Xueyuan Liu, Carol Jingyi Li, Craig Jin et al. · IEEE Access · 2022
In this paper, we present a comprehensive survey and detailed comparison of techniques that have been applied to the problem of identifying the type of modulation contained within received wireless signals. Known as automatic modulation classification (AMC), the problem has been studied for many decades. AMC plays a significant role in both military and civilian scenarios and is the main step in smart receivers. Especially with the development of software-defined radios and automatic communication systems, IoT technology and the spread of 5G technology bring the number of spectrum-using equipment explosion, making the problem of scarce spectrum resources more prominent. Although AMC techniques can be optimized from the classifier’s point of view, signal pre-processing also plays a critical role. Relevant data representation approaches include time-frequency analysis, cyclostationary transforms, and hybrid techniques.We provide a taxonomy of common approaches based on order and dimensionality along with an overall analysis of signal pre-processing algorithms for AMC. Furthermore, we reproduce the major existing schemes under uniform conditions, allowing an objective comparison among different methodologies. Finally, we create an open-source Python library to simulate these techniques so the results in this paper are reproducible for future research.
Cited by 17Open access
Bo Xu, Uzair Aslam Bhatti, Hao Tang et al. · Journal of Cloud Computing Advances Systems and Applications · 2024
Abstract With the development of artificial intelligence technology and edge computing technology, deep learning-based automatic modulation classification (AI-based AMC) deployed at edge devices using centralised or distributed learning methods for optimisation has emerged in recent years, and has made great progress in the recognition accuracy and recognisable range of wireless signals. However, the lack of sufficient explanation of these models leads to low accuracy and training efficiency of model training, and their applications and further improvements are limited. Researchers have started to propose interpretable methods for technical analysis of deep learning-based AMC. In this paper, based on the research and application development of interpretable methods in recent years, we review the applicable methods and existing research challenges of interpretable automatic modulation classification. And an interpretable AI-based automatic modulation classification framework is proposed to map the interpretability of automatic modulation classification results by obtaining the contribution of wireless signal features to deep learning network training. Experimental results show that the proposed method possesses the ability to explore the classification mechanism of non-transparent auto-modulated classification networks and has the potential to help edge devices train networks with lower energy consumption and higher accuracy.
Cited by 16Open access
Anu Jagannath, Jithin Jagannath · 2021
Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, and secure communications. Consequently, it will become a key enabler with the emerging fifth-generation (5G) and beyond 5G communications, Internet of Things networks, among others. State-of-the-art studies in wireless signal recognition have only focused on a single task which in many cases is insufficient information for a system to act on. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks in conjunction with multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. Additionally, we consider the problem of heterogeneous wireless signals such as radar and communication signals in the electromagnetic spectrum. Accordingly, we have shown how the proposed MTL model outperforms several state-of-the-art single-task learning classifiers while maintaining a lighter architecture and performing two signal characterization tasks simultaneously. Finally, we also release the only known open heterogeneous wireless signals dataset that comprises of radar and communication signals with multiple labels.
Cited by 18Open access
Anu Jagannath, Jithin Jagannath · 2021
Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, and secure communications. Consequently, it will become a key enabler with the emerging fifth-generation (5G) and beyond 5G communications, Internet of Things networks, among others. State-of-the-art studies in wireless signal recognition have only focused on a single task which in many cases is insufficient information for a system to act on. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks in conjunction with multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. Additionally, we consider the problem of heterogeneous wireless signals such as radar and communication signals in the electromagnetic spectrum. Accordingly, we have shown how the proposed MTL model outperforms several state-of-the-art single-task learning classifiers while maintaining a lighter architecture and performing two signal characterization tasks simultaneously. Finally, we also release the only known open heterogeneous wireless signals dataset that comprises of radar and communication signals with multiple labels.
Cited by 15Open access
Y. Zhang, Nirwan Ansari, Wei Su · 2011
Automatic blind modulation classification (MC) is deployed, as the intermediate step between signal detection and demodulation, to identify modulation schemes automatically. Modulation classification is still a challenging task, especially in a non-cooperative environment, owing to the lack of prior information on the transmitted signal at the receiver. The proposed MC scheme based on multi-sensor signal fusion makes the premise that the combined signal from multiple sensors provides a more accurate description than any one of the individual signal alone. Multi-sensor signal fusion offers increased reliability and huge gains in overall performance as compared to the single sensor one, thus making automatic modulation classification (AMC) of weak signals in non-cooperative communication environment more reliable and successful. Modulation constellations improvements using multi-sensor signal fusion in the AWGN channel are studied first by using numerical simulations. In order to further study SNR improvement through multi-sensor signal fusion, Q-PSK signal SNR estimations using the M2M4 method after multi-sensor signal fusion with 10 sensors versus SNR are also presented. Finally, classification performances based on multi-sensor signal fusion in the AWGN channel are investigated and evaluated in terms of correct classification probability by taking the effects of timing synchronization, phase jitter, phase offset and frequency offset into consideration, respectively. Through Monte Carlo simulations, we demonstrate that the proposed multi-sensor signal fusion based AMC algorithm can greatly outperform other existing AMC schemes.
Cited by 16
Qi An, Zishu He, Huiyong Li et al. · Mobile Information Systems · 2016
Promptitude and accuracy of signals’ non-data-aided (NDA) identification is one of the key technology demands in noncooperative wireless communication network, especially in information monitoring and other electronic warfare. Based on this background, this paper proposes a new signal classifier for phase shift keying (PSK) signals. The periodicity of signal’s phase is utilized as the assorted character, with which a fractional function is constituted for phase clustering. Classification and the modulation order of intercepted signals can be achieved through its Fast Fourier Transform (FFT) of the phase clustering function. Frequency offset is also considered for practical conditions. The accuracy of frequency offset estimation has a direct impact on its correction. Thus, a feasible solution is supplied. In this paper, an advanced estimator is proposed for estimating the frequency offset and balancing estimation accuracy and range under low signal-to-noise ratio (SNR) conditions. The influence on estimation range brought by the maximum correlation interval is removed through the differential operation of the autocorrelation of the normalized baseband signal raised to the power of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"><mml:mrow><mml:mi>Q</mml:mi></mml:mrow></mml:math>. Then, a weighted summation is adopted for an effective frequency estimation. Details of equations and relevant simulations are subsequently presented. The estimator proposed can reach an estimation accuracy of<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mn mathvariant="normal">1</mml:mn><mml:msup><mml:mrow><mml:mn mathvariant="normal">0</mml:mn></mml:mrow><mml:mrow><mml:mo>-</mml:mo><mml:mn mathvariant="normal">4</mml:mn></mml:mrow></mml:msup></mml:math>even when the SNR is as low as<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"><mml:mo>-</mml:mo><mml:mn mathvariant="normal">15</mml:mn><mml:mo> </mml:mo><mml:mi mathvariant="normal">d</mml:mi><mml:mi mathvariant="normal">B</mml:mi></mml:math>. Analytical formulas are expressed, and the corresponding simulations illustrate that the classifier proposed is more efficient than its counterparts even at low SNRs.
Cited by 3Open access
Huimin Han, Zeeshan Zeeshan, Muhammad Asif et al. · SPIN · 2024
After further review and discussions among the authors, we want to do further experiment to improve the existing premature results. Specifically, authors want to add more complex analysis to support the results. Given the importance of maintaining the highest standards of academic integrity, we believe that withdrawal is the most appropriate course of action. All authors are fully aware of this decision and have agreed to the withdrawal. We have had several rounds of correspondence regarding this matter, and all authors have been included in these communications to ensure transparency and prevent any potential disputes in the future.
Cited by 0
Anu Jagannath, Jithin Jagannath · arXiv (Cornell University) · 2022
Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, comprehensive spectrum awareness on the edge has the potential to serve as a key enabler for the emerging beyond 5G networks. State-of-the-art studies in this domain have (i) only focused on a single task - modulation or signal (protocol) classification - which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.
Cited by 4Open access
Anu Jagannath, Jithin Jagannath · 2022
<p>Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Efforts are underway to address spectrum coexistence, enhance spectrum awareness, and bolster authentication schemes. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, <em>comprehensive spectrum awareness on the edge</em> has the potential to serve as a key enabler for the emerging beyond 5G (fifth generation) networks. State-of-the-art studies in this domain have (i) only focused on a single task - modulation or signal (protocol) classification - which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.</p>
Cited by 0Open access
Anu Jagannath, Jithin Jagannath · 2022
<p>Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Efforts are underway to address spectrum coexistence, enhance spectrum awareness, and bolster authentication schemes. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, <em>comprehensive spectrum awareness on the edge</em> has the potential to serve as a key enabler for the emerging beyond 5G (fifth generation) networks. State-of-the-art studies in this domain have (i) only focused on a single task - modulation or signal (protocol) classification - which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.</p>
Cited by 4Open access
Md. Shahanur Alam, Shuo Zhang, Chris Yakopcic et al. · 2023
A memristor based neuromorphic processor for on-chip training is presented. Additionally, a novel approach utilizing in-situ learning to improve wireless signal modulation classification under adversarial jamming is described. The neuromorphic system is over 50× energy efficient than optimized digital systems at this wireless signal modulation task for similar accuracy levels.
Cited by 0
Han Jia, Zhiyong Yu, Jian Yang · IET Communications · 2024
Abstract The wireless Internet of Things (IoT) is widely used for data transmission in power systems. Wireless communication is an important part of the IoT. The existing modulation classification algorithms have low classification accuracy when facing strong electromagnetic interference, which causes decoding error link interruption and wastes wireless channel resources. Therefore, it is necessary to study signal modulation classification methods in a low signal‐to‐noise ratio (SNR) environment. In this paper, a lightweight Deep Neural Networks (DNNs) modulation classification method based on the Informer architecture classifier and two‐dimensional (2‐D) curves input of the spectral correlation function (SCF) is proposed, which uses in‐phase and quadrature (I/Q) signals to generate 2‐D cross‐section SCF curve first and then feeds the feature curve into the Informer network to classify the modulation method. This model can better learn the robustness characteristics in a long sequence. Through testing, the classification accuracy of the modulation signal is not much lower than that of the current good classification method when the SNR is 10 dB, and this method can still show higher accuracy when hardware resources are limited. It is a compact design of a modulation classification model and easy to deploy on low‐cost embedded platforms.
Cited by 5Open access
Chengliang Di, Jinwei Ji, Chao Sun et al. · Electronics · 2024
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.
Cited by 3Open access
Qianfan Yu, Yanyun Guo · 2022
Modulation recognition is a key technology in the field of communication, especially in the field of non cooperative communication. It can realize the automatic recognition and classification of unknown signal modulation without prior knowledge. With the rapid development of modern communication technology, modulation methods become complex and diverse, and modulation recognition technology is also facing more challenges. Although there are relevant studies, there are still many problems and research work to be solved and improved. Based on this, a modulation recognition method of wireless communication digital signal considering multi-dimensional characteristics is proposed. By extracting multidimensional characteristic parameters, constructing multi-dimensional characteristic signal modulation decision tree model and wireless communication digital signal modulation recognition algorithm based on multi-dimensional characteristic model, the modulation mode recognition of digital signal is realized. The experiment shows that compared with the traditional methods, this recognition method has more advantages in the overall modulation recognition accuracy when the signal-to-noise ratio is rising.
Cited by 0
Clayton A. Harper, Lauren Lyons, Mitchell A. Thornton et al. · 2020
In our work, we investigate alternative forms of automatic modulation classification with deep learning and statistical methods. With a growing number of devices communicating through wireless transmission mediums, automatic modulation classification plays a critical role in reading an observed signal. We compare our proposed method with the current state of the art and show that traditional convolutional neural networks can outperform residual neural networks for the task of modulation classification. Using an approach inspired by research from the speaker verification community, we show that the modulation method used to transmit a signal can be classified into one of 24 candidate modulation types with greater than 98% accuracy for signals with high signal to noise ratios.
Cited by 6
Kai Ma, Yongbin Zhou, Jianyun Chen · 2020
Based on simulation samples of open source data collection and communication system signal pretreatment methods, we design a Convolution Neural Network (CNN) that contains three full connection layers and three convolution layers to recognize 11 different kinds of wireless signal modulation. In additive white Gaussian noise(AWGN) model, CNN networks can realize automatic modulation classification of the wireless signal by learning the deep characters of sample data, and the average recognition accuracy is up to 81% under different ratio of signal to noise (SNR). We analyze the influence between modulation recognition accuracy and network hyperparameters such as network structures, convolutional layers, dropout value, batch size, and network training methods.
Cited by 13
Lu Yin · 2025
In the background of the wide application of wireless communication technology, the electromagnetic environment is becoming more and more complex, and the traditional signal recognition and modulation classification methods based on artificial design characteristics are difficult to meet the needs. In this study, a deep learning model that integrates the local perception characteristics of convolutional neural network (CNN) and the temporal dynamic analysis capability of long short-term memory network (LSTM) is used to study various modulated signals such as BPSK, PSK8 and QAM16 under multi-SNR. By standardizing the signal amplitude with Z-score, the accuracy and robustness of signal recognition and modulation classification are improved by using the feature extraction capability of CNN and the advantages of LSTM in processing sequence data. The experimental results show that the accuracy of this model is 0.8139 on the 10-SNR test set, which is superior to other advanced algorithms. With the increase of signal-to-noise ratio, the classification accuracy is improved, and the model is robust to noise. Although some similar modulation types (such as QAM series) are misclassified, the overall classification is good. This research provides an efficient and reliable signal processing scheme for wireless communication system, which is of great significance for promoting the development of wireless communication technology.
Cited by 0
Chengliang Di, Jinwei Ji, Chao Sun et al. · Preprints.org · 2024
Abstract—Traditional automatic modulation classificationmethods operate under the closed-set assumption, which provesto be impractical in real-world scenarios due to the diversenature of wireless technologies and the dynamic characteristicsof wireless propagation environments. Open-set environments introduce substantial technical challenges, particularly in terms ofdetection effectiveness and computational complexity. To addressthe limitations of modulation classification and recognition inopen-set scenarios, this paper proposes a semi-supervised openset recognition approach, termed SOAMC (Semi-SupervisedOpen-Set Automatic Modulation Classification). The primaryobjective of SOAMC is to accurately classify unknown modulation types, even when only a limited subset of samples ismanually labeled. The proposed method consists of three keystages: (1) A signal recognition pre-training model is constructedusing data augmentation and adaptive techniques to enhancerobustness. (2) Feature extraction and embedding are performedvia a specialized extraction network. (3) Label propagation isexecuted using a graph convolutional neural network (GCN) toefficiently annotate the unlabeled signal samples. Experimentalresults demonstrate that SOAMC significantly improves classification accuracy, particularly in challenging scenarios with limitedlabeled data and high signal similarity. These findings are criticalfor the practical identification of complex and diverse modulationsignals in real-world wireless communication systems.
Cited by 2Open access
Bojun Zhang · 2024
Automatic modulation identification plays an important role in wireless communication systems. With the development of deep learning technology, more and more researches have begun to adopt deep learning methods for modulation identification. However, traditional deep learning methods face interference from nonlinearity, noise, and time-varying nature of the signal when processing the signal, resulting in degradation of classification performance. Meanwhile, single modal features are difficult to fully capture the time and spatial domain information of the signal, which is important for accurately identifying the signal modulation type. To overcome these limitations, this study proposes a multi-modal deep learning based signal modulation recognition scheme. The scheme improves the modulation recognition performance by fusing features from different modalities, including time, frequency and spatial domain features. Experimental results show that the proposed method achieves significant performance improvement in the signal modulation recognition task. This provides a more robust and accurate modulation identification capability for wireless communication systems.
Cited by 1
Maolin Wang, Dongming Fan, Yuanyuan Ma · 2024
In the rapidly evolving landscape of wireless communication technology, the increasing number of wireless communication devices has led to high spectrum utilization rates. To effectively monitor and manage wireless communication, this paper proposes an automatic modulation recognition (AMR) method based on the short-time fourier transform (STFT). Through STFT, communication signal features can be effectively extracted and converted into feature maps. A method of overlapping block processing is proposed, combined with Vision Transformer (ViT), to identify the modulation scheme of the signal. Experimental results demonstrate that the proposed architecture, based on STFT and VIT, achieves a modulation classification accuracy of 96.4% for six different modulation formats of communication signals, and maintains excellent recognition accuracy under various signal-to-noise ratios. This research provides a new method for radio detection and spectrum management, contributing to the assurance of communication security.
Cited by 3