Modulation Recognition of Communication Signals Based on Deep Learning Joint Model

Automatic modulation recognition is a rapidly evolving area of signal analysis. In recent years, interest from the academic and military research institutes has focused around the research and development of modulation recognition algorithms. Any communication intelligence (COMINT) system comprises three main blocks: receiver front-end, modulation recogniser and output stage. Considerable work has been done in the area of receiver front-ends. The work at the output stage is concerned with information extraction, recording and exploitation and begins with signal demodulation, that requires accurate knowledge about the signal modulation type. There are, however, two main reasons for knowing the current modulation type of a signal; to preserve the signal information content and to decide upon the suitable counter action, such as jamming. Automatic Modulation Recognition of Communications Signals describes in depth this modulation recognition process. Drawing on several years of research, the authors provide a critical review of automatic modulation recognition. This includes techniques for recognising digitally modulated signals. The book also gives comprehensive treatment of using artificial neural networks for recognising modulation types. Automatic Modulation Recognition of Communications Signals is the first comprehensive book on automatic modulation recognition. It is essential reading for researchers and practising engineers in the field. It is also a valuable text for an advanced course on the subject.

Modulation recognition of communication signals is a key task in the fields of spectrum management and cognitive radio. Traditional methods rely on artificial feature design and have limited generalization ability in complex channel environment. In this study, a hybrid deep learning model combining convolutional neural network and long-term and short-term memory network is constructed to automatically extract the spatial local features of signals and capture their temporal dependencies through end-to-end learning. The model uses multi-modal inputs including time-frequency map, in-phase quadrature series and manual statistical features to process different modal data through parallel branch structure and fuse multi-dimensional information to enhance feature discrimination. Experimental results show that the accuracy, recall and AUC of the proposed model are superior to those of support vector machine and ResNet18 models in the recognition tasks of analog modulation, digital modulation and spread spectrum modulation on a dataset containing 120000 signal samples, which verifies the effectiveness of the joint spatial-temporal feature modeling. This study provides a robust solution for intelligent modulation recognition in complex electromagnetic environment.

A new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) clustering is used to get the membership matrix of different clusters. Then, a clustering validity measure is applied to extract features. To enhance clustering results at low SNR, a neural network with a conjugate gradient learning algorithm is utilized. Fletcher-Reeves learning approach enhances the recognition rate and widely improves the speed and rate of convergence. Simulation results show the validity of proposed approach compared with other approaches using only clustering or using back propagation neural networks. Misclassification rate is less for low order MQAM signals. This algorithm is applicable in high order MQAM signals. In Non-cooperative Communications, the modulated signal parameters are unknown. Some Modulation Recognition algorithms rely on estimating these parameters first, then applying recognition algorithms. Proposed algorithm doesn't need any prior information to achieve modulation recognition.

In communication signal recognition, there are problems such as a tedious feature extraction process and low applicability of extracted features. This paper simulates wireless communication channels and suggests an algorithm that uses nearest neighbor component analysis (NCA) along with convolutional neural networks (CNN) for classification. The algorithm chooses wavelet entropy (WE), wavelet approximate energy ratio (WAER), and the first 2–4 singular values as the core features. Eight different forms of modulations, including GFSK, CPFSK, B-FM, DSB-AM, SSB-AM, BPSK, QPSK and PAM4 would be automatically classified using the technique. According to the experiment results, the average recognition accuracy for the eight signals is 93.6% when the signal-to-noise ratio is 30dB. In addition, this paper also discusses the results and accuracy of the model to identify 6 and 10 types of signal modulation and studies the accuracy of the recognition under different signal-to-noise ratios, verifying the robustness of the model.

To improve the recognition rate of the end-to-end modulation recognition method based on deep learning, a modulation recognition method of communication signals based on a cascade network is proposed, which is composed of two networks: Stacked Denoising Auto Encoder (SDAE) network and DCELDNN(Dilated Convolution, ECA Mechanism, Long Short-Term Memory, Deep Neural Networks) network. SDAE network is used to denoise the data, reconstruct the input data through encoding and decoding, and extract deep information from the data. DCELDNN network is constructed based on the CLDNN (Convolutional, Long Short-Term Memory, Fully Connected Deep Neural Networks) network. In the DCELDNN network, dilated convolution is used instead of normal convolution to enlarge the receptive field and extract signal features, the Efficient Channel Attention (ECA) mechanism is introduced to enhance the expression ability of the features, the feature vector information is integrated by a Global Average Pooling (GAP) layer, and signal features are extracted by the DCELDNN network efficiently. Finally, end-to-end classification recognition of communication signals is realized. The test results on the RadioML2018.01a dataset show that the average recognition accuracy of the proposed method reaches 63.1% at SNR of -10 to 15dB, compared with CNN, LSTM, and CLDNN models, the recognition accuracy is improved by 25.8%, 12.3%, and 4.8% respectively at 10dB SNR.

