RSSI-Based Indoor Localization Using Two-Step XGBoost
Taisei Kosaka, Steven Wandale, Koichi Ichige
Abstract
In this letter, we propose a Received Signal Strength Indicator (RSSI)-based indoor localization method using two-step extreme gradient boosting (XGBoost). The proposed two-step XGBoost leverages one of the location coordinates <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(x$</tex> or <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$y$</tex> ) as a feature to enhance the estimation accuracy. Simulation examples confirm that the proposed two-step XG-Boost approach could improve the estimation accuracy while maintaining low computational complexity.
Topics & Concepts
Computer scienceArtificial intelligenceBoosting (machine learning)Feature (linguistics)Signal strengthPattern recognition (psychology)Wireless sensor networkComputer networkLinguisticsPhilosophyIndoor and Outdoor Localization TechnologiesRobotics and Sensor-Based LocalizationIoT-based Smart Home Systems