Reproduce “Transforming Indoor Localization: Advanced Transformer Architecture for NLOS Dominated Wireless Environments with Distributed Sensors” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Saad Masrur, Jung-Fu, Cheng, Atieh R. Khamesi, Ismail Guvenc
The paper presents sensor-snapshot tokenization (SST) for Transformer-based indoor positioning from power delay profiles (PDPs), giving each sensor’s delay history its own token so attention can compare sensors. In a simulated obstructed factory, SST reaches a 90th-percentile 2D error of 0.388 m, versus 0.6598 m with patch tokens. This result is simulation-bound.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.