Automatic modulation recognition of radiation source signals based on two-dimensional data matrix and improved residual neural network

Automatic modulation recognition(AMR)of radiation source signals is a research focus in the field of cognitive radio.However,the AMR of radiation source signals at low SNRs still faces a great challenge.Therefore,the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper.First,the time series of the radiation source signals are reconstructed into two-dimensional data matrix,which greatly simplifies the signal preprocessing process.Second,the depthwise convolution and large-size convolutional kernels based residual neural network(DLRNet)is proposed to improve the feature extraction capability of the AMR model.Finally,the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type.Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method.The recognition accuracy of the proposed method maintains a high level greater than 90% even at -14 dB SNR.

Automatic modulation recognition of radio fuzes using a DR2D-based adaptive denoising method and textural feature extraction

The identification of intercepted radio fuze modulation types is a prerequisite for decision-making in interference systems.However,the electromagnetic environment of modern battlefields is complex,and the signal-to-noise ratio(SNR)of such environments is usually low,which makes it difficult to implement accurate recognition of radio fuzes.To solve the above problem,a radio fuze automatic modulation recognition(AMR)method for low-SNR environments is proposed.First,an adaptive denoising algorithm based on data rearrangement and the two-dimensional(2D)fast Fourier transform(FFT)(DR2D)is used to reduce the noise of the intercepted radio fuze intermediate frequency(IF)signal.Then,the textural features of the denoised IF signal rearranged data matrix are extracted from the statistical indicator vectors of gray-level cooccurrence matrices(GLCMs),and support vector machines(SVMs)are used for classification.The DR2D-based adaptive denoising algorithm achieves an average correlation coefficient of more than 0.76 for ten fuze types under SNRs of-10 d B and above,which is higher than that of other typical algorithms.The trained SVM classification model achieves an average recognition accuracy of more than 96%on seven modulation types and recognition accuracies of more than 94%on each modulation type under SNRs of-12 d B and above,which represents a good AMR performance of radio fuzes under low SNRs.

Intelligent Modulation Recognition of Communication Signal for Next-Generation 6G Networks

In recent years,the need for a fast,efficient and a reliable wireless network has increased dramatically.Numerous 5G networks have already been tested while a few are in the early stages of deployment.In noncooperative communication scenarios,the recognition of digital signal modulations assists people in identifying the communication targets and ensures an effective management over them.The recent advancements in both Machine Learning(ML)and Deep Learning(DL)models demand the development of effective modulation recognition models with self-learning capability.In this background,the current research article designs aDeep Learning enabled Intelligent Modulation Recognition of Communication Signal(DLIMR-CS)technique for next-generation networks.The aim of the proposed DLIMR-CS technique is to classify different kinds of digitally-modulated signals.In addition,the fractal feature extraction process is appliedwith the help of the Sevcik Fractal Dimension(SFD)approach.Then,the extracted features are fed into the Deep Variational Autoencoder(DVAE)model for the classification of the modulated signals.In order to improve the classification performance of the DVAE model,the Tunicate Swarm Algorithm(TSA)is used to finetune the hyperparameters involved in DVAE model.A wide range of simulations was conducted to establish the enhanced performance of the proposed DLIMR-CS model.The experimental outcomes confirmed the superior recognition rate of the DLIMR-CS model over recent state-of-the-art methods under different evaluation parameters.

Modulation Recognition with Frequency Offset and Phase Offset over Multipath Channels

Modulation recognition becomes unreliable at low signal-to-noise ratio(SNR)over fading channel.A novel method is proposed to recognize the digital modulated signals with frequency and phase offsets over multi-path fading channels in this paper.This method can overcome the effects of phase offset,Gaussian noise and multi-path fading.To achieve this,firstly,the characteristic parameters search is constructed based on the cyclostationarity of received signals,to overcome the phase offset,Gaussian white noise,and influence caused by multi-path fading.Then,the carrier frequency of the received signal is estimated,and the maximum characteristic parameter is searched around the integer multiple carriers and their vicinities.Finally,the modulation types of the received signal with frequency and phase offsets are classified using decision thresholds.Simulation results demonstrate that the performance of the proposed method is better than the traditional methods when SNR is over 5dB,and that the proposed method is robust to frequency and phase offsets over multipath channels.

