Author(s): Torres-Sospedra, Joaquín ; Aranda, Fernando J. ; Alvarez, Fernando J. ; Quezada-Gaibor, Darwin ; Silva, Ivo Miguel Menezes ; Pendão, Cristiano Gonçalves ; Moreira, Adriano
Date: 2021
Persistent ID: https://hdl.handle.net/1822/82113
Origin: RepositóriUM - Universidade do Minho
Subject(s): Indoor Positioning; Fingerprinting; Radio Map; Noisy samples; Ensemble
Fingerprint-based indoor positioning is widely used in many contexts, including pedestrian and autonomous vehicles navigation. Many approaches have used traditional Machine Learning models to deal with fingerprinting, being k-NN the most common used one. However, the reference data (or radio map) is generally limited, as data collection is a very demanding task, which degrades overall accuracy. In this work, we propose a novel approach to add random noise to the radio map which will be used in combination with an ensemble model. Instead of augmenting the radio map, we create n noisy versions of the same size, i.e. our proposed Indoor Positioning model will combine n estimations obtained by independent estimators built with the n noisy radio maps. The empirical results have shown that our proposed approach improves the baseline method results in around 10% on average.
