Sensor platform for real-time monitoring of animal health and welfare
The NLAS-P3 project is aiming to develop a sensor data-based platform for real-time monitoring of animal health and welfare status. This platform is integrating farm, (sub)clinical data and data obtained from individual animals using quantified animal technologies (e.g., wearable sensors) by employing data-driven modelling approaches (e.g., dynamical systems machine learning).
The EnegyTag sensor system
In general, living things are very energy expensive. For example, the average energy consumed by one cow for one day is around 70 Mega Joules (19.4kWh » 5400 AA batteries), which is the same amount of energy needed to power a Tesla car for 100 km. This energy, which is the means for the animal to survive, is time-varying depending on many internal and external factors.
Hence, continuous monitoring of the dynamic energy consumption is crucial for assessing the health, welfare, and productivity of our animals.
Currently, we are working, in collaboration with KU Leuven university, on developing a wearable sensor (the EnergyTag) for real-time monitoring of animal’s (dairy cows and pigs) energy expenditure. The EnergyTag is a software sensor, which is a combination of hardware sensors such as for temperature and heart rate sensors and software: an online estimation algorithm.
Soft-sensing platform for BRD-related outcome prediction
Bovine respiratory disease (BRD) is the most common cause of morbidity and mortality in cattle around the world causing important health problems (e.g., mortality and low productivity) in all cattle husbandry systems.
BRD is a multifactorial syndrome, with various predisposing factors (stressors) being necessary to induce disease and affect disease severity. Hence, the BRD-related progression outcome is farm-dependant if not individual-dependant as well.
In collaboration with Wageningen Bioveterinary Research, we are developing a soft-sensing platform for the prediction of bovine respiratory diseased related severity and mortality.