Signal-to-noise Ratio Environment Research Articles

Dual-Branch feature fusion residual neural network for individual radar signal recognition in low SNR environments

Abstract To address the challenge of radar emitter signal individual recognition, where single-dimensional radar fingerprint features are susceptible to noise interference and neural networks exhibit low recognition accuracy in low signal-to-noise ratio (SNR) environments, this study introduces a residual neural network predicated on a two-branch feature fusion. This approach amalgamates two-dimensional time-frequency domain features with one-dimensional intermediate-frequency signal features. Unlike existing algorithms, our proposed method integrates the knowledge gleaned from features learned across different dimensions. This integration enables the neural network to utilize features from multiple dimensions for recognition, thereby mitigating the impact of noise on a single feature. Experimental results demonstrate that our proposed algorithm outperforms others under various low SNRs, achieving an average recognition rate of 88.39%.

A RSBU-LSTM network for radio frequency fingerprint identification relying on multiple features

Radio frequency fingerprint identification (RFFI) can distinguish highly similar wireless communication devices to protect physical layer security and improve the security of wireless networks effectively, which has been widely used for spectrum management and physical layer secure communication. However, most RFFI methods show a degradation of performance under low signal-to-noise ratio (SNR) environments. In this paper, we propose a RSBU-LSTM network relying on multiple features to improve the identification accuracy with low SNR. Firstly, we use multiple features of in-phase (I), quadrature (Q), and phase as inputs. Then, we use multiple Residual Shrinkage Building Units (RSBUs) to extract the correlation features within the cycle of signals and preserve as many features as possible in low SNR environments. Finally, we use the long short-term memory (LSTM) to extract the relevant features of the signals of non-adjacent cycles. The experimental results show that the proposed network can effectively complete RFFI in low SNR environments and show better performance than other models used for comparison.

IncepSeqNet: Advancing Signal Classification with Multi-Shape Augmentation (Student Abstract)

This work proposes and analyzes IncepSeqNet which is a new model combining the Inception Module with the innovative Multi-Shape Augmentation technique. IncepSeqNet excels in feature extraction from sequence signal data consisting of a number of complex numbers to achieve superior classification accuracy across various SNR(Signal-to-Noise Ratio) environments. Experimental results demonstrate IncepSeqNet’s outperformance of existing models, particularly at low SNR levels. Furthermore, we have confirmed its applicability in practical 5G systems by using real-world signal data.

Time-difference reassigned transform with application to time difference of arrival for impulsive signal

Time difference of arrival (TDOA) is essential in localization, communication, and navigation. Under ambient noise interference, the impulsive signal is transmitted over a long distance and reaches the sensor with a low signal-to-noise ratio (SNR). Aiming to achieve a precise time delay estimation in scenarios with low SNR, this paper extends the time-reassigned extracting transform (TRET) theory to TDOA and proposes a time difference rearrangement extracting transform (TDRT) algorithm. The implementation process of the proposed algorithm comprises three steps. Initially, a rough two-dimensional time delay estimation is obtained by calculating the partial derivative of the short-time cross-power spectrum with respect to the frequency variable. Secondly, a rearrangement operation separates the signal's time-frequency (TF) points from the noise. Thirdly, a refined TDOA estimation is obtained by inverse Fourier transforming TF points extracted from the time-delay energy ridge. Simulation results show that the TDRT algorithm is effective in time delay estimation. Furthermore, experimental results prove that the performance of the TDRT algorithm outperforms comparable algorithms in low SNR environments.

A cooperative spectrum sensing method based on semi-supervised clustering with variational mode decomposition and information geometry

In practice, obtaining a large number of sample labels for the supervised learning-based cooperative spectrum sensing (CSS) method is challenging. Additionally, the CSS method based on information geometry (IG) and clustering algorithm exhibited low detection performance in low signal-to-noise ratio (SNR) environment. This paper proposes a cooperative spectrum sensing method based on variational mode decomposition and IG with semi-supervised clustering. First, the secondary users (SUs) reconstruct the received signals using variational mode decomposition. Next, the fusion center combines all the reconstructed signals into a single matrix and calculates its corresponding covariance matrix. Finally, a binary classifier is obtained via training offline on the matrix manifold space using a semi-supervised clustering algorithm based on IG. The simulation results show that increasing the number of SUs and sampling points can improve the CSS performance of the proposed algorithm. Furthermore, the proposed algorithm is compared with other CSS algorithms, demonstrating its superior spectrum sensing performance regardless of whether the SUs are in the same very low SNR environment.

