Adaptive Dual Reinforcement Learning for Hybrid Spatial–Temporal Networks in RIS-Assisted Indoor Localization (ADRL-HSTNet)
Mostafa Mohamed, Ahmed Radi, Shady Zahran · 2026
Read Adaptive Dual Reinforcement Learning for Hybrid Spatial–Temporal Networks in RIS-Assisted Indoor Localization (ADRL-HSTNet) by Mostafa Mohamed, Ahmed Radi, Shady Zahran (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/pmc-13165723.txt.
Description
Mostafa Mohamed, Ahmed Radi, and Shady Zahran build a learning system that pinpoints devices indoors using smart radio surfaces. Their 2026 paper works with reconfigurable intelligent surfaces, panels that steer wireless signals on purpose. Reading a location from such signals is hard: reflections multiply, noise intrudes, and the channel changes in tangled ways across space and time.
Their framework, ADRL-HSTNet, starts from two signal channels, strength and phase, cleaned and sliced into sliding windows. Handcrafted features, wavelet views, and patch features feed lightweight transformer encoders. A first reinforcement learner weights the most useful feature branches; spatial and temporal modules then process the fused result, and a second learner blends their outputs. The design aims at accuracy that adapts as rooms change.
Catalog record
| CREATOR | Mostafa Mohamed, Ahmed Radi, Shady Zahran |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |