Automatic Digital Modulation Recognition Based on Machine Learning Algorithms

Ansari, Sam; Alnajjar, Khawla A.; Abdallah, Saeed; Saad, Mohamed

doi:10.1109/ccci49893.2020.9256809

Cited by 11 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their study concentrated on phase-shift keying, quadrature phase-shift keying, amplitude shift keying, frequency-shift keying, quadrature amplitude shift keying, frequency-shift keying, quadrature and 12 quadrature amplitude modulation, among other types of digital modulations (Marzuki et al, 2014). The authors of the paper (Ansari et al, 2020;Jajoo et al, 2017) proposed a modulation recognition and separation method by choosing useful features from the modulated signal for identifying the modulation type using a decision tree and probabilistic neural network methods. They were conducted using MATLAB simulations with a signal-tonoise ratio over an additive white Gaussian noise channel.…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Digital Signal Modulation Recognition using Machine Learning

Mala¹,

Aminifar²

2022

Journal of Computer Science

View full text Add to dashboard Cite

In recent years, modulation type recognition has received a lot of attention across the board. There are several methods to detect modulation types, but there are only a few effective methods to handle signals with a higher level of noise. This study introduces an approach to verify the ability of different machine learning algorithms to automatically manage noise in detecting digital modulations. This research examines two of the most common digital modulations, Phase Shift Keying and Quadrature Phase Shift Keying. A signal noise rate ranging from-10 to +25 dB is used to identify these modulations and use PCA to reduce the number of features and the data complexity. We used machine learning algorithms like Decision Tree, Random Forest, Support Vectors Machine and k-nearest neighbors to identify the modulation type. Our proposed method considers signals' features after proper shifting of the IQ and RF signals samples. The findings show that the proposed method successfully recognizes the signals with higher noise levels. The random forest algorithm presents better results with low noise levels and SVM with higher noise levels.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Digital Signal Modulation Recognition using Machine Learning

Mala¹,

Aminifar²

2022

Journal of Computer Science

View full text Add to dashboard Cite

show abstract

“…In recent years, machine learning (ML) has been applied in the field of signal processing, including signal modulation pattern recognition [13][14][15][16], CRS individual recognition [17][18][19], communication specific signal type recognition [20,21], and other fields, and a series of achievements have been achieved. However, research on CRS behavior recognition is still in the beginning stage.…”

Section: Introductionmentioning

confidence: 99%

Identification of Shortwave Radio Communication Behavior Based on Autocorrelation Spectrogram Features

Chen

Lei

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Cognitive communication behavior is becoming a research hotspot in the field of communication confrontation. In theory, the behavioral intention of noncooperating parties can be obtained by analyzing communication signals. Considering the complexity of the actual electromagnetic environment, even when the signal-to-noise ratio (SNR) is low, a certain accuracy still needs to be guaranteed. In this paper, according to five types of physical burst waveforms defined by the shortwave radio interoperability standard, a signal feature extraction method based on autocorrelation spectrogram features is proposed, and a two-input convolutional neural network (CNN) for classification is designed to improve the identification ability of shortwave communication behavior. The experimental results illustrate that the five kinds of shortwave radio communication behaviors can be accurately identified even when the noise is large. The research in this paper can directly analyze the communication behavior through physical layer signal without demodulation, which has the ability to grasp the communication behavior of the shortwave radio station in real time.

show abstract

“…Although the method based on likelihood estimation can classify modulation types well, it requires a large number of experimental samples to effectively identify the modulation type in the unknown channel, with excessive computational complexity. Traditional feature-based methods pay more attention to extracting expert feature, and combine with pattern recognition algorithm [9] to classify the extracted expert features. However, because feature-based approaches rely heavily on expert experience, it performs well only in specific environments and is hardly to extend to other modulation types.…”

Section: Introductionmentioning

confidence: 99%

Dual-Channel Hybrid Neural Network for Modulation Recognition

et al. 2021

View full text Add to dashboard Cite

In the blind recognition of wireless communication modulation based on deep learning, how to further improve the recognition accuracy has become a key research issue. In this work, we propose a dual-channel hybrid model termed as CLDR (convolutional long short-term deep neural and residual network). The CLDR consists of the convolutional long short-term deep neural network (CLDNN) and the residual network (ResNet), where CLDNN is to reduce the variations in the spectrum and time, ResNet is to avoid gradient vanishing or exploding. In addition, we design an exponential curve decay adaptive cyclical learning rate method to decrease the training time cost of the neural network model. This method eliminates the need to experimentally search the optimal learning rate as with the fixed learning rate policy. It also avoids the slow convergence of the model due to the excessive attenuation amplitude as with the triangular learning rate policy. We test the feasibility of the CLDR model and discuss the influence of the exponential decay cyclical learning rate on the training of CLDR model based on the RadioML2016.10b public dataset. Simulation results show that the CLDR model yields a recognition accuracy of 93.1% at high SNRs, which effectively reduces the influence of external environment such as noise and fading on recognition accuracy. The training time cost of CLDR using exponential cyclical learning rate is reduced by 14.6% and 32.1% compared with triangular and fixed methods. Therefore, the exponential cyclical learning rate policy effectively reduces the training time cost of the model in the same classification accuracy. INDEX TERMSDeep neural network, Residual network, Cyclical learning rate, Modulation recognition.

show abstract

Automatic Digital Modulation Recognition Based on Machine Learning Algorithms

Cited by 11 publications

References 23 publications

Intelligent Digital Signal Modulation Recognition using Machine Learning

Intelligent Digital Signal Modulation Recognition using Machine Learning

Identification of Shortwave Radio Communication Behavior Based on Autocorrelation Spectrogram Features

Dual-Channel Hybrid Neural Network for Modulation Recognition

Contact Info

Product

Resources

About