Energy-efficient task scheduling and physiological assessment in disaster management using UAV-assisted networks

Abstract

Internet of Things (IoT) and unmanned aerial vehicles (UAVs) together can significantly enhance the performance of disaster management systems. UAVs can collect massive heterogeneous data from disaster-affected areas using fifth-generation (5G)/beyond 5G networks and this data can be analyzed to get the information required by the first responders such as marking the boundary of the affected area, identifying the infrastructure damaged and the roads blocked, and the health situation of people living in that area. This paper presents an overview of different platforms (UAVs-based, IoT-based, and IoT, coupled with UAVs) for disaster management. We propose an energy-efficient task scheduling scheme for data collection by UAVs from the ground IoT network. The focus is to optimize the path taken by the UAVs to minimize energy consumption. We also analyze the vital signs data collected by UAVs for people in disaster-affected areas and apply the decision tree classification algorithm to determine their health risk status. The risk status will enable the first responders to decide the areas which need the most immediate help Simulation results compare the effectiveness of our proposed scheduling scheme with the traditional approach used for data collection. Also, we present the results of our predicted risk status compared with the risk status calculated through the National Early Warning Score 2 (NEWS2) method.