Santos, R. X. M., & Krishnan, S. (2022). Multilateration-based Machine Learning for Indoor Localization. TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON). https://doi.org/10.1109/tencon55691.2022.9977482
Indoor Positioning Systems (IPS) are becoming increasingly beneficial as they can provide real-time location data to improve various workflows. Their accuracies can be improved by deploying machine learning solutions to serve as the positioning engine. Fingerprinting-based models have been widely proposed as they can utilize the available network devices as reference nodes to build a wireless signal profile of the location. However, this approach requires repetitive manual data collection, which may not be feasible in restricted spaces and is impractical for off-the-shelf consumer solutions. This paper therefore proposes an alternative multilateration-based machine learning model trained on a minimal training set. Experimental results showed that the proposed trilateration-based model outperformed both the traditional multilateration and the fingerprinting-based models.
There was no specific funding for the research done