Modulation Classification Algorithm Research Articles

A lightweight deep learning architecture for automatic modulation classification of wireless internet of things

AbstractThe 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.

Generative UAP attacks against deep‐learning based modulation classification

AbstractThanks for its powerful feature extraction capability and unprecedented success in computer vision and language processing tasks, deep learning (DL) has also been applied in recent years to wireless communications. However, DL models are proved to be inherently vulnerable to adversarial perturbations: carefully crafted perturbations that appear imperceptible but can fool the models to induce misclassification. Existing researches in wireless communications employ the gradient‐based or optimization based methods, for example, FGSM, PGD and iterative FGSM, to craft input‐dependent adversarial perturbations. However, these methods have a high computational complexity and the perturbations they craft cannot be readily applied to fool DL‐based algorithms in wireless communications. In this paper, the efficient generation of universal (input‐agnostic) adversarial perturbations (UAPs) used to attack DL‐based modulation classification algorithms is studied. Communication signals exhibit unique characteristics, for example, received modulated signals after transmitting through noisy channels are densely distributed around the modulation constellation points. In this work, the authors have proposed, by making use of this unique characteristics, a generative network to model the distribution of adversarial perturbations for high‐efficiency generation of UAPs, which can fool the DL‐based modulation classification algorithms for most inputs. Instead of attacking all regions of modulated signals, attention mechanisms are introduced in generative network design that enables the perturbations to be concentrated around the constellation points. In this way, a higher attack efficiency and a lower perceptibility are achieved by crafting UAPs with smooth variations and more focused attack. In addition, a diversity term is included in loss function to help capture a wide range distribution of adversary perturbations that will help the generation of more diverse adversary perturbations. Once trained, the generative network can construct with ease a large number of UAPs with some favorable features, which will benefit more efficient adversarial attack and faster adversarial training. Experimental results show the superiority of our proposed method in terms of attack efficiency, imperceptibility and diversity over existing methods.

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.

Deep Learning Based Cognitive Radio Modulation Parameter Estimation

Automatic Modulation Classification (AMC) is a critical issue in electromagnetic spatial perception. Currently traditional recognition techniques are difficult to adapt to complex signal situations. Most existing modulation classification algorithms ignore the complementarity between different features and the importance of feature fusion. Based on this, we proposed a method for image feature fusion for AMC that fully uses the complementarity between different image features. The original signal is converted into an image by the Gramian Angular Field (GAF) method, and the GAF image is used as the input to the network, meanwhile the received signal is converted from the Inphase-Quadrature (I-Q) domain to the r-θ domain using the Accumulated Polar Feature conversion technique, and the original signal is feature coded from the r-θ domain and then converted into an image. The fused features of the two images are used as input to the neural network for model training to achieve automatic modulation classification of multiple types of signals. In the evaluation phase, the differences in the recognition effectiveness of the proposed method by different neural networks are discussed. Experiments show that the best performance is achieved using the Swin-Transformer network model, with a more than 90% recognition rate for the modulation method at signal-to-noise ratios greater than 4dB.

A Survey of Modulation Classification Using Deep Learning: Signal Representation and Data Preprocessing.

Modulation classification is one of the key tasks for communications systems monitoring, management, and control for addressing technical issues, including spectrum awareness, adaptive transmissions, and interference avoidance. Recently, deep learning (DL)-based modulation classification has attracted significant attention due to its superiority in feature extraction and classification accuracy. In DL-based modulation classification, one major challenge is to preprocess a received signal and represent it in a proper format before feeding the signal into deep neural networks. This article provides a comprehensive survey of the state-of-the-art DL-based modulation classification algorithms, especially the techniques of signal representation and data preprocessing utilized in these algorithms. Since a received signal can be represented by either features, images, sequences, or a combination of them, existing algorithms of DL-based modulation classification can be categorized into four groups and are reviewed accordingly in this article. Furthermore, the advantages as well as disadvantages of each signal representation method are summarized and discussed.

BacalhauNet: A tiny CNN for lightning-fast modulation classification

Deep learning methods have been shown to be competitive solutions for modulation classification tasks, but suffer from being computationally expensive, limiting their use on embedded devices. We propose a new deep neural network architecture which employs known structures, depth-wise separable convolution and residual connections, as well as a compression methodology, which combined lead to a tiny and fast algorithm for modulation classification. Our compressed model won the first place in ITU's AI/ML in 5G Challenge 2021, achieving 61.73� compression over the challenge baseline and being over 2.6� better than the second best submission. The source code of this work is publicly available at github.com/ITU-AI- ML-in-5G-Challenge/ITU-ML5G-PS-007-BacalhauNet.

