Title: Dairy cows' localisation and feeding behaviour monitoring using a combination of IMU and RFID network
Authors: Samir Aoughlis; Rafik Saddaoui; Brahim Achour; Mourad Laghrouche
Addresses: Laboratoire de Vision Artificielle et Automatique de Systèmes, Mouloud Mammeri University, BP 17 RP, 15000, Tizi-Ouzou, Algeria ' Laboratoire d'Analyse et Modélisation des Phénomènes Aléatoires, Mouloud Mammeri University, BP 17 RP, 15000, Tizi-Ouzou, Algeria ' Laboratoire de Recherche en Informatique, Mouloud Mammeri University, BP 17 RP, 15000, Tizi-Ouzou, Algeria ' Laboratoire d'Analyse et Modélisation des Phénomènes Aléatoires, Mouloud Mammeri University, BP 17 RP, 15000, Tizi-Ouzou, Algeria
Abstract: Localisation systems have become recently important for the monitoring of cow's health. However, the main limitations of these systems lie in the lack of information about cow's activities such as feeding and drinking in the monitored zone. To overcome these limits, we have developed a non-invasive ear-attached sensor based on a combination of a low-cost radio frequency identification system with an inertial measurement unit (IMU). With this procedure, the cows are localised and their feeding behaviours are classified. The localisation is realised by means of an accelerometer and a gyroscope permitting the trajectory estimation thanks to the dead reckoning and the sensor fusion method. However, problems related to instability emerge which are solved with the particle filter algorithm. In order to monitor the standing and the feeding behaviours, the decision tree technique is adopted to filter them. The obtained results proved that the algorithm has achieved high classification and localisation rates.
Keywords: wireless sensor networks; dairy cow; RFID; radio frequency identification; IMU; inertial measurement unit; particle filter; dead reckoning; decision tree; feeding behaviour.
DOI: 10.1504/IJSNET.2021.117962
International Journal of Sensor Networks, 2021 Vol.37 No.1, pp.23 - 35
Received: 22 Jan 2021
Accepted: 23 Jan 2021
Published online: 05 Oct 2021 *