Fast Deep Learning for Automatic Modulation Classification

Abstract

In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a GNU radio-based data set that mimics the imperfections in a real wireless channel and uses 10 different modulation types. A Convolutional Neural Network (CNN) architecture was then developed and shown to achieve performance that exceeds that of expert-based approaches. Here, we continue this line of work and investigate deep neural network architectures that deliver high classification accuracy. We identify three architectures - namely, a Convolutional Long Short-term Deep Neural Network (CLDNN), a Long Short-Term Memory neural network (LSTM), and a deep Residual Network (ResNet) - that lead to typical classification accuracy values around 90% at high SNR. We then study algorithms to reduce the training time by minimizing the size of the training data set, while incurring a minimal loss in classification accuracy. To this end, we demonstrate the performance of Principal Component Analysis in significantly reducing the training time, while maintaining good performance at low SNR. We also investigate subsampling techniques that further reduce the training time, and pave the way for online classification at high SNR. Finally, we identify representative SNR values for training each of the candidate architectures, and consequently, realize drastic reductions of the training time, with negligible loss in classification accuracy.

29 pages, 30 figures, submitted to Journal on Selected Areas in Communications - Special Issue on Machine Learning in Wireless Communications

References in corpus (1)

• Over the Air Deep Learning Based Radio Signal Classification

Cited by in corpus (18)

• Robust and Fast Automatic Modulation Classification with CNN under Multipath Fading Channels
• Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classification
• Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification
• Distributed Learning in Wireless Networks: Recent Progress and Future Challenges
• Data Augmentation for Deep Learning-based Radio Modulation Classification
• A light neural network for modulation detection under impairments
• Deep Learning for Cooperative Radio Signal Classification
• Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems
• Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection
• Efficient Wrapper Feature Selection using Autoencoder and Model Based Elimination
• Hybrid HMM Decoder For Convolutional Codes By Joint Trellis-Like Structure and Channel Prior
• Autoregressive Belief Propagation for Decoding Block Codes
• Gradient-based Adversarial Deep Modulation Classification with Data-driven Subsampling
• A Novel Automatic Modulation Classification Scheme Based on Multi-Scale Networks
• Visualizing Deep Learning-based Radio Modulation Classifier
• Data-Driven Modulation and Antenna Classification of Wireless Digital Communication Signals
• Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates
• High-Capacity Complex Convolutional Neural Networks For I/Q Modulation Classification