Low SNRs Research Articles

LSTM-BIGRU based Spectrum Sensing for Cognitive Radio

There is a shortage of wireless spectrum due to developments in the area of wireless communications as well as the number of users that are using resources. Spectrum sensing is a method that solves the issue of shortage. Deep learning surpasses classical methods in spectrum sensing by enabling autonomous feature learning, which enables the adaptive identification of complicated patterns in radio frequency data for cognitive radio in wireless sensor networks. This innovation increases the system's capacity to manage dynamic, real-time circumstances, resulting in increased accuracy over traditional approaches. Spectrum sensing (SS) using LSTM-BIGRU with gaussian noise has been suggested in this article. Long-term dependencies in sequential data are well- preserved by LSTM due to its dedicated memory cells. In addressing and man- aging long-term dependencies in sequential data, BIGRU's integration enhances the efficacy of the model as a whole. To conduct the investigation, RadioML2016.04C.multisnr open-source dataset was utilized. Whereas, by using RadioML2016.10b open-source dataset, QAM64, QPSK and QAM16 performance evaluation has been investigated. The experimental findings demonstrate that the suggested Spectrum Sensing has better accuracy on the dataset particularly at lower SNRs. The improved spectrum sensing (SS) performance of our suggested model is shown by the evaluation of performance indicators, such as the F1 Score, CKC and Matthew's correlation coefficient, highlighting its potency in the field of spectrum sensing applications.

A Time-Domain Doppler Estimation and Waveform Recovery Approach with Iterative and Ensemble Techniques for Bi-Phase Code in Radar Systems

This paper presents a novel, cost-effective technique for estimating the Doppler effect in the time domain using a single pulse and subsequently leveraging the precise Doppler value to recover the radar waveform. The proposed system offers several key advantages over existing techniques, including the ability to calculate the target speed without any frequency ambiguity and the ability to detect a wide range of target speeds. These two features are not available in any existing techniques, including the conventional moving target detection (MTD) processor. To ensure improved accuracy and robust estimation, the system employs ensemble and iterative techniques by recursively and efficiently reducing the Doppler residues from the signal. Furthermore, the proposed system demonstrates effective signal recovery of a well-known bi-phase code shape at low signal-to-noise ratios in just a few iterations. The performance evaluation of the new algorithm demonstrates its practicability and its superiority over traditional radar systems. Implementation on software-defined radio (SDR) reveals that the proposed system excels in Doppler estimation and signal recovery at low SNRs, demonstrating promising results.

Spectrum sensing using deep learning for proficient data transmission in wireless sensor networks for wireless communication

Cognitive radio has been recommended for enhancing wireless spectrum usage, and an important part of cognitive radio is spectrum sensing. Conventional spectrum sensing techniques rely on energy detection and feature extraction from a received signal at a specific position. The advancement of artificial intelligence and deep learning has provided a chance to increase spectrum sensing efficiency. The proposed investigation presented a hybrid model comprising CNN, BILSTM, and Transformer Networks (TN) for spectrum sensing. With the aid of Transformer networks, the proposed model improves sensing accuracy even for lower SNR signals, particularly at −20 dB. The results of the proposed technique show that CNN-BILSTM-TN enhances spectrum sensing in comparison to earlier models studied in this domain. The proposed approach outperforms prior methods in terms of F1 Score and has an improved probability of detection at −20 dB and a lower likelihood of missed detection. Analysis of ten modulation techniques' performance criteria, such as the Jaccard index, Cohen Kappa coefficient, and Matthew's correlation coefficient, demonstrates that the suggested method's spectrum sensing is better even at lower SNRs.