A robust and lightweight voice activity detection algorithm for speech enhancement at low signal-to-noise ratio

Voice Activity Detection (VAD) is a crucial component of Speech Enhancement (SE) for accurately estimating noise, which directly affects the SE effectiveness in improving speech quality. However, conventional non-data-driven VADs often suffer from decreased accuracy at a low signal-to-noise ratio (SNR). To address this issue, a multi-feature and cosine similarity-based multi-observation VAD algorithm (mVAD) are proposed in this study. This algorithm selects noise-robust features, with Mel-frequency Cepstral Coefficients (MFCCs) as the main features, and utilizes several optimization techniques and an adaptive threshold for background noise updating. Furthermore, the soft VAD results are smoothed with an improved exponential moving average (EMA) algorithm. Besides, a shifting window is utilized to track the mean value and obtain an adaptive threshold for converting the soft results to binary ones. Experimental results indicate that mVAD can maintain high classification accuracy down to -10 dB with an increment of approximately 28% while also being computationally efficient for the CPU time (about 1/3 of statistical model-based methods). It also maintained high robustness at SNRs less than 0 dB (Δ≤2.1%). Moreover, sometimes mVAD even achieved higher accuracy levels than deep learning-based VADs. To further demonstrate the effectiveness of the proposed method, the VAD results are used as an additional feature to train and test a neural network (NN)-based SE model, enhancing the SE performance. This study proves that mVAD does not rely on prior noise knowledge, reaching the dual effect of complexity reduction and accuracy improvement for speech enhancement, making it a promising approach for robust VAD in low SNR environments.

Enhancing Hybrid Spectrum Access in CR-IoT Networks: Reducing Sensing Time in Low SNR Environments

The current utilization of the licensed spectrum band is not optimal. the abundance of Internet of Things (IoT) gadgets could lead to congestion in the unlicensed spectrum band. A potential solution is to integrate cognitive radios into IoT devices, specifically by developing CR-IoT (cognitive-radio-enabled IoT) devices that leverage the hybrid spectrum access (HSA) technique to access the licensed spectrum band and employ energy detectors for spectrum sensing. While HSA can enable high data throughput for CR-IoT networks, environments with low signal-to-noise ratio (SNR) may experience reduced performance. Particularly, in low SNR environments with SNR values ranging from -20dB to -24dB, the high level of noise uncertainty can cause the energy detector to spend more time sensing, which results in a significant reduction in transmission time and overall throughput. In this study, a novel approach is presented to address the challenge of noise uncertainties on the energy detector by implementing an adaptive sensing threshold. The simulation outcomes reveal that the proposed technique can significantly improve the throughput in scenarios characterized by low signal-to-noise ratio (SNR), with a maximum enhancement of up to 28%. This innovative approach can pave the way for more robust and efficient energy detectors in the presence of noise uncertainties .

Ultra-Short Wave Communication Squelch Algorithm Based on Deep Neural Network

The squelch problem of ultra-short wave communication under non-stationary noise and low Signal-to-Noise Ratio (SNR) in a complex electromagnetic environment is still challenging. To alleviate the problem, we proposed a squelch algorithm for ultra-short wave communication based on a deep neural network and the traditional energy decision method. The proposed algorithm first predicts the speech existence probability using a three-layer Gated Recurrent Unit (GRU) with the speech banding spectrum as the feature. Then it gets the final squelch result by combining the strength of the signal energy and the speech existence probability. Multiple simulations and experiments are done to verify the robustness and effectiveness of the proposed algorithm. We simulate the algorithm in three situations: the typical Amplitude Modulation (AM) and Frequency Modulation (FM) in the ultra-short wave communication under different SNR environments, the non-stationary burst-like noise environments, and the real received signal of the ultra-short wave radio. The experimental results show that the proposed algorithm performs better than the traditional squelch methods in all the simulations and experiments. In particular, the false alarm rate of the proposed squelch algorithm for non-stationary burst-like noise is significantly lower than that of traditional squelch methods.

Narrowband IoT Signal Identification in LTE Networks Using Convolutional Neural Networks

Narrowband Internet of Things (NB-IoT) is an emerging standard serving massive wireless communications devices. It is implemented based on the legacy long-term evolution (LTE) technology and thus shares many system configurations with it. In fact, NB-IoT is deployed on some of the spectrum allocated to LTE. This sometimes introduces interference to the frequency bands with LTE transmission. Signal identification has been found as a critical and effective method for spectrum awareness and the improvement of resource allocation performance thus mitigating potential interference. While not been studied in previous work, this article fills the hole in identifying NB-IoT transmissions in different communications scenarios. In particular, we develop a convolutional neural network (CNN)-based signal identification method to distinguish NB-IoT signals from other cellular signals. The performance of the signal identification method is tested with different CNN training setups. Our experiments demonstrate that the proposed model can successfully identify the existence of NB-IoT signal with 98.13% accuracy in the Rayleigh fading channel where the signal-to-noise ratio (SNR) = 10 dB. Our results also show that the proposed signal identification method is able to provide promising identification accuracy under various and unknown SNR environments in both additive white Gaussian noise (AWGN) and Rayleigh fading channels.

Adaptive cascade detection of weak magnetic anomalies based on marine predators algorithm-stochastic resonance

Magnetic anomaly detection is a new technology for underground or underwater ferromagnetic targets using the physical principle that ferromagnetic targets will be long-term magnetized by the geomagnetic field to generate abnormal magnetic fields. This technology is often used in underwater security, mineral exploration, and other areas. But it is quite challenging to effectively detect weak magnetic anomaly signals in a complex underwater environment. Therefore, we propose an adaptive cascade weak magnetic anomaly detection method based on Marine Predators Algorithm-Stochastic Resonance (MPA-SR). According to the characteristics of magnetic anomaly signals, the cascade detection method of low-pass filtering, stochastic resonance, and threshold detection is designed to improve the detection probability of magnetic anomaly signals. In addition, the Marine predator algorithm with optimized initialization strategy and step size control parameters is used to improve the stochastic resonance system to adaptively detect the magnetic anomaly signal in more applications. The simulation results show that the signal-to-noise ratio (SNR) of the output signal of the MPA-SR method is 2.41 dB higher than the input signal, and the detection probability of the method is 57% higher than that of the minimum entropy (ME) method under the same low SNR environment. The method can provide the theoretical basis and empirical reference for further application of magnetic anomaly data like identifying, locating, and tracking underwater magnetic targets.

A sound source localization method based on improved second correlation time delay estimation

The sound source localization (SSL) system based on the microphone array has important applications in audio and video conference, security monitoring and intelligent cockpit. However, the SSL method based on time difference of arrival is susceptible to ambient noise. Therefore, an improved second correlation delay estimation algorithm is proposed in this paper. The pure source signal is obtained by wavelet denoising, and then the time delay is calculated by the second correlation time delay estimation algorithm with the weighting functions of the smoothed coherence transform and the Roth processor. The position of the sound target is calculated from the time delay. Aiming at the moving target, an extended Kalman filter is introduced to track the moving trajectory of the sound source. The static and moving SSL simulations are conducted and the results of the proposed algorithm are compared with those of the single-weighted quadratic correlation (SQC) algorithm and the high-power quadratic correlation algorithm. The static sound source positioning errors of the proposed algorithm under −10 dB SNR are respectively 3.97 m and 5.86 m smaller than those of the HQC algorithm and the SQC algorithm. The moving SSL trajectory based on the proposed algorithm is still closest to the real track under −10 dB SNR. This indicates that the proposed algorithm has high precision and strong robustness for sound source location in the low signal-to-noise ratio (SNR) environment. In the experiment, the proposed algorithm can accurately calculate the direction of arrival (DOA) of static sound source and stably track DOA of moving sound source. This is consistent with the simulation results, which further verifies the effectiveness and practicability of the algorithm. This novel algorithm with high time delay estimation accuracy is of great significance for SSL in low SNR environment.

Optimized Deep Learning Model for Effective Spectrum Sensing in Dynamic SNR Scenario

The main components of Cognitive Radio networks are Primary Users (PU) and Secondary Users (SU). The most essential method used in Cognitive networks is Spectrum Sensing, which detects the spectrum band and opportunistically accesses the free white areas for different users. Exploiting the free spaces helps to increase the spectrum efficiency. But the existing spectrum sensing techniques such as energy detectors, cyclo-stationary detectors suffer from various problems such as complexity, non-responsive behaviors under low Signal to Noise Ratio (SNR) and computational overhead, which affects the performance of the sensing accuracy. Many algorithms such as Long-Short Term Memory (LSTM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) play an important role in designing intelligent spectrum sensing techniques due to the excellent learning ability of deep learning frameworks, but still require improvisation in terms of sensing accuracy under dynamic environmental conditions. This paper, we propose the novel and hybrid CNN-Cuttle-Fish Optimized Long Short Term Memory (COLSTM), an improved version of LSTM that is well suited for the dynamic changes of environmental SNR with less computational overhead and complexity. The proposed COLSTM based spectrum sensing technique exploits the various statistical features from spectrum data of PU to improve the sensing efficiency. Furthermore, the addition of shuttle-fish optimization in LSTM has reduced the computational overhead and complexity which in turn enhanced the sensing performances. The proposed methodology is validated on spectrum data acquired using RaspberryPi-RTLSDR experimental test-beds. The proposed spectrum sensing technique and the existing classical spectrum sensing techniques are compared. Experimental results show that the proposed scheme has shown the brighter enhancement of performance under different SNR environments. Further, the improvised performance has been achieved at low complexity and low computational overhead when compared with the other existing LSTM networks.

A MLE-based blind signal separation method for time–frequency overlapped signal using neural network

The blind signal separation (BSS) algorithm obtains each original/source signal from the observed signal collected by the receiving antenna or sensor. Objective/loss/cost function and optimization method are two key parts of BSS algorithm. Modifying the objective function and optimization from the perspective of neural network (NN) is a novel concept in BSS domain. L_2 regularization is adopted as a term of maximum likelihood estimation (MLE)-based objective function like in Liu et al. (Sensors 21(3):973, 2021); however, we modified the probability density function (PDF) term of the objective function and used the kernel density estimation method for time–frequency overlapped digital communication signal. Multiple optimizers are studied in this paper, and we figure out the right optimizer for our application scenario. A varies of comparison experiments—whose separation results will be provided in forms of correlation coefficient and performance index—are carried out, which indicate our method can converge quickly and achieve satisfactory separation results with performance index (PI) lower than 0.02 when signal-to-noise ratio (SNR) no less than 10dB. Additionally, it demonstrates performance of our method is better than that of typical separation—FastICA, especially for the lower SNR environment, and it shows that our method is not sensitive to the frequency overlap level (FOL) of the source signal, even FOL as high as 100%; it still can get high-precision separation results with textrm{PI}<0.02.

Perceptual Characteristics of Voice Identification in Noisy Environments

Auditory analysis is an essential method that is used to recognize voice identity in court investigations. However, noise will interfere with auditory perception. Based on this, we selected white noise, pink noise, and speech noise in order to design and conduct voice identity perception experiments. Meanwhile, we explored the impact of the noise type and frequency distribution on voice identity perception. The experimental results show the following: (1) in high signal-to-noise ratio (SNR) environments, there is no significant difference in the impact of noise types on voice identity perception; (2) in low SNR environments, the perceived result of speech noise is significantly different from that of white noise and pink noise, and the interference is more obvious; (3) in the speech noise with a low SNR (−8 dB), the voice information contained in the high-frequency band of 2930~6250 Hz is helpful for achieving accuracy in voice identity perception. These results show that voice identity perception in a better voice transmission environment is mainly based on the acoustic information provided by the low-frequency and medium-frequency bands, which concentrate most of the energy of the voice. As the SNR gradually decreases, a human’s auditory mechanism will automatically expand the receiving frequency range to obtain more effective acoustic information from the high-frequency band. Consequently, the high-frequency information ignored in the objective algorithm may be more robust with respect to identity perception in our environment. The experimental studies not only evaluate the quality of the case voice and control the voice recording environment, but also predict the accuracy of voice identity perception under noise interference. This research provides the theoretical basis and data support for applying voice identity perception in forensic science.

