Performance Of Automatic Modulation Classification Research Articles

Time and Space Complexity Reduction of KFDA-based LTE Modulation Classification

Background: Kernel Fisher discriminant analysis (KFDA) is a nonlinear discrimination technique for improving automatic modulation classification (AMC) accuracy. Our study showed that the higher-order cumulants (HOCs) of the Long-term evolution (LTE) modulation types are nonlinearly separable, so the KFDA technique is a good solution for its modulation classification problem. Still, research papers showed that the KFDA suffers from high time and space computational complexity. Some studies concentrated on reducing the KFDA time complexity while preserving the AMC performance accuracy by finding faster calculation techniques, but unfortunately, they couldn't reduce the space complexity. Objective: This study aims to reduce the time and space computational complexity of the KFDA algorithm while preserving the AMC performance accuracy. Methods: Two new time and space complexity reduction algorithms have been proposed. The first algorithm is the most discriminative dataset points (MDDP) algorithm, while the second is the k-nearest neighbors-based clustering (KNN-C) algorithm Results: The simulation results show that these algorithms could reduce the time and space complexities, but their complexity reduction is a function of signal-to-noise ratio (SNR) values. On the other hand, the KNN-C-based KFDA algorithm has less complexity than the MDDP-based KFDA algorithm Conclusion: The time and space computation complexity of the KFDA could be effectively reduced using MDDP and KNN-C algorithms; as a result, its calculation became much faster and had less storage size.

Automatic Modulation Classification for Underwater Acoustic Communication Signals Based on Deep Complex Networks

Automatic modulation classification (AMC) is an important method for monitoring and identifying any underwater communication interference. Since the underwater acoustic communication scenario is full of multi-path fading and ocean ambient noise (OAN), coupled with the application of modern communication technology, which is usually susceptible to environmental influences, automatic modulation classification (AMC) becomes particularly difficult when it comes to an underwater scenario. Motivated by the deep complex networks (DCN), which have an innate ability to process complex data, we explore DCN for AMC of underwater acoustic communication signals. To integrate the signal processing method with deep learning and overcome the influences of underwater acoustic channels, we propose two complex physical signal processing layers based on DCN. The proposed layers include a deep complex matched filter (DCMF) and deep complex channel equalizer (DCCE), which are designed to remove noise and reduce the influence of multi-path fading for the received signals, respectively. Hierarchical DCN is constructed using the proposed method to achieve better performance of AMC. The influence of the real-world underwater acoustic communication scenario is taken into account; two underwater acoustic multi-path fading channels are conducted using the real-world ocean observation dataset, white Gaussian noise, and real-world OAN are used as the additive noise, respectively. Contrastive experiments show that the AMC based on DCN can achieve better performance than the traditional deep neural network based on real value (the average accuracy of the DCN is 5.3% higher than real-valued DNN). The proposed method based on DCN can effectively reduce the influence of underwater acoustic channels and improve the AMC performance in different underwater acoustic channels. The performance of the proposed method was verified on the real-world dataset. In the underwater acoustic channels, the proposed method outperforms a series of advanced AMC method.

Red deer optimization for automatic modulation classification using hybrid extreme learning machine with bagging classifier

Automatic modulation classification (AMC) became an important process in various communication systems including commercial, telecommunication and military applications. Further, the accuracy of AMC impacts the performance of these applications. Various machine learning approaches were developed to improve the performance of AMC. However, they failed to classify the different modulation schemes, which needs to satisfy all the spectrum requirements under multipath fading environment. Further, the conventional methods suffer with computational complexity in training to satisfy the real-time operational requirements. So, this paper focuses on implementation of extreme learning machine (ELM) for reduction of training complexities and improves the classification performance. Initially, deep leaning convolutional neural network (DLCNN) model is introduced for extracting the interdependent modulation features based on different modulation types. Then, red deer optimization algorithm (RDOA) is introduced for selecting the best features from DLCNN extracted features. Further, the hybrid ELM with bagging classifier (HELM-BC) is used to classify the various modulation types, i.e., families. The simulation results show that the performance of the proposed AMC system using RDOA-based HELM-BC approach is superior to the conventional AMC systems.

