Convolutional Radio Modulation Recognition Networks

We study the adaptation of convolutional neural networks to the complex-valued temporal radio signal domain. We compare the efficacy of radio modulation classification using naively learned features against using expert feature based methods which are widely used today and e show significant performance improvements. We show that blind temporal learning on large and densely encoded time series using deep convolutional neural networks is viable and a strong candidate approach for this task especially at low signal to noise ratio.

• Publication year

  2016

• Venue

  International Conference on Engineering Applications of Neural Networks

• Publication date

  2016-02-12

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1007/978-3-319-44188-7_16arXiv 1602.04105
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• The convolutional neural network approach is especially strong at low signal-to-noise ratio.

  Confidence 0.90

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• Blind temporal learning on large, densely encoded time series is a viable approach for radio modulation recognition.

  Confidence 0.93

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• Convolutional neural networks with naively learned features achieve significant performance improvements over expert feature-based methods for radio modulation recognition.

  Confidence 0.96

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review

• blind temporal learning

  learning approach, method

  A learning approach that directly learns from time-series signal data without relying on expert-designed features.

  Aliases: temporal learning, blind learning

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• complex-valued temporal radio signal domain

  data domain, signal domain

  A signal representation setting in which radio measurements are treated as complex-valued time series over time.

  Aliases: complex-valued radio signal domain, temporal radio signal domain

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• convolutional neural networks

  method, model

  A deep learning model architecture that applies convolutional filters to learn features from radio signal inputs.

  Aliases: CNNs, CNN

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• dense encoded time series

  data representation

  Time-series inputs represented with a high-density encoding suitable for convolutional processing.

  Aliases: densely encoded time series, dense time series

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• expert feature-based methods

  baseline, method

  Hand-engineered feature approaches used to represent radio signals before classification.

  Aliases: feature-based methods, expert features

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• radio modulation recognition

  task, classification task

  The classification task of identifying modulation types from radio signal observations.

  Aliases: modulation classification, radio modulation classification

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review
• signal-to-noise ratio

  measurement, condition

  The ratio describing how much signal power is present relative to background noise in the radio observations.

  Aliases: SNR

  박진우 (dztg5apj7m) extractionAnonymous (12632b8b5f) reviewmexicorea (qjvnbu8xg3) reviewAll you need is Python (5d7gwfm5zu) review

• Spatial Transformer Networks

  2015cited by this paper
• Learning the speech front-end with raw waveform CLDNNs

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Deconvolutional networks

  2010cited by this paper
• Applications of Machine Learning to Cognitive Radio Networks

  2007cited by this paper
• Cyclostationary Approaches to Signal Detection and Classification in Cognitive Radio

  2007cited by this paper
• Application of artificial intelligence to wireless communications

  2007cited by this paper
• Efficient sparse coding algorithms

  2006cited by this paper
• Dynamic Spectrum Policies: Promises and Challenges

  2004cited by this paper
• GNU radio: tools for exploring the radio frequency spectrum

  2004cited by this paper
• Cognitive radio: making software radios more personal

  1999cited by this paper
• Signal interception: performance advantages of cyclic-feature detectors

  1992cited by this paper

• Adversarial Transfer Attack Against and Adaptive Defense for Intelligent Modulation Recognition

  2026cites this paper
• Efficient Automatic Modulation Classification for Next-Generation Wireless Networks

  2026cites this paper
• Tr‐AMR: A Lightweight Transformer With Enhanced Temporal Modeling for Automatic Modulation Recognition

  2026cites this paper
• Modulation Recognition Using Frequency-Prior Multi-Scale Convolution and Time-Frequency Interaction Attention Mechanism

  2026cites this paper
• Improved Distribution Difference Driven Diffusion Generative Method for AMOSR

  2026cites this paper
• An Effective Masked Transformer Model for Automatic Modulation Recognition

  2026cites this paper
• S3AT: Self-Paced, Self-Distilled, and Self-Finetuned Adversarial Training for Robust Automatic Modulation Recognition

  2026cites this paper
• TACM-MR: Topographically Augmented Channel Model Multi-Receiver Dataset

  2026cites this paper
• A Multi-Level Feature Distribution Learning Method for Automatic Modulation Open-Set Recognition

  2026cites this paper
• Domain Adaptive Hybrid Network for Automatic Modulation Recognition

  2026cites this paper
• Unsupervised Transformer-Based ClusterGAN and Infinite Gaussian Mixture Models for Modulation Signal Clustering

  2026cites this paper
• Class Feature Space Reconstruction for Automatic Modulation Open Set Recognition

  2026cites this paper
• Adversarial Defense in Modulation Recognition via Diffusion and Segment-Wise Classification

  2026cites this paper
• Joint Identification of Encoders and Interleavers Using Deep Learning With Hardware Validation

  2026cites this paper
• DDMNet: A Dual-Stream Network With Differential Temporal and Multiscale Spectral Features for Automatic Modulation Recognition

  2026cites this paper
• C2F-Net: Coarse-to-Fine Feature Alignment for Cross-Channel Automatic Modulation Classification

  2026cites this paper
• A Few-Shot Open-Set Modulation Recognition Scheme Under Low SNR Condition

  2026cites this paper
• Multi-Oriented Open Set Adversarial Attacks to Automatic Modulation Classification

  2026cites this paper
• SCAW: Exploring Semantic Structures of Radio Signals via Soft Top-k Contrastive and Adaptive Consistency With Wavelet Refinement

  2026cites this paper
• MM-CL: Enhancing Modulation Classification Through Multi-Modal Contrastive Learning With Phase Density

  2026cites this paper
• Radio Frequency Signal Recognition of Unmanned Aerial Vehicle Based on Complex-Valued Convolutional Neural Network

  2026cites this paper
• Transformer-Based Phase Space Graph Convolutional Network for Modulation Recognition

  2026cites this paper
• CCIFE: Channel-Resilient Ensemble Adversarial Attack Against DNN-Based Modulation Classifiers

  2026cites this paper
• An Orthogonal Pseudo-Prototype and Pseudo-Target-Based Method for Few-Shot Class-Incremental Automatic Modulation Recognition

  2026cites this paper
• Few-Shot Automatic Modulation Classification via Semi-Supervised Metric Learning and Lightweight Conv-Transformer Model

  2026cites this paper
• FUTUREs: Feature Utility Transfer for Uncooperative Recognition of Electromagnetic Signals Toward 6G Wireless Communications

  2026cites this paper
• TMGpCN: Semi-Supervised GpCN Based on Transformer Mask for Automatic Modulation Recognition

  2026cites this paper
• An Expert-Assistant Network With Temporal Shuffling for Efficient Automatic Modulation Recognition

  2026cites this paper
• Leveraging Machine Learning Classifiers in Transfer Learning for Few-Shot Modulation Recognition

  2026cites this paper
• On the Vulnerability of Deep Automatic Modulation Classifiers to Explainable Backdoor Threats

  2026cites this paper
• Potential Threat to Cognitive Radio Networks: A Black-Box and Label-Consistent Backdoor Attack Against Modulation Recognition

  2026cites this paper
• Disentangling Domain-Invariant Features From Few Samples for Automatic Modulation Classification

  2026cites this paper
• Federated Prototype Adaptation Learning: Personalized and Generalizable Learning in Distributed Networks

  2026cites this paper
• High-Order Feature Modeling and Multi-Level Reconstruction for Modulation Open-Set Detection

  2026cites this paper
• FedPML: Federated Prototype Meta-Learning for Adaptation and Generalization in Distributed Environments

  2026cites this paper
• DFENet: A diverse feature extraction neural network for improving automatic modulation classification accuracy in wireless communication systems

  2026cites this paper
• Deep learning based algorithms for automatic modulation classification: Trends, challenges, and future directions

  2026cites this paper
• Enhancing Noise Robustness in Few-Shot Automatic Modulation Classification via Complex-Valued Autoencoders

  2026cites this paper
• Automatic Modulation Recognition for Radar Signal Based on Multi-Level and Multi-Scale Feature

  2025cites this paper
• Unveiling the power of features: A comparative study of machine learning and deep learning for modulation recognition

  2025cites this paper
• DUSE: A Data Expansion Framework for Low-resource Automatic Modulation Recognition based on Active Learning

  2025cites this paper
• Deep learning-based automatic modulation classifier

  2025influential citation
• DNEN-ACVIT: A Deep Neural Ensemble Network for Automatic Modulation Classification Based on Attention Convolution and Vision Transformer

  2025cites this paper
• Multi-Level Wavelet Transform Network Based Automatic Modulation Classification

  2025cites this paper
• Integrated Radio Sensing Capabilities for 6G Networks: AI/ML Perspective

  2025cites this paper
• Advanced Methods for Optimization of Neural Networks for Signal Processing: A Survey

  2025cites this paper
• A Transfer Learning and Time-Frequency Fusion Framework for Few-Shot Modulation Classification in LEO Satellite Communications

  2025cites this paper
• I Can’t Believe It’s Not Real: CV-MuSeNet: Complex-Valued Multi-Signal Segmentation

  2025cites this paper
• PFRTF: A Robust Training Framework to Counter Adversarial Attacks in Signal Classification for Next-G Consumer Electronics

  2025cites this paper
• FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition

  2025cites this paper
• Automatic classification of radar and communication waveforms through interpretable deep learning

  2025cites this paper
• Frequency-learning adversarial networks based on transfer learning for cross-scenario signal modulation classification

  2025cites this paper
• Time-stretch enabled multifunctional incoherent optical processor for analog-digital computing

  2025cites this paper
• Deep Learning-Driven Classification of 5G and LTE Signals for Next-Generation Wireless Networks

  2025cites this paper
• Toward Interference-Tolerant Automatic Modulation Recognition via Multi-Stage Feature Extraction Network

  2025cites this paper
• Learnable Gaussian Filter-Based Automatic RF Waveform Modulation Recognition

  2025cites this paper
• Exploiting Complex-Valued Representations in Automatic Modulation Recognition: A Framework Integrating a Transformer With Relative Positional Encoding and Separable Convolution

