Combinatorial Data Augmentation for Real-Time Indoor Positioning: Concepts and Experiments

초록

Precise positioning has become one core topic in wireless communications by facilitating candidate techniques of beyond 5G and 6G. Nevertheless, most existing positioning algorithms, categorized into geometry-driven and data-driven approaches, fail to simultaneously fulfill diversified requirements for practical use, e.g., accuracy, real-time operation, scalability, maintenance, etc. This article aims at introducing a new principle, called combinatorial data augmentation (CDA), a catalyst for tightly integrating geometry and data-driven approaches. We first explain the concept of CDA and its critical advantages over the two standalone approaches, followed by validating its effectiveness by field experiments with WiFi round-trip time and inertial measurement units.

키워드