Name
Abstract | ||
|---|---|---|
It is well-known that fingerprinting-based positioning requires an exhaustive calibration phase to create a radio map, which often requires recalibration. Model-based and geometric approaches try to mitigate this effort at the expense of a lower accuracy or high computational cost. This paper introduces FastGraph, where a 3D graph is used to rapidly model the radio propagation environment. By means of unsupervised techniques, FastGraph is able to operate shortly after its deployment without previous knowledge about the environment. The proposed solution uses a novel algorithm to automatically provide location while simultaneously updating the radio map; and learn the position of the Access Points (APs) and location-specific radio propagation parameters. FastGraph has been evaluated in two real-world environments, a factory-plant and a regular university building, with results comparable to those obtained by conventional radio map-based solutions. |
Year | Venue | Field |
|---|---|---|
2018 | IPIN | Graph,Computer vision,Software deployment,Fingerprint recognition,Radio map,Artificial intelligence,Engineering,Simultaneous localization and mapping,Calibration,Radio propagation |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Cristiano G. Pendao | 1 | 7 | 4.23 |
| Adriano Moreira | 2 | 234 | 59.85 |