Multilateration-based Machine Learning for Indoor Localization

Page view(s)
23
Checked on Feb 13, 2025
Multilateration-based Machine Learning for Indoor Localization
Title:
Multilateration-based Machine Learning for Indoor Localization
Journal Title:
TENCON 2022 - 2022 IEEE Region 10 Conference (TENCON)
Keywords:
Publication Date:
20 December 2022
Citation:
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
Abstract:
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.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2159-3450
Files uploaded: