Using GA for Locating Post-disaster Field Hospitals: The Case of Istanbul

Abstract

Most of the post-disaster losses occur due to the lack of humanitarian relief planning or inadequate implementations. Locating temporary field hospitals (FHs) and assignment of the injured people to the hospitals are key issues in natural disaster management. The capacities of existing emergency units of hospitals (EH) are expected to be not enough for the injured people in case of a serious earthquake in Istanbul. Thus, the FHs which will serve as additional capacity are needed. The objectives of this study are to minimize the total travel cost and the total cost of establishing FHs in order to respond to all of the injured as quickly as possible. To this aim, a heuristic solution methodology, genetic algorithm (GA) is developed in MATLAB. Different crossover and replacement strategies have been tested in order to improve the performance of the algorithm. In the experimental study, the performances of different GAs strategies are compared using experimental datasets where optimal results are known. According to the result of the comparison, the best GA is selected and applied the for the real Istanbul dataset.