Unmanned Aerial Vehicle Design for Smart City Application

Abstract

Nowadays, Unmanned Aerial Vehicles (UAVs) or drones are also one of the applications to provide the required services and to gather information from the target location. Because smart city applications effectively deal the drone interaction and enhance the human lifestyle with drones. Moreover, UAVs are generally utilized due to their privacy threats, lower cost, pose security, and versatility, which request dependable detection at lower altitudes. However, the less sensing module in the drone has earned the low sensing accuracy of location tracking. So, this paper aims to develop a novel Firefly-based Recurrent Neural Mechanism (FRNM) to enrich the sensing capacity of the drone vehicle. In addition, the sound of the research is medicine delivery through UAVs in emergencies. This UAV system is one of the most crucial features to delivering essential medical items aids by reaching properly correspondent patients. Moreover, the client's needs are stored in the FRNM cloud then that stored data is trained to the UAV machine. Hereafter, based on the trained details, the drone can reach the destination and has delivered the requested medicine to the specific clients. The planned design is drawn in Network Simulator (NS2) environment, and the robustness of the projected replica is valued by calculating the chief parameters. Hereafter, the improvement score was valued by the comparison assessment. Hence, the FRNM has reported the finest performance by earning less location finding duration, running period, and error rate.