RT info:eu-repo/semantics/article
T1 Machine learning-based prediction of cattle activity using sensor-based data
A1 Hernández, Guillermo
A1 González Sánchez, Carlos
A1 González Arrieta, Angélica
A1 Sánchez Brizuela, Guillermo
A1 Fraile Marinero, Juan Carlos
K1 Cattle
K1 Ganado vacuno
K1 Animal behavior
K1 Animales - Hábitos y conducta
K1 Extensive livestock
K1 Animales - Cría y explotación
K1 Machine learning
K1 Aprendizaje automático
K1 Monitoring
K1 Sistema de Monitoreo
K1 Wearable device
K1 Detectors
K1 Detectores
K1 Technological innovations
K1 5102.11 Ganadería
K1 3104 Producción Animal
K1 1203.25 Diseño de Sistemas Sensores
K1 5306.02 Innovación Tecnológica
AB Livestock monitoring is a task traditionally carried out through direct observation by experienced caretakers. By analyzing its behavior, it is possible to predict to a certain degree events that require human action, such as calving. However, this continuous monitoring is in many cases not feasible. In this work, we propose, develop and evaluate the accuracy of intelligent algorithms that operate on data obtained by low-cost sensors to determine the state of the animal in the terms used by the caregivers (grazing, ruminating, walking, etc.). The best results have been obtained using aggregations and averages of the time series with support vector classifiers and tree-based ensembles, reaching accuracies of 57% for the general behavior problem (4 classes) and 85% for the standing behavior problem (2 classes). This is a preliminary step to the realization of event-specific predictions.
PB MDPI
SN 1424-8220
YR 2024
FD 2024
LK https://uvadoc.uva.es/handle/10324/68147
UL https://uvadoc.uva.es/handle/10324/68147
LA eng
NO Sensors, 2024, Vol. 24, Nº. 10, 3157
NO Producción Científica
DS UVaDOC
RD 24-nov-2024