This paper presents an initial investigation on the feasibility of modeling structural dynamics of complex structures using the Long Short-Time Memory (LSTM) deep learning neural networks, and predicting the structures’ vibration responses due to random excitation. LSTM networks are applied to the responses of various simulated systems subjected to random excitation loads, including mass-spring-damper systems with linear or nonlinear Duffing springs, a cantilever beam, and a tapered, cambered wing structure. Given a known force input, the dynamic response of the system is simulated in Matlab or ANSYS, which is used to train the LSTM model. In the case of mass-spring-damper and beam systems, the excellent agreement between the test and LSTM-predicted responses demonstrates the potential of the LSTM method for predicting vibration responses. In the case of cambered wing structure, the LSTM shows difficulties in dealing with responses consisting of multiple modes. Parametric studies are also performed to discover possible means for performance improvement. The studied learning parameters include the number of hidden units, the number of LSTM layers, and the size of train data. It is found that all these parameters have significant impact on the model accuracy. While it is always beneficial to have as much and there could be an optimal setting for the number of is not determined by the studies, they provide valuable directions to.

Rainfall–runoff models are valuable tools for flood forecasting, management of water resources, and drought warning. With the advancement in space technology, a plethora of satellite precipitation products (SPPs) are available publicly. However, the application of the satellite data for the data-driven rainfall–runoff model is emerging and requires careful investigation. In this work, two satellite rainfall data sets, namely Global Precipitation Measurement-Integrated Multi-Satellite Retrieval Product V6 (GPM-IMERG) and Climate Hazards Group Infrared Precipitation with Station (CHIRPS), are evaluated for the development of rainfall–runoff models and the prediction of 1-day ahead streamflow. The accuracy of the data from the SPPs is compared to the India Meteorological Department (IMD)-gridded precipitation data set. Detection metrics showed that for light rainfall (1–10 mm), the probability of detection (POD) value ranges between 0.67 and 0.75 and with an increasing rainfall range, i.e., medium and heavy rainfall (10–50 mm and >50 mm), the POD values ranged from 0.24 to 0.45. These results indicate that the satellite precipitation performs satisfactorily with reference to the IMD-gridded data set. Using the daily precipitation data of nearly two decades (2000–2018) over two river basins in India's eastern part, artificial neural network, extreme learning machine (ELM), and long short-time memory (LSTM) models are developed for rainfall–runoff modelling. One-day ahead runoff prediction using the developed rainfall–runoff modelling confirmed that both the SPPs are sufficient to drive the rainfall–runoff models with a reasonable accuracy estimated using the Nash–Sutcliffe Efficiency coefficient, correlation coefficient, and the root-mean-squared error. In particular, the 1-day streamflow forecasts for the Vamsadhara river basin (VRB) using LSTM with GPM-IMERG inputs resulted in Nash-Sutcliffe Efficiency Coefficient (NSC) values of 0.68 and 0.67, while ELM models for Mahanadhi river basin (MRB) with the same input resulted in NSC values of 0.86 and 0.87, respectively, during training and validation stages. At the same time, the LSTM model with CHIRPS inputs for the VRB resulted in NSC values of 0.68 and 0.65, and the ELM model with CHIRPS inputs for the MRB resulted in NSC values of 0.89 and 0.88, respectively, in training and validation stages. These results indicated that both the SPPs could reliably be used with LSTM and ELM models for rainfall–runoff modelling and streamflow prediction. This paper highlights that deep learning models, such as ELM and LSTM, with the GPM-IMERG products can lead to a new horizon to provide flood forecasting in flood-prone catchments.

Automatic identification of the communication signal modulation mode is a hot topic of research in the signal processing field in recent years. It is an important part of electronic countermeasures, and also a rapidly developed field of signal analysis. Communication signal modulation recognition is widely used in signal confirmation, interference identification, radio listening, signal monitoring, as well as software-defined radio, satellite communications and other fields. This paper proposed a digital modulation signal automatic recognition algorithm for satellite communication applications,. The algorithm uses the higher order cumulants of modulating signal, combined with constellation map features, to classify the signal. It has invariance in signal amplitude and phase deviation, and inhibits the additive Gaussian noise at the same time. Compared with other identification algorithms, it has the characteristics of stability and wide application. Computer simulations show that, under the given data length and moderate SNR conditions, a higher recognition rate (> 95%) can be obtained.

