Author(s): Torres-Sospedra, Joaquín ; Silva, Ivo Miguel Menezes ; Klus, Lucie ; Quezada-Gaibor, Darwin ; Crivello, Antonino ; Barsocchi, Paolo ; Pendão, Cristiano ; Lohan, Elena Simona ; Nurmi, Jari ; Moreira, Adriano
Date: 2021
Persistent ID: https://hdl.handle.net/1822/82120
Origin: RepositóriUM - Universidade do Minho
Subject(s): Evaluation; Indoor Positioning; Benchmarking; Indoor Positioning Benchmarking
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.
