Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 16, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

Multi-Filter Quantum Neural Networks for Efficient Channel Estimation in RIS-Assisted Systems.

Min-Hyeok Choi1,2, Ja-Eun Kim1,2, Seung-Han Kim2,3

  • 1Department of Information and Communication Engineering, Sejong University, Seoul 05006, Republic of Korea.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

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

An Unsupervised Detection-to-Mitigation Framework for Resource Exhaustion Attacks in 5G/6G Network Slicing.

Sensors (Basel, Switzerland)·2026
Same author

Carboxylate polystyrene nanoplastics disrupt mitotic progression and induce chromosomal instability.

Ecotoxicology and environmental safety·2025
Same author

Activation of autophagy as a strategy to overcome Osimertinib-resistance in non-small cell lung cancer.

European journal of pharmacology·2025
Same author

Single-cell transcriptomic and pharmacological studies of onvansertib for small cell lung cancer treatment.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2025
Same author

A Novel <i>Phaeoacremonium</i> Species Isolated from Galls on the Chinese Magnolia-Vine (<i>Schisandra chinensis</i>) in Korea.

Mycobiology·2025
Same author

Beamforming for the Cooperative Non-Orthogonal Multiple Access Transmission with Full-Duplex Relaying with Application to Security Attack.

Sensors (Basel, Switzerland)·2025

This study introduces a Multi-Filter Quantum Convolutional Neural Network (MF-QCNN) for efficient channel estimation in Reconfigurable Intelligent Surface (RIS) wireless systems. The MF-QCNN significantly reduces errors and improves data rates compared to existing methods.

Area of Science:

  • Wireless Communications
  • Quantum Computing
  • Machine Learning

Background:

  • Reconfigurable Intelligent Surfaces (RIS) are crucial for future wireless networks (B5G/6G).
  • Cascaded channel estimation in RIS systems is challenging due to passive reflection and double-fading.
  • Existing methods like CNNs have high parameter counts, while PQCs have limited feature representation or face NISQ device limitations.

Purpose of the Study:

  • To propose a novel Multi-Filter Quantum Convolutional Neural Network (MF-QCNN) for accurate cascaded channel estimation in RIS-assisted systems.
  • To address the limitations of conventional CNNs and single-filter Quantum Convolutional Neural Networks (QCNNs).
  • To enable efficient and compact quantum-aided estimation for RIS technologies.

Main Methods:

Keywords:
B5G/6G wireless communicationscascaded channel estimationmulti-filter architecturequantum convolutional neural networkquantum machine learningquantum-aided networkingreconfigurable intelligent surface

Related Experiment Videos

Last Updated: Jul 16, 2026

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit
05:30

Large Scale Energy Efficient Sensor Network Routing Using a Quantum Processor Unit

Published on: September 8, 2023

  • Developed an MF-QCNN using multiple parallel shallow Parameterized Quantum Circuits (PQCs) as filters.
  • Concatenated measured features from PQCs and used a classical dense head for channel estimation.
  • Analyzed parameter scaling with F parallel filters as 182F+696.

    • Main Results:

    • The 3-filter MF-QCNN achieved significant Normalized Mean Squared Error (NMSE) reductions: 22.9 dB vs. single-filter QCNN, 8.1 dB vs. CNN, and 4.6 dB vs. MLP at 20 dB SNR.
    • MF-QCNN used only 19.3% of CNN trainable parameters.
    • Achieved superior achievable sum rates under zero-forcing precoding, improving over CNN and MLP by 17.4% and 12.8% respectively at 30 dB SNR.

    Conclusions:

    • The parallel shallow-PQC design in MF-QCNN offers a compact and effective quantum-aided estimator for RIS channel estimation.
    • MF-QCNN presents a viable approach for AI-native transceiver design in B5G/6G networks.
    • This model provides a strong foundation for future research in quantum-enhanced wireless communications.