Strategies for DOA-DNN estimation accuracy improvement at low and high SNRs

Strategies for DOA-DNN estimation accuracy improvement at low and high SNRs

DOA estimation of coherent signals in underdetermined problems using sparse-based Toeplitz covariance reconstruction

Direction-Of-Arrival (DOA) estimation in environments with coherent sources is a challenging problem, when the number of narrowband sources is more than elements and current coherent algorithms cannot accurately overcome such underdetermined problems. In this paper, we propose the Sparse-based Toeplitz Covariance Reconstruction (STCR) algorithm, which obtains a hole-free extended-aperture array with increased Degrees of Freedom (DOF) by exploiting a minimum redundancy array. This method provides superiority in estimating coherent sources by Toeplitz covariance matrix reconstruction. Also, using a Sparse Signal Representation (SSR) framework makes the DOA estimator stronger in source detection and robust to the noise power. Numerical results show the effectiveness of the proposed method even at low SNRs for over- and underdetermined DOA estimators compared to well-known methods. Also, it has high accuracy in DOA estimation of closely-located coherent sources using a small number of snapshots.

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

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

A Low-Cost High-Throughput C-Band Communication System for CubeSats

This paper presents the physical layer of a proprietary broadband communication system for CubeSats. The system operates in the C band (5.8 GHz), delivering at least 10 Mbps of the net user throughput. Operation at low elevation angles (and therefore low SNRs) and high Doppler shifts is made possible thanks to a sophisticated synchronization subsystem. The system can be adapted to propagation conditions experienced during a given visibility window by changing the signal bandwidth and coding rate. It is implemented using Software Defined Radio (SDR) technology. The system will be used in two missions that are scheduled for 2023 and 2024 and are planned in cooperation with the National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” and SatRev S.A.

TFF_aDCNN: A Pre-Trained Base Model for Intelligent Wideband Spectrum Sensing

In the beyond 5 G (B5G)/6 G era, to achieve ultra-dense and ultra-large-capacity intelligent connection of all things, an intelligent wideband spectrum sensing technology is particularly important. However, in an extremely wide frequency range, it is still a challenge to achieve high-precision and high-reconstruction-capability wideband spectrum sensing (WSS) under a very low SNR. We propose a Time-Frequency-Fused adjustable Deep Convolutional Neural Network (TFF_aDCNN). Meanwhile, a novel TFF_aDCNN-based sensing framework is also proposed. In this framework, we can obtain a pre-trained base model with a single distribution by training TFF_aDCNN. Then, for the sensing task in the actual environment, we use the base model for transfer learning, so that a newly trained sensing model can be obtained very quickly (i.e. fine-tuned model). In the TFF_aDCNN, we design a main network and an adjustable auxiliary network, where the former learns complex and abstract signal features, while the latter assists the main network in learning different data distribution patterns during the training process and regulates the focus direction of the main network during the perception process. Simulation results show that TFF_aDCNN can significantly reduce hardware cost and improve reconstruction accuracy and reconstruction capability, when compared with SOMP and SwSOMP-based WSS algorithms, single-dimensional deep learning spectrum sensing method, and deep learning-based WSS (DLWSS), especially at very low SNRs.

A Sparse Bayesian Learning Method for Direction of Arrival Estimation in Underwater Maneuvering Platform Noise

The underwater maneuvering platform generates self-noise when sailing, which shows spatial directionality to the arrays fixed on the platform. In this paper, it is called spatially colored noise (SCN). The direction of arrival (DOA) estimation results are often influenced by this self-noise, leading to a decrease in estimation accuracy and to the appearance of spurious peaks. To resolve this problem, a sparse Bayesian learning (SBL) method adapted to underwater maneuvering platform noise is proposed in this paper. The SBL framework with unknown SCN is established first. Then, the SCN covariance matrix is estimated by projecting the received data covariance matrix into the noise subspace, and the DOA estimation results are finally obtained through multiple iterations. The simulation results show that the proposed method avoids spurious peaks, and compared to the existing methods, the proposed method achieves a higher accuracy in the case of low SNRs and small snapshot numbers. The sea trial data processing results show that the proposed method provides lower and flatter noise spectrum levels without spurious peaks.

