Convolutional Radio Modulation Recognition Networks
arXiv:1602.04105
Abstract
We study the adaptation of convolutional neural networks to the complex temporal radio signal domain. We compare the efficacy of radio modulation classification using naively learned features against using expert features which are widely used in the field today and we 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.
References in corpus (1)
Cited by in corpus (20)
- Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
- Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey
- Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial
- The RFML Ecosystem: A Look at the Unique Challenges of Applying Deep Learning to Radio Frequency Applications
- Deep Neural Network Architectures for Modulation Classification
- Deep Architectures for Modulation Recognition
- An Introduction to Deep Learning for the Physical Layer
- Deep Learning for Launching and Mitigating Wireless Jamming Attacks
- Building Encoder and Decoder with Deep Neural Networks: On the Way to Reality
- Unsupervised Representation Learning of Structured Radio Communication Signals
- Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
- End-to-End Radio Traffic Sequence Recognition with Deep Recurrent Neural Networks
- ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworks
- A Deep Learning Framework using Passive WiFi Sensing for Respiration Monitoring
- Application of End-to-End Deep Learning in Wireless Communications Systems
- Fast calculation of correlations in recognition systems
- Deep Neural Networks based Modrec: Some Results with Inter-Symbol Interference and Adversarial Examples
- L0 Regularization Based Neural Network Design and Compression
- End-to-end Learning from Spectrum Data: A Deep Learning approach for Wireless Signal Identification in Spectrum Monitoring applications
- Resource Constrained Neural Networks for 5G Direction-of-Arrival Estimation in Micro-controllers