IADIZA   20886
INSTITUTO ARGENTINO DE INVESTIGACIONES DE LAS ZONAS ARIDAS
Unidad Ejecutora - UE
congresos y reuniones científicas
Título:
Behavior Classification of A Grazing Goat in the Argentine Monte Desert by Using Inertial Sensors
Autor/es:
GONZALEZ, R.; CATANIA, C.; PAEZ LAMA, S.
Lugar:
SALTA
Reunión:
Congreso; 48 CONGRESO ARGENTINO DE AGROINFORMATICA (JAIIO); 2019
Institución organizadora:
Sociedad Argentina de Informática
Resumen:
The knowledge generated by animal behavior studies hasbeen gaining importance due to it can be used to improve the efficiencyof animal production systems. In recent years, sensor-based approachesfor animal behavior classification has emerged as a promising alternative for analyzing animals grazing patterns. In the present article it isproposed the use of a classification system based on inertial sensors foridentifying a goat?s grazing behavior in the Argentine Monte Desert. Thedata acquisition system is based on commercial off-the-self devices. It isused to create a reliable dataset for performing the animal behavior predictions. By fixing the system on the head of a goat it was possible to logits movements when it was grazing in a natural pasture. A preliminaryversion of the dataset is evaluated using a classical statistical learningalgorithm. Results show that goat activities can be predicted with anaverage precision value above 85% and a recall of 84%.