A Repetitive Spectrum Learning Framework for Monaural Speech Enhancement in Extremely Low SNR Environments (Student Abstract)

Monaural speech enhancement (SE) at an extremely low signal-to-noise ratio (SNR) condition is a challenging problem and rarely investigated in previous studies. Most SE methods experience failures in this situation due to three major factors: overwhelmed vocals, expanded SNR range, and short-sighted feature processing modules. In this paper, we present a novel and general training paradigm dubbed repetitive learning (RL). Unlike curriculum learning that focuses on learning multiple different tasks sequentially, RL is more inclined to learn the same content repeatedly where the knowledge acquired in previous stages can be used to facilitate calibrating feature representations. We further propose an RL-based end-to-end SE method named SERL. Experimental results on TIMIT dataset validate the superior performance of our method.

Range profile similarity‐oriented method for radar imaging of moving target under low signal‐to‐noise ratio environment

Inverse synthetic aperture radar (ISAR) imaging is an advanced technique for reconstructing high-resolution images of moving targets. However, noise interference degrades the readability of the ISAR images under low echo signal-to-noise ratio (SNR) environments. Furthermore, noise impairs the performance of ISAR motion compensation, which induces severe defocussing. Thus, a novel range profile similarity-oriented (RAP-SO) method with a two-step denoising strategy is presented. First, attributed to the coherence between ISAR range profiles, the coherent weighted template (CWT) is proposed to preliminarily remove the noise in a high-resolution range profile (HRRP) and restore the range profile similarity impaired by noise. In order to robustly complete range alignment under a low SNR environment, Keystone transform (KT) is utilised. Thereafter, the weighted template is constructed by virtue of coherent integration. The CWT adaptively gives different weights to HRRP signals and noise, which is called coarse denoising. Second, inspired by the similarities of range profiles, the minimum weighted nuclear norm (Min-WNN) optimisation is proposed to further reduce the residual noise. The coarse denoised HRRPs are rearranged into an approximate low-rank matrix. Subsequently, rank-constraint optimisation on the HRRP matrix via minimising the weighted nuclear norm is performed, aiming to efficiently suppress the residual noise. This step is called fine denoising. As a result, ISAR image quality is significantly improved. Comprehensive experiments illustrate the effectiveness and superiority of the presented method.

High-Precision Log-Ratio Spot Position Detection Algorithm with a Quadrant Detector under Different SNR Environments.

In atmospheric laser communication, a beam is transmitted through an atmospheric channel, and the photocurrent output from a quadrant detector (QD) used as the tracking sensor fluctuates significantly. To ensure uninterrupted communication and to adapt to such fluctuations, in this paper we apply logarithmic amplifiers to process the output signals of a QD. To further improve the measurement accuracy of the spot position, we firstly propose an integral infinite log-ratio algorithm (IILRA) and an integral infinity log-ratio algorithm based on the signal-to-noise ratio (BSNR-IILRA) through analysis of the factors influencing the measurement error considering the signal-to-noise ratio (SNR) parameter. Secondly, the measurement error of the two algorithms under different SNRs and their variations are analyzed. Finally, a spot position detection experiment platform is built to correctly and efficiently verify the two algorithms. The experimental results show that when the SNR is 54.10 dB, the maximum error and root mean square error of the spot position of the IILRA are 0.0054 mm and 0.0039 mm, respectively, which are less than half those of the center approximation algorithm (CAA). When the SNR is 23.88 dB, the maximum error and root mean square error of the spot position of the BSNR-IILRA are 0.0046 mm and 0.0034 mm, respectively, which are one-thirtieth and one-twentieth of the CAA, respectively. The spot position measurement accuracy of the two proposed algorithms is significantly improved compared with the CAA.

