Development of an open-source algorithm based on inertial measurement units (IMU) of a smartphone to detect cattle grass intake and ruminating behaviors

Abstract In this paper, an open algorithm was developed for the detection of cattle’s grass intake and rumination activities. This was done using the widely available inertial measurement unit (IMU) from a smartphone, which contains an accelerometer, a gyroscope, a magnetometer and location sensors signals sampled at 100 Hz. This equipment was mounted on 19 grazing cows of different breeds and daily video sequences were recorded on pasture of different forage allowances. After visually analyzing the cows’ movements on a calibration database, signal combinations were selected and thresholds were determined based on 1-s time windows, since increasing the time window did not increase the accuracy of detection. The final algorithm uses the average value and standard deviation of two signals in a two-step discrimination tree: the gravitational acceleration on x-axis (Gx) expressing the cows’ head movements and the rotation rate on the same x-axis (Rx) expressing jaw movements. Threshold values encompassing 95% of the normalized calibrated data gave the best results. Validation on an independent database resulted in an average detection accuracy of 92% with a better detection for rumination (95%) than for grass intake (91%). The detection algorithm also allows for characterization of the diurnal feeding activities of cattle at pasture. Any user can make further improvements, for data collected at the same way as the iPhone’s IMU has done, since the algorithm codes are open and provided as supplementary data .

[1]  D. Berckmans,et al.  Precision livestock farming technologies for welfare management in intensive livestock systems. , 2014, Revue scientifique et technique.

[2]  J Dijkstra,et al.  Technical note: Evaluation of an ear-attached movement sensor to record cow feeding behavior and activity. , 2014, Journal of dairy science.

[3]  A Haeussermann,et al.  Suitability of feeding and chewing time for estimation of feed intake in dairy cows. , 2016, Animal : an international journal of animal bioscience.

[4]  Andriamasinoro Andriamandroso,et al.  Synthèse sur l'utilisation de capteurs pour le suivi des mouvements de mâchoire et du comportement de bovins au pâturage , 2016 .

[5]  Tim Wark,et al.  Using high fix rate GPS data to determine the relationships between fix rate, prediction errors and patch selection , 2008 .

[6]  Mikkel Baun Kjærgaard,et al.  High Classification Rates for Continuous Cow Activity Recognition Using Low-Cost GPS Positioning Sensors and Standard Machine Learning Techniques , 2011, ICDM.

[7]  P. Chilibroste,et al.  Behavioural adaptation of grazing dairy cows to changes in feeding management: do they follow a predictable pattern? , 2015 .

[8]  John G. Hodgson,et al.  The influence of sward canopy structure on foraging decisions by grazing cattle. II. Regulation of bite depth , 2003 .

[9]  M. J. Gibb,et al.  The effect of physiological state (lactating or dry) and sward surface height on grazing behaviour and intake by dairy cows , 1999 .

[10]  Christian Peham,et al.  [Lameness detection in cows by accelerometric measurement of motion at walk]. , 2012, Berliner und Munchener tierarztliche Wochenschrift.

[11]  F. Nydegger,et al.  Automatic measurement of rumination and feeding activity using a pressure sensor. , 2010 .

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

[13]  M. Kolehmainen,et al.  Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines , 2009 .

[14]  S. Mark Rutter,et al.  Changes in ingestive behaviour of yearling dairy heifers due to changes in sward state during grazing down of rotationally stocked ryegrass or white clover pastures , 2004 .

[15]  Claudia Bahr,et al.  Original paper: Real-time automatic lameness detection based on back posture extraction in dairy cattle: Shape analysis of cow with image processing techniques , 2010 .

[16]  Mirjam Holinger,et al.  Intake estimation in dairy cows fed roughage-based diets: An approach based on chewing behaviour measurements , 2016 .

[17]  D Berckmans,et al.  Analysis of individual classification of lameness using automatic measurement of back posture in dairy cattle. , 2013, Journal of dairy science.

[18]  Robert J. Kilgour,et al.  In pursuit of "normal": A review of the behaviour of cattle at pasture , 2012 .

[19]  Md. Sumon Shahriar,et al.  Behavior classification of cows fitted with motion collars: Decomposing multi-class classification into a set of binary problems , 2016, Comput. Electron. Agric..

[20]  Herbert H. T. Prins,et al.  Deriving Animal Behaviour from High-Frequency GPS: Tracking Cows in Open and Forested Habitat , 2015, PloS one.

[21]  Pascal Sirguey,et al.  Performance and Accuracy of Lightweight and Low-Cost GPS Data Loggers According to Antenna Positions, Fix Intervals, Habitats and Animal Movements , 2015, PloS one.

[22]  James P. S. Neel,et al.  Original papers: Acoustic monitoring system to quantify ingestive behavior of free-grazing cattle , 2011 .

[23]  Jérôme Bindelle,et al.  A review on the use of sensors to monitor cattle jaw movements and behavior when grazing , 2016, BASE.

[24]  David Ganskopp,et al.  GPS Error in Studies Addressing Animal Movements and Activities , 2007 .

[25]  Greg Bishop-Hurley,et al.  Dynamic cattle behavioural classification using supervised ensemble classifiers , 2015, Comput. Electron. Agric..

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

[27]  Cécile Cornou,et al.  Estimation of grass intake on pasture for dairy cows using tightly and loosely mounted di- and tri-axial accelerometers combined with bite count , 2013 .

[28]  Lars Relund Nielsen,et al.  Quantifying walking and standing behaviour of dairy cows using a moving average based on output from an accelerometer. , 2010 .

[29]  Raja Ariffin Raja Ghazilla,et al.  Reviews on Various Inertial Measurement Unit (IMU) Sensor Applications , 2013, SiPS 2013.

[30]  John G. Hodgson,et al.  The influence of sward canopy structure on foraging decisions by grazing cattle. I. Patch selection , 2003 .

[31]  Wilhelmiina Hämäläinen,et al.  Measuring behaviour accurately with instantaneous sampling: A new tool for selecting appropriate sampling intervals , 2016 .

[32]  John F. Vallentine.  Grazing Activities/Behavior , 2001 .

[33]  Matti Pastell,et al.  CowLog: Open-source software for coding behaviors from digital video , 2009, Behavior research methods.

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

[35]  E. Schlecht,et al.  The use of differentially corrected global positioning system to monitor activities of cattle at pasture , 2004 .

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

[37]  Dimitris Kanellopoulos,et al.  Data Preprocessing for Supervised Leaning , 2007 .

[38]  D. P. Poppi,et al.  Defoliation patterns and their implications for the management of vegetative tropical pastures to control intake and diet quality by cattle , 2016 .

[39]  M. J. Gibb,et al.  Effect of time of day on grazing behaviour by lactating dairy cows , 1998 .

[40]  Emilio A. Laca,et al.  Spatial and temporal domains of scale of grazing cattle , 2015 .

[41]  Amots Hetzroni,et al.  Automatic recognition of jaw movements in free-ranging cattle, goats and sheep, using acoustic monitoring ☆ , 2013 .

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

[43]  S M Rutter,et al.  Graze: A program to analyze recordings of the jaw movements of ruminants , 2000, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.