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-n...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.展开更多
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 ...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.展开更多
With the deepening development of communication technology,the technology of automatic modulation and recognition of communication signals has been more and more widely used in military and civilian fields.This paper ...With the deepening development of communication technology,the technology of automatic modulation and recognition of communication signals has been more and more widely used in military and civilian fields.This paper mainly studies the implementation of automatic modulation recognition using Deep Learning as a computing tool,focusing on CNN neural network and LSTM neural network,and conducting simulation experiments on public data sets.Based on the original CNN neural network,this paper introduces the structure of LSTM neural network and combines the advantages of the two types of neural networks to explore a combined neural network that is superior to the originally used CNN network.The experimental results of this thesis show that introducing the features of dynamic time series modeling of LSTM networks into Deep Learning networks can capture the global and local information of signals more effectively and improve the accuracy of neural networks in automatic modulation recognition.展开更多
Aiming at the problem that the recognition rate of existing Automatic Modulation Recognition(AMR)models needs to be improved under high signal-to-noise ratio conditions,a model consisting of phase transformation,resid...Aiming at the problem that the recognition rate of existing Automatic Modulation Recognition(AMR)models needs to be improved under high signal-to-noise ratio conditions,a model consisting of phase transformation,residual Convolutional Neural Network(CNN)network and bidirectional Long Short-Term Memory(LSTM)network is proposed.First,the DeepSig RadioML 2018.01A dataset is normalized as the model input;the phase parameter is extracted through the phase recognition module,and then the phase is corrected according to the phase parameter;then the spatial features are extracted through the residual CNN network to avoid gradient vanishing and explosion;then the data is passed to the bidirectional LSTM network to extract the bidirectional time series features of the data;finally,the deep neural network is used for classification and recognition.Experimental results show that under high signal-to-noise ratio conditions,the model improves the recognition rate of modulation modes such as 16PSK,and the highest recognition rate and average recognition rate reach 96.79%and 62.13%respectively.Compared with other existing models,the overall optimization of recognition rate and model efficiency is achieved.展开更多
This paper presents work on modulated signal recognition using an artificial neural network （ANN） developed using the Python programme language. The study is basically on the analysis of analog modulated signals. Fo...This paper presents work on modulated signal recognition using an artificial neural network （ANN） developed using the Python programme language. The study is basically on the analysis of analog modulated signals. Four of the best-known analog modulation types are considered namely： amplitude modulation （AM）, double sideband （DSB） modulation, single sideband （SSB） modulation and frequency modulation （FM）. Computer simulations of the four modulated signals are carried out using MATLAB. MATLAB code is used in simulating the analog signals as well as the power spectral density of each of the analog modulated signals. In achieving an accurate classification of each of the modulated signals, extensive simulations are performed for the training of the artificial neural network. The results of the study show accurate and correct performance of the developed automatic modulation recognition with average success rate above 99.5%.展开更多
Automatic modulation recognition plays a critical role in both civilian and military communication systems.While traditional approaches rely on manual feature extraction with limited accuracy,deep learning methods off...Automatic modulation recognition plays a critical role in both civilian and military communication systems.While traditional approaches rely on manual feature extraction with limited accuracy,deep learning methods offer promising alternatives for this pattern recognition task.This paper presents a systematic performance evaluation of classical deep lea rning models for automatic modulation classification,aiming to establish baseline references for future research.Through comparat ive experiments using the RadioML2018.01a dataset containing 24 modulation types across Signal-to-Noise Ratio(SNR)levels from-20dB to 20dB,we demonstrate that modulation signals exhibit multidimensional characteristics with temporal dependencies.Our analysis reveals that the proposed Multi-Scale Contextual Attention Network(MCNet)outperforms conventional Convolutional Neural Network(CNN)and Residual Network(ResNet)architectures,achieving 82.39%accuracy at high SNR conditions.The network's superior performance stems from its ability to extract multiscale spatiotemporal featur es through parallel asymmetric convolutions,preserve signal correlations via attention mechanisms,and maintain computational efficiency through optimized layer configurations.These findings provide two key contributions:quantitative benchmarks for model selection in practical implementations,and architectural insights for developing next-generation recognition systems.The study particularly highlights MCNet's robustness in processing high-order Quadrature Amplitude Modulation/Phase Shift Keying(QAM/PSK)modulations,though challenges remain for low-SNR scenarios.展开更多
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 c...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.展开更多
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation 2022M720419 to provide fund for conducting experiments。
文摘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.
