Indoor and outdoor seamless localization method based on simulated annealing optimized bp neural network

Abstract

The present invention claims to protect an indoor and outdoor seamless positioning method based on simulated annealing optimized BP neural network, which belongs to the field of navigation and positioning, and specifically includes the following steps: firstly establishing an indoor and outdoor seamless positioning algorithm model based on BP neural network, and secondly according to the established The indoor and outdoor seamless positioning algorithm model based on BP neural network, combined with simulated annealing algorithm, establishes the indoor and outdoor seamless positioning algorithm model based on simulated annealing optimization BP neural network, and then uses the collected samples to analyze the BP neural network optimized by simulated annealing. The network model is trained to determine the optimal weights and thresholds, and finally the trained BP neural network based on simulated annealing optimization is used for indoor and outdoor seamless positioning. The experimental results show that using simulated annealing to optimize the indoor and outdoor seamless localization algorithm of BP neural network, its average absolute error is reduced by about 69% compared with that of BP neural network, and the positioning accuracy is improved by about 55.11% compared with that of PDR.

Description

technical field [0001] The invention belongs to the field of navigation and positioning, and in particular relates to an algorithm suitable for indoor and outdoor seamless positioning. The algorithm mainly fuses GPS and PDR positioning results through a BP neural network, and uses simulated annealing to optimize the BP neural network, thereby improving the Indoor and outdoor seamless positioning accuracy. Background technique [0002] With the rapid development of science and technology, researchers have carried out a lot of research on pedestrian navigation and positioning technology. At present, the relatively mature pedestrian navigation and positioning technologies mainly include: GPS positioning technology, WiFi positioning technology, UWB positioning technology, geomagnetic positioning technology, PDR positioning technology, Bluetooth positioning technology, etc. Since a single positioning technology cannot achieve seamless indoor and outdoor positioning of pedestrian...

AI Technical Summary

Problems solved by technology

Although the theoretical integrity of the learning algorithm of the BP neural network makes it widely used in practice, it has the disadvantages of slow convergence and easy to fall into local optimal solutions.

Images