Wireless modulation classification based on Radon transform and convolutional neural networks

Convolutional Neural Networks (CNNs) are efficient tools for pattern recognition applications. They have found applications in wireless communication systems such as modulation classification from constellation diagrams. Unfortunately, noisy channels may render the constellation points deformed and scattered, which makes the classification a difficult task. This paper presents an efficient modulation classification algorithm based on CNNs. Constellation diagrams are generated for each modulation type and used for training and testing of the CNNs. The proposed work depends on the application of Radon Transform (RT) to generate more representative patterns for the constellation diagrams to be used for training and testing. The RT has a good ability to represent discrete points in the spatial domain as curved lines. Several pre-trained networks including AlexNet, VGG-16, and VGG-19 are used as classifiers for modulation type from the spatial-domain constellation diagrams or their RTs. Several simulation experiments are presented in this paper to compare different scenarios for modulation classification at different Signal-to-Noise Ratios (SNRs) and fading channel conditions.

Automatic Classification of Superimposed Modulations for 5G MIMO Two-Way Cognitive Relay Networks

To promote reliable and secure communications in the cognitive radio network, the automatic modulation classification algorithms have been mainly proposed to estimate a single modulation. In this paper, we address the classification of superimposed modulations dedicated to 5G multiple-input multiple-output (MIMO) two-way cognitive relay network in realistic channels modeled with Nakagami- distribution. Our purpose consists of classifying pairs of users modulations from superimposed signals. To achieve this goal, we apply the higher-order statistics in conjunction with the MultiBoostAB classifier. We use several efficiency metrics including the true positive (TP) rate, false positive (FP) rate, precision, recall, F-Measure and receiver operating characteristic (ROC) area in order to evaluate the performance of the proposed algorithm in terms of correct superimposed modulations classification. Computer simulations prove that our proposal allows obtaining a good probability of classification for ten superimposed modulations at a low signal-to-noise ratio, including the worst case (i.e., ), where the fading distribution follows a one-sided Gaussian distribution. We also carry out a comparative study between our proposal using MultiBoostAB classifier with the decision tree (J48) classifier. Simulation results show that the performance of MultiBoostAB on the superimposed modulations classifications outperforms the one of J48 classifier. In addition, we study the impact of the symbols number, path loss exponent and relay position on the performance of the proposed automatic classification superimposed modulations in terms of probability of correct classification.

Accuracy Analysis of Feature-Based Automatic Modulation Classification via Deep Neural Network.

A feature-based automatic modulation classification (FB-AMC) algorithm has been widely investigated because of its better performance and lower complexity. In this study, a deep learning model was designed to analyze the classification performance of FB-AMC among the most commonly used features, including higher-order cumulants (HOC), features-based fuzzy c-means clustering (FCM), grid-like constellation diagram (GCD), cumulative distribution function (CDF), and raw IQ data. A novel end-to-end modulation classifier based on deep learning, named CCT classifier, which can automatically identify unknown modulation schemes from extracted features using a general architecture, was proposed. Features except GCD are first converted into two-dimensional representations. Then, each feature is fed into the CCT classifier for modulation classification. In addition, Gaussian channel, phase offset, frequency offset, non-Gaussian channel, and flat-fading channel are also introduced to compare the performance of different features. Additionally, transfer learning is introduced to reduce training time. Experimental results showed that the features HOC, raw IQ data, and GCD obtained better classification performance than CDF and FCM under Gaussian channel, while CDF and FCM were less sensitive to the given phase offset and frequency offset. Moreover, CDF was an effective feature for AMC under non-Gaussian and flat-fading channels, and the raw IQ data can be applied to different channels’ conditions. Finally, it showed that compared with the existing CNN and K-S classifiers, the proposed CCT classifier significantly improved the classification performance for MQAM at N = 512, reaching about 3.2% and 2.1% under Gaussian channel, respectively.

A Lightweight CNN Architecture for Automatic Modulation Classification

Automatic modulation classification (AMC) algorithms based on deep learning (DL) have been widely studied in the past decade, showing significant performance advantage compared to traditional ones. However, the existing DL methods generally behave worse in computational complexity. For this, this paper proposes a lightweight convolutional neural network (CNN) for AMC task, where we design a depthwise separable convolution (DSC) residual architecture for feature extraction to prevent the vanishing gradient problem and lighten the computational burden. Besides that, in order to further reduce model complexity, global depthwise convolution (GDWConv) is adopted for feature reconstruction after the last (non-global) convolutional layer. Compared to recent works, the experimental results show that the proposed network can save approximately 70~98% model parameters and 30~99% inference time on two well-known benchmarks.

Iterative Modulation Classification Algorithm for Two-Path Successive Relaying Systems

Two-path successive relaying (TPSR) systems have been recently proposed as powerful candidates for improving the spectral efficiency of cooperative communications. The previously reported investigations for such systems are limited to information-theoretic analysis, parameters estimation, interference cancellation, and data detection. In this contribution, we discuss the problem of modulation classification (MC) for TPSR systems for the first time in the literature. We exploit the specific nature of the received signal to derive a maximum-likelihood (ML) estimate of the modulation format of a received signal. Since the exact ML solution is shown to be too challenging for real applications, we resort to the expectation-maximization (EM) method as a low complexity iterative procedure. Channel estimation is also introduced as an auxiliary task for the proposed algorithm. The computational complexity analysis and simulation results confirm the effectiveness of the proposed iterative algorithm where no existing alternatives are available.

Code-Aided Modulation Classification Algorithm for Multiuser Uplink SC-FDMA Systems

Modulation classification has attracted great interest in rapid deployment in wireless radios for civilian and military applications. While there is a massive amount of works on this topic for single-signal transmissions, a few works are reported in the literature for multi-signal transmissions. Therefore, there is an urgent need to explore different modulation classification algorithms for such scenarios. In this work, we propose a novel modulation classification algorithm for multiuser uplink single-carrier frequency division multiple access systems exploiting the channel decoder's soft information as a beneficial resource to improve the classification performance. Starting from the maximum-likelihood principle, we analytically design the proposed algorithm using a space-alternating generalized expectation-maximization approach. Channel estimation is also developed as an auxiliary task for the proposed algorithm. Simulation results indicate that the proposed algorithm is superior to the traditional algorithms with reduced processing time.

Design and Implementation of Blind Modulation Classification for Asynchronous MIMO-OFDM System

In this article, we design and implement a tree-based blind modulation classification algorithm for asynchronous multiple-input–multiple-output and orthogonal frequency-division multiplexing (MIMO-OFDM) systems. It can classify many of the linearly modulated signals, such as binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), offset QPSK, minimum shift keying, and 16-quadrature amplitude modulation. The proposed classifier works in the presence of unknown frequency, timing, and phase offsets and with no prior knowledge of channel state information. Classification is performed in three steps. In the first step, preprocessing is done on the received signal to nullify the effect of timing offset. In the second step, key features are extracted by calculating higher order cumulants of the frequency-domain signal. In the third step, thresholds are determined by using the likelihood ratio test. A closed-form theoretical derivation for the probability of correct classification is obtained. The Monte Carlo simulations are conducted to compare the performance of the proposed algorithm with the existing algorithms. Finally, the proposed algorithm is validated through radio frequency testbed measurements over an indoor propagation environment.

A blind classification method of adaptive coding and modulation signals based on cumulants

This paper proposes a blind modulation classification method for adaptive coding and modulation signals base on the difference in high-order cumulants of different modulation types. Use high-order cumulants to establish features to design modulation classification algorithm and decision thresholds. Because of the time-varying characteristics of adaptive coding and modulation signals, the segmentation classification method is used to realize the modulation classification of each frame in the time dimension. Finally, the designed algorithm is simulated, and the classification performance of the algorithm under different modulation types, segment lengths and signal-to-noise ratios is analyzed.

Deep learning based modulation classification for 5G and beyond wireless systems

The 5G and beyond wireless networks will be more dynamic and heterogeneous, which needs to work on multistrand waveforms. One of the most significant challenges in such a dynamic network, especially non cooperated cases, is the identification of particular modulation type, which the transmitter uses at the given time to decode the data successfully. This research proposes a modulation classification algorithm using the combination architectures of modified convolutional neural network. The proposed deep learning architecture is developed by combining the convolutional neural network, dense network, and long short-term memory network (LSTM), which is named as convolutional LSTM dense neural network (CLDNN). Moreover, the mean cumulative sum metric (MCS) is introduced in the pooling layer for improved classification accuracy. Dimensionality reduction through Principal Component Analysis is also applied to minimize the training time, so that the proposed architecture can be adopted for its practical usage. The simulation results prove that the presented CLDNN outperforms an ordinary CNN, while taking less training time.

Towards an accurate radar waveform recognition algorithm based on dense CNN

Existing algorithms for radar waveform classification currently exhibit the lower recognition accuracy, especially at the lower signal to noise ratio (SNR) environment. To remedy these flaws, this paper proposes an accurate automatic modulation classification algorithm based on dense convolutional neural networks (AAMC-DCNN). The algorithm owns the competitive advantages of strengthening the feature reuse and extracting the detailed feature, for improving the recognition performance of radar waveform at the lower SNR. First, the dense convolutional neural networks (CNN) are designed, which connects each layer to every other layer in a feed-forward pattern. In the latter, 8 types of signals are converted into time-frequency images by choi-williams distribution (CWD), and the large training and testing datasets are fabricated. Then, the transfer learning and Adam optimization are introduced. Finally, the experimental analyses are carried out to evaluate the recognition performance. It is worth mentioning that the classification accuracy can be up to 93.4% when the SNR is −8 dB, and even reach to 100% at 0 dB, which demonstrates the superior performance over others. The present work provides a sound experimental basis for further studying automatic modulation classification for the sake of future field application in electronic warfare systems.

Automatic Modulation Classification Based on Constellation Density Using Deep Learning

Deep learning (DL) is a newly addressed area of research in the field of modulation classification. In this letter, a constellation density matrix (CDM) based modulation classification algorithm is proposed to identify different orders of ASK, PSK, and QAM. CDM is formed through local density distribution of the signal’s constellation generated using LabVIEW for a wide range of SNR. Two DL models, ResNet-50 and Inception ResNet V2 are trained through color images formed by filtering the CDM. Classification accuracy achieved demonstrates better performance compared to many existing classifiers in the literature.

Blind Modulation Classification for Asynchronous OFDM Systems Over Unknown Signal Parameters and Channel Statistics

Blind modulation classification (MC) is an integral part of designing an adaptive or intelligent transceiver for future wireless communications. However, till date, only a few works have been reported in the literature for blind MC of orthogonal frequency division multiplexing (OFDM) system over frequency-selective fading environment. In this paper, a blind MC algorithm has been proposed and implemented over National Instruments (NI) testbed setup for linearly modulated signals of OFDM system by using discrete Fourier transform (DFT) and normalized fourth-order cumulant. The proposed MC algorithm works in the presence of synchronization errors, i.e., frequency, timing, and phase offsets and without the prior information about the signal parameters and channel statistics. To nullify the effect of timing offset in the feature extraction process, a statistical average has been taken over OFDM symbols after introducing uniformly distributed random timing offsets in each of the OFDM symbols. In this work, we have classified a more extensive pool of modulation formats for OFDM signal, i.e., binary phase-shift keying (BPSK), quadrature PSK (QPSK), offset QPSK (OQPSK), minimum shift keying (MSK), and 16 quadrature amplitude modulation (16-QAM). Classification is performed in two stages. At the first stage, a normalized fourth-order cumulant is used on the DFT of the received OFDM signal to classify OQPSK, MSK, and 16-QAM modulation formats. At the second stage, first we compute the DFT of the square of the received OFDM signal and then a normalized fourth-order cumulant is used to classify BPSK and QPSK modulation formats. The success rate of the proposed MC algorithm is evaluated through analytical and Monte Carlo simulations and compared with existing methods. Finally, the work is validated by providing an experimental setup on NI hardware over an indoor propagation environment.

Low overhead NOMA receiver with automatic modulation classification techniques

Recently non-orthogonal multiple access (NOMA) technique has been proposed for boosting spectral efficiencies in 5G cellular networks. In NOMA the transmitter maps a predefined number of user symbols on to the same resources. The conventional receiver for NOMA is the well-known serial interference cancellation. To overcome the problem of high overhead signalling, a receiver with an automatic modulation classification (AMC) algorithm for a K-user NOMA which identifies the modulation scheme of users before symbol detection is proposed. First, a two-user NOMA (TU-NOMA) scheme is treated and the receiver is extended to more general cases. For evaluating the performance of the proposed receiver its bit error rate (BER) for TU-NOMA case has been driven and shown that this can be approximated as the sum of the demodulator BER and the AMC algorithm error probability. The simulation results show the BER degradation can be neglected if an enough number of symbols with sufficiently large SNR values are available.

Modulation Order Reduction Method for Improving the Performance of AMC Algorithm Based on Sixth–Order Cumulants

For the last two decades a large number of different automatic modulation classification (AMC) algorithms were developed, and many improvements in classification performance are reported. This was commonly achieved by engaging complex structures of neural networks, or other adaptable mechanisms for achieving better precision, when it comes to decision-making. Still, from practical implementation point of view, low algorithm complexity, economical usage of resources and fast execution remain to represent very desirable properties of an AMC algorithm. These properties are recognized in AMC algorithms based on higher - order cumulants as classification features, so their further improvement is of interest. Previous performance analysis of an algorithm based on sixth - order cumulants, in scenarios with complex valued signals' classification, showed that improvements are possible in the context of resources engaged and speed of execution. In this paper a novel approach is presented, for improving the correctness of classification process with sixth-order cumulants and simple two-step feature extraction structure, by engaging a new method for reduction of observed signal's modulation order which directly improves the classification performance. While tested with sixth-order cumulants, proposed method preserves good statistical properties of signal's higher - order cumulants in general, so it can be adopted in other AMC algorithms as well. Proposed modulation order reduction method is described in details, tested through computer simulations within the sixth-order cumulant AMC algorithm, and achieved improvements in performance are presented and explained.