Optimized Path Planning for a Mobile Real Time Location System (mRTLS) in an Emergency Department

Data collection methods used for localization in healthcare facilities involving human data collection often tend to generate inconsistent and ambiguous data. To address these issues, an automated ceiling mounted mobile Real-Time Location System (mRTLS) is proposed. The system utilizes mobile Radio Frequency IDentification (RFID) and is evaluated using agent based modeling. A prototypical agent model for an emergency facility is created using the AnyLogic simulation software. The model developed is based on the real hospital data to approximate patient flow in a real system. The emergency department model is outfitted with mRTLS using mobile ceiling mounted RFID readers in an emergency facility layout. Path planning and resource provisioning of mobile readers is accomplished using both multi objective genetic and simulated annealing algorithms. The genetic algorithm provides an initial placement of static readers extracted from areas of more frequently read RFID tags. The genetic algorithm solution initializes the input parameters for the simulated annealing algorithm. The simulated annealing algorithm provides the final optimized path for the deployment of mobile readers. The results generated by the model are analyzed in the simulation of the emergency facility augmented with mobile RFID readers. The applicability of the proposed model in a complex system like a healthcare facility is demonstrated through simulation.