Deep learning based automatic modulation recognition: Models, datasets, and challenges

Article Engineering, Electrical & Electronic

Combining neural networks for modulation recognition

Fengyuan Shi et al.

Summary: This study introduces a combined Convolutional Neural Network (CNN) scheme for automatic modulation recognition, achieving a high accuracy of 98.7% on the DeepSig dataset and outperforming current state-of-the-art methods.

DIGITAL SIGNAL PROCESSING (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Signal Processing-Based Deep Learning for Blind Symbol Decoding and Modulation Classification

Samer Hanna et al.

Summary: The study introduces a dual path network design that combines digital signal processing and deep learning, achieving a 5% improvement in modulation classification compared to other designs. Testing on simulated and actual radio capture data, DPN demonstrates superior performance over traditional blind signal processing algorithms.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Real-Time Radio Technology and Modulation Classification via an LSTM Auto-Encoder

Ziqi Ke et al.

Summary: The paper presents a learning framework based on an LSTM denoising auto-encoder designed to automatically extract stable and robust features from noisy radio signals, and infer modulation or technology type using the learned features. The algorithm utilizes a compact neural network architecture readily implemented on a low-cost computational platform while exceeding state-of-the-art accuracy. Results on realistic synthetic as well as over-the-air radio data demonstrate that the proposed framework reliably and efficiently classifies received radio signals, often demonstrating superior performance compared to state-of-the-art methods.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Multitask-Learning-Based Deep Neural Network for Automatic Modulation Classification

Shuo Chang et al.

Summary: Automatic modulation classification (AMC) plays a vital role in identifying the modulation type of a received signal for ensuring the physical-layer security of IoT networks. This article focuses on reproducing and evaluating popular AMC algorithms using the in-phase/quadrature (I/Q) and amplitude/phase (A/P) representations for comparison. Based on the experimental results, it is found that CNN-RNN-like algorithms using A/P as input data perform better at high signal-to-noise ratio (SNR), while the opposite is true at low SNR. Inspired by these findings, a multitask learning-based deep neural network (MLDNN) is proposed, which effectively fuses I/Q and A/P. Extensive simulations demonstrate the superior performance of the proposed MLDNN in a public benchmark.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

MIMO-OFDM Modulation Classification Using Three-Dimensional Convolutional Network

Thien Huynh-The et al.

Summary: In this paper, we propose an efficient automatic modulation classification (AMC) method for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) communication systems. By utilizing a three-dimensional MIMO-OFDM convolutional neural network (MONet) to learn modulation patterns from received signals, the proposed method achieves high classification accuracy under various channel impairments.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

添加到收藏夹

Article Telecommunications

An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and Transformation

Fuxin Zhang et al.

Summary: The efficient DL-AMR model proposed in this letter combines phase parameter estimation and transformation with CNN and GRU, achieving high recognition accuracy while reducing parameter volume. Compared to state-of-the-art models, it has shorter training and testing times.

IEEE COMMUNICATIONS LETTERS (2021)

添加到收藏夹

Article Engineering, Aerospace

Intelligent Denoising-Aided Deep Learning Modulation Recognition With Cyclic Spectrum Features for Higher Accuracy

Lin Zhang et al.

Summary: Deep-learning-based modulation recognition methods can automatically extract signal features using deep neural networks (DNN). The proposed method in this article utilizes spectral correlation function (SCF) to construct datasets and incorporates a convolutional neural network denoising module for better feature extraction performances. In low SNR regions, the intelligent system achieves higher recognition accuracy compared to counterpart schemes.

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Automatic Modulation Recognition: A Few-Shot Learning Method Based on the Capsule Network

Lixin Li et al.

Summary: With the rapid development of deep learning in automatic modulation recognition, a new network structure AMR-CapsNet has been proposed to achieve higher classification accuracy with fewer samples, with simulation results showing accuracy over 80% under specific conditions.

IEEE WIRELESS COMMUNICATIONS LETTERS (2021)

添加到收藏夹

Article Telecommunications

Visualizing Deep Learning-Based Radio Modulation Classifier

Liang Huang et al.

Summary: This article introduces a visualization method for deep learning-based radio modulation classifiers, presenting the extracted features through class activation vectors. The study on CNN and LSTM classifiers reveals that the extracted features are related to modulation reference points, with LSTM features being similar to human expert knowledge. The numerical results suggest that radio features extracted by deep learning-based classifiers heavily rely on the content carried by radio signals, where a short radio sample may cause misclassification.

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (2021)

添加到收藏夹

Article Telecommunications

Ensemble Wrapper Subsampling for Deep Modulation Classification

Sharan Ramjee et al.

Summary: The study introduces a subsampling technique for automatic modulation classification in wireless communication systems, utilizing deep neural network architectures to improve classification accuracy. This data-driven subsampling strategy reduces classifier training time and enhances performance by avoiding retraining the wrapper models and leveraging transferability of deep neural networks for ensemble learning.

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (2021)

添加到收藏夹

Article Telecommunications

Shared Spectrum Monitoring Using Deep Learning

Farrukh Aziz Bhatti et al.

Summary: This paper presents signal classification using deep neural networks to identify various radio technologies and their associated interferences. Six well-known CNN models are employed to train for ten signal classes, including LTE, Radar, WiFi and FBMC, achieving 98% classification accuracy. Additionally, a simple WiFi classification scheme is proposed to detect WiFi presence and quantify WiFi traffic density.

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (2021)

添加到收藏夹

Article Telecommunications

Real-Time OFDM Signal Modulation Classification Based on Deep Learning and Software-Defined Radio

Limin Zhang et al.

Summary: This study presents initial results of a real-time modulation classification system based on deep learning and software-defined radio. By generating a modulation classification dataset under a dynamic fading channel, the proposed neural network with triple-skip residual stack (TRS) achieved a classification accuracy of 64% at -10 dB, outperforming ResNet and VGG by 7%. The system design incurs a processing delay of about 4 ms.

IEEE COMMUNICATIONS LETTERS (2021)

添加到收藏夹

Article Telecommunications

Automatic Modulation Recognition Based on Adaptive Attention Mechanism and ResNeXt WSL Model

Zhi Liang et al.

Summary: A novel framework for Automatic Modulation Recognition (AMR) utilizing ResNeXt network and adaptive attention mechanism modules is proposed, achieving higher accuracy and robustness on RadioML datasets compared to state-of-the-art techniques.

IEEE COMMUNICATIONS LETTERS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Deep Learning Based Modulation Recognition With Multi-Cue Fusion

Tuo Wang et al.

Summary: A novel multi-cue fusion (MCF) network for automatic modulation recognition was proposed, achieving experimental results that outperformed the state-of-the-art works. The network consists of a signal cue multi-stream module and a visual cue discrimination module, utilizing CNN and IndRNN for modeling spatial-temporal correlations and extracting structural information from different data forms.

IEEE WIRELESS COMMUNICATIONS LETTERS (2021)

添加到收藏夹

Article Telecommunications

SSRCNN: A Semi-Supervised Learning Framework for Signal Recognition

Yihong Dong et al.

Summary: This paper presents a new semi-supervised learning method to enhance the performance of deep learning in signal recognition. Through carefully designed loss functions and neural network structure, it can effectively leverage unlabeled data for training models.

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Automatic Modulation Classification: A Deep Architecture Survey

Thien Huynh-The et al.

Summary: Automatic modulation classification (AMC) is a fundamental signal processing technique in wireless communication systems. Deep learning (DL) has been increasingly used to improve modulation classification performance by leveraging the underlying characteristics of radio signals. Various deep architectures, such as neural networks, recurrent neural networks, and convolutional neural networks, have been studied for AMC in wireless communications.

IEEE ACCESS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Spatial-Diversity MIMO Dataset for RF Signal Processing Research

Pejman Ghasemzadeh et al.

Summary: The study introduces a simulated signal reference dataset named MIMOSigRef-SD, which includes a variety of signal streams modulated by different digital modulation schemes to address the lack of reliability and multivariate environment analysis in automatic modulation classifiers in real-world environments. The dataset also incorporates the impact of different channel models at 2450 MHz and can be applicable to other applications beyond AMC.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

SR2CNN: Zero-Shot Learning for Signal Recognition

Yihong Dong et al.

Summary: This paper proposes a ZSL framework called SR2CNN for signal recognition and reconstruction, addressing the issue of lacking training data for signal recognition tasks. By introducing appropriate losses and distance metrics, SR2CNN learns the representation of signal semantic feature space, enabling signal recognition even without training data.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Machine Learning Based Automatic Modulation Recognition for Wireless Communications: A Comprehensive Survey

Bachir Jdid et al.

Summary: The article discusses the challenges posed by the rapid development of information and wireless communication technologies on spectrum usage and emphasizes the importance of Automatic Modulation Recognition in intelligent communication systems. Through advancements in deep learning technology, problems in single-input single-output and multiple-input multiple-output systems have been overcome.

IEEE ACCESS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Low-complexity deep learning and RBFN architectures for modulation classification of space-time block-code (STBC)-MIMO systems

Maqsood H. Shah et al.

DIGITAL SIGNAL PROCESSING (2020)

添加到收藏夹

Article Telecommunications

MCNet: An Efficient CNN Architecture for Robust Automatic Modulation Classification

Thien Huynh-The et al.

IEEE COMMUNICATIONS LETTERS (2020)

添加到收藏夹

Article Telecommunications

CNN-Based Automatic Modulation Classification for Beyond 5G Communications

Ade Pitra Hermawan et al.

