MudiNet uses a variational autoencoder with self-attention to separate useful specular reflections from diffuse noise in CIRs, improving simulated 5G indoor positioning.
A novel 3-D indoor localization algorithm based on BLE and multiple sensors,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MudiNet: Task-guided Disentangled Representation Learning for 5G Indoor Multipath-assisted Positioning
MudiNet uses a variational autoencoder with self-attention to separate useful specular reflections from diffuse noise in CIRs, improving simulated 5G indoor positioning.