Published January 4, 2022 | Version v1
Conference paper Open

Towards Ubiquitous Indoor Positioning: Comparing Systems across Heterogeneous Datasets

Authors/Creators

  • 1. UBIK Geospatial Solutions S.L., Spain
  • 2. University of Minho, Portugal
  • 3. Tampere University, Finland; Universitat Jaume I, Spain
  • 4. Universitat Jaume I, Spain; Tampere University, Finland
  • 5. Information Science and Technologies Institute, National Research Council, Italy
  • 6. Tampere University, Finland

Description

The evaluation of Indoor Positioning Systems (IPSs) mostly relies on local deployments in the researchers’ or partners’ facilities. The complexity of preparing comprehensive experiments, collecting data, and considering multiple scenarios usually limits the evaluation area and, therefore, the assessment of the proposed systems. The requirements and features of controlled experiments cannot be generalized since the use of the same sensors or anchors density cannot be guaranteed. The dawn of datasets is pushing IPS evaluation to a similar level as machine-learning models, where new proposals are evaluated over many heterogeneous datasets. This paper proposes a way to evaluate IPSs in multiple scenarios, that is validated with three use cases. The results prove that the proposed aggregation of the evaluation metric values is a useful tool for high-level comparison of IPSs.

Notes

The authors gratefully acknowledge funding from European Union's Horizon 2020 Research and Innovation programme under the Marie Sklodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). FCT – Fundacao para a Ciencia e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020 and the PhD fellowship PD/BD/137401/2018. J. Torres-Sospedra acknowledges funding from MICIU (INSIGNIA, PTQ2018-009981).

Files

IPIN_2021_Towards Ubiquitous_FRONT PAGE.pdf

Files (1.4 MB)

Name Size Download all
md5:c10916c3ca5c5ef5797d73d0096a8180
1.4 MB Preview Download

Additional details

Funding

European Commission
A-WEAR - A network for dynamic WEarable Applications with pRivacy constraints 813278