Abstract
Animal activity during the night period is of enormous importance, since it represents approximately half of animals’ lives, and monitoring it during this period makes it possible to detect problems related to well-being and safety, and allows us to infer energy expenditure on the basis of their activity level. The present study analyzes a sheep activity dataset created during the night period to validate non-invasive techniques of monitoring that can be used to infer energy expenditure at night and to detect abnormal nocturnal activity. The study allowed us to detect cyclic changes in activity during the night period, which is composed of inactive and active periods, and to identify sheep lying positions. The analysis of the joint activity of the flock allowed us to perceive a time lag in the rest cycles, which consisted of periods of activity of ewes undone between elements of the flock. Although it does not allow us to identify the components of the period of inactivity, since the method used does not monitor brain activity, the results allow us to confirm the cyclical character of the nocturnal activity of sheep that has been reported in the literature, as well as their typical posture when lying down. Although this is an exploratory application with a very small number of animals, the similarity between the results obtained and the results documented in the existing literature, which have mostly been obtained using invasive methods, is encouraging, and suggests it is possible to rely on activity monitoring processes based on inertial sensors.
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference31 articles.
1. Monteiro, A., Santos, S., and Gonçalves, P. (2021). Precision Agriculture for Crop and Livestock Farming—Brief Review. Animals, 11.
2. Silva, S.R., Sacarrão-Birrento, L., Almeida, M., Ribeiro, D.M., Guedes, C., González Montaña, J.R., Pereira, A.F., Zaralis, K., Geraldo, A., and Tzamaloukas, O. (2022). Extensive Sheep and Goat Production: The Role of Novel Technologies towards Sustainability and Animal Welfare. Animals, 12.
3. Application of Deep Learning in Sheep Behaviors Recognition and Influence Analysis of Training Data Characteristics on the Recognition Effect;Comput. Electron. Agric.,2022
4. Deep Transfer Learning in Sheep Activity Recognition Using Accelerometer Data;Expert Syst. Appl.,2022
5. Uknowledge, U., and King, E. (2021). Accelerometer-Based Vigilance State Classification in Dairy Cows. [Master’s Thesis, University of Kentucky].
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献