Integrating Bio-Inspired Approaches with UAV-FSN Systems for Clustered Target Area Detection in Agriculture

Abstract

Target area detection in agriculture plays a crucial role in optimizing crop management and resource allocation. Traditional methods often lack the precision and efficiency required for modern farming practices. Integrating bio-inspired approaches with UAV-FSN systems offers a promising solution to this challenge. By harnessing principles from nature, such as swarm intelligence and reinforcement learning, it becomes possible to optimize the deployment and coordination of UAVs within FSN for clustered target area detection in agriculture. This research explores the integration of bio-inspired approaches with UAV-FSN systems for clustered target area detection in agriculture. The increasing demand for precision agriculture necessitates efficient methods for identifying target areas affected by various factors. In this study, we introduce a novel algorithm, the QL-ABC Algorithm, which combines the Artificial Bee Colony (ABC) Algorithm with Q-Learning to optimize the deployment and movement of unmanned aerial vehicles (UAVs) within flying sensor networks (FSN) for target area detection. The performance outcomes of the proposed QL-ABC Algorithm on comparison with the existing algorithms are analysed using extensive simulation analysis with the appropriate simulation metrics: packet delivery ratio, mean end-to-end delay, and energy consumption. Results validate the usefulness of the proposed QL-ABC algorithm in accurately detecting clustered target areas in agricultural landscapes, thus contributing to advancements in precision farming practices and sustainable agriculture. Keywords: Flying Sensor Networks, Artificial Bee Colony Algorithm, Clustered Target Area Detection, Q-Learning, Unmanned Aerial Vehicles.