The discrimination algorithms for overlapped MPSK and MQAM modulations using higher-order cumulants

Automatic Modulation Classification (AMC) is responsible for detecting the correct modulation types in the intelligent receivers. AMC performance degrades when the signal-to-noise ratio (SNR) decreases because of the overlapping among the digital modulation types’ features, and this performance worsens under fading channel conditions. This paper proposes two new algorithms that improve the AMC performance accuracy of the overlapped digital modulations in feature space by improving their discrimination. These algorithms are named temporal Fisher discriminant analysis (TFDA) and supervised Fisher discriminant analysis (SFDA). The simulation results show that TFDA improves AMC performance accuracy up to 19.01% compared with the reference paper (Ge et al., 2021) and up to 38.15% compared with the reference paper (Teng et al., 2018). In contrast, SFDA improves AMC performance accuracy up to 23.12 % compared with the reference paper (Ge et al., 2021) and up to 49.025% compared with the reference paper (Teng et al., 2018).

Modulation Classification of Active Attacks in Internet of Things: Lightweight MCBLDN With Spatial Transformer Network

The Internet of Things (IoT) permeates every aspect of our daily lives as billions of interconnected devices are deployed in the physical world. However, IoT networks operate in an untrusted environment and often suffer from many malicious active attacks. Automatic modulation classification (AMC), which can identify the modulation format of intercepted signals without prior knowledge, is a vital technology in countering physical-layer threats of IoT. However, most of the existing algorithms assume the channel is time invariant, and the AMC in time-varying channels is not been well studied. To deal with this dilemma, a novel AMC algorithm MCBLDN consisting of multiple convolutional neural networks (CNNs), a bidirectional long short-term memory network (BLSTM), and a deep neural network (DNN) is proposed. In MCBLDN, a multislot constellation diagram (CD) method is proposed to extract time-evolution characteristics for generating more discriminative features. Specifically, different grayscale subimages generated by slotted CDs are processed serially by their respective CNNs. Therefore, MCBLDN is overparameterized and time consuming. In addition, the frequency offset and phase offset caused by time-varying channels are neglected in MCBLDN, which is detrimental to the performance of AMC. To address the mentioned disadvantages, a lightweight MCBLDN with a spatial transformer network (SLCBDN) is proposed. First, the multiple CNNs in MCBLDN are pruned into a lightweight classification model, and the input data are rearranged to facilitate parallel processing by the lightweight CNN. Additionally, the spatial transformer network (STN) is utilized to reduce the influence of frequency offset and phase offset. Numerical results verify that the proposed method achieves superior performance and higher speed compared to the baseline algorithm MCBLDN.

UniQGAN: Unified Generative Adversarial Networks for Augmented Modulation Classification

Deep learning has been widely applied to automatic modulation classification (AMC), and there have been many studies on data augmentation techniques using deep generative models to improve performance. However, existing solutions need to train different models independently for each SNR, which leads to undeniable overhead. This letter presents <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">UniQGAN</i> , Unified Generative Adversarial Networks for IQ constellations of various SNRs, requiring a single model training. The proposed method introduces <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-conditions embedding</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">multi-domains classification</i> to leverage both conditions, i.e., modulation type and SNR. Experimental results show that UniQGAN effectively improves the AMC performance, while the training time is reduced.

Automatic modulation classification over MIMO amplify and forward (AF)-relay fading channels

Automatic Modulation Classification (AMC) plays an important role in many civilian applications such as spectrum monitoring (SM) and cognitive radio (CR). The majority of the AMC algorithms for MIMO systems are developed for rich scattering environments, which offer a full rank channel matrix. A rank deficient channel such as a keyhole channel severely affects the AMC performance. It is reported that cooperative relaying is an attractive solution to overcome the rank deficiency of multiple-input multiple-output (MIMO) channels. This work investigates the effect of cooperative relaying on the AMC performance. A higher-order cumulant (HOC)-based AMC method, namely the relay assisted RA-AMC method, is proposed to classify a pool of modulation types, namely BPSK, OQPSK, QPSK, π4-QPSK, 8-PSK and 16-QAM over an amplify and forward (AF) relay network. Simulation results show that the proposed method performs reasonably well over AF-relay fading channels.

