.png){kind=icon}
.png){kind=icon}
Return
XAI-Driven Feature Optimization for Single-Cell Localization
.png){kind=icon}
PRE
AI
DOI：10.1109/lwc.2026.3712391.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This letter proposes a novel single-cell TDOA localization framework utilizing multi-beam transmission, which eliminates the dependency on multiple base stations. To mitigate environmental instability and high dimensionality, the proposed method introduces a dual-stage pipeline: first, similarity-based data refinement filters unstable environmental noise, and second, SHAP-guided feature selection optimizes input dimensionality. Field experiments in a realistic environment demonstrate that this approach maintains robust localization accuracy while achieving up to a 60% reduction in training overhead.
Keywords:
Time difference of arrival
feature selection
wireless localization
deep learning
Journal
I
IF:
5.5
Papers:
665
Citations:
0