Copper price forecasted by hybrid neural network with Bayesian Optimization and wavelet transform

Irregular ocean waves cause fluctuating non-linear hydrodynamic forces on the body, which is an importance factor to account for in offshore and marine applications. While physical experimental and computational techniques provide valuable physics insight, they are generally time-consuming and expensive for design space exploration. We present an efficient Long Short Time Memory (LSTM) based deep-learning technique to predict unsteady hydrodynamic forces on slender bodies, where drag forces are more dominant than inertia forces. A leaky non-linear rectification is employed to approximate the mapping between surface elevation time series and hydrodynamic (drag) force time series. The deep neural network is fed with irregular waves based on JONSWAP spectrum as the input and the target data generated by the full-order Navier-Stokes computations using a generic offshore jack-up platform. The LSTM is trained using a stochastic gradient descent method to predict time series of the hydrodynamic forces on the jack-up and the results are compared with the full-order computations. Within the error threshold, the predictions based on our deep convolutional network have a speed-up of nearly 2 orders of magnitude compared to the full-order results and consume an insignificant fraction of computational resources. Overall, the proposed LSTM-based approximation procedure has the potential to be used for parametric design and digital twinning of jack-up platforms.

Aiming at the problems of network complexity, large computation amount and high hardware platform requirements in the current process of applying deep learning to realize digital signal modulation recognition, this paper proposes a method of using signal constellation diagram modulation recognition in the improved MobileNetV3 lightweight neural network, and introduces the cross-layer structure of Resnet into the MobileNetV3 network. The phenomenon of vanishing gradient caused by decreasing weight with increasing network layers is solved. Firstly, the received MPSK and MQAM signals are converted into constellation diagrams, which are extracted from gray images and enhanced. The image data set of constellation diagram is constructed, which is used to train the lightweight neural network weight of MobileNetV3, and then the constellation diagram is recognized. MobileNetV3 is based on deep convolution separable and Network Architecture Search (NAS) technology, which greatly reduces the number of parameters and training time on the premise of ensuring the recognition accuracy. For the modulation recognition of simple signals, the lightweight neural Network can effectively simplify the Network structure caused to reduce hardware requirements. The simulation results show that the modulated signals (BPSK, QPSK, 8PSK, 16QAM, 64QAM) can achieve the recognition rate of 99.76%. Compared with the traditional network using deep learning to realize the modulation recognition, the number of network parameters and the computational cost are significantly reduced.

Deep residual learning in modulation recognition of radar signals using higher-order spectral distribution

Automatic modulation recognition (AMR) stands as a crucial core technology within the realm of signal processing and perception, playing a significant part in harsh electromagnetic environments. The time–frequency image (TFI) of communication signals can manifest modulation characteristics and serve as a foundation for signal modulation recognition and classification. However, under the influence of the electromagnetic environment, communication signals are exposed to varying degrees of interference, which poses a challenge to the recognition of modulation types. Taking into account the effects of interference and channel fading, this paper introduces a communication signal modulation recognition algorithm based on deep learning (DL) and time–frequency analysis. This approach employs short-time Fourier transform (STFT) to generate time–frequency diagrams from time-domain signals. Subsequently, it binarizes the image and feeds it as input data to the neural network. Our research presents a composite deep convolutional neural network (CNN) architecture known as the composite dense-residual neural network (CDRNN). This architecture focuses on enhancing the feature extraction and identification, aiming to achieve accurate recognition of modulation types in harsh electromagnetic environments. Finally, simulation results validate that the proposed deep learning algorithm holds remarkable advantages in boosting the accuracy of modulation type recognition with better adaptability. The algorithm shows better performance even in harsh electromagnetic environments. When the signal-to-noise ratio (SNR) is 18 dB, the recognition accuracy can reach 92.1%.

Modulation recognition of non-cooperation underwater acoustic communication signals using principal component analysis

Wideband interference (WBI) is detrimental to high-resolution radar due to its high power and wide frequency occupancy. In this study, a deep learning (DL) method is proposed to predict the time–frequency (TF) feature of WBI and applied to cognitive radar high-resolution range profile (HRRP) estimation. Specifically, by performing short-time Fourier transform (STFT) on the WBI signal collected in the past and using a sliding window, a series of WBI TF figures is generated. A long short-time memory (LSTM) network is then used to learn the spatiotemporal (ST) correlation of these TF figures, thus predicting the WBI TF feature in the future, based on which, a cognitive method is used for target HRRP estimation with reduced influences of WBI. Numerical results demonstrate the effectiveness of the proposed methods.