Three-dimensional positioning method based on PSO_BP neural network

Abstract

The invention provides a terminal three-dimensional positioning method based on a BP neural network optimized by a particle swarm optimizer (PSO), wherein the method can be widely used in a wireless positioning field. The method comprises the steps of measuring distance data between a plurality of base stations in an area and the terminal; sequencing actually measured distances from lowest to highest, selecting four base stations with shortest distances, and calculating a terminal position which comprises a non-sight-distance influence by means of the four base stations through a least square method; calculating all terminal positions which comprise the non-sight-distance, and calculating a three-dimensional direction angle of each base station to the terminal; and finally using the obtained terminal position coordinates, the distances between the base stations and the terminal, and the three-dimensional direction angle as a characteristic value input layer of the PSO_BP neural network, and using the corrected terminal position coordinates as an output layer. The terminal three-dimensional positioning method optimizes the BP neural network by means of a PSO algorithm, and an obtained result eliminates a terminal position measurement error caused by the non-sight-distance factor. The repented algorithm has advantages of stable performance, high algorithm convergence, high positioning precision, and high suitability for popularization, etc.

Description

technical field [0001] The invention designs a terminal three-dimensional positioning method based on the BP neural network optimized by the particle swarm algorithm, which can be widely used in the field of wireless positioning. Background technique [0002] With the vigorous development of wireless communication networks and mobile Internet, providing Location Based Service (LBS for short) has become one of the businesses with the most market prospect and development potential. From traditional GPS navigation to consumer information services and social software based on geographic location such as e-commerce and catering platforms, the basis for realizing its functions is to obtain the location of the user's handheld terminal (including mobile phones or tablets and other devices). [0003] Although commercial GPS has been widely used with the development of smart phones, GPS positioning performance is poor in many scenarios such as indoors, underground, and urban areas wit...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to propose a three-dimensional terminal positioning method based on PSO_BP neural network in view of the low accuracy of the terminal positioning method in the case of multiple indoor base stations in the prior art

Images