Towards Ubiquitous Indoor Positioning: Comparing Systems across Heterogeneous Datasets
This addresses the challenge of limited and non-generalizable evaluations in IPS research, though it is incremental as it builds on existing dataset-based approaches.
The paper tackles the problem of evaluating Indoor Positioning Systems (IPS) by proposing a method to compare them across multiple heterogeneous datasets, validated with three use cases, showing that the aggregation of evaluation metrics is a useful tool for high-level comparison.
The evaluation of Indoor Positioning Systems (IPS) 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.