WiFi RSS and RTT Indoor Positioning with Graph Temporal Convolution Network
Lila Rana, Aayush Dulal, Xin Chen, Xinhua Tang · 2025
Read WiFi RSS and RTT Indoor Positioning with Graph Temporal Convolution Network by Lila Rana, Aayush Dulal, Xin Chen, Xinhua Tang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12736580.txt.
Description
Lila Rana, Aayush Dulal, Xin Chen, and Xinhua Tang propose a graph temporal convolutional network for indoor positioning with WiFi signals. Their 2025 paper deals with locating people inside buildings, where satellite signals fail.
Commodity WiFi positioning struggles with multipath fading and blocked paths, so sub-meter accuracy is hard. Their hybrid model uses graph convolutions to encode access point geometry, and temporal convolutions to capture signal dynamics. Both signal strength and round-trip time features are used, with a gating mechanism that weighs each access point. Tests ran in four areas, from a lecture theatre to a full building floor. Sensitivity to access point density was also analyzed.
Catalog record
| CREATOR | Lila Rana, Aayush Dulal, Xin Chen, Xinhua Tang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |