Animal welfare is becoming an increasingly important requirement in the livestock sector to improve, and therefore raise, the quality and healthiness of food production. By monitoring the behaviour of the animals, such as feeding, rumination, walking, and lying, it is possible to understand their physical and psychological status. Precision Livestock Farming (PLF) tools offer a good solution to assist the farmer in managing the herd, overcoming the limits of human control, and to react early in the case of animal health issues. The purpose of this review is to highlight a key concern that occurs in the design and validation of IoT-based systems created for monitoring grazing cows in extensive agricultural systems, since they have many more, and more complicated, problems than indoor farms. In this context, the most common concerns are related to the battery life of the devices, the sampling frequency to be used for data collection, the need for adequate service connection coverage and transmission range, the computational site, and the performance of the algorithm embedded in IoT-systems in terms of computational cost.

In recent years, the research focusing on extensive farming systems has attracted considerable interest among experts in the field. Environmental sustainability and animal welfare are emerging as key elements, assuming a crucial role in global agriculture. In this context, monitoring animals is important not only to ensure their welfare, but also to preserve the balance of the land. Inadequate grazing management can in fact damage vegetation due to soil erosion. Therefore, monitoring the habits of animals during grazing is a challenging and crucial task for livestock management. Internet of Things (IoT) technologies, which allow for remote and real-time monitoring, may be a valid solution to these challenges in extensive farms where farmer-to-animal contact is not usual. In this regard, this paper examined three different methods to classify the behavioral activities of grazing cows, by using data collected with collars equipped with accelerometers. Three distinct approaches were compared: the former based on statistical methods, and the other on the use of Machine and Deep Learning techniques. From the comparison of the results obtained, strengths and weaknesses of each approach were examined, so to determine the most appropriate choice in relation to the characteristics of extensive livestock systems. In detail, Machine and Deep Learning-based approaches were found to be more accurate but highly energy-intensive. Therefore, in rural environments, the approach based on statistical methods, combined with LPWAN applications, was preferable due to its long range and low energy consumption. Ultimately, the statistical approach was found to be 64% accurate in classifying four behavioral classes.