On the use of on-cow accelerometers for the classification of behaviours in dairy barns. (August 2019)

• Record Type: Journal Article
• Authors: Benaissa, Said; Tuyttens, Frank A.M.; Plets, David; de Pessemier, Toon; Trogh, Jens; Tanghe, Emmeric; Martens, Luc; Vandaele, Leen; Van Nuffel, Annelies; Joseph, Wout; Sonck, Bart
• Is Part Of: Research in veterinary science. Volume 125(2019)
• Page Start: 425
• Page End: 433
• Publication Date: 2019-08
• Subjects: Accelerometer -- Dairy cows -- Machine learning -- Behaviours classification -- Feature extraction; Veterinary medicine -- Periodicals; Veterinary Medicine -- Periodicals; Médecine vétérinaire -- Périodiques; Médecine vétérinaire -- Recherche -- Périodiques; Diergeneeskunde; 636.089
• DOI: 10.1016/j.rvsc.2017.10.005
• Languages: English
• ISSNs: 0034-5288

Abstract

Abstract: Analysing behaviours can provide insight into the health and overall well-being of dairy cows. Automatic monitoring systems using e.g., accelerometers are becoming increasingly important to accurately quantify cows' behaviours as the herd size increases. The aim of this study is to automatically classify cows' behaviours by comparing leg- and neck-mounted accelerometers, and to study the effect of the sampling rate and the number of accelerometer axes logged on the classification performances. Lying, standing, and feeding behaviours of 16 different lactating dairy cows were logged for 6 h with 3D–accelerometers. The behaviours were simultaneously recorded using visual observation and video recordings as a reference. Different features were extracted from the raw data and machine learning algorithms were used for the classification. The classification models using combined data of the neck- and the leg-mounted accelerometers have classified the three behaviours with high precision (80–99%) and sensitivity (87–99%). For the leg-mounted accelerometer, lying behaviour was classified with high precision (99%) and sensitivity (98%). Feeding was classified more accurately by the neck-mounted versus the leg-mounted accelerometer (precision 92% versus 80%; sensitivity 97% versus 88%). Standing was the most difficult behaviour to classify when only one accelerometer was used. In addition, the classification performances were not highly influenced when only X, X and Z, or Z and Y axes were used for the classification instead of three axes, especially for the neck-mounted accelerometer. Moreover, the accuracy of the models decreased with about 20% when the sampling rate was decreased from 1 Hz to 0.05 Hz. Highlights: Automatic classification of cows' behaviours by comparing leg- and neck-mounted accelerometers, studying the sampling rate, and investigating the effect of the number of accelerometer axes logged on the classification performances. The models based on the leg-mounted accelerometer data classified lying behaviour with high precision and sensitivity (98%). Feeding was classified more accurately by the neck- mounted accelerometer (precision 91%, sensitivity 96%). Standing was the most difficult behaviour to classify for both accelerometers. The accuracy of the models decreased when the sampling rate was decreased. However, for both leg- and neck-mounted accelerometers, the classification accuracy was still over 80% when 0.25 Hz was used. The classification performances were not highly influenced when only X, X-Z, or Z-Y axes were used for the classification.