Subclinical ketosis is a metabolic disease in early lactation. It contributes to economic losses because of reduced milk yield and may promote the development of secondary diseases. Thus, an early detection seems desirable as it enables the farmer to initiate countermeasures. To support early detection, we examine different types of data recordings and use them to build a flexible algorithm that predicts the occurence of subclinical ketosis. This approach shows promising results and can be seen as a step toward automatic health monitoring in farm animals.

In this paper the problem of optimal control over a Markov queueing system with heterogeneous servers and a joint queue is considered, which is also known in the literature as “the slow server problem.” The classical model is generalized here to the case with delay and call serving penalties. It is proved here that the optimal control policy for servers’ activating is of monotonic and threshold nature.