LoneSTAR: Analog Beamforming Codebooks for Full-Duplex Millimeter Wave Systems

This work develops LONESTAR, a novel enabler of full-duplex millimeter wave (mmWave) communication systems through the design of analog beamforming codebooks. LONESTAR codebooks deliver high beamforming gain and broad coverage while simultaneously reducing the self-interference coupled by transmit and receive beams at a full-duplex mmWave transceiver. Our design framework accomplishes this by tolerating some variability in transmit and receive beamforming gain to strategically shape beams that reject self-interference spatially while accounting for digitally-controlled analog beamforming networks and self-interference channel estimation error. By leveraging the coherence time of the self-interference channel, a mmWave system can use the same LONESTAR design over many time slots to serve several downlink-uplink user pairs in a full-duplex fashion without the need for additional self-interference cancellation. Compared to those using conventional codebooks, full-duplex mmWave systems employing LONESTAR codebooks can mitigate higher levels of self-interference, tolerate more cross-link interference, and demand lower SNRs in order to outperform half-duplex operation—all while supporting beam alignment. This makes LONESTAR a potential standalone solution for enabling simultaneous transmission and reception in mmWave systems, from which it derives its name.

Automatic modulation recognition of radiation source signals based on two-dimensional data matrix and improved residual neural network

Automatic modulation recognition (AMR) of radiation source signals is a research focus in the field of cognitive radio. However, the AMR of radiation source signals at low SNRs still faces a great challenge. Therefore, the AMR method of radiation source signals based on two-dimensional data matrix and improved residual neural network is proposed in this paper. First, the time series of the radiation source signals are reconstructed into two-dimensional data matrix, which greatly simplifies the signal preprocessing process. Second, the depthwise convolution and large-size convolutional kernels based residual neural network (DLRNet) is proposed to improve the feature extraction capability of the AMR model. Finally, the model performs feature extraction and classification on the two-dimensional data matrix to obtain the recognition vector that represents the signal modulation type. Theoretical analysis and simulation results show that the AMR method based on two-dimensional data matrix and improved residual network can significantly improve the accuracy of the AMR method. The recognition accuracy of the proposed method maintains a high level greater than 90% even at −14 dB SNR.

Efficient and robust Levenberg–Marquardt Algorithm based on damping parameters for parameter inversion in underground metal target detection

The Levenberg–Marquardt (LM) algorithm has been widely used to solve nonlinear least-squares problems in underground target detection. However, the LM algorithm has an unsatisfactory performance of convergence due to the influence of noise in the environment. Therefore, a new modified LM (NMLM) algorithm has been proposed in this paper to improve its accuracy and efficiency of parameter estimation with low SNR. The NMLM algorithm can also converge globally under certain conditions and converge quadratically under the error-bound condition, which updates based on the gain ratio and determines the damping factor based on the gradient value. An experimental investigation has been conducted under different SNRs and the amount of data, and the results indicate the new algorithm can accurately and quickly estimate the parameters of underground metal targets under the lower SNRs and smaller amounts of data. More specifically, the estimation accuracy of position, principal axes polarizability, and orientation of the metal target can be increased by up to 1.6 cm, 0.00013, and 2.31 degree, respectively. This paper also verifies that the new algorithm finds the optimal solution for standard numerical problems with low errors and a finite number of iterations.

Voting-Based Deep Convolutional Neural Networks (VB-DCNNs) for M-QAM and M-PSK Signals Classification

Automatic modulation classification (AMC) using convolutional neural networks (CNNs) is an active area of research that has the potential to improve the efficiency and reliability of wireless communication systems significantly. AMC is the approach used in a communication system to detect the type of modulation format at the receiver end. This paper proposes a voting-based deep convolutional neural network (VB-DCNN) for classifying M-QAM and M-PSK signals. M-QAM and M-PSK signal waveforms are generated and passed through the fading channel in the presence of additive white Gaussian noise (AWGN). The VB-DCNN extracts features from the input signal through convolutional layers, and classification is performed on these features. Multiple network instances are trained on different subsets of training data in the VB-DCNN. A network instance predicts the input signal during testing. Based on the votes, the final prediction is made. Different simulation experiments are carried out to analyze the performance of the trained network, and the DCNN is designed with the Deep Neural Network Toolbox in MATLAB. The generated frames are divided into training, validation, and test datasets. Lastly, the classification accuracy of the trained network is determined using test frames. The proposed model’s accuracy is near to 100% at lower SNRs. The simulation results show the superiority of the proposed VB-DCNN compared to existing state-of-the-art techniques.

