Non-cooperative Communication Research Articles

Communication behavior recognition using CNN-based signal analysis

This article explores the technology of recognizing non-cooperative communication behavior, with a specific emphasis on analyzing communication station signals. Conventional techniques for analyzing signal data frames to determine their identity, while precise, do not have the ability to operate in real-time. In order to tackle this issue, we developed a pragmatic architecture for recognizing communication behavior and a system based on polling. The method utilizes a one-dimensional convolutional neural network (CNN) to segment data, hence improving its ability to recognize various communication activities. The study assesses the reliability of CNN in several real-world scenarios, examining its accuracy in the presence of noise interference, varying lengths of interception signals, interferences at different frequency points, and dynamic changes in outpost locations. The experimental results confirm the efficacy and dependability of the convolutional neural network in recognizing communication behavior in various contexts.

Blind recognition of channel codes based on a multiscale dilated convolution neural network

Channel coding is an essential part of communication. In a non-cooperative communication system, the receiver has to recover the signal without any priori knowledge. Therefore, it is important to recognize channel code types and parameters. At present, only a few studies focus on channel code type recognition. In this paper, a multiscale dilated convolution neural network (MSDCNN) is proposed to achieve fine-grained recognition of seven commonly used channel code types. MSDCNN has three multiscale modules. Based on the characteristics of each channel code type, the first two identical modules are designed to extract the overall features of codewords with unit convolution and three parallel regular convolution layers. To lower complexity, the third module uses dilated convolution instead of regular convolution to extract features between codewords. Simulation results show that MSDCNN has higher average recognition accuracy than other neural networks. More importantly, MSDCNN lowers complexity, making it more suitable for deployment so that it can be applied in practical non-cooperative receivers.

SDR implementation of a light deep learning model based CNN for joint spectrum sensing and AMC

Automatic modulation classification (AMC) aims to blindly recognize the modulation type of a received signal in wireless systems. It is also a critical component of non-cooperative communication systems after the detection of the presence of a signal. In this paper, we introduce a robust approach, termed DET-AMC (joint Detection and Automatic Modulation Classification), employing Convolutional Neural Networks (CNNs) trained via transfer learning methodology. The main advantage of our approach is its ability to handle a wide range of modulation types, including 10 different schemes generated in Gnuradio and their detection using the same model. Through extensive experimentation, we evaluate the performance of our light CNN-based DET-AMC method across varying signal-to-noise ratio (SNR) levels, as well as in the presence of phase noise and frequency offset. We find that the CNN’s learned features, obtained through transfer learning, exhibit robustness, particularly in low SNR and various challenging conditions, leading to accurate modulation classification. In general, our approach outperforms existing methods by using the effectiveness of deep learning in capturing relevant discriminative features. Additionally, our model offers a robust solution for join detection and AMC by achieving an accurate probability of detection and modulation classification without the need for manual feature engineering or the consideration of frequency offset, phase noise or noise estimation. Our model achieves 100% accuracy for synthetic and real data at an SNR equal to -10 dB for detection, and 100% and 98% for classification of synthetic and real signals at −4 dB, respectively.

Intelligent non-cooperative optical networks: Leveraging scattering neural networks with small training data

Artificial intelligence (AI) is enabling intelligent communications where learning based signal classification simplifies optical network signal allocation and shifts signal processing pressure to each network edge. This work proposes a non-orthogonal signal waveform framework that leverages its unique spectral compression characteristic as a user address for efficiently forwarding messages to target users. The primary focus of this work lies in the physical layer intelligent receiver design, which can automatically identify different received signal formats without preamble notification in a non-cooperative communication approach. Traditional signal classification methods, such as convolutional neural network (CNN), rely on extensive training, resulting in a heavy dependency on large training datasets. To overcome this limitation, this work designs a specific two-layer scattering neural network that can accurately separate signals even when the training data is limited, leading to reduced training complexity. Its performance remains robust in diverse transmission conditions. Furthermore, the scattering neural network is interpretable because features are extracted based on deterministic wavelet filters rather than training based filters.

Contrastive Self-Supervised Clustering for Specific Emitter Identification

Specific Emitter Identification (SEI) is crucial for attacking and defending Internet of Things (IoT) devices in untrusted scenarios or battlefield environments. However, existing SEI methods usually require annotation information, which is often unavailable in non-cooperative communications and untrusted scenarios. In this paper, we propose a signal contrastive self-supervised clustering (SCSC) method for unsupervised SEI applications. First, we propose SCSC with 1D fingerprint pyramid feature extractor (1D-FPFE) for obtaining hierarchical subtle features of emitter signals. Then, we propose a bit-pulse selection (BPS) strategy and several signal data augmentation methods. By constructing signal positive and negative instance pairs through data augmentation, our approach generates cluster preference representations in a contrastive self-supervised learning manner. Extensive experimental results based on communication burst emitter dataset show that SCSC achieves an accuracy improvement of about 26% over the current best communication signal clustering algorithm. Moreover, SCSC also exhibits good performance and generalization for 30 emitter clustering and few-shot unlabeled signal clustering.

Deep Learning-Based Automatic Modulation Classification Using Robust CNN Architecture for Cognitive Radio Networks

Automatic modulation classification (AMC) is an essential technique in intelligent receivers of non-cooperative communication systems such as cognitive radio networks and military applications. This article proposes a robust automatic modulation classification model based on a new architecture of a convolutional neural network (CNN). The basic building convolutional blocks of the proposed model include asymmetric kernels organized in parallel combinations to extract more meaningful and powerful features from the raw I/Q sequences of the received signals. These blocks are connected via skip connection to avoid vanishing gradient problems. The experimental results reveal that the proposed model performs well in classifying nine different modulation schemes simulated with different real wireless channel impairments, including AWGN, Rician multipath fading, and clock offset. The performance of the proposed system systems shows that it outperforms its best rivals from the literature in recognizing the modulation type. The proposed CNN architecture remarkably improves classification accuracy at low SNRs, which is appropriate in realistic scenarios. It achieves 86.1% accuracy at −2 dB SNR. Furthermore, it reaches an accuracy of 96.5% at 0 dB SNR and 99.8% at 10 dB SNR. The proposed architecture has strong feature extraction abilities that can effectively recognize 16QAM and 64QAM signals, the challenging modulation schemes of the same modulation family, with an overall average accuracy of 81.02%.

CrossTLNet: A Multitask-Learning-Empowered Neural Network with Temporal Convolutional Network–Long Short-Term Memory for Automatic Modulation Classification

Amidst the evolving landscape of non-cooperative communication, automatic modulation classification (AMC) stands as an essential pillar, enabling adaptive and reliable signal processing. Due to the advancement of deep learning (DL) technology, neural networks have found application in AMC. However, the previous DL models face the inter-class confusion problem in high-order modulations. To address this issue, we propose a multitask-learning-empowered hybrid neural network, named CrossTLNet. Specifically, after the signal enters the model, it is first transformed into two task components: in-phase/quadrature (I/Q) form and amplitude/phase (A/P) form. For each task, we design a method that combines a temporal convolutional network (TCN) with a long short-term memory (LSTM) network to effectively capture long-term dependency features in high-order modulations. To enable interaction between these two different dimensional features, we innovatively introduce a cross-attention method, thereby further enhancing the model’s ability to distinguish signal features. Moreover, we also design a simple and efficient knowledge distillation method to reduce the size of CrossTLNet, making it easier to deploy in real-time or resource-limited scenarios. The experimental results indicate that the suggested method exhibits exceptional performance in AMC on public benchmarks, especially in high-order modulations.

Attentive Siamese Networks for Automatic Modulation Classification Based on Multitiming Constellation Diagrams.

Automatic modulation classification (AMC) is an essential part in a cognitive radio receiver. Benefited from the discriminative constellation characteristics among most modulations, AMC methods based on constellation diagrams usually achieve pleasant performance. However, in noncooperation communication systems, constellation diagrams expressing modulations explicitly are difficult to obtain via blind symbol timing synchronization, especially in complicated wireless channels. Therefore, this article proposes a novel constellation diagram-based AMC architecture called attentive Siamese networks (ASNs) by considering multitiming constellation diagrams (MCDs) and selecting the proper symbol timings at the feature level, which is a more robust way than the conventional signal-level symbol timing synchronization. In detail, convolutional neural networks sharing the same parameters first extract deep feature vectors for MCDs. Then, an attention inference module weights all the deep feature vectors. Finally, AMC is realized based on the weighted feature vectors. Moreover, the ASN architecture can be trained end-to-end. Comparing with the state-of-the-art methods that take diverse representations of received baseband signals as input, experimental results based on the RadioML 2018.01A dataset and non-Gaussian noise dataset demonstrate that ASN achieves a remarkable improvement, whose classification accuracy goes over 99% when the signal-to-noise ratio (SNR) > 10 dB.

TS-WHT: A Two-Step Walsh–Hadamard Transform Approach for Blind Error Correcting Code Classification

Blind classification of error-correcting codes is essential for intelligent wireless communication, cognitive radio, and non-cooperative communication. The object of this paper is to investigate the differences in the Walsh spectrum between linear block code, convolutional code, and Turbo code. Based on these differences, a two-step Walsh Hadamard transform (TS-WHT) strategy is proposed for error-correcting code blind classification. Further, according to the detection theory, the peak detection threshold is detailed and optimized with the cyclic feature of CRC codes. The results indicate that when employing the optimized threshold, probabilities of correct classification are superior for linear block codes and convolutional codes. Moreover, with the help of the fault-tolerant feature of the WHT technique, the classification accuracy of the proposed method is substantially better than existing approaches under low signal-to-noise ratio(SNR) conditions.

Learning Dynamic Computing Resource Allocation in Convolutional Neural Networks for Wireless Interference Identification

Wireless interference identification (WII) is a critical technology for the non-cooperative communication systems, and it is widely applied into military and civilian scenarios. With enormous success in many computer vision and language processing applications, deep learning (DL) has also achieved the remarkable performance for WII. However, existing DL based WII methods can not dynamically allocate proper computing resources conditioned on the inputs, causing serious waste of resources and low computational efficiency, which is unacceptable for edge computing devices, such as unmanned aerial vehicle (UAV)-aided systems. In this paper, the problem of dynamic computation resource allocation is modeled as adaptively learning forward propagation depth of networks on a per-input basis, and this novel method is termed as dynamic computing resource allocation in convolutional neural networks (DCRACNN). In particular, the proposed DCRACNN is composed of two subnetworks: a main network and a policy network. The main network is equipped with multiple classifiers at different depths, allowing test examples to stop early during inference so as to significantly improve computational efficiency. The policy network is optimized with reinforcement learning to address the bottleneck of non-differentiable decisions of optimal forward propagation depth for the main network while preserving recognition accuracy. To address the challenges of high error rates of early classifiers in the main network, novel methods are introduced, which can be seamlessly integrated into DRCACNN. In addition, a novel network pruning process is proposed for the main network to further reduce model sizes and computational complexity. Experiments demonstrate that DCRACNN can significantly reduce the calculation cost with boosting accuracy for WII.

Reduced-Complexity RS Codes Recognizer Based on Spectra Update Algorithm

In non-cooperative communication systems, the effective recognition by intercepted bitstream at the 3rd-party receiver is an important mission for military or security purposes. However, the existing recognition schemes lead to long latency and significant hardware due to the large number of traversal operations. Hence, the spectra update algorithm (SUA) is proposed by analyzing the differences between the adjacent reconstructed matrices. Compared with the spectra calculations available like the Galois field Fourier transform (GFFT) and simplified-GFFT (S-GFFT), the presented algorithm reduces the computational complexity to 2/ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> and 2/λ without performance loss, respectively, where <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</i> is the code length and λ is the cardinality of the conjugacy class of the corresponding Galois fields. Besides, a reduced-complexity RS recognizer architecture is designed and analyzed to show the effectiveness of the proposed SUA.

A Cascade Network for Blind Recognition of LDPC Codes

Coding blind recognition plays a vital role in non-cooperative communication. Most of the algorithm for coding blind recognition of Low Density Parity Check (LDPC) codes is difficult to apply and the problem of high time complexity and high space complexity cannot be solved. Inspired by deep learning, we propose an architecture for coding blind recognition of LDPC codes. This architecture concatenates a Transformer-based network with a convolution neural network (CNN). The CNN is used to suppress the noise in real time, followed by a Transformer-based neural network aimed to identify the rate and length of the LDPC codes. In order to train denoise networks and recognition networks with high performance, we build our own datasets and define loss functions for the denoise networks. Simulation results show that this architecture is able to achieve better performance than the traditional method at a lower signal-noise ratio (SNR). Compared with the existing methods, this approach is more flexible and can therefore be quickly deployed.

FOLMS-AMDCNet: an automatic recognition scheme for multiple-antenna OFDM systems

The existing recognition algorithms of space-time block code (STBC) for multi-antenna (MA) orthogonal frequency-division multiplexing (OFDM) systems use feature extraction and hypothesis testing to identify the signal types in a complex communication environment. However, owing to the restrictions on the prior information and channel conditions, these existing algorithms cannot perform well under strong interference and noncooperative communication conditions. To overcome these defects, this study introduces deep learning into the STBC-OFDM signal recognition field and proposes a recognition method based on the fourth-order lag moment spectrum (FOLMS) and attention-guided multi-scale dilated convolution network (AMDCNet). The fourth-order lag moment vectors of the received signals are calculated, and vectors are stitched to form two-dimensional FOLMS, which is used as the input of the deep learning-based model. Then, the multi-scale dilated convolution is used to extract the details of images at different scales, and a convolutional block attention module (CBAM) is introduced to construct the attention-guided multi-scale dilated convolution module (AMDCM) to make the network be more focused on the target area and obtian the multi-scale guided features. Finally, the concatenate fusion, residual block and fully-connected layers are applied to acquire the STBC-OFDM signal types. Simulation experiments show that the average recognition probability of the proposed method at −12 dB is higher than 98%. Compared with the existing algorithms, the recognition performance of the proposed method is significantly improved and has good adaptability to environments with strong disturbances. In addition, the proposed deep learning-based model can directly identify the pre-processed FOLMS samples without a priori information on channel and noise, which is more suitable for non-cooperative communication systems than the existing algorithms.

Wireless interference classification with low complexity multi-branch networks

In non-cooperative communication systems, wireless interference classification (WIC) is one of the most essential technologies. Recently, deep learning (DL) based WIC methods have been proposed. However, conventional DL-based WIC methods have high computational complexity and unsatisfactory accuracy, especially when the interference-to-noise ratio (INR) is low. To this end, we propose three effective approaches. Firstly, we introduce multi-branch convolutional neural networks (CNNs) for interference recognition. The multi-branch CNN is constructed by repeating a layer that aggregates several transformations with the same topology, and it notably improves the recognition ability for WIC. Our design avoids the carefully crafted selection of each transformation. Unfortunately, multi-branch CNNs are computationally expensive and memory-inefficient. To this end, we further propose Low complexity multi-branch networks (LCMN), which are mathematically equivalent to multi-branch CNNs but maintain low computing costs and efficient inference. Thirdly, we present novel loss function, which encourages networks to have consistent prediction probabilities for samples with high visual similarities, resulting in increasing recognition accuracy of LCMN. Experimental results demonstrate the proposed methods consistently boost the classification performance of WIC without substantially increasing computational overhead compared to traditional DL-based methods.

A Robust Constellation Diagram Representation for Communication Signal and Automatic Modulation Classification

Automatic modulation recognition is a necessary part of cooperative and noncooperative communication systems and plays an important role in military and civilian fields. Although the constellation diagram (CD) is an essential feature for different digital modulations, it is hard to be extracted under noncooperative complex communication environment. Frequency offset, especially the nonlinear frequency offset is a vital problem of complex communication environment, which greatly affects the extraction of traditional CD and the performance of modulation recognition methods. In the current paper, we propose an antifrequency offset constellation diagram (AFO-CD) extraction method, which combines the constellation diagram with a convolutional neural network (CNN). The proposed method indicates the change of the CD with time and enables us to suppress the influence of frequency offset efficiently. Additionally, a residual units-based classifier is designed for multiscale feature extraction and modulation classification. The experimental results demonstrate that the proposed method can effectively improve the recognition accuracy and has a good application prospect in the complex electromagnetic environment.

Blind Identification of Polar Codes Based on Estimation and Derivation Approaches

The blind identification of polar codes is to identify code parameters such as the code length, the number and positions of information bits in a polar code in non-cooperative communications. In this letter, we propose two low-complexity algorithms to identify code length and information bits of polar codes, respectively, by taking the union of both the estimated code parameters and the derived code parameters from the allowable shortest code without the candidate code sets. Simulations show that our proposed scheme is robust to the error and significantly improves the identification performance as compared to the existing purely code parameter estimation approaches.

Automatic Modulation Recognition Based on Deep-Learning Features Fusion of Signal and Constellation Diagram

In signal communication based on a non-cooperative communication system, the receiver is an unlicensed third-party communication terminal, and the modulation parameters of the transmitter signal cannot be predicted in advance. After the RF signal passes through the RF band-pass filter, low noise amplifier, and image rejection filter, the intermediate frequency signal is obtained by down-conversion, and then the IQ signal is obtained in the baseband by using the intermediate frequency band-pass filter and down-conversion. In this process, noise and signal frequency offset are inevitably introduced. As the basis of subsequent analysis and interpretation, modulation recognition has important research value in this environment. The introduction of deep learning also brings new feature mining tools. Based on this, this paper proposes a signal modulation recognition method based on multi-feature fusion and constructs a deep learning network with a double-branch structure to extract the features of IQ signal and multi-channel constellation, respectively. It is found that through the complementary characteristics of different forms of signals, a more complete signal feature representation can be constructed. At the same time, it can better alleviate the influence of noise and frequency offset on recognition performance, and effectively improve the classification accuracy of modulation recognition.

A Super-Resolution Data Processing for Automatic Modulation Classification Based on Tree Compression Networks

Automatic modulation classification (AMC) algorithms play a vital role in modern non-cooperative communication systems and are widely used for malicious attack analysis and reliable communication. Our research confirms that reducing the negative impact of few-shot learning and computational complexity is key to implementing the AMC algorithm on edge intelligence devices. This paper proposes a novel super-resolution (SR) data processing method, which is based on a tree compression network (TCNet), aiming to improve the accuracy and reduce the complexity of the few-shot learning AMC algorithm. Firstly, the SR data processing method is used for data augmentation where the number of examples is insufficient. Additionally, the TCNet is proposed to process SR data based on the compression network and the tree classification strategy. The compression network is employed to reduce model complexity, and the tree classification strategy improves classification accuracy. Lastly, the implementation of lightweight TCNet subnet will facilitate deployment on edge devices with limited computing power. The simulation results show that the proposed TCNet achieved a maximum accuracy of more than 91.98%. It is shown by processing fewer dataset examples on two well-known datasets, that TCNet outperforms previous approaches by offering improved classification accuracy and less complexity.

Robust Automatic Modulation Classification in Low Signal to Noise Ratio

In a non-cooperative communication environment, automatic modulation classification (AMC) is an essential technology for analyzing signals and classifying different kinds of signal modulation before they are demodulated. Deep learning (DL)-based AMC has been proposed as an efficient method of achieving high classification performance. However, most current DL-AMC methods have limited generalization capabilities under varying noise conditions, especially at low signal-to-noise ratios (SNRs). Therefore, these methods can not be directly applied to practical systems. In this paper, we propose a threshold autoencoder denoiser convolutional neural network (TADCNN), which consists of a threshold autoencoder denoiser (TAD) and a convolutional neural network (CNN). TADs reduce noise power and clean input signals, which are then passed on to CNN for classification. The TAD network generally consists of three components: the batch normalization layer, the autoencoder, and the threshold denoise. The threshold denoise component uses an auto-learning threshold sub-network to compute thresholds automatically. According to experiments, AMC with TAD improved classification accuracy by 70% at low SNR compared with a model without a denoiser. Additionally, our model achieves an average accuracy of 66.64% on the RML2016.10A dataset, which is 6% to 18% higher than the current AMC model.

Blind Recognition Method for Non-Cooperative Communication Signals Based on Aerial Computing

Blind Recognition Method for Non-Cooperative Communication Signals Based on Aerial Computing