Spectrogram-Based Automatic Modulation Recognition Using Convolutional Neural Network

Jeong, Sinjin; Lee, Uhyeon; Kim, Suk Chan

doi:10.1109/icufn.2018.8436654

Cited by 24 publications

(13 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, these kinds of DNNs have been shown, as indicated in Section 2.2, to perform well in other related tasks such as modulation recognition. These models work either directly with raw spectrum data as input (e.g., IQ or Fast Fourier transform (FFT) samples) or with image representations of that raw spectrum data 23,21 .…”

Section: Convolutional Neural Network For Traffic Recognitionmentioning

confidence: 99%

Traffic classification at the radio spectrum level using deep learning models trained with synthetic data

et al. 2020

View full text Add to dashboard Cite

Traffic recognition is commonly done using Deep Packet Inspection or packet-based approaches. However, these methods require the listening device to be part of the network and raise privacy concerns. Traffic recognition models that operate directly at the spectrum level could, for instance, be used for smart spectrum management.To this extent, we present such an approach using deep learning methods. In particular, we present a Convolutional Neural Network architecture that forms the basis for prediction models to recognize different transport protocols, burst traffic with different duty cycles, and different transmission rates. These models are trained with pure synthetic data to lighten the burden of data collection. As such, we validate recent successes in the area of robotics in the context of wireless networks. We compare the performance of two different datasets that contain spectrum images in either time or time-frequency domain. Our evaluation shows that using time-domain data results in an accuracy of at least 96 % across all models. Time-frequency information improves this accuracy even further. Furthermore, a validation with real-life data shows that it is still possible to discriminate between different transmission rates with an accuracy of around 87 %, while the detection of duty cycles and transport protocols takes place with accuracies of, respectively, around 73 and 78 %. Finally, we also present a small-scale real-life prototype.

show abstract

Section: Convolutional Neural Network For Traffic Recognitionmentioning

confidence: 99%

Traffic classification at the radio spectrum level using deep learning models trained with synthetic data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It usually consists of a feature extractor and a classifier. For the feature extractor, some specific features from the received signal are extracted, such as instantaneous amplitude, phase and frequency [11]- [13], higher order cumulants [14], [15], cyclostationary features such as the spectral correlation function [16]- [18], shorttime Fourier transform [19]- [21], and constellation diagram (CD) [22], [23], etc. For the classifier, the extracted feature is then classified into different modulation formats.…”

Section: Introduction a Motivation And Backgroundmentioning

confidence: 99%

Automatic Modulation Classification in Time-Varying Channels Based on Deep Learning

2020

View full text Add to dashboard Cite

Automatic modulation classification (AMC) is an important technology in military signal reconnaissance and civilian communications such as cognitive radios. Most of the existing works focused on the AMC in additional white Gaussian noise channels, but the AMC in time-varying wireless channels is more practical and challenging. In this paper, we investigate the AMC in time-varying channels by using the deep learning method for high classification accuracy. Specifically, we take the modulation constellation diagram (CD) as the key feature and propose a slotted constellation diagram (slotted-CD) scheme in order to extract the feature of the time-evolution of the CD due to channel variation. We then develop an advanced neural network for modulation classification, where the output sub-images from the slotted-CD feature extractor are first processed separately by a number of parallel convolutional neural networks and then further processed by a recurrent neural network for exploring their time relationship. Experimental results show that the proposed AMC scheme achieves higher classification accuracy in both slow and fast fading channels when compared with the traditional deep learning based AMC schemes. Such performance improvement can be clearly illustrated by visualizing the outputs of the convolutional layers of the classifier. We also show that visualization can help optimize the parameters of the AMC neural networks.INDEX TERMS Automatic modulation classification, Constellation diagram, Time-varying, Convolutional neural network, Bidirectional long short-term memory network.

show abstract

“…The authors of [9], [10] started using supervised learning for AMC in 2016 firstly, they used convolution neural network (CNN) to construct an end-to-end learning model, and successfully identified 11 digital signals with different modulations, including Wide Band Frequency Modulation (WBFM), Double Side Band (DSB), Binary Phase Shift Keying (BPSK) and 16 Quadrature Amplitude Modulation (QAM). In [11], Short time Fourier transform (STFT) is utilized to convert signals from time domain to time-frequency domain, and then CNN is used to extract the time-frequency features. The experiment shows that several kinds of modulation types including 2 Frequency Shift Keying (FSK), 4FSK and 8FSK can be classified with an accuracy rate more than 90% even when the signal to noise ratio (SNR) is low to -4dB.…”

Section: Introductionmentioning

confidence: 99%

Few-Shot Modulation Classification Method Based on Feature Dimension Reduction and Pseudo-Label Training

Shi

Jiang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

In modulation classification domain, handcrafted feature based method can fit well from a few labeled samples, while deep learning based method require a large amount of samples to achieve the superior classification performance. In order to improve the modulation classification accuracy under the constraint of limited labeled samples, this paper proposes a few-shot modulation classification method based on feature dimension reduction and pseudo-label training (FDRPLT), which combines handcrafted feature based method with deep learning based method. First, an optimal low-dimensional feature subset is created by the combination of the handcrafted features and autoencoder-extracted features post-processed by a feature selection algorithm. Then, a fully connected network (FCN), trained on a small number of labeled signals, is designed for the automated annotating, where unlabeled samples can be annotated and used for the later convolution neural network (CNN) training. The simulation results show that the classification accuracy of eight kinds of modulation types can reach to 98.3% when the SNR is 20dB.

show abstract

Spectrogram-Based Automatic Modulation Recognition Using Convolutional Neural Network

Cited by 24 publications

References 2 publications

Traffic classification at the radio spectrum level using deep learning models trained with synthetic data

Traffic classification at the radio spectrum level using deep learning models trained with synthetic data

Automatic Modulation Classification in Time-Varying Channels Based on Deep Learning

Few-Shot Modulation Classification Method Based on Feature Dimension Reduction and Pseudo-Label Training

Contact Info

Product

Resources

About