A hybrid intelligent optimization algorithm combining weighted K-means clustering and improved ABC for optimal deployment of prehospital emergency heliports

Prehospital emergency helicopters, with excellent maneuverability and response speed, have become the key equipment for improving the quality of emergency medical services. However, the scientific deployment of heliports directly determines the efficiency and cost of the rescue network. To solve this complex optimization problem, this paper proposes a hybrid intelligent optimization algorithm that combines weighted K-means clustering and improved artificial bee colony (WKM-IABC). Firstly, depending on the severity of patient injury, differentiated weights are assigned to the demand points, and the weighted K-means algorithm is used to determine high-quality initial heliport locations. Secondly, considering the three primary objectives of service coverage ratio, rescue response time and economic cost, the Analytic Hierarchy Process (AHP) is applied to quantify weighted preferences and construct a multi-objective integrated optimization model. Finally, an improved ABC (IABC) algorithm is designed to optimize the heliport locations accurately and efficiently through global optimal guidance, dynamic selection strategy, and high-quality initialization. The simulation experiment results demonstrate that compared with state-of-the-art optimization algorithms, the proposed WKM-IABC algorithm exhibits significant advantages in comprehensive fitness, service coverage ratio, convergence speed, and robustness. Statistical significance tests further verify the superiority of WKM-IABC. This study will provide a more reasonable and feasible deployment scheme for prehospital emergency heliports.