RSSI fingerprinting via sparse GPS reference sensors and machine learning achieves 80% location classification accuracy (up to 92% with spaced classes) for UNB IoT devices over a 2.5 km city radius, with multilateration gains when reference density allows.
An energy-efficient and lightweight indoor localization system for internet-of-things (iot) environments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Localization in Ultra Narrow Band IoT Networks: Design Guidelines and Trade-Offs
RSSI fingerprinting via sparse GPS reference sensors and machine learning achieves 80% location classification accuracy (up to 92% with spaced classes) for UNB IoT devices over a 2.5 km city radius, with multilateration gains when reference density allows.