Detecting dairy cows' lying behaviour using noisy 3D ultra-wide band positioning data

Abstract

In precision livestock farming, technology-based solutions are used to monitor and manage livestock and support decisions based on on-farm available data. In this study, we developed a methodology to monitor the lying behaviour of dairy cows using noisy spatial positioning data, thereby combining time-series segmentation based on statistical changepoints and a machine learning classification algorithm using bagged decision trees. Position data (x, y, z -coordinates) collected with an ultra-wide band positioning system from 30 dairy cows housed in a freestall barn were used. After the data preprocessing and selection, statistical changepoints were detected per cow-day (no. included = 331) in normalized 'distance from the centre of the barn' and (z) time series. Accelerometer-based lying bout data were used as a practical ground truth. For the segmentation, changepoint detection was compared with getting-up or lying-down events as indicated by the accelerometers. For the classification of segments into lying or nonlying behaviour, two data splitting techniques resulting in 2 different training and test sets were implemented to train and evaluate performance: one based on the data collection day and one based on cow identity. In 85.5% of the lying-down or getting-up events a changepoint was detected in a window of 5 minutes. Of the events where no detection had taken place, 86.2% could be associated with either missing data (large gaps) or a very short lying or non-lying bout. Overall classification and lying behaviour prediction performance was above 91% in both independent test sets, with a very high consistency across cow-days. Per cow-day, the average error in the estimation of the lying durations were 7.1% and 7.8% for the cow-identity and time-based data splits respectively. This resulted in sufficient accuracy for automated quantification of lying behaviour in dairy cows, for example for health or welfare monitoring purposes.

Quantification of play behaviour in calves using automated ultra-wideband location data and its association with age, weaning and health status

“…This suggests that play behaviour can be predicted using automated location data. Location data has also been successfully used to predict personality in dairy calves 24 and lying behaviour of dairy cows 23 . Our results suggest that our quantification method could be used to detect other low prevalence behaviours from location data.…”

“…Ultra-wide band (UWB) location sensors offer a means of monitoring animal behaviour by providing precise location data of individual animals with minimal human input, over longer periods of time. Although these data have been shown to perform well when predicting lying behaviour of dairy cows 23 and were used to measure movement behaviours in calves 24 , the use of UWB location sensors in cattle is still limited. To the authors’ knowledge, location data have not been used to measure behaviours associated with positive welfare, such as locomotor play.…”