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.

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.

Radar Signal Intra-Pulse Modulation Recognition Based on Deep Residual Network

In view of low recognition rate of complex radar intra-pulse modulation signal type by traditional methods under low signal-to-noise ratio(SNR),the paper proposes an automatic recog-nition method of complex radar intra-pulse modulation signal type based on deep residual network.The basic principle of the recognition method is to obtain the transformation relationship between the time and frequency of complex radar intra-pulse modulation signal through short-time Fourier transform(STFT),and then design an appropriate deep residual network to extract the features of the time-frequency map and complete a variety of complex intra-pulse modulation signal type recognition.In addition,in order to improve the generalization ability of the proposed method,label smoothing and L2 regularization are introduced.The simulation results show that the proposed method has a recognition accuracy of more than 95%for complex radar intra-pulse modulation sig-nal types under low SNR(2 dB).

Automatic Recognition Algorithm of AM Signals Based on Spectrum and Modulation Characters

To meet the actual requirement of automatic monitoring of the shortwave signals under wide band ranges, a technique for automatic recognition is studied in this paper. And basing upon the spectrum and modulation characters of amplitude modulation （AM） signals, an automatic recognition scheme for AM signals is proposed. The proposed scheme is achieved by a joint judgment with four different characteristic parameters. Experiment results indicate that the proposed scheme can effectively recognize AM signals in practice.

Automatic Recognition of Analog Modulated Signals Using Artificial Neural Networks

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%.

Investigation on Analog and Digital Modulations Recognition Using Machine Learning Algorithms

In the field of radiocommunication, modulation type identification is one of the most important characteristics in signal processing. This study aims to implement a modulation recognition system on two approaches to machine learning techniques, the K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN). From a statistical and spectral analysis of signals, nine key differentiation features are extracted and used as input vectors for each trained model. The feature extraction is performed by using the Hilbert transform, the forward and inverse Fourier transforms. The experiments with the AMC Master dataset classify ten (10) types of analog and digital modulations. AM_DSB_FC, AM_DSB_SC, AM_USB, AM_LSB, FM, MPSK, 2PSK, MASK, 2ASK, MQAM are put forward in this article. For the simulation of the chosen model, signals are polluted by the Additive White Gaussian Noise (AWGN). The simulation results show that the best identification rate is the MLP neuronal method with 90.5% of accuracy after 10 dB signal-to-noise ratio value, with a shift of more than 15% from the k-nearest neighbors’ algorithm.

基于生成式对抗网络和多模态注意力机制的扩频与常规调制信号识别方法

针对低信噪比条件下的扩频与常规调制信号分类精度低的问题,该文提出一种基于生成式对抗网络(GAN)、卷积神经网络(CNN)和长短期记忆(LSTM)网络的多模态注意力机制信号调制识别方法。首先生成待识别信号的时频图像(TFIs),并利用GAN实现TFIs降噪处理;然后将信号的同相正交数据(I/Q data)与TFIs作为模型输入,并搭建基于CNN的TFIs识别支路和基于LSTM的I/Q数据识别支路;最后,在模型中添加注意力机制,增强I/Q数据和TFIs中重要特征对分类结果的决定作用。实验结果表明,该文所提方法相较于单模态识别模型以及其它基线模型,整体分类精度有效提升2%~7%,并在低信噪比条件下具备更强的特征表达能力和鲁棒性。

基于可微分架构搜索的多载波信号自动调制识别

针对城市多径信道下缺乏多载波信号通用数据集,以及传统信号特征与网络模型难以有效识别低信噪比下失真信号调制类型的问题,提出一种基于可微分架构搜索的多载波信号自动调制识别算法。首先,产生了常见OFDM、FBMC与OTFS多载波信号经过典型城市多径信道的接收信号数据集,选取对调制参数不敏感的信号时频图作为特征向量来训练神经网络;其次,采用可微分架构搜索方法自动搜索最佳网络结构,避免了网络结构设计的反复验证工作;最后,在特征学习过程中引入联合注意力机制,将失真信号特征进行空间转换以降低多径干扰影响,同时计算特征图各通道信息权重并排序,以提升相关特征图通道的分类效果。仿真结果表明,所提算法不仅能提升在城市多径信道环境下尤其是低信噪比时的识别正确率,而且对调制参数变化和小样本场景具有更好的鲁棒性。