IEEE COMMUNICATIONS LETTERS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Automatic Modulation Classification for MIMO Systems via Deep Learning and Zero-Forcing Equalization

Yu Wang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

An Improved Neural Network Pruning Technology for Automatic Modulation Classification in Edge Devices

Yun Lin et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Deep Learning-Based Cooperative Automatic Modulation Classification Method for MIMO Systems

Yu Wang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

LightAMC: Lightweight Automatic Modulation Classification via Deep Learning and Compressive Sensing

Yu Wang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Transfer Learning for Semi-Supervised Automatic Modulation Classification in ZF-MIMO Systems

Yu Wang et al.

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Spatiotemporal Multi-Channel Learning Framework for Automatic Modulation Recognition

Jialang Xu et al.

IEEE WIRELESS COMMUNICATIONS LETTERS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Automatic Modulation Classification Using CNN-LSTM Based Dual-Stream Structure

Zufan Zhang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Novel Deep Learning and Polar Transformation Framework for an Adaptive Automatic Modulation Classification

Pejman Ghasemzadeh et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Novel Attention Cooperative Framework for Automatic Modulation Recognition

Shiyao Chen et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Data Augmentation for Deep Learning-Based Radio Modulation Classification

Liang Huang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

A Learnable Distortion Correction Module for Modulation Recognition

Kumar Yashashwi et al.

IEEE WIRELESS COMMUNICATIONS LETTERS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios

Yu Wang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2019)

添加到收藏夹

Article Computer Science, Information Systems

Spectrum Analysis and Convolutional Neural Network for Automatic Modulation Recognition

Yuan Zeng et al.

IEEE WIRELESS COMMUNICATIONS LETTERS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Convolutional neural network and multi-feature fusion for automatic modulation classification

Hao Wu et al.

ELECTRONICS LETTERS (2019)

添加到收藏夹

Article Engineering, Aerospace

Deep Learning Based Radio-Signal Identification With Hardware Design

Gihan Janith Mendis et al.

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS (2019)

添加到收藏夹

Article Computer Science, Information Systems

Deep Neural Network Compression Technique Towards Efficient Digital Signal Modulation Recognition in Edge Device

Ya Tu et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Information Systems

Particle Swarm Optimization-Based Deep Neural Network for Digital Modulation Recognition

Wenzhe Shi et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Over-the-Air Deep Learning Based Radio Signal Classification

Timothy James O'Shea et al.

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING (2018)

添加到收藏夹

Article Telecommunications

Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors

Sreeraj Ratendran et al.

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING (2018)

添加到收藏夹

Article Telecommunications

k-Sparse Autoencoder-Based Automatic Modulation Classification With Low Complexity

Afan Ali et al.

IEEE COMMUNICATIONS LETTERS (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep Learning

Danshi Wang et al.

IEEE PHOTONICS TECHNOLOGY LETTERS (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Automatic Modulation Classification Using Deep Learning Based on Sparse Autoencoders With Nonnegativity Constraints

Afan Ali et al.

IEEE SIGNAL PROCESSING LETTERS (2017)

添加到收藏夹

Article Engineering, Electrical & Electronic

Online Hybrid Likelihood Based Modulation Classification Using Multiple Sensors

Berkan Dulek

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2017)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Likelihood-Ratio Approaches to Automatic Modulation Classification

Jefferson L. Xu et al.

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS (2011)

添加到收藏夹

Review Engineering, Electrical & Electronic

Survey of automatic modulation classification techniques: classical approaches and new trends

O. A. Dobre et al.

IET COMMUNICATIONS (2007)

添加到收藏夹

Article Engineering, Electrical & Electronic

Blind estimation of MIMO channels with an upper bound for channel orders

YH Zeng et al.

SIGNAL PROCESSING (2006)

添加到收藏夹

Article Engineering, Electrical & Electronic

MIMO transmission over a time-varying channel using SVD

G Lebrun et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2005)

添加到收藏夹

Article Engineering, Electrical & Electronic

Automatic digital modulation recognition using artificial neural network and genetic algorithm

MLD Wong et al.

SIGNAL PROCESSING (2004)

添加到收藏夹

Article Engineering, Electrical & Electronic

Blind estimation and equalization of MIMO channels via multidelay whitening

JK Tugnait et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2001)

添加到收藏夹

Article Engineering, Electrical & Electronic

Maximum-likelihood classification for digital amplitude-phase modulations

W Wei et al.

IEEE TRANSACTIONS ON COMMUNICATIONS (2000)

添加到收藏夹

Article Engineering, Electrical & Electronic

Hierarchical digital modulation classification using cumulants

A Swami et al.

IEEE TRANSACTIONS ON COMMUNICATIONS (2000)

添加到收藏夹

Deep learning based automatic modulation recognition: Models, datasets, and challenges

相关参考文献

导出引文

分享论文