Joint Optimization of Received Signal Power and Signal Space Dimensions for MIMO Broadcast Channels

In Multiple-input multiple-output (MIMO) broadcast channels (BCs), the transmitter simultaneously broadcasts signals to multiple receivers at same frequency band, resulting in that the communication capacity is affected by both interference, channel fading and random noise. Although channel fading can be mitigated by transceivers, the signal-to-noise-ratio (SNR) of the practical communication system is still dynamically changing due to the randomly changing noise. Traditional MIMO transceiver optimization algorithms can not flexibly adapt to the dynamic changes of SNR, resulting in large performance degradation. In this paper, we comprehensively consider signal power and signal space dimensions of the received signal in MIMO BCs, and propose two transceiver optimization algorithms which can dynamically adapt to the variance of SNRs. In the proposed algorithms, SNR is adopted to be an adjustment factor to cope with its variance. When SNR is low, i.e, large noise, the algorithm parameters are automatically adjusted so that the signal power is preserved as much as possible to combat the loss of communication capacity caused by large random noise. Correspondingly, under the condition of high SNR environment, the algorithm parameters are adjusted automatically to effectively compress the inter-user-interference (IUI) and intra-user-inter-stream-interference (ISI) by optimizing signal space dimensions. Simulation results show that in different SNR environments, the proposed algorithms can automatically adjust the focus of optimization, so that the optimization of signal power and signal space dimensions can automatically adapt to different SNRs. Compared with traditional transceiver optimization algorithms, the proposed algorithms can improve the communication capacity within a large dynamic range of SNR.

Sound source localization of non-synchronous measurements beamforming based on the truncated nuclear norm regularization

Due to the size and aperture limitations of the microphone array, poor resolution and limited working frequency range are challenging for acoustic imaging with beamforming methods. In this work, two fast iteration algorithms, alternating direction method of multipliers (ADMM) and accelerated proximal gradient line search method (APGL) based on truncated nuclear norm regularization (TNNR), are proposed to complete the cross-spectral matrix for non-synchronous measurements beamforming. Compared with current matrix completion algorithm based on nuclear norm minimization (NNM), TNNR is regarded as a better approximation to the rank function, which means it can approach the real solution better and restore the sound sources accurately at a low signal-to-noise ratio (SNR) environment. Among the TNNR-APGL and TNNR-ADMM, the TNNR-APGL algorithm has a lower matrix completion error and a shorter calculation time. The localization results of TNNR-ADMM method are more robust to the number of measurements. The experiment results show that TNNR methods greatly improve the resolution of conventional beamforming (CBF) and suppress the sidelobes under low SNR conditions, which indicates that the non-synchronous measurements beamforming based on TNNR methods has the potential to be applied in the industrial scene and low SNR environment.

A Robust Translational Motion Compensation Method Based on Weighted Optimization Framework—Second-Order Drift Particle Swarm Optimization

Accurate translational motion compensation is critical for ISAR imaging, especially for datasets with low signal-to-noise ratio (SNR) or sparse aperture. Among the existing translational motion compensation methods, the methods that based on the polynomial model have profound noise robustness but are easily affected by the variation of the reference distance. The methods that based on the range profile alignment have good versatility but are far from ideal under low SNR and sparse aperture environment. Therefore, we propose a novel and robust translational motion compensation method to overcome the shortcoming of the existing methods. Specifically, we estimate the translational phase error sequence by maximizing Laplacian average gray level and peak value. It can improve the robustness of translational motion compensation for noise and sparse aperture. Since such principle creates a large-scale multi-objective optimization problem, we design weighted optimization framework - second-order drift particle swarm optimization (WOF - SDPSO) to solve it accurately. WOF-SDPSO achieves full exploration of high-dimensional variable space by variable dimension reducing, random drift update, and second-order oscillation convergence. These ensure the global optimal solution easier to be found. Experimental results of the measured dataset prove that the proposed method is effective and accurate under the conditions of low SNR and sparse aperture. Moreover, the proposed method is noise robust for polynomial translational motion model with sparse aperture.