Author:

Abstract:

PLF systems aim to offer a real time monitoring and managing system for the farmer. This is fundamentally different from all approaches that aim to offer a monitoring tool without improving the life of the animal under consideration. It is nice to detect a problem after an animal has arrived at the slaughterhouse. It is better to detect a problem while the animal is being reared and to take immediate management action. The idea of PLF is to provide a real-time warning when something goes wrong so that immediate action can be taken by the farmer. This requires real-time algorithms that are able to detect or predict problems while the rearing process is ongoing. To successfully develop such algorithms in an efficient way, some basic principles must be respected. This paper aims to explain the interaction between taking field data, applying a gold standard and using labelling techniques to develop real-time algorithms that allow real time monitoring and management of living organisms.