fbpx Simone Silvestri to Give Keynote at WiSARN 2022 | University of Kentucky College of Engineering

Simone Silvestri to Give Keynote at WiSARN 2022

July 06, 2022

Simone Silvestri, associate professor in the Department of Computer Science, is the keynote speaker at the 15th IEEE International Workshop on Wireless Sensor, Robot and UAV Networks (WiSARN 2022).

WiSARN 2022 is organized in conjunction with IEEE ICDCS 2022, the 42nd IEEE International Conference on Distributed Computing Systems, which will be held in Bologna on July 10-13, 2022. The workshop aims to bring together practitioners and researchers from academia and industry to have a forum for discussion and technical presentations on the broad area of UAV and robotic networks.

Silvestri will discuss the “Internet of Agricultural Things: How Computer Science Can Help Next Generation Farming.”

Abstract
Farming is experiencing increasing challenges such as higher costs, difficulty finding skilled laborers, the need to increase efficiency and product quality, and public pressure to provide better animal welfare. Internet of Agricultural Things (IoAT) technologies, such as weather and soil sensors, sticky insect traps, automatic feeders, cameras, RFID tags, etc., offer a plethora of opportunities to address these challenges. The collected information can be used to enhance the farm operation by, for example, detecting the onset of animal illnesses or insect infestations, providing information on the need for irrigation or plant health, etc. However, it is important to take into account, through interdisciplinary collaborations, relevant aspects such as farmers’ needs, farms’ economy, and practicality, to define efficient methods with the potential of successfully addressing the above-mentioned challenges. In this talk, we provide an overview of IoAT technologies and, subsequently, focus on the specific problem of early detection of Bovine Respiratory Disease (BRD). BRD is an infection of the respiratory tract in cattle that is not only economically costly, but the second leading cause of disease and death in young dairy calves. We discuss how IoAT technologies can be used to design interesting computational problems that combine machine learning with optimization, to maximize efficiency while reducing costs. Finally, we discuss the data collected by 106 calves observed during the preweaning period of 50 days, and show the ability of our methods to detect BRD early and allow early treatments.