SmartFPS: Neural Network based Wireless-inertial fusion positioning system

TL;DR

This paper introduces SmartFPS, a neural network-based wireless-inertial fusion positioning system that leverages transfer learning to enhance accuracy across diverse scenarios, outperforming traditional filtering methods.

Contribution

It proposes a deep learning fusion system with transfer learning strategies to improve positioning accuracy in complex, real-world environments.

Findings

Average positioning accuracy of 0.506m in whole floor scenario

Transfer learning improves inertial navigation step size and rotation angle estimation by 53.3%

Bluetooth positioning accuracy improves by 33.4%, fusion accuracy by 31.6%

Abstract

The current fusion positioning systems are mainly based on filtering algorithms, such as Kalman filtering or particle filtering. However, the system complexity of practical application scenarios is often very high, such as noise modeling in pedestrian inertial navigation systems, or environmental noise modeling in fingerprint matching and localization algorithms. To solve this problem, this paper proposes a fusion positioning system based on deep learning and proposes a transfer learning strategy for improving the performance of neural network models for samples with different distributions. The results show that in the whole floor scenario, the average positioning accuracy of the fusion network is 0.506m. The experiment results of transfer learning show that the estimation accuracy of the inertial navigation positioning step size and rotation angle of different pedestrians can be improved by 53.3% on average, the Bluetooth positioning accuracy of different devices can be improved by 33.4%, and the fusion can be improved by 31.6%.