Self-adaptive positioning fingerprint database construction method in complex indoor signal environment

Abstract

The invention discloses a self-adaptive positioning fingerprint database construction method in a complex indoor signal environment, and belongs to the technical field of indoor positioning. Accordingto an AP laying position and a space structure, a system adopts a one-to-many support vector machine algorithm to perform partition operation on a target region so as to precisely determine a regionrange of signal change. A multivariate Gaussian mixture model based on mutual interference among signals is established by utilizing a coupling relationship among the signals in narrow partitions, sothat the positioning precision reduction caused by signal fluctuation is improved. When the indoor environment changes, the credibility of fingerprint data of each partition can be judged by adoptinga self-adaptive updating algorithm based on the partition multivariate Gaussian mixture model, and model parameters of the partition with large signal fluctuation are updated by adopting a self-adaptive algorithm, so that the coupling degree between the model and the existing environment is improved. Experimental results show that a stable and maintainable indoor signal distribution model can be constructed by utilizing a relatively small amount of sample data, and compared with other algorithms, the positioning precision of the self-adaptive positioning fingerprint database construction method is further improved to a certain extent.

Description

technical field [0001] The invention relates to an offline fingerprint library construction optimization technology for indoor positioning, which belongs to the technical field of indoor positioning. Background technique [0002] Global satellite navigation systems have been widely used to provide location services for people in outdoor environments, but the lack of signals also prevents the system from functioning in complex indoor environments. With the widespread deployment of WiFi facilities and the popularity of smart phones, indoor positioning systems based on Received Signal Strength (RSS) values ​​have attracted the close attention of a large number of researchers. However, since the original design of wireless communication facilities is not to provide people with indoor navigation, how to reduce the influence of environmental fluctuations on positioning caused by uncertain interference of wireless signals has become a difficult point that existing research has to f...

AI Technical Summary

Problems solved by technology

However, since the original intention of the design of wireless communication facilities is not to provide people with indoor navigation, how to reduce the influence of environmental fluctuations on positioning caused by uncertain interference of wireless signals has become a difficult point that existing research has to face and solve.

[0003] Based on the positioning system of existing wireless facilities, its common commercial devices do not have the function of self-editing, and can only provide indoor general RSS measurement values, which makes the traditional methods based on time difference of arrival and distance difference of arrival unable to be directly translated

Images