Convolutional Radio Modulation Recognition Networks

O’Shea, Timothy J.; Corgan, Johnathan; Clancy, T. Charles

doi:10.48550/arxiv.1602.04105

Cited by 11 publications

(16 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We build a model which is not prone to trivial parser based security vulnerabilities and we form a model which does not incur cost and complexity to development which scales with the number of specific protocols implemented since they are derived from datasets using a model that generalizes well. We have previously demonstrated [13] that this class of approach using deep neural networks to learn a radio discrimination task on low level modulations can be highly effective, but in this work we show that this potential also spans up the stack to higher layer traffic types as well.…”

Section: Introductionmentioning

confidence: 79%

End-to-end radio traffic sequence recognition with recurrent neural networks

O’Shea

Hitefield²,

Corgan

2016

2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

Self Cite

View full text Add to dashboard Cite

We investigate sequence machine learning techniques on raw radio signal time-series data. By applying deep recurrent neural networks we learn to discriminate between several application layer traffic types on top of a constant envelope modulation without using an expert demodulation algorithm. We show that complex protocol sequences can be learned and used for both classification and generation tasks using this approach.

show abstract

Section: Introductionmentioning

confidence: 79%

End-to-end radio traffic sequence recognition with recurrent neural networks

O’Shea

Hitefield²,

Corgan

2016

2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the application of non-cooperative communication, the receiver does not know the current modulation type, thus it needs to firstly perform modulation recognition, as shown in the dashed box in the Figure 1 . We chose the automatic modulation classification (AMC) module proposed in [ 34 ] to finish the modulation recognition.…”

Section: Communication System Modelmentioning

confidence: 99%

Dual Residual Denoising Autoencoder with Channel Attention Mechanism for Modulation of Signals

Duan

Chen

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Aiming to address the problems of the high bit error rate (BER) of demodulation or low classification accuracy of modulation signals with a low signal-to-noise ratio (SNR), we propose a double-residual denoising autoencoder method with a channel attention mechanism, referred to as DRdA-CA, to improve the SNR of modulation signals. The proposed DRdA-CA consists of an encoding module and a decoding module. A squeeze-and-excitation (SE) ResNet module containing one residual connection is modified and then introduced into the autoencoder as the channel attention mechanism, to better extract the characteristics of the modulation signals and reduce the computational complexity of the model. Moreover, the other residual connection is further added inside the encoding and decoding modules to optimize the network degradation problem, which is beneficial for fully exploiting the multi-level features of modulation signals and improving the reconstruction quality of the signal. The ablation experiments prove that both the improved SE module and dual residual connections in the proposed method play an important role in improving the denoising performance. The subsequent experimental results show that the proposed DRdA-CA significantly improves the SNR values of eight modulation types in the range of −12 dB to 8 dB. Especially for 16QAM and 64QAM, the SNR is improved by 8.38 dB and 8.27 dB on average, respectively. Compared to the DnCNN denoising method, the proposed DRdA-CA makes the average classification accuracy increase by 67.59∼74.94% over the entire SNR range. When it comes to the demodulation, compared with the RLS and the DnCNN denoising algorithms, the proposed denoising method reduces the BER of 16QAM by an average of 63.5% and 40.5%, and reduces the BER of 64QAM by an average of 46.7% and 18.6%. The above results show that the proposed DRdA-CA achieves the optimal noise reduction effect.

show abstract

“…In the case that we do have some expertly labeled data, we can also generate a sparse representation space using discriminative features learned during supervised training. In prior work [14] we trained a convolutional neural network in a purely supervised way to to label examples, but here we leverage this trained network and discard the final softmax layer to keep only high level learned feature maps as sparse representations. The networks used in supervised training and extraction of sparse representation using the learned featuremaps are shown in figure 4 Features formed in this way leverage and distill available expertly curated labels, but in many cases they also generalize and provide a capacity to separate additional classes in feature space which do not have class labels.…”

Section: B Supervised Bootstrapping Of Sparse Representationmentioning

confidence: 99%

“…We recently demonstrated the viability of naive feature learning for supervised radio classification systems [14] which allows for joint feature and classifier learning given labeled datasets and examples. In this case we were able to outperform traditional expert decision statistic based classification in sensitivity and accuracy by a significant margin.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised radio signal identification

O’Shea

West

Vondal

et al. 2017

2017 19th International Conference on Advanced Communication Technology (ICACT)

Self Cite

View full text Add to dashboard Cite

Abstract-Radio emitter recognition in dense multi-user environments is an important tool for optimizing spectrum utilization, identifying and minimizing interference, and enforcing spectrum policy. Radio data is readily available and easy to obtain from an antenna, but labeled and curated data is often scarce making supervised learning strategies difficult and time consuming in practice. We demonstrate that semi-supervised learning techniques can be used to scale learning beyond supervised datasets, allowing for discerning and recalling new radio signals by using sparse signal representations based on both unsupervised and supervised methods for nonlinear feature learning and clustering methods.

show abstract

Convolutional Radio Modulation Recognition Networks

Cited by 11 publications

References 0 publications

End-to-end radio traffic sequence recognition with recurrent neural networks

End-to-end radio traffic sequence recognition with recurrent neural networks

Dual Residual Denoising Autoencoder with Channel Attention Mechanism for Modulation of Signals

Semi-supervised radio signal identification

Contact Info

Product

Resources

About