AMC2N: Automatic Modulation Classification Using Feature Clustering-Based Two-Lane Capsule Networks

The automatic modulation classification (AMC) of a detected signal has gained considerable prominence in recent years owing to its numerous facilities. Numerous studies have focused on feature-based AMC. However, improving accuracy under low signal-to-noise ratio (SNR) rates is a serious issue in AMC. Moreover, research on the enhancement of AMC performance under low and high SNR rates is limited. Motivated by these issues, this study proposes AMC using a feature clustering-based two-lane capsule network (AMC2N). In the AMC2N, accuracy of the MC process is improved by designing a new two-layer capsule network (TL-CapsNet), and classification time is reduced by introducing a new feature clustering approach in the TL-CapsNet. Firstly, the AMC2N executes blind equalization, sampling, and quantization in trilevel preprocessing. Blind equalization is executed using a binary constant modulus algorithm to avoid intersymbol interference. To extract features from the preprocessed signal and classify signals accurately, the AMC2N employs the TL-CapsNet, in which individual lanes are incorporated to process the real and imaginary parts of the signal. In addition, it is robust to SNR variations, that is, low and high SNR rates. The TL-CapsNet extracts features from the real and imaginary parts of the given signal, which are then clustered based on feature similarity. For feature extraction and clustering, the dynamic routing procedure of the TL-CapsNet is adopted. Finally, classification is performed in the SoftMax layer of the TL-CapsNet. This study proves that the AMC2N outperforms existing methods, particularly, convolutional neural network(CNN), Robust-CNN (R-CNN), curriculum learning(CL), and Local Binary Pattern (LBP), in terms of accuracy, precision, recall, F-score, and computation time. All metrics are validated in two scenarios, and the proposed method shows promising results in both.

Effective Feature Selection Method for Deep Learning-Based Automatic Modulation Classification Scheme Using Higher-Order Statistics

Recently, in order to satisfy the requirements of commercial communication systems and military communication systems, automatic modulation classification (AMC) schemes have been considered. As a result, various artificial intelligence algorithms such as a deep neural network (DNN), a convolutional neural network (CNN), and a recurrent neural network (RNN) have been studied to improve the AMC performance. However, since the AMC process should be operated in real time, the computational complexity must be considered low enough. Furthermore, there is a lack of research to consider the complexity of the AMC process using the data-mining method. In this paper, we propose a correlation coefficient-based effective feature selection method that can maintain the classification performance while reducing the computational complexity of the AMC process. The proposed method calculates the correlation coefficients of second, fourth, and sixth-order cumulants with the proposed formula and selects an effective feature according to the calculated values. In the proposed method, the deep learning-based AMC method is used to measure and compare the classification performance. From the simulation results, it is indicated that the AMC performance of the proposed method is superior to the conventional methods even though it uses a small number of features.

A Modulation Classification Algorithm for Multipath Signals Based on Cepstrum

Automatic modulation classification (AMC) is an important intermediate step between signal detection and demodulation by the receiving instrument in the noncooperative communication system. Multipath fading causes serious degradation in classification performance of AMC. For the purpose of improving the performance of AMC for multipath modulation signals, we proposed a novel cepstrum-based preprocessing algorithm to eliminate the effect of multipath channel coefficient, and a logarithmic functional fitting method to classify modulated signals. First, we mathematically proved the feasibility of the proposed approach. Then, we experimentally tested our algorithm by the practically measured modulation data of quadrature phase-shift keying (QPSK), 16-ary quadrature amplitude modulation (16QAM), and 64-ary quadrature amplitude modulation (64QAM). The results confirmed that our algorithm performed well for multipath signals and was robust to slight frequency and timing offsets. Compared with the existing methods, our algorithm also performed better than the techniques based on high-order cumulants or cyclic statistics and suffered less computational complexity than the cumulant-based method with channel estimation procedure.

Modulation classification in multipath fading channels using sixth‐order cumulants and stacked convolutional auto‐encoders

Automatic modulation classification (AMC) plays an important role in both cooperative and non-cooperative communication applications. However, the performance of AMC is seriously degraded in multipath fading channels. Higher-order cumulants of the received signal are resistant to additive white Gaussian noise and multipath fading. Moreover, features extracted from unlabelled data using stacked convolutional auto-encoders (SCAEs) are comparable with or superior to most of the best hand-engineered ones. In this study, the authors propose a new algorithm, which applies sixth-order cumulants and SCAEs to modulation classification in multipath fading channels. Simulation results show that the proposed method can achieve better classification accuracy than the existing approaches under various channel conditions. The proposed approach is also robust to model imperfections such as phase, timing, and frequency offsets.

Cumulants‐based modulation classification technique in multipath fading channels

Automatic modulation classification (AMC) is a classical topic in the signal classification field and is often performed when the modulation type is adaptive. For typical modulation types such as M-PSK and M-QAM, the fourth-order cumulant statistics are usually used for modulation classification. Besides, it is also known that the AMC performance can be seriously degraded by the effects of multipath fading in wireless channels when compared with the ideal white Gaussian noise channel. In this study, a new modulation classification method is proposed, exploring different features of normalised fourth-order cumulant statistics for a modified blind channel estimation method in the multipath fading channel. The relationship between the cumulants of the received signal and the multipath fading effects is established to cope with the channel impulse response in the new algorithm. Simulation results show that the performance of the proposed AMC method is much improved than that of previously proposed ones in terms of the probability of correct classification.

Joint cumulant estimate correction and decision for cooperative modulation classification by using multiple sensors

In this paper, several data fusion and soft decision fusion methods are proposed for cooperative automatic modulation classification (AMC) by using multiple sensors. A well-known AMC using fourth-order cumulant is considered. Also, a novel joint cumulant estimate correction is proposed. The AMC performance of proposed fusion methods with and without joint estimate correction is evaluated through the extensive Monte Carlo trials for different multipath fading channels, sensor spatial distributions, and application scenarios, and compared to those of the existing methods. Numerical results have confirmed huge performance improvement achievable with here proposed methods, especially in the non-idealized application scenarios.

Dimensionality Reduction and Improving the Performance of Automatic Modulation Classification using Genetic Programming (RESEARCH NOTE)

This paper shows how we can make advantage of using genetic programming in selection of suitable features for automatic modulation recognition. Automatic modulation recognition is one of the essential components of modern receivers. In this regard, selection of suitable features may significantly affect the performance of the process. Simulations were conducted with 5db and 10db SNRs. Test and training data released from real ones recorded in an actual communication system. For performance analyzing of the proposed method a set of experiments were conducted considering signals with 2PSK, 4PSK, 2FSK, 4FSK, 16QAM and 64 QAM modulations. The results show that the selected features by the model improve the performance of automatic modulation recognition substantially. During our experiments, we also reached the suitable values and forms for mutation and crossover ratio, fitness function as well as other parameters for the proposed model.

Spectrum sensing and modulation classification for cognitive radios using cumulants based on fractional lower order statistics

Two key tasks in the development of cognitive radio networks in commercial and military applications are spectrum sensing and automatic modulation classification (AMC). These tasks become even more difficult when the cognitive radio receiver has no information about the channel or the modulation type. An integrated scheme which includes both these aspects is proposed in this paper. Spectrum sensing is done using cumulants derived from fractional lower order statistics. It is shown through simulations that the proposed sensing method has improved performance, especially in low SNR environments in Gaussian and non-Gaussian noise when compared with the conventional higher-order statistics (HOS) based method. The performance of the automatic modulation classifier is presented in the form of conditional probability of classification, probability of correct classification and confusion matrix under noisy and under fading conditions. Simulations in our previous work showed that the proposed method achieved better classification accuracy when compared to cumulant based AMC method in noise conditions that are highly impulsive than Gaussian. In this paper, simulations show significant improvement in the performance of AMC in the presence of AWGN and under multipath fading, for a known frequency band of interest when compared with the conventional AMC methods available.

Novel Automatic Modulation Classification Using Cumulant Features for Communications via Multipath Channels

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.