Automatic Modulation Recognition Based on CNN and GRU

Based on a comparative analysis of the Long Short-Term Memory(LSTM)and Gated Recurrent Unit(GRU)networks,we optimize the structure of the GRU network and propose a new modulation recognition method based on feature extraction and a deep learning algorithm.High-order cumulant,Signal-to-Noise Ratio(SNR),instantaneous feature,and the cyclic spectrum of signals are extracted firstly,and then input into the Convolutional Neural Network(CNN)and the parallel network of GRU for recognition.Eight modulation modes of communication signals are recognized automatically.Simulation results show that the proposed method can achieve high recognition rate at low SNR.

Modulation Recognition of Radio Signals Based on Edge Computing and Convolutional Neural Network

Software defined radio(SDR)is a wireless communication technology that uses modern software to control the traditional“pure hardware circuit”.It can provide an effective and secure solution to the problem of building multi-mode,multi-frequency and multifunction wireless communication equipment.Although the concept and application of SDR have been studied a lot,there is little discussion about the operating efficiency of the established system.For the purpose of shortening the delay of mapping and reducing the high computing load in the cloud,a radio monitoring system based on edge computing is developed to achieve the flexible,extensible and real-time monitoring of high-performance SDR applications.To promote the edge intelligence of deep learning(DL)service deployment through edge computing(EC),we developed an edge intelligence algorithm of convolutional neural network(CNN)based on attention mechanism to carry out modulation recognition(MR)of the edge signal and make MR closer to the antenna terminal.Through the experiment of the system and the edge algorithm,this thesis verifies the effectiveness of the developed multifunction radio signal monitoring system.

Recognition Analysis and Simulation Implementation Based on High-Order Cumulants of Wireless Digital Modulation Mode

This paper mainly studies the data characteristics of high order cumulants using digitally modulated signals, and constructs the identification feature parameters that can distinguish the signal modulation type by the high-order cumulants data of the digital modulation signal. Set the identification signal modulation type determination threshold based on the value of the identification feature parameter. The identification feature parameter value of the signal modulation type is compared with the set determination threshold, to realize the recognition of digital modulation signal. This identification method is implemented based on MATLAB design, with a 2ASK (2-ary Amplitude Shift Keying) signal, 4ASK (4-ary Amplitude Shift Keying) signal, 2PSK (2-ary Phase Shift Keying) signal, 4PSK (4-ary Phase Shift Keying) signal, 2FSK (2-ary Frequency Shift Keying) signal, 4FSK (4-ary Frequency Shift Keying) signal. The second, fourth and sixth order cumulants of the six signals were analyzed. Calculate the selected identification feature parameter value and the determination threshold to identify the six signals. The six signals have made MATLAB identification simulation. Simulation results show that this method is feasible and has high recognition rate. Simulation results verify that such recognition methods maintain a high recognition rate under conditions with low signal-to-noise ratio. This identification method can be extended to more MASK (M-ary Amplitude Shift Keying), MPSK (M-ary Phase Shift Keying), MFSK (M-ary Frequency Shift Keying), MQAM (M-ary Quadrature Amplitude Modulation) signal identification.

Study on fractal features of modulation signals

Based on fractal theory, the note presents a novel method of modulation signals classification that adopts box dimension and information dimension extracted from received signals as features of classification. These features contain the characteristics of magnitude, frequency and phase of signals, and collect discriminatory information among various modulation modes. They are effective features in classification sense, and are insensitive to noises interfering. The theoretical analysis also proves the above conclusion. The classifier design is very simple based on such features. The simulation results show that the performances of signal classification are superior.

An Improved Algorithm for Blind Carrier Frequency Estimation with Burst MPSK Transmissions

This paper presents an improved non-data-aided algo-rithm for carrier frequency estimation for burst M-ary PSK signals when modulation order M and training symbols are unknown. Unlike data-aided estimation, a phase clustering algorithm is used first to estimate M and modulated information is removed by a vari-able interval linear phase unwrapping. Then, a high-order correlation algorithm with proper correction is present, which reduces the probability of phase ambiguity and promotes anti-noise capability of the estimation. Simulations are given to analyze the unbiased esti-mation range, and the asymptotic performance and symbol number are needed to compare with the former algorithms. The new algo-rithm has a large estimation range close to the theoretical maximum value for non-data-aided estimation and has a better performance than earlier non-data-aided techniques for large frequency offset, low signal-to-noise ratio, and limited symbol numbers.