Centroid Optimization of DNN Classification in DOA Estimation for UAV

Classifications based on deep learning have been widely applied in the estimation of the direction of arrival (DOA) of signal. Due to the limited number of classes, the classification of DOA cannot satisfy the required prediction accuracy of signals from random azimuth in real applications. This paper presents a Centroid Optimization of deep neural network classification (CO-DNNC) to improve the estimation accuracy of DOA. CO-DNNC includes signal preprocessing, classification network, and Centroid Optimization. The DNN classification network adopts a convolutional neural network, including convolutional layers and fully connected layers. The Centroid Optimization takes the classified labels as the coordinates and calculates the azimuth of received signal according to the probabilities of the Softmax output. The experimental results show that CO-DNNC is capable of acquiring precise and accurate estimation of DOA, especially in the cases of low SNRs. In addition, CO-DNNC requires lower numbers of classes under the same condition of prediction accuracy and SNR, which reduces the complexity of the DNN network and saves training and processing time.

Structured illumination microscopy based on principal component analysis

Structured illumination microscopy (SIM) is one of the powerful super-resolution modalities in bioscience with the advantages of full-field imaging and high photon efficiency. However, artifact-free super-resolution image reconstruction requires precise knowledge about the illumination parameters. The sample- and environment-dependent on-the-fly experimental parameters need to be retrieved a posteriori from the acquired data, posing a major challenge for real-time, long-term live-cell imaging, where low photobleaching, phototoxicity, and light dose are a must. In this work, we present an efficient and robust SIM algorithm based on principal component analysis (PCA-SIM). PCA-SIM is based on the observation that the ideal phasor matrix of a SIM pattern is of rank one, leading to the low complexity, precise identification of noninteger pixel wave vector and pattern phase while rejecting components that are unrelated to the parameter estimation. We demonstrate that PCA-SIM achieves non-iteratively fast, accurate (below 0.01-pixel wave vector and 0.1% of 2pi relative phase under typical noise level), and robust parameter estimation at low SNRs, which allows real-time super-resolution imaging of live cells in complicated experimental scenarios where other state-of-the-art methods inevitably fail. In particular, we provide the open-source MATLAB toolbox of our PCA-SIM algorithm and associated datasets. The combination of iteration-free reconstruction, robustness to noise, and limited computational complexity makes PCA-SIM a promising method for high-speed, long-term, artifact-free super-resolution imaging of live cells.

Through-the-Wall Radar under electromagnetic complex wall: A deep learning approach

This paper employed deep learning to do two-dimensional, multi-object locating in Through-the-Wall Radar under conditions where the wall is treated as a complex electromagnetic medium. We made five assumptions about the wall and two about the number of objects. There are two object modes available: single target and double targets. The wall scenarios include a homogeneous wall, a wall with an air gap, an inhomogeneous wall, an anisotropic wall, and an inhomogeneous–anisotropic wall. Target locating is accomplished through the use of a deep neural network technique. We constructed a dataset using the Python FDTD module and then modeled it using deep learning. Assuming the wall is a complex electromagnetic medium, we achieved 97.7% accuracy for single-target 2D locating and 94.1% accuracy for two-target locating. Additionally, we noticed a loss of 10% to 20% inaccuracy when noise was added at low SNRs, although this decrease dropped to less than 10% at high SNRs.

