Enhancing Anomaly Detection in Agriculture by Considering the Impact of Concept Drift: An Exploratory Study Using Digital Replica
Dongyang Huo, Asad Waqar Malik, Sri Devi Ravana, Anis Ur Rahman, Ismail Ahmedy · 2023
The advent of precision agriculture is disrupting traditional farming practices, leading to a significant increase in the data flow. However, current anomaly detection methods overlook the impact of concept drift. The phenomenon of concept drift refers to the changes in the underlying distribution of the data over time, which can result in unexpected and misleading results. As such, it is essential to consider the impact of theconcept drift in the context of anomaly detection in precision agriculture. This study uses a digital replica of an agricultural system equipped with intelligent agents to examine the system dynamics and the temporal variability of end-to-end data flow in precision agriculture. It highlights the need for robust methods that can effectively address the challenges posed by concept drift and systems’ dynamism enabling accurate and reliable anomaly detection in the IoT farming system.