Towards Accelerated Localization Performance Across Indoor Positioning Datasets

TL;DR

This paper introduces a multi-model fingerprinting localization method that significantly accelerates indoor positioning speed across various datasets without sacrificing accuracy.

Contribution

It proposes a cascade of three optimized models for building, floor, and 2D localization, validated on 14 datasets, achieving up to 71% faster predictions.

Findings

Mean prediction time reduced by 71%

Achieved comparable accuracy across datasets

Prediction time drops to 1% with large training data

Abstract

The localization speed and accuracy in the indoor scenario can greatly impact the Quality of Experience of the user. While many individual machine learning models can achieve comparable positioning performance, their prediction mechanisms offer different complexity to the system. In this work, we propose a fingerprinting positioning method for multi-building and multi-floor deployments, composed of a cascade of three models for building classification, floor classification, and 2D localization regression. We conduct an exhaustive search for the optimally performing one in each step of the cascade while validating on 14 different openly available datasets. As a result, we bring forward the best-performing combination of models in terms of overall positioning accuracy and processing speed and evaluate on independent sets of samples. We reduce the mean prediction time by 71% while achieving comparable positioning performance across all considered datasets. Moreover, in case of voluminous training dataset, the prediction time is reduced down to 1% of the benchmark's.