FSOS-AMC: Few-Shot Open-Set Learning for Automatic Modulation Classification Over Multipath Fading Channels

Automatic modulation classification (AMC), which aims to identify the modulation types of unknown signals without any prior knowledge, plays a key role in intelligent wireless communication. In recent years, the outstanding achievements of deep learning in the fields of computer vision and nature language processing have promoted the continuous researches of deep learning in AMC. In view of the fact that the existing deep learning-based AMC ignores the frequency attribute of the modulated signals, this paper proposed an AMC approach based on deep learning which comprehensively considers the contribution of frequency and spatiotemporal characteristics of the modulated signals. Specifically, we utilize the sliding window to divide the raw signals into short-time signal slices. In order to obtain the representation of frequency domain of the signals, each short-time signal slice is decomposed into several modes by variational mode decomposition (VMD), which is an adaptive signal decomposition technique. Finally, all the modes are used as input of the convolutional neural network (CNN) as a tensor to learn high-level features from the frequency and spatiotemporal domain to identify the modulation type. In this paper, we verify the effectiveness of the proposed approach with 10 kinds of modulation types generated by SMW200A Vector Signal Generator. More importantly, the proposed approach achieves 99.2% of the overall classification accuracy at 8dB signal to noise ratio (SNR) and shows better robustness to noise than the existing AMC approaches.

Automatic modulation classification (AMC) is a typical technology for identifying different modulation types, which has been widely applied into various scenarios. Recently, deep learning (DL), one of the most advanced classification algorithms, has been applied into AMC. However, these previously proposed AMC methods are centralized in nature, i.e., all training data must be collected together to train the same neural network. In addition, they are generally based on powerful computing devices and may not be suitable for edge devices. Thus, a distributed learning-based AMC (DistAMC) method is proposed, which relies on the cooperation of multiple edge devices and model averaging (MA) algorithm. When compared with the centralized AMC (CentAMC), there are two advantages of the DistAMC: the higher training efficiency and the lower computing overhead, which are very consistent with the characteristics of edge devices. Simulation results show that there are slight performance gap between the DistAMC and the CentAMC, and they also have similar convergence speed, but the consumed training time per epoch in the former method will be shorter than that on the latter method, if the low latency and the high bandwidth are considered in model transmission process of the DistAMC. Moreover, the DistAMC can combine the computing power of multiple edge devices to reduce the computing overhead of a single edge device in the CentAMC.

Nowadays, automatic modulation classification (AMC) plays an important role in both cooperative and non-cooperative communication applications. Very often, multipath fading channels result in the severe AMC performance degradation or induce large classification errors. The negative impacts of multipath fading channels on AMC have been discussed in the existing literature but no solution has ever been proposed so far to the best of our knowledge. In this paper, we propose a new robust AMC algorithm, which applies higher-order statistics (HOS) in a generic framework for blind channel estimation and pattern recognition. We also derive the Cramer-Rao lower bound for the fourth-order cumulant estimator when the AMC candidates are BPSK and QPSK over the additive white Gaussian noise channel, and it is a nearly minimum-variance estimator leading to robust AMC features in a wide variety of signal-to-noise ratios. The advantage of our new algorithm is that, by carefully designing the essential features needed for AMC, we do not really have to acquire the complete channel information and therefore it can be feasible without any a priori information in practice. The Monte Carlo simulation results show that our new AMC algorithm can achieve the much better classification accuracy than the existing AMC techniques.

Cognitive Radio (CR) systems allow optimizing the use of the shared radio spectrum and enhancing the coexistence among different technologies by efficiently changing certain operating parameters of the radios such as transmit-power, carrier frequency, and modulation and coding scheme in real-time. Dynamic Spectrum Access (DSA), which allows radios to dynamically access and use the unused spectrum, is one of the tasks that are fundamental for a better use of the spectrum. In this paper, we extend the previous work on Automatic Modulation Classification (AMC) by using Deep Neural Network (DNNs) and evaluate the performance of these architectures on signals that are not only modulated but are also encoded. We call this the Automatic Modulation and Coding Scheme Classification problem, or \(AMC^2\). In this problem, radio signals are classified according to the Modulation and Coding Scheme (MCS) used during their transmission. Evaluations on a data set of 802.11 radio signals, transmitted with different MCS and Signal to Noise Ratio (SNR), provide important results on the impact of some DNN hyperparameters, e.g. number of layers, batch size, etc., in the classification accuracy.

Automatic modulation classification (AMC) is deployed, as the intermediate step between signal detection and demodulation, to identify modulation schemes automatically. Modulation classification is a challenging task, especially in a non-cooperative environment, owing to the lack of prior information on the transmitted signal at the receiver; the problem will be more challenging in the multipath fading channel. The proposed AMC method based on optimal decision fusion by using wireless sensor networks provides a more accurate classification result than any one of the individual signal alone. Wireless sensor networks offer increased reliability and optimal decision fusion provides huge gains in overall classification performance as compared to that of the single sensor. Thus, optimal decision fusion based AMC by using wireless sensor networks greatly enhances classification performance of weak signals in non-cooperative communication environment. Classification performances of optimal decision fusion based AMC by using wireless sensor networks in the multipath fading channel are investigated and evaluated in terms of correct classification probability. Through Monte Carlo simulations, we demonstrate that the proposed AMC algorithm can greatly outperform that of single sensor in multipath fading channel.

Automatic modulation classification (AMC) is a signal processing technology used to identify the modulation type of unknown signals without prior information such as modulation parameters for drone communications. In recent years, deep learning (DL) has been widely used in AMC methods due to its powerful feature extraction ability. The significant performance of DL-based AMC methods is highly dependent on large amount of data. However, with the increasingly complex signal environment and the emergence of new signals, several recognition tasks have difficulty obtaining sufficient high-quality signals. To address this problem, we propose an AMC method based on a deep residual neural network with masked modeling (DRMM). Specifically, masked modeling is adopted to improve the performance of a deep neural network with limited signal samples. Both complex-valued and real-valued residual neural networks (ResNet) play an important role in extracting signal features for identification. Several typical experiments are conducted to evaluate our proposed DRMM-based AMC method on the RadioML 2016.10A dataset and a simulated dataset, and comparison experiments with existing AMC methods are also conducted. The simulation results illustrate that our proposed DRMM-based AMC method achieves better performance in the case of limited signal samples with low signal-to-noise ratio (SNR) than other existing methods.

Automatic modulation classification (AMC) has recently attracted widespread attention nowadays due to its desirable features of generalisability and requirement of little prior knowledge through artificial intelligence (AI) technology. The authors propose a stacked auto-encoder (SAE) based on various optimisation methods structure to intelligently process a feature space that includes spectral-based features and high-order cumulants. To unify the dimensionality of the features, they apply different normalisation methods to the feature space before training the SAE model to decide corresponding normalisations under different noise environments. Linear normalisation is superior when signal-to-noise ratio (SNR) is low, and standardisation is superior when SNR is between -1 and 4 dB. Regularisation works best when SNR is greater than 5 dB. To increase the recognition accuracy of the proposed model, they introduce the unconstrained optimisation theory to adjust the proposed SAE model, including Nelder-Mead method, Newton optimisation method, conjugate gradient method and quasi-Newton method. They observe that the quasi-Newton method offers desirable performance when optimising SAE model. It is the first time to compare these data normalisation methods and discuss unconstrained optimisation theory together to recognise modulation types. The recognition accuracy of this model for eight modulation types can reach 99.8% when SNR ranges from − 5 to 10 dB.

Traditional automatic modulation classification methods operate under the closed-set assumption, which proves to be impractical in real-world scenarios due to the diverse nature of wireless technologies and the dynamic characteristics of wireless propagation environments. Open-set environments introduce substantial technical challenges, particularly in terms of detection effectiveness and computational complexity. To address the limitations of modulation classification and recognition in open-set scenarios, this paper proposes a semi-supervised open-set recognition approach, termed SOAMC (Semi-Supervised Open-Set Automatic Modulation Classification). The primary objective of SOAMC is to accurately classify unknown modulation types, even when only a limited subset of samples is manually labeled. The proposed method consists of three key stages: (1) A signal recognition pre-training model is constructed using data augmentation and adaptive techniques to enhance robustness. (2) Feature extraction and embedding are performed via a specialized extraction network. (3) Label propagation is executed using a graph convolutional neural network (GCN) to efficiently annotate the unlabeled signal samples. Experimental results demonstrate that SOAMC significantly improves classification accuracy, particularly in challenging scenarios with limited amounts of labeled data and high signal similarity. These findings are critical for the practical identification of complex and diverse modulation signals in real-world wireless communication systems.

Automatic Modulation Classification (AMC) is a critical technology in the field of non-cooperative communication. Carrier frequency offset is an inevitable impairment factor in communication systems, and it significantly affects the performance of AMC, especially when the range is large. Therefore, frequency offset estimation and compensation are essential for automatic modulation classification. To address this issue, this paper proposes an innovative cascading network based on deep learning, primarily comprising pre-classification and compensation mechanisms. With the pre-classification mechanism, we categorize the eleven unknown modulation formats into three major classes: PSK, FSK, and QAM. Subsequently, we utilize deep neural networks to estimate the frequency offset of signals within these major classes, followed by performing the corresponding signal compensation. The experimental results demonstrate that the pre-classification mechanism effectively reduces the error in frequency offset estimation, minimizing the error <Formula format="inline"><TexMath><?TeX $\log MSE$ ?></TexMath><File name="a00--inline1" type="gif"/></Formula> (mean-square error) to as low as -3.9. Under various signal-to-noise ratio (SNR) ranges, the classification accuracy achieved through pre-classification and compensation is up to 14% higher than the accuracy without this method. Specifically, at SNR = 10 dB, it can reach 99%. Moreover, the proposed scheme is robust and performs stably across different frequency offsets range, outperforming other existing network classification schemes to some extent.

Automatic modulation classification (AMC) is to identify the modulation type of a received signal, which plays a vital role to ensure the physical-layer security for Internet of Things (IoT) networks. Inspired by the great success of deep learning in pattern recognition, the convolutional neural network (CNN) and recurrent neural network (RNN) are introduced into the AMC. In general, there are two popular data formats used by AMC, which are the in-phase/quadrature (I/Q) representation and amplitude/phase (A/P) representation, respectively. However, most of AMC algorithms aim at structure innovations, while the differences and characteristics of I/Q and A/P are ignored to analyze. In this article, lots of popular AMC algorithms are reproduced and evaluated on the same data set, where the I/Q and A/P are used, respectively, for comparison. Based on the experimental results, it is found that: 1) CNN-RNN-like algorithms using A/P as input data are superior to those using I/Q at high signal-to-noise ratio (SNR), while it has an opposite result in low SNR and 2) the features extracted from I/Q and A/P are complementary to each other. Motivated by the aforementioned findings, a multitask learning-based deep neural network (MLDNN) is proposed, which effectively fuses I/Q and A/P. In addition, the MLDNN also has a novel backbone, which is made up of three blocks to extract discriminative features, and they are CNN block, bidirectional gated recurrent unit (BiGRU) block, and a step attention fusion network (SAFN) block. Different from most of CNN-RNN-like algorithms (i.e., they only use the last step outputs of RNN), all step outputs of BiGRU can be effectively utilized by MLDNN with the help of SAFN. Extensive simulations are conducted to verify that the proposed MLDNN achieves superior performance in the public benchmark.

Automatic modulation classification (AMC) plays an important role in many fields to identify the modulation type of wireless signals. In this paper, we introduce deep learning to signal recognition. Based on architecture analysis of the convolutional neural network (CNN), we used real signal data generated by instruments as dataset, and proposed an improved CNN architecture to achieve compatible recognition accuracy of modulation classification. According to various conditions of signal noise ratio (SNR), we test the proposed CNN architecture with the real sampled signals. Experiments results show that the high-layer network is not necessary for modulation recognition with high SNR signals. The proposed CNN architecture has higher average classification accuracy than RESNET and is more compatible for modulation classification of signals with lower SNR.

Wiener filter is the best linear filter under the minimum mean square error criterion. It can effectively eliminate the influence of noise, which may deal with the problem of Automatic modulation classification (AMC) performing poorly at low Signal-to-Noise Ratio (SNR). This paper explores how to use Wiener filter to improve the classification performance in the AMC, combining cumulant and Back Propagation (BP) neural network to classify Six kinds of digital modulation signals. The simulation results show that the AMC with Wiener filter preprocessing has a higher classification rate under low SNR (-10dB).

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.

Automatic modulation classification (AMC), as a key technology of cognitive radio, has become a focal point of research. However, most deep learning-based AMC methods require an extensive number of labeled signals to acquire a comprehensive understanding of modulation types, placing substantial pressure on signal acquisition and labeling. To solve this issue, we propose a few-shot AMC (FSAMC) method to facilitate rapid generalization and recognition with limited data, namely multi-scale feature fusion and distribution similarity network (MS2F-DS). Firstly, we design a multi-scale feature fusion (MS2F) model, which aims to extract features with varying fields of view and boost feature fusion, enabling the derivation of contextual information from the signal. Furthermore, we introduce a distribution similarity (DS) classifier to address the insufficient measurement of current similarity measurement functions by considering both micro and macro perspectives of vectors, further increasing intra-class compactness and inter-class separability. Finally, extensive experiments were conducted on 3-way 1, 3, and 5-shot FSAMC tasks using public datasets RML2016.10a and RML2016.10b, and the results demonstrated the effectiveness of our method.

Recently, automatic modulation classification (AMC) has been studied by more and more researchers, and a host of methods based on deep learning have been proposed. Different from image data, signal data is a sequence that changes with time, and has temporal characteristics. Like the spatial feature, the temporal feature cannot be ignored. In this paper, we add a Long Short-Term Memory (LSTM) module to the convolutional neural network (CNN) to learn the time-related features of wireless signals. LSTM learns the dependency relationship between the current element and the elements before-after through the gating structure. Experimental results show that our proposed methods perform better than the model without LSTM. The proposed network Incept-LSTM has a classification accuracy of 97.5% at a high signal-to-noise ratio (SNR). Compared to the model without LSTM, the classification accuracy of our proposed model is improved by 0.1% to 5.7%. At the same time, we compared the classification accuracy under different SNRs to explore its impact on classification performance. We found the classification ability of LSTM is more prominent at the low SNRs.