摘要：Background and Objective: Traditional particle filter has long convergence time and it easily falls into local solution, which can results in the low precision of indoor localization. Materials and Methods: So, this study proposes an improved particle filter based on firefly algorithm to improve the positioning accuracy. The processes are divided into three steps. First, it introduces dynamic adaptive inertia weight into firefly algorithm to update the position of firefly. Second, the improved firefly algorithm is used to improve the sampling process of particle filter. It defines a new fitness function for particle filter. That makes the particles approach high likelihood area before weight updating and improves the re-sampling strategy. At last, it applies this new method into indoor localization. That is the first proposed scheme to improve particle filter currently. Results: Experiments show that new method improves the positioning accuracy and convergence speed. Whats more, the accuracy of improved particle filter algorithm is better than traditional particle filter algorithm. Also, it makes comparison to other filter methods to demonstrate the effectiveness of new method. Conclusion: Particle filter based on firefly algorithm is an effective method, which can effectively improve the accuracy of localization.