Capacity Performance of Tensor Multi-Domain Communication Systems With Discrete Signalling Constellations

Modern communication systems employ multi-domain modulation and coding techniques for effectively exploiting all available resources. Hence in such systems the transmit and receive signals have an inherent multi-domain structure which can be represented using tensors. This work considers the capacity of higher order tensor channels associated with such multi-domain communication systems when the elements of the input tensor are constrained to be drawn from discrete signalling constellations. We establish a relationship between the tensor gradient of the mutual information and the error covariance tensor associated with the minimum mean squared error estimator at the receiver. This relation is used to iteratively find a multi-linear precoder at the input which achieves capacity of the tensor channel under the signalling constellation constraints. Through numerical examples, we show the convergence behavior of the proposed precoder, and compare the capacity achieved under different constellations with the capacity when the input is Gaussian. Further, we exploit the tensor formulation of the problem to find the channel capacity under a variety of different power constraints spanning across several domains. At high SNR, the constellation constraints saturates the capacity while at low SNRs, the constellation constraints are not too relevant, and the power constraints dominate and limit the performance. The capacity saturation level depends on the input order and distribution.

An expert algorithm for spectrum sensing and signal detection in NOMA-enabled 5G networks

The Spectrum sensing is an essential function in the various types of fifth-generation (5G) networks and beyond, which can address some of the fundamental challenges for 5G, including spectral efficiency and the reliable connectivity of internet of things (IoT) devices. In this article, we aim to present a real-time and expert spectrum sensing algorithm for 5G cellular networks. The novel method exploits the cyclostationary nature of the spread spectrum signal without any prior knowledge of its structure. In the proposed algorithm, the multi-carrier code division multiple access (MC-CDMA) technique will be utilized by the users. The multidimensional spectrum sensing method introduces a novel correlation measurement based on the algebraic characteristics of pseudo-noise (PN) sequences. The existence of periodic peaks in the new correlation function presents new modelling of the emergence of the spread-spectrum signal. Our basis for this is to use the cyclostatic property of the pseudo-noise code and obtain the distance between the two main peaks in the received signal correlation. According to the simulation results, the proposed algorithm exhibits excellent performance in signal detection and exact estimation of PN code length in low SNRs and multipath fading environments.

Automatic Modulation Recognition Based on the Optimized Linear Combination of Higher-Order Cumulants.

Automatic modulation recognition (AMR) is used in various domains—from general-purpose communication to many military applications—thanks to the growing popularity of the Internet of Things (IoT) and related communication technologies. In this research article, we propose an innovative idea of combining the classical mathematical technique of computing linear combinations (LCs) of cumulants with a genetic algorithm (GA) to create super-cumulants. These super-cumulants are further used to classify five digital modulation schemes on fading channels using the K-nearest neighbor (KNN). Our proposed classifier significantly improves the percentage recognition accuracy at lower SNRs when using smaller sample sizes. A comparison with existing techniques manifests the supremacy of our proposed classifier.

Evaluating the efficacy of sonification for signal detection in univariate, evenly sampled light curves using astronify

ABSTRACT Sonification is the technique of representing data with sound, with potential applications in astronomy research for aiding discovery and accessibility. Several astronomy-focused sonification tools have been developed; however, efficacy testing is extremely limited. We performed testing of astronify, a prototype tool for sonification functionality within the Barbara A. Mikulski Archive for Space Telescopes. We created synthetic light curves containing zero, one, or two transit-like signals with a range of signal-to-noise ratios (SNRs = 3–100) and applied the default mapping of brightness to pitch. We performed remote testing, asking participants to count signals when presented with light curves as a sonification, visual plot, or combination of both. We obtained 192 responses, of which 118 self-classified as experts in astronomy and data analysis. For high SNRs (=30 and 100), experts and non-experts performed well with sonified data (85–100 per cent successful signal counting). At low SNRs (=3 and 5), both groups were consistent with guessing with sonifications. At medium SNRs (=7 and 10), experts performed no better than non-experts with sonifications but significantly better (factor of ∼2–3) with visuals. We infer that sonification training, like that experienced by experts for visual data inspection, will be important if this sonification method is to be useful for moderate SNR signal detection within astronomical archives and broader research. None the less, we show that even a very simple, and non-optimized, sonification approach allows users to identify high SNR signals. A more optimized approach, for which we present ideas, would likely yield higher success for lower SNR signals.