基于高效双流输入结构的自动调制识别方法

自动调制识别是现代通信系统中一项重要技术。为提高通信系统对不同调制信号间的识别性能,文中首先探索了包含11类调制信号的公开数据集RML2016.10A上原始同相正交(In-phase and Quadrature,IQ)格式数据和经过数据预处理后的幅度和相位(Amplitude and Phase,AP)格式数据的差异;随后,依据原始IQ格式数据和AP格式数据在特征提取过程中对局部相关性及时序特征敏感性的差异,设计了针对空间特征提取的SFE-Block模块、针对长期依赖关系提取的TFE-Block模块,以及联合时空特征提取模块STFE-Block,并将前两者的输出特征作为STFE-Block模块输出特征的重要补充进行特征融合,以全连接(Fully Connected)层负责最终分类。实验结果表明,本模型在数据集RML2016.10A上表现良好。当信噪比(Signal to Noise Ratio,SNR)低于-8 dB时,平均识别精度比其他模型提升7%,而SNR在0~18 dB时,平均识别精度比其他模型提高1%~8%,且在SNR为16 dB时,最高识别精度达92.95%。此外,在RML2016.10B数据集上重复了实验以检验模型泛化性,所得结果同样最优,且当SNR为12 dB时,最高识别精度达到93.6%。

基于时频融合的深度学习调制识别算法

自动调制识别(Automatic Modulation Recognition,AMR)能够在缺少先验信息的条件下,识别出接收信号的调制类型,在非合作通信中起着至关重要的作用。为提高调制识别的准确率,提出了一种基于时频融合的深度学习调制识别算法。该算法将调制信号的时频图作为网络的输入,使用一维卷积分别提取信号的时频特征,并通过计算时频维度上的权重来突出重要的时频信息,使网络学习到更具区分度的时频特征。为了充分利用时频特征之间的互补性和相关性,使用了基于压缩和激励网络(Squeeze-and-Excitation Network,SENet)的时频特征融合策略。利用该网络对11种调制类型进行识别,实现了最高92.5%的识别准确率;在0 dB以上时,平均识别准确率达到90.87%,优于其他的深度学习算法。

基于循环谱的去模糊调制识别算法

针对当前调制识别算法在低信噪比下识别率低和循环谱应用中由于部分信号谱图相似而性能下降的问题,提出基于二维循环谱灰度图的去模糊调制识别算法。针对谱图特征相似的信号构建了二维循环谱灰度图模板库,通过与模板库进行谱图匹配将信号分流成两部分:谱图相似信号和谱图可区分信号。在信号分流基础上提出差异化识别方法,针对谱图可区分信号,通过构建基于二维循环谱灰度图的卷积神经网络(CSG-Net)完成识别;针对谱图相似信号,借助多通道学习深度神经网络(MCLDNN)完成识别。实验结果表明,提出的算法综合了不同网络的优势,提升了网络整体的识别性能,在-10 dB信噪比时依然有接近70%的识别率。

基于CBAM-GRU的通信信号自动调制识别

本文研究了一种基于卷积注意力机制模块(CBAM)与门控循环单元网络(GRU)结合的CBAM-GRU分类模型,用于非合作通信系统中的自动调制识别技术。将信号预处理后的时域幅度值、相位值以及I/Q值合并,转换为输入采样值矩阵,进入网络进行信号分类识别。使用无线电数据集RadioML2016.10a进行仿真实验,并将CBAM-GRU模型与卷积神经网络(CNN)、长短期记忆网络(LSTM)、GRU、卷积长短时深度神经网络(CLDNN)进行比较。实验结果表明:CBAM-GRU模型的分类识别率达到92.79%,相较于对比模型分别提高了8.52%、1.84%、1.75%、8.61%,比传统的CNN或LSTM模型,在处理信号时能够更有效地捕捉时空特征,从而提高识别精度。

基于注意力机制的门控密集卷积网络调制识别算法

自动调制识别(AMR)是非合作通信系统中的重要组成部分,也是一个通信领域的研究难点。针对该难点,利用深度学习,将密集卷积网络(DenseNet)、门控循环单元(GRU)和注意力机制(Attention)三者结合,提出一种基于注意力机制的门控密集卷积网络(AGDCN)的调制识别算法。该算法提取了信号的空间特征和时序特征,将两者相结合解决了信号识别率低的问题。同时,在网络中加入注意力机制,对GRU训练过程进行权重的自适应调整,有效地加强关键特征的学习。通过实验验证了AGDCN模型性能优于其他神经网络算法,在信噪比超过2 dB时,对11种调制类型的识别率可以达到90%。

基于相位变换和CNN-BiLSTM的自动调制识别算法

针对真实信道使无线通信信号发生相位偏移导致信号识别率下降的问题,提出了相位变换算法。该算法将信号输入神经网络,通过Flatten层和Dense层估计出相位参数,再利用参数变换器完成相位变换,减轻相位偏移对调制识别准确率的影响,提高了调制识别的准确率。同时提出一种卷积双向长短期记忆(Convolutional Neural Network-Bidirectional Long Short-Term Memory,CNN-BiLSTM)网络,其中CNN用于提取信号的高维特征,BiLSTM用于提取信号的双向时间特征。所提出的调制信号分类模型识别率达到96.7%,相较于卷积神经网络(Convolutional Neural Network,CNN)提高了12%。