基金National Natural Science Foundation of China under Grant No.61973037China Postdoctoral Science Foundation under Grant No.2022M720419。
文摘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.
文摘With the deepening development of communication technology,the technology of automatic modulation and recognition of communication signals has been more and more widely used in military and civilian fields.This paper mainly studies the implementation of automatic modulation recognition using Deep Learning as a computing tool,focusing on CNN neural network and LSTM neural network,and conducting simulation experiments on public data sets.Based on the original CNN neural network,this paper introduces the structure of LSTM neural network and combines the advantages of the two types of neural networks to explore a combined neural network that is superior to the originally used CNN network.The experimental results of this thesis show that introducing the features of dynamic time series modeling of LSTM networks into Deep Learning networks can capture the global and local information of signals more effectively and improve the accuracy of neural networks in automatic modulation recognition.
文摘Aiming at the problem that the recognition rate of existing Automatic Modulation Recognition(AMR)models needs to be improved under high signal-to-noise ratio conditions,a model consisting of phase transformation,residual Convolutional Neural Network(CNN)network and bidirectional Long Short-Term Memory(LSTM)network is proposed.First,the DeepSig RadioML 2018.01A dataset is normalized as the model input;the phase parameter is extracted through the phase recognition module,and then the phase is corrected according to the phase parameter;then the spatial features are extracted through the residual CNN network to avoid gradient vanishing and explosion;then the data is passed to the bidirectional LSTM network to extract the bidirectional time series features of the data;finally,the deep neural network is used for classification and recognition.Experimental results show that under high signal-to-noise ratio conditions,the model improves the recognition rate of modulation modes such as 16PSK,and the highest recognition rate and average recognition rate reach 96.79%and 62.13%respectively.Compared with other existing models,the overall optimization of recognition rate and model efficiency is achieved.
文摘This paper presents work on modulated signal recognition using an artificial neural network （ANN） developed using the Python programme language. The study is basically on the analysis of analog modulated signals. Four of the best-known analog modulation types are considered namely： amplitude modulation （AM）, double sideband （DSB） modulation, single sideband （SSB） modulation and frequency modulation （FM）. Computer simulations of the four modulated signals are carried out using MATLAB. MATLAB code is used in simulating the analog signals as well as the power spectral density of each of the analog modulated signals. In achieving an accurate classification of each of the modulated signals, extensive simulations are performed for the training of the artificial neural network. The results of the study show accurate and correct performance of the developed automatic modulation recognition with average success rate above 99.5%.
文摘Automatic modulation recognition plays a critical role in both civilian and military communication systems.While traditional approaches rely on manual feature extraction with limited accuracy,deep learning methods offer promising alternatives for this pattern recognition task.This paper presents a systematic performance evaluation of classical deep lea rning models for automatic modulation classification,aiming to establish baseline references for future research.Through comparat ive experiments using the RadioML2018.01a dataset containing 24 modulation types across Signal-to-Noise Ratio(SNR)levels from-20dB to 20dB,we demonstrate that modulation signals exhibit multidimensional characteristics with temporal dependencies.Our analysis reveals that the proposed Multi-Scale Contextual Attention Network(MCNet)outperforms conventional Convolutional Neural Network(CNN)and Residual Network(ResNet)architectures,achieving 82.39%accuracy at high SNR conditions.The network's superior performance stems from its ability to extract multiscale spatiotemporal featur es through parallel asymmetric convolutions,preserve signal correlations via attention mechanisms,and maintain computational efficiency through optimized layer configurations.These findings provide two key contributions:quantitative benchmarks for model selection in practical implementations,and architectural insights for developing next-generation recognition systems.The study particularly highlights MCNet's robustness in processing high-order Quadrature Amplitude Modulation/Phase Shift Keying(QAM/PSK)modulations,though challenges remain for low-SNR scenarios.
基金Supported by the National Natural Science Foundation of China (61001111)
文摘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.
