Dynamic Accuracy Estimation in a Wi-Fi-based Positioning System

TL;DR

This paper introduces a dynamic accuracy estimation method for Wi-Fi-based indoor positioning, validated through experiments showing that random forest regression provides the most accurate error predictions with a mean absolute error of 0.72 meters.

Contribution

It proposes a novel dynamic accuracy estimation approach and evaluates multiple regression models, identifying the most effective method for Wi-Fi indoor positioning error prediction.

Findings

Random forest regression achieved the lowest mean absolute error of 0.72 m.

The dynamic accuracy estimation method effectively predicts localization errors.

Experimental validation confirms the approach's applicability in real indoor environments.

Abstract

The paper presents a concept of a dynamic accuracy estimation method, in which the localization errors are derived based on the measurement results used by the positioning algorithm. The concept was verified experimentally in a Wi\nobreakdash-Fi based indoor positioning system, where several regression methods were tested (linear regression, random forest, k-nearest neighbors, and neural networks). The highest positioning error estimation accuracy was achieved for random forest regression, with a mean absolute error of 0.72 m.