基于人工神经网络的无线通信信号自动调制识别方法研究

对于一些复杂的调制方式,现有的自动调制识别方法可能无法完全准确地识别,现提出基于人工神经网络的无线通信信号自动调制识别方法。首先,基于人工神经网络构建无线通信信号调制模型,判定调制方式,并给出其对应的调制参数,然后,使用maxout函数作为人工神经网络卷积层和全连接层的激活函数,取代原先的Re LU函数,增加卷积层的数量,降低池化层的层数,提取无线通信信号特征参数,构建适合神经网络训练的特征矢量。最后,结合自适应调整的识别阈值,进行无线通信信号初始自动调制识别,通过相似度进一步优化调制识别方法,实现无线通信信号自动调制识别。通过测试数据集验证该方法的有效性和准确性。实验结果表明,使用人工神经网路模型在识别方面相较于文献方法更具优势,因此,可以证明基于人工神经网络的无线通信信号自动调制识别方法具有更高的精准度。

基于CGDNN的低信噪比自动调制识别方法

针对非协作通信环境中,自动调制识别(automatic modulation recognition,AMR)在低信噪比下泛化能力有限、分类精度不高的问题,提出一种由卷积神经网络、门控循环单元和深度神经网络组成的模型—CGDNN(convolutional gated recurrent units deep neural networks)。首先对I/Q采样信号进行小波阈值去噪,降低噪声对信号调制识别的影响;然后用CNN和GRU提取信号空间和时间特征;最后,通过全连接层进行识别分类。与其他模型对比,验证CGDNN模型在提高AMR性能的同时,显著降低了计算复杂度。实验结果显示,CGDNN模型在RML2016.10b数据集上的平均识别准确率达到了64.32%,提高了-12 dB~0 dB的信号分类精度,该模型大幅减少了16QAM与64QAM的混淆程度,在18 dB时达到了93.9%的最高识别准确率。CGDNN模型既提高了低信噪比下AMR的识别准确率,也提高了模型训练的效率。

基于特征融合的自动调制识别算法

目前大多数基于神经网络的调制识别算法,只使用时域或频域的单一信息来源,忽视利用多个变换域信息特征进行优势互补。提出基于特征融合的深度学习自动调制识别算法,可有效改善只利用时域或频域单一信息来源的调制识别效果。上述算法包含时频特征提取模块,将信号在不同变换域中的特征进行融合,然后采用基于注意力机制的长短期记忆网络和全连接层进行分类,通过多个变换域信息的特征融合,实现了优势互补。仿真结果表明,相比传统的深度学习调制识别算法,基于特征融合的自动调制识别算法能够有效地提取信号特征,具有更高的识别准确度。

基于多尺度循环卷积神经网络的卫星通信信号识别

针对目前的卫星通信调制分类算法大多忽略了不同尺度特征的融合问题,提出了一个多尺度循环卷积神经网络模型。该网络结构整合了双分支设计、压缩与激励策略、多尺度残差网络以及长短期记忆网络,旨在全面捕捉信号的多尺度特性并有效建模时间序列。实验结果表明:文中所提模型在0 dB以上的识别准确率达到了97.1%,在13 dB时更进一步提升至99%;与经典的CNN2模型和LSTM2模型相比,在识别准确率上展现了显著优势,且相较于识别性能接近的CLDNN2模型,参数量减少了47.7%,训练时间缩短了68%;尤其是QAM16和QAM64两种调制样式识别准确率显著上升并且保持较高水平,这也进一步证实了模型多尺度特征融合策略的有效性。

基于人工智能模型的通信信号自动调制识别研究

现行的自动识别方法无法准确识别某些复杂的调制方式。针对此问题,文章提出基于人工智能模型的通信信号自动调制识别方法。首先,在构建通信信号调制模型时,采用人工智能来判定调制方式,并给出相应的调制参数。其次,采用maxout函数替代原有的ReLU函数,同时增加卷积层的数量,减少池化层的层数,提取通信信号的特征参数,从而构建适合人工智能模型训练的特征矢量。最后,结合自适应调整的识别阈值进行通信信号的初始自动调制识别,并通过相似度进一步优化调制识别方法。通过测试数据集,验证该方法的有效性和准确性。实验结果显示,相较于文献方法,基于人工智能的通信信号自动调制识别方法具有更高的精准度。

基于前置LSTM编码的残差-注意力网络的调制方式识别方法

高效的调制方式识别方法可以提高通信效率,推动通信行业的进一步发展。文中设计了一种基于前置LSTM编码的残差-注意力网络,其可以明显提高识别准确率。在第一部分,给出了网络的基本结构。该网络主体使用残差结构,前置LSTM层对数据序列编码,并采用加入了软阈值降噪的注意力机制。第二部分使用包含了24种调制方式的开源数据集作为数据来源,设计了多个实验来比较网络的性能表现,并探究了数据质量、调制方式、网络深度等多个因素对神经网络识别性能的影响。实验结果表明,文中搭建的网络表现优秀,在高信噪比数据下的准确率仍超过了95%。