NLOS/LOS identification with LightGBM ensemble
Xiaofeng Yang, Zhao Wu, Danlei Mo · 2026
Read NLOS/LOS identification with LightGBM ensemble by Xiaofeng Yang, Zhao Wu, Danlei Mo (2026) 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/plos-pone-0353288.txt.
Description
Yang, Wu, and Mo built a classifier for indoor radio positioning in a 2026 study. Ultra-wideband signals locate people and goods indoors, but walls block direct paths and warp the signal. Telling a blocked path from a clear one is the key first step.
Their method combines several fast tree models in parallel and reads signal patches at multiple scales across time and frequency. Tests on a public data set beat deep learning and single-tree rivals on accuracy and held up on new data, with workable computing cost. Reliable blocked-path detection could steady indoor navigation in warehouses, hospitals, and malls where satellite signals fail.
Catalog record
| CREATOR | Xiaofeng Yang, Zhao Wu, Danlei Mo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 21051 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |