Fuzzy knowledge-based ant colony optimization for sequential RFID network design in hospitals using heterogeneous readers and antennas

Radio Frequency Identification (RFID) plays a vital role in hospital asset tracking, yet most existing RFID Network Planning (RNP) models assume identical antennas and single-antenna readers, leading to higher costs and limited flexibility. To address these challenges, this study proposes a Cost-Efficient Fuzzy-Driven Ant Colony Optimization (CEFD-ACO) framework for optimizing RNP in hospital environments. The framework introduces heterogeneous directional multi-antenna readers, where each reader can host multiple antennas with varying costs, beamwidths, and read ranges. This design allows for more efficient coverage and reduced interference. A fuzzy inference system is integrated into the metaheuristic-driven optimization process to guide intelligent decisions in reader placement and antenna selection. Simulation results from two hospital case studies show that CEFD-ACO improves coverage by 7.8%, reduces interference by 84.5%, and lowers deployment cost by 28.4% compared with existing approaches. These results demonstrate the framework's potential to enhance cost-effectiveness and reliability in real-world RFID-based hospital asset tracking.