Over the Air Deep Learning Based Radio Signal Classification

Abstract

We conduct an in depth study on the performance of deep learning based radio signal classification for radio communications signals. We consider a rigorous baseline method using higher order moments and strong boosted gradient tree classification and compare performance between the two approaches across a range of configurations and channel impairments. We consider the effects of carrier frequency offset, symbol rate, and multi-path fading in simulation and conduct over-the-air measurement of radio classification performance in the lab using software radios and compare performance and training strategies for both. Finally we conclude with a discussion of remaining problems, and design considerations for using such techniques.

13 pages, 22 figures

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• WaveNet: A Generative Model for Raw Audio
• Self-Normalizing Neural Networks

Cited by in corpus (90)

• Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey
• Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels
• SR2CNN: Zero-Shot Learning for Signal Recognition
• Fast Deep Learning for Automatic Modulation Classification
• DeepReceiver: A Deep Learning-Based Intelligent Receiver for Wireless Communications in the Physical Layer
• Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing
• Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classification
• Machine Learning for Wireless Link Quality Estimation: A Survey
• Interference Suppression Using Deep Learning: Current Approaches and Open Challenges
• Spatio-Temporal Representation with Deep Neural Recurrent Network in MIMO CSI Feedback
• Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification
• Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification
• AI-Aided Online Adaptive OFDM Receiver: Design and Experimental Results
• Machine Learning Framework for Sensing and Modeling Interference in IoT Frequency Bands
• DeepBeam: Deep Waveform Learning for Coordination-Free Beam Management in mmWave Networks
• Next-generation Wireless Solutions for the Smart Factory, Smart Vehicles, the Smart Grid and Smart Cities
• Transfer Learning for Future Wireless Networks: A Comprehensive Survey
• Hardware realization of the multiply and accumulate operation on radio-frequency signals with magnetic tunnel junctions
• Radio-Frequency Multiply-And-Accumulate Operations with Spintronic Synapses
• Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers
• Calibrating AI Models for Few-Shot Demodulation via Conformal Prediction
• Training Data Augmentation for Deep Learning Radio Frequency Systems
• Microwave signal processing using an analog quantum reservoir computer
• HybNet: A Hybrid Deep Learning -- Matched Filter Approach for IoT Signal Detection
• Automatic Modulation Classification Using Involution Enabled Residual Networks
• The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
• The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications
• Adversarial Examples in RF Deep Learning: Detection of the Attack and its Physical Robustness
• Towards Optimal Power Control via Ensembling Deep Neural Networks
• Multi-task Learning for Radar Signal Characterisation
• Adversarial Machine Learning in Wireless Communications using RF Data: A Review
• Efficient Automatic Modulation Classification for Next-Generation Wireless Networks
• DeepCSI: Rethinking Wi-Fi Radio Fingerprinting Through MU-MIMO CSI Feedback Deep Learning
• Using Capsule Networks to Classify Digitally Modulated Signals with Raw I/Q Data
• Waveform-Defined Security: A Low-Cost Framework for Secure Communications
• Robust Classification of Digitally Modulated Signals Using Capsule Networks and Cyclic Cumulant Features
• On Deep Learning Classification of Digitally Modulated Signals Using Raw I/Q Data
• Data Augmentation for Deep Learning-based Radio Modulation Classification
• Next2You: Robust Copresence Detection Based on Channel State Information
• Classification of Radio Signals and HF Transmission Modes with Deep Learning
• FSOS-AMC: Few-Shot Open-Set Learning for Automatic Modulation Classification Over Multipath Fading Channels
• SafeAMC: Adversarial training for robust modulation recognition models
• Self-supervised Learning for Clustering of Wireless Spectrum Activity
• Robust Deep Sensing Through Transfer Learning in Cognitive Radio
• RL-Based Hyperparameter Selection for Spectrum Sensing With CNNs
• PRONTO: Preamble Overhead Reduction with Neural Networks for Coarse Synchronization
• Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Survey
• A light neural network for modulation detection under impairments
• ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
• Noise-Aware Ensemble Learning for Efficient Radar Modulation Recognition
• Permutation Entropy for Signal Analysis
• Intelligent Radio Signal Processing: A Survey
• Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems
• Real-Time Radio Technology and Modulation Classification via an LSTM Auto-Encoder
• Hacking the Waveform: Generalized Wireless Adversarial Deep Learning
• Adaptive LPD Radar Waveform Design with Generative Deep Learning
• Deep Learning for Cooperative Radio Signal Classification
• Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers
• On the Impact of CDL and TDL Augmentation for RF Fingerprinting under Impaired Channels
• Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments
• Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection
• Big Data Goes Small: Real-Time Spectrum-Driven Embedded Wireless Networking Through Deep Learning in the RF Loop
• Channel Effects on Surrogate Models of Adversarial Attacks against Wireless Signal Classifiers
• A hybrid model-based and learning-based approach for classification using limited number of training samples
• Deep Feature Learning for Wireless Spectrum Data
• Adversarial Attacks with Multiple Antennas Against Deep Learning-Based Modulation Classifiers
• Low-Interception Waveform: To Prevent the Recognition of Spectrum Waveform Modulation via Adversarial Examples
• Chain-Net: Learning Deep Model for Modulation Classification Under Synthetic Channel Impairment
• Spectrum Sensing with Deep Clustering: Label-Free Radio Access Technology Recognition
• Topological Neural Networks over the Air
• A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks
• Gradient-based Adversarial Deep Modulation Classification with Data-driven Subsampling
• The Tags Are Alright: Robust Large-Scale RFID Clone Detection Through Federated Data-Augmented Radio Fingerprinting
• DeepFIR: Addressing the Wireless Channel Action in Physical-Layer Deep Learning
• Visualizing Deep Learning-based Radio Modulation Classifier
• Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification
• Data-Rate Driven Transmission Strategy for Deep Learning Based Communication Systems
• PolymoRF: Polymorphic Wireless Receivers Through Physical-Layer Deep Learning
• Accumulated Polar Feature-based Deep Learning for Efficient and Lightweight Automatic Modulation Classification with Channel Compensation Mechanism
• Model-Driven DNN Decoder for Turbo Codes: Design, Simulation and Experimental Results
• High-Capacity Complex Convolutional Neural Networks For I/Q Modulation Classification
• LinksIQ: Robust and Efficient Modulation Recognition with Imperfect Spectrum Scans
• Wavelet Classification for Over-the-Air Non-Orthogonal Waveforms
• Deep Modulation Recognition with Multiple Receive Antennas: An End-to-end Feature Learning Approach
• Deep Learning for Wireless Communications
• Scaled-Time-Attention Robust Edge Network
• Non-Orthogonal Waveforms in Secure Communications
• Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates
• Resource Constrained Neural Networks for 5G Direction-of-Arrival Estimation in Micro-controllers
• An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and Transformation