Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Adaptive Dual Reinforcement Learning for Hybrid Spatial-Temporal Networks in RIS-Assisted Indoor Localization

Mostafa Mohamed^1,2, Ahmed Radi^1,2, Shady Zahran^1,2

¹Mobile Multi-Sensor Systems (MMSS) Research Group, Calgary, AB T2N 1N4, Canada.

Sensors (Basel, Switzerland)

|May 13, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Optical and Mass Flow Sensors for Aiding Vehicle Navigation in GNSS Denied Environment.

Sensors (Basel, Switzerland)·2020

Same author

Radar and Visual Odometry Integrated System Aided Navigation for UAVS in GNSS Denied Environment.

Sensors (Basel, Switzerland)·2018

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Reconfigurable intelligent surface sensors (RISs) enhance indoor localization. Our Adaptive Dual-Reinforcement Learning-Hybrid Spatial-Temporal Network (ADRL-HSTNet) improves accuracy by adaptively processing complex signal features.

Area of Science:

Wireless Communication and Signal Processing
Artificial Intelligence and Machine Learning
Indoor Localization Technologies

Background:

Reconfigurable intelligent surfaces (RISs) offer advanced wireless signal control for localization.
Challenges in RIS-assisted localization include multipath fading, noise, and dynamic channel behavior.
Existing methods struggle with extracting reliable localization fingerprints from complex RIS signals.

Purpose of the Study:

To propose a novel Adaptive Dual-Reinforcement Learning-Hybrid Spatial-Temporal Network (ADRL-HSTNet) for robust RIS-assisted indoor localization.
To address the limitations of current approaches in handling signal complexities and nonlinear dynamics.
To enhance the accuracy and reliability of indoor positioning systems using RIS technology.

Main Methods:

Keywords:

indoor localization reconfigurable intelligent surfaces (RISs)reinforcement learning spatial–temporal modeling

Related Experiment Videos

Utilized dual-channel RSSI and phase measurements with preprocessing (filtering, normalization, segmentation).
Employed multi-branch feature extraction including handcrafted features, wavelet representations, and segmentation masks.
Integrated lightweight transformer encoders and dual reinforcement learning selectors for adaptive feature fusion and processing.
Developed an end-to-end model for classification, coordinate regression, and uncertainty estimation.

Main Results:

The ADRL-HSTNet significantly outperformed baseline models like KAN, LSTM-KAN, and RHL-Net.
Achieved high localization accuracies across various RIS configurations, reaching up to 93.33%.
Demonstrated the effectiveness of adaptive feature weighting and fusion for robust localization embedding.

Conclusions:

The proposed ADRL-HSTNet effectively overcomes challenges in RIS-assisted indoor localization.
The adaptive, hybrid spatial-temporal approach provides superior performance compared to existing methods.
This work advances the development of accurate and reliable indoor positioning systems leveraging RIS technology.