Search research articles

Search research articles

Related Experiment Videos

DGrA: Lightweight Modulation Recognition Based on Hybrid Neural Networks.

Xu Chen¹, Rui Gao², Ding Xu¹

¹Jiangsu Key Laboratory of Wireless Communications, Nanjing University of Posts and Telecommunications, Nanjing 210003, China.

Sensors (Basel, Switzerland)

|May 27, 2026

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

Mesenchymal Stromal Cell-Derived Extracellular Vesicles Mediate Mitochondrial Delivery in Injury: Mechanistic Insights, Evidentiary Tiers, and Translational Challenges.

Stem cell reviews and reports·2026

Same author

Revealing bond level origin of stability in disordered solids from marginal stability to ultrastability.

Nature communications·2026

Same author

Impact of Hospital Hierarchy on Nurses' Attitudes Toward Artificial Intelligence: Mediating Roles of Artificial Intelligence Literacy and Anxiety.

Journal of nursing management·2026

Same author

Nociceptive sensory nerves induce an IL4Rα<sup>hi</sup> anti-inflammatory macrophage subset that protects against kidney ischemia-reperfusion injury.

Kidney international·2026

Same author

Mechanistic Insights into Xihuang Wan against Bladder Cancer via PI3K/ AKT/BCL2-Mediated Apoptosis Inhibition: Integrated Network Pharmacology, Molecular Docking, Molecular Dynamics Simulations and Experimental Validation.

Current pharmaceutical design·2026

Same author

Heparan sulfate promotes autoactivation of procathepsin K by destabilizing the propeptide-catalytic domain interaction.

The Biochemical journal·2026

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

This study introduces a novel lightweight method for automatic modulation recognition, enhancing accuracy and reducing model size. The approach effectively differentiates signal sequences for intelligent transmission applications.

Area of Science:

Electrical Engineering
Computer Science
Signal Processing

Background:

Automatic modulation recognition is vital for non-cooperative communication and intelligent transmission.
Existing methods often face challenges with spatial costs and computational complexity.

Purpose of the Study:

To propose a new lightweight method for automatic modulation recognition.
To enhance recognition accuracy while reducing spatial and computational costs.
To validate the method's effectiveness in real-world scenarios.

Main Methods:

Combines an improved attention block and convolutional operations with a recurrent neural network.
Utilizes depthwise separable convolutions to reduce computational complexity and enhance feature extraction.

Keywords:

SDR deep learning feature extraction intelligent signal processing lightweight modulation recognition

Related Experiment Videos

Incorporates pruning to reduce ineffective features and decrease model size.

Main Results:

The proposed method outperforms comparative methods on the RadioML2016.10a dataset in terms of recognition accuracy and model size.
Achieved 87.22% accuracy on a software-defined radio platform under practical conditions with environmental noise.
Demonstrated reduced computational complexity and enhanced feature extraction capabilities.

Conclusions:

The developed lightweight method offers superior performance for automatic modulation recognition.
The approach is effective in real-world applications, even in noisy environments.
This technique contributes to more efficient and accurate intelligent transmission systems.