The invention discloses an indoor positioning method based on a Bayesian iteration improved
particle swarm optimization algorithm, which is called a BCLPSO
algorithm for short, and comprises the following steps of: 1) acquiring a positioning
database and acquiring unknown node measurement data di; 2) substituting into a BCLPSO
algorithm for calculation, and executing initialization of a
particle position vector and a speed vector; 3) calculating a learning probability Pci and acquiring an individual extreme value pbesti,d; 4) calculating a particle
posterior probability Pit, and screening an optimal sample exemplart of a current group; 5) updating position vectors and velocity vectors of the particles; and 6) obtaining a convergence condition, judging an
iteration process, and obtaining an optimization result. The method is applied to the technical field of indoor positioning, replaces a traditional KNN algorithm to be used for position
estimation, solves the problem that the traditional KNN algorithm is prone to falling into a local optimal solution, can inherit and utilize historical information of each particle based on the BCLPSO algorithm, effectively retains diversity of a particle
population, and prevents
premature convergence caused by neglecting a potential optimal solution, the
global optimal positioning point can be better found, and the positioning precision is improved.