Classification and Analysis of Multiple Cattle Unitary Behaviors and Movements Based on Machine Learning Methods

• Published in: Animals (Basel) 2022-04, Vol.12 (9), p.1060
• Main Authors: Li, Yongfeng, Shu, Hang, Bindelle, Jérôme, Xu, Beibei, Zhang, Wenju, Jin, Zhongming, Guo, Leifeng, Wang, Wensheng
• Format: Article
• Language: English
• Subjects: Accelerometers; Algorithms; Animal behavior; Animal diseases; Animal husbandry; Animal production & animal husbandry; Animal Science and Zoology; Animal welfare; Behavior; behavior classification; Biting; Cattle; Chewing; Classification; Computer science; Dairy cattle; Dairy farming; Disease detection; Engineering, computing & technology; Feeding behavior; Feeds; General Veterinary; inertial measurement units; Inertial platforms; Ingénierie, informatique & technologie; Learning algorithms; Life sciences; Livestock; Machine learning; Mastication; Motion sensors; precision livestock farming; Productions animales & zootechnie; Remote monitoring; Remote sensors; Sciences du vivant; Sciences informatiques; Sensors; Social factors; Social interactions; Time series; Veterinary (all)
• ISSN: 2076-2615; 2076-2615
• DOI: 10.3390/ani12091060

The behavior of livestock on farms is the primary representation of animal welfare, health conditions, and social interactions to determine whether they are healthy or not. The objective of this study was to propose a framework based on inertial measurement unit (IMU) data from 10 dairy cows to classify unitary behaviors such as feeding, standing, lying, ruminating-standing, ruminating-lying, and walking, and identify movements during unitary behaviors. Classification performance was investigated for three machine learning algorithms (K-nearest neighbors (KNN), random forest (RF), and extreme boosting algorithm (XGBoost)) in four time windows (5, 10, 30, and 60 s). Furthermore, feed tossing, rolling biting, and chewing in the correctly classified feeding segments were analyzed by the magnitude of the acceleration. The results revealed that the XGBoost had the highest performance in the 60 s time window with an average F1 score of 94% for the six unitary behavior classes. The F1 score of movements is 78% (feed tossing), 87% (rolling biting), and 87% (chewing). This framework offers a possibility to explore more detailed movements based on the unitary behavior classification.