Indoor positioning and localization are widely used in multiple environments, due to the wide range of services it can provide by leveraging Internet of Things (IoT), and ubiquitous connectivity. Thus, the article presented at ICUMT 2020 workshop implements a new post-processing method to improve DBSCAN for indoor positioning using Wi-Fi radio maps. This small improvement is in pro of reducing the computational load in low profile devices (IoT and wearables devices), and it will be part of a new reliable, accurate, scalable and open-source indoor positioning platform.

The main authors, Darwin Quezada-Gaibor and Lucie Klus, are an Early Stage Researcher in the A-WEAR program funded by the European Union’s Horizon 2020 (H2020) Marie Skłodowska-Curie Innovative Training Networks. Darwin is currently pursuing a joint PhD at GEOTEC research group at Universitat Jaume I (Castellón de la Plana – Spain) and Tampere University (Tampere – Finland), whereas Lucie is in Tampere university and will join GEOTEC for a research stay in the coming months, as part of her phD programme.

Abstract: IoT devices and wearables may rely on Wi-Fi fingerprinting to estimate the position indoors. The limited resources of these devices make it necessary to provide adequate methods to reduce the operational computational load without degrading the positioning error. Thus, the aim of this article is to improve the positioning error and reduce the dimensionality of the radio map by using an enhanced DBSCAN. Moreover, we provide additional analysis of combining DBSCAN + PCA analysis for further dimensionality reduction. Thereby, we implement a post-processing method based on the correlation coefficient to join “noisy” samples to the formed clusters with DBSCAN. As a result, the positioning error was reduced by 10% with respect to the plain DBSCAN, and the radio map dimensionality was reduced in both dimensions, samples and AP.

Cite: Quezada-Gaibor, D. ; Klus, L. ; Torres-Sospedra, J. ; Lohan, E.S. ; Nurmi, J. ; Huerta, J. Improving DBSCAN for Indoor Positioning Using Wi-Fi Radio Maps in Wearable and IoT Devices. In: 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), 5-8 October 2020. Brno, Czech Republic. http://www.doi.org/10.1109/ICUMT51630.2020.9222411