A light neural network for modulation detection under impairments (2020-03-27T00:00:00.000000Z)

TL;DR

A neural network architecture able to efficiently detect modulation scheme in a portion of I/Q signals that is lighter by up to two orders of magnitude than other state-of-the-art architectures working on the same or similar tasks and results in a signal-length invariant network.

Abstract

We present a neural network architecture able to efficiently detect modulation scheme in a portion of I/Q signals. This network is lighter by up to two orders of magnitude than other state-of-the-art architectures working on the same or similar tasks. Moreover, the number of parameters does not depend on the signal duration, which allows processing stream of data, and results in a signal-length invariant network. In addition, we have generated a dataset based on the simulation of impairments that the propagation channel and the demodulator can bring to recorded I/Q signals: random phase shifts, delays, roll-off, sampling rates, and frequency offsets. We benefit from this dataset to train our neural network to be invariant to impairments and quantify its accuracy at disentangling between modulations under realistic real-life conditions. Data and code to reproduce the results are made publicly available.

Authors

Thomas Courtat

1 papers

Hélion Marie du Mas des Bourboux

1 papers

References29 items

Accumulated Polar Feature based Deep Learning with Channel Compensation Mechanism for Efficient Automatic Modulation Classification under Time varying Channels

TL;DR

Abstract

Authors

References29 items

Accumulated Polar Feature based Deep Learning with Channel Compensation Mechanism for Efficient Automatic Modulation Classification under Time varying Channels

Data Augmentation for Deep Learning-Based Radio Modulation Classification

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels

Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments

Fast Deep Learning for Automatic Modulation Classification

ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks

Robustness of Deep Modulation Recognition under AWGN and Rician Fading

Adversarial Attacks on Deep-Learning Based Radio Signal Classification

Over-the-Air Deep Learning Based Radio Signal Classification

Radio Machine Learning Dataset Generation with GNU Radio

Unsupervised representation learning of structured radio communication signals

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Convolutional Radio Modulation Recognition Networks

Deep Residual Learning for Image Recognition

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Adam: A Method for Stochastic Optimization

Very Deep Convolutional Networks for Large-Scale Image Recognition

Network In Network

Deep Sparse Rectifier Neural Networks

Understanding the difficulty of training deep feedforward neural networks

Curriculum learning

GNU radio: tools for exploring the radio frequency spectrum

Finite State Automata and Simple Recurrent Networks

Learning State Space Trajectories in Recurrent Neural Networks

Dropout: a simple way to prevent neural networks from overfitting

Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters

Handwritten Digit Recognition with a Back-Propagation Network

Keras

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names