  2025cites this paper
• A Bayesian Neural Network for Robust Automatic Modulation Classification: Mitigating Adversarial Amplification

  2025cites this paper
• SpectrumFM: A Foundation Model for Intelligent Spectrum Management

  2025cites this paper
• DFN-YOLO: Detecting Narrowband Signals in Broadband Spectrum

  2025cites this paper
• DualBranch-AMR: A Semi-Supervised AMR Method Based on Dual-Student Consistency Regularization with Dynamic Stability Evaluation

  2025influential citation
• Modulation Classification: Diverse Techniques and Constellation Model Training at Varying Resolution

  2025cites this paper
• Research Progress on Modulation Format Recognition Technology for Visible Light Communication

  2025cites this paper
• Noise-Resilient Graph-LSTM Transformer for Enhanced Modulation Recognition

  2025cites this paper
• Adversarial Robust ViT-Based Automatic Modulation Recognition in Practical Deep Learning-Based Wireless Systems

  2025influential citation
• Research and implementation of modulation recognition based on deep learning

  2025cites this paper
• A Modified Convolutional Neural Network Model for Automatic Modulation Classification

  2025cites this paper
• STF-GCN: A Multi-Domain Graph Convolution Network Method for Automatic Modulation Recognition via Adaptive Correlation

  2025cites this paper
• A Multitarget Backdoor Attack Against Automatic Modulation Recognition for IoT Wireless Signals

  2025cites this paper
• Large-Scale Classification of Shortwave Communication Signals with Machine Learning

  2025cites this paper
• Multi-Agent Reinforcement Learning for Graph Discovery in D2D-Enabled Federated Learning

  2025cites this paper
• A Novel Distributed Solution for Automatic Modulation Classification Based on Federated Learning and Modified LSTM

  2025cites this paper
• Newton-Puiseux Analysis for Interpretability and Calibration of Complex-Valued Neural Networks

  2025cites this paper
• Fading-Invariant Adversarial Attacks on Neural Modulation Recognition

  2025cites this paper
• FA-GAN: Defense Against Adversarial Attacks in Automatic Modulation Recognition

  2025cites this paper
• Adversarial Attack and Reliable Defense Based on Frequency Domain Feature Enhancement for Automatic Modulation Classification

  2025cites this paper
• Mixed Data Augmentation Through the Integration of Mode Decomposition and Time-Series Transformation for Radio Signal Classification

  2025cites this paper
• SNR-Enhanced Automatic Modulation Classification in Artificial Intelligence of Things for Consumer Electronics

  2025cites this paper
• Self-Supervised Learning and Nearest Neighbors for Out-of-Distribution Modulation Classification

  2025cites this paper
• EET-MoCo: An Efficient Embedding Transformer With Momentum Contrast Learning for Automatic Modulation Recognition

  2025cites this paper
• MCLRL: A Multi-Domain Contrastive Learning with Reinforcement Learning Framework for Few-Shot Modulation Recognition

  2025cites this paper
• Multifeature Fusion-Based Closed-Box Attack Detection Method for Automatic Modulation Classification

  2025influential citation
• Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions

  2025cites this paper
• Few-Shot Specific Emitter Identification: A Knowledge, Data, and Model-Driven Fusion Framework

  2025cites this paper
• Modulation recognition method based on multimodal features

  2025cites this paper
• Research on Several Neural Network Structure for Automatic Modulation Recognition

  2025influential citation
• Adaptive signal recognition in mines based on deep learning

  2025cites this paper
• Radio Signal Modulation Pattern Recognition Based on Time-Frequency Adaptive Decomposition and Hybrid Neural Network

  2025cites this paper
• Real-Time 5.7–5.8 GHz 32-Beam Approximate Discrete Fourier Transform Spectrum Sensor for RF Perception on Xilinx Sx475T

  2025cites this paper
• Modulation recognition based on adaptive denoising residual neural network

  2025influential citation
• Classification of RF Signals Based on Image and Sequence Inputs

  2025cites this paper
• DL-AMC: Deep Learning for Automatic Modulation Classification

  2025influential citation
• A Lightweight Dual-Branch Complex-Valued Neural Network for Automatic Modulation Classification of Communication Signals

  2025cites this paper
• 6G WavesFM: A Foundation Model for Sensing, Communication, and Localization

  2025cites this paper
• Multicomponent Radar Signal Recognition via Signal Quantity Detection and Feature Enhancement

  2025cites this paper
• TF-Transformer: Temporal-Frequency Transformer for OFDM Signal Recognition

  2025cites this paper
• 3M‐Net: Automatic Modulation Recognition Based on Multiscale Mobile Inverted Bottleneck Convolution and Manhattan Self‐Attention Network

  2025cites this paper
• ResGCN: A Scalable, Robust and Efficient Approach for Radio Fingerprinting

  2025cites this paper
• Adversarial Sample Generation Method for Modulated Signals Based on Edge-Linear Combination

  2025cites this paper
• MSNCIL: A Domain-Agnostic Class-Incremental Learning Method Tailored for Automatic Modulation Recognition

  2025cites this paper