy Expenditure of Grazing Farm Animals: Relationship with Heart Rate , 2015, PloS one.

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

[24]  Klaus Manfred Scheibe,et al.  Application testing of a new three-dimensional acceleration measuring system with wireless data transfer (WAS) for behavior analysis , 2006, Behavior research methods.

[25]  Eugene D. Ungar,et al.  Classifying cattle jaw movements: Comparing IGER Behaviour Recorder and acoustic techniques , 2006 .

[26]  P. V. Soest Nutritional Ecology of the Ruminant , 1994 .

[27]  Lorenz Gygax,et al.  Mesure automatique des mouvements de rumination par capteur de pression , 2011 .

[28]  M. J. Gibb,et al.  Animal grazing/intake terminology and definitions , 1997 .

[29]  K. McLennan,et al.  Technical note: Validation of an automatic recording system to assess behavioural activity level in sheep (Ovis aries) , 2015 .

[30]  Mac Schwager,et al.  Robust classification of animal tracking data , 2007 .

[31]  J. Hodgson,et al.  The development and use of equipment for the automatic recording of ingestive behaviour in sheep and cattle , 1981 .

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

[33]  Rory P. Wilson,et al.  The need for speed: testing acceleration for estimating animal travel rates in terrestrial dead-reckoning systems. , 2012, Zoology.

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

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

[36]  Jérôme Bindelle,et al.  Changes in biting characteristics recorded using the inertial measurement unit of a smartphone reflect differences in sward attributes , 2015 .