Alsaaod, Maher; Niederhauser, J J; Beer, Gian; Zehner, N; Schüpbach, Gertraud; Steiner, Adrian (2015). Development and validation of a novel pedometer algorithm to quantify extended characteristics of the locomotor behavior of dairy cows. Journal of dairy science, 98(9), pp. 6236-6242. American Dairy Science Association 10.3168/jds.2015-9657
|
Text
1-s2.0-S0022030215004609-main.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND). Download (620kB) | Preview |
Behavior is one of the most important indicators for assessing cattle health and well-being. The objective of this study was to develop and validate a novel algorithm to monitor locomotor behavior of loose-housed dairy cows based on the output of the RumiWatch pedometer (ITIN+HOCH GmbH, Fütterungstechnik, Liestal, Switzerland). Data of locomotion were acquired by simultaneous pedometer measurements at a sampling rate of 10 Hz and video recordings for manual observation later. The study consisted of 3 independent experiments. Experiment 1 was carried out to develop and validate the algorithm for lying behavior, experiment 2 for walking and standing behavior, and experiment 3 for stride duration and stride length. The final version was validated, using the raw data, collected from cows not included in the development of the algorithm. Spearman correlation coefficients were calculated between accelerometer variables and respective data derived from the video recordings (gold standard). Dichotomous data were expressed as the proportion of correctly detected events, and the overall difference for continuous data was expressed as the relative measurement error. The proportions for correctly detected events or bouts were 1 for stand ups, lie downs, standing bouts, and lying bouts and 0.99 for walking bouts. The relative measurement error and Spearman correlation coefficient for lying time were 0.09% and 1; for standing time, 4.7% and 0.96; for walking time, 17.12% and 0.96; for number of strides, 6.23% and 0.98; for stride duration, 6.65% and 0.75; and for stride length, 11.92% and 0.81, respectively. The strong to very high correlations of the variables between visual observation and converted pedometer data indicate that the novel RumiWatch algorithm may markedly improve automated livestock management systems for efficient health monitoring of dairy cows.
Actions (login required)
 |
Edit item |