Comparison between GA and ACO for emergency coverage problem in a smart healthcare environment

Abstract

Healthcare management is widely used by researchers around the world to strengthen the hospital logistics and improve the patients' service. Adopting smart technologies in healthcare environment helps us to improve the quality of care and minimize the waiting time of patients during emergency interventions. Recently, communication technologies such as Internet Of Things, Cloud Computing and optimization algorithms are emerged. The objective of this paper is to compare solutions of the emergency coverage problem done by two approaches: Genetic Algorithm 'GA' & Ant Colony Optimization 'ACO'. The coverage model aims to minimize the total lateness of ambulances. Implementations using GA and ACO are based on random instances during the two periods of the day: day and night. An instance contains hospitals and fire stations where ambulances are located and the intervention sectors which are patients' locations. The solution has two parts; the minimal lateness (fitness) and the best distribution of the given ambulances in waiting sites (hospitals & fire stations). A comparative analysis between GA & ACO is shown. GA brings best solution.