Enhancing Feature Extraction for Indoor Fingerprint Localization Using Diversified Data

TL;DR

This paper introduces Secci, a novel indoor localization method that enhances feature extraction from diversified CSI data transformed into RGB images, leveraging deep learning for improved accuracy and robustness in complex environments.

Contribution

The paper presents a new CSI data transformation and deep learning approach that significantly improves indoor fingerprint localization performance.

Findings

Secci outperforms four existing algorithms in indoor environments.

Diversified CSI data enhances feature robustness for localization.

Deep CNN with SE attention improves prediction accuracy.

Abstract

Given the rapid advancements in wireless communication and terminal devices, high-speed and convenient WiFi has permeated various aspects of people's lives, and attention has been drawn to the location services that WiFi can provide. Fingerprint-based methods, as an excellent approach for localization, have gradually become a hot research topic. However, in practical localization, fingerprint features of traditional methods suffer from low reliability and lacking robustness in complex indoor environments. To overcome these limitations, this paper proposes a innovative feature extraction-enhanced intelligent localization scheme named Secci, based on diversified channel state information (CSI). By modifying the device driver, diversified CSI data are extracted and transformed into RGB CSI images, which serve as input to a deep convolutional neural network (DCNN) with SE attention mechanism-assisted training in the offline stage. Employing a greedy probabilistic approach, rapid prediction of the estimated location is performed in the online stage using test RGB CSI images. The Secci system is implemented using off-the-shelf WiFi devices, and comprehensive experiments are carried out in two representative indoor environments to showcase the superior performance of Secci compared to four existing algorithms.