In recent decades, animal production in Greece has been developing rapidly due to the increasing demand for animal products. This demand has led to a transition from traditional to intensive farming systems in order to intensify production. Goats and sheep, being one of the most important livestock species in the industry, significantly contribute to the country’s economic development. As a result of these changes, unknown health problems have emerged or existing ones have worsened, mainly due to mismanagement of intensively reared animals.

One such problem is the increased occurrence of lameness, particularly in animals that remain confined throughout the year. Lameness is a decisive factor of distress, often painful, which significantly reduces both the welfare level and milk production of affected animals in case of delayed disease detection. This results in the mandatory slaughter of the animal, with serious direct and indirect economic implications for the enterprise. The delayed diagnosis of lameness is attributed to the currently applied detection methods, which primarily rely on visual observation of the animal’s mobility, a method that almost excludes the early detection of the problem.

The objective of this initiative is to establish a new lameness detection system, initially in the Greek livestock context, based on parameters of animal movement and monitoring of their feeding. The aim is to detect lameness at an early stage and avoid the economic consequences of production loss for livestock units.

The proposed system structure includes both commercial components and elements that result from original laboratory research. Specifically, the system successfully combines commercial motion-sensing sensors (accelerometers) with a temporary integrated electronic feeding system and an innovative information system. The information system utilizes machine learning algorithms appropriately adapted to diagnose lameness at an early stage, even if the symptoms are not visually evident. This ability is attributed to the system’s capability to identify differences in the motion signatures of diseased animals and compare them with those of healthy ones.

The differentiation of the proposed system compared to those available on the market lies primarily in its ability to continuously record the animal’s movements without affecting them and without altering their daily routines.