Low Signal-to-noise Ratio Research Articles

Multi-task deep learning for quantifying methane emissions from 2-D plume imagery with Low Signal-to-Noise Ratio

ABSTRACT Methane is the second most significant greenhouse gas after carbon dioxide. As global warming intensifies, the quantification of methane point sources is becoming increasingly crucial. However, retrieving high-quality methane signals from remote sensing data remains challenging due to various factors, including surface reflectance, atmospheric interference, sensor noise, wind speed, and sensor sensitivity. In real-world scenarios, methane remote sensing quantification often encounters unfavourable conditions that lead to low signal-to-noise ratio (SNR) signals, resulting in reduced quantification accuracy. To address these challenges, we introduce a novel multi-task learning-based approach. Specifically, we incorporate a denoising auxiliary task into the quantification network by introducing an additional denoising branch that recovers clean plume column concentration maps. The network is trained with supervision using both denoising and quantification losses, which enables it to acquire robust feature representations to noise and benefits the quantification of low SNR images. During the inference phase, the denoising branch is removed, resulting in an efficient and robust single quantification network with reduced inferring time, supporting onboard computation. We construct a low SNR database based on the AVIRIS-NG sensor and evaluate the generalization ability of our method. DQNet achieves the highest RMSE, MAPE, and R of 16.478 kg/h, 15.296%, and 95.167% respectively on the synthetic dataset. Across the entire range of SNR, DQNet exhibits a greater relative advantage as SNR decreases. However, our approach is not limited to AVIRIS-NG and can be easily extended to various multispectral and hyperspectral satellites.

Radiofrequency Enhancer to Recover Signal Dropouts in 7 Tesla Diffusion MRI

Diffusion magnetic resonance imaging (dMRI) allows for a non-invasive visualization and quantitative assessment of white matter architecture in the brain by characterizing restrictions on the random motion of water molecules. Ultra-high field MRI scanners, such as those operating at 7 Tesla (7T) or higher, can boost the signal-to-noise ratio (SNR) to improve dMRI compared with what is attainable at conventional field strengths such as 3T or 1.5T. However, wavelength effects at 7T cause reduced transmit magnetic field efficiency in the human brain, mainly in the posterior fossa, manifesting as signal dropouts in this region. Recently, we reported a simple approach of using a wireless radiofrequency (RF) surface array to improve transmit efficiency and signal sensitivity at 7T. In this study, we demonstrate the feasibility and effectiveness of the RF enhancer in improving in vivo dMRI at 7T. The electromagnetic simulation results demonstrated a 2.1-fold increase in transmit efficiency with the use of the RF enhancer. The experimental results similarly showed a 1.9-fold improvement in transmit efficiency and a 1.4-fold increase in normalized SNR. These improvements effectively mitigated signal dropouts in regions with inherently lower SNR, such as the cerebellum, resulting in a better depiction of principal fiber orientations and an enhanced visualization of extended tracts.

New scheme of cooperative compressed spectrum sensing

Abstract This study addresses key challenges in sparse signal recovery and compressed spectrum sensing (CSS), focusing on low signal-to-noise ratios (SNR), and the computational complexity of cooperative systems. Motivated by the need for faster and more accurate recovery techniques, we first investigate and generalize the Reduced-Set Matching Pursuit (RMP) algorithm, which overcomes the speed and accuracy limitations of conventional greedy algorithms. Secondly, we propose a novel spatial averaging technique that enhances detection performance by exploiting data from multiple users to counteract low SNR. Lastly, we integrate cooperation into CSS, further improving the detection capabilities during the recovery process. Compared to existing techniques like Joint Sparse Recovery (JSR) and CoSaMP, which face computational and accuracy constraints in real-time applications, the RMP algorithm, combined with the Virtual method (data transformation) and AND fusion rule, delivers superior performance than JSR methods. Moreover, spatial averaging significantly increases the probability of cooperative detection Q d , with SNR increasing linearly by a factor of L − 1 per channel. The results are validated through the implementation of SDR. These findings demonstrate the potential of RMP and cooperation to overcome current limitations in CSS, advancing the state-of-the-art in spectrum sensing for collaborative networks.

Two-Phase Globally Coupled Low-Density Parity Check Decoding Aided with Early Termination and Forced Convergence

To enhance the decoding efficiency of Globally Coupled (GC) LDPC codes, we incorporated Early Termination (ET) and Forced Convergence (FC) into the local/global two-phase decoding algorithm to expedite the decoding process. The two-phase decoding scheme integrates the ET technique to halt unnecessary iterations in the local decoding phase while employing the FC technique to accelerate convergence in the global phase decoding. The application of ET technology in the local decoding of GC-LDPC codes will not cause performance loss as in traditional block codes and will cause considerable complexity gains. For a longer code length and larger convergence differences between nodes’ global codes, the FC technique operates more efficiently in global code than local code. Two variants are proposed for the ET scheme in the local decoding, namely ET-1 and ET-2. The initial variant, ET-1, predicts whether local decoding can be successful according to data characteristics and stop the local decoding iteration that is not expected to be successful in time. In the case of ET-2, the saved local iterations are transformed to global decoding equally. The results show that ET-1 saves considerable decoding time complexity and ET-2 improves the performance of the GC-LDPC code with the same decoding time complexity. The combined approach of ET-1 with FC reduces the decoding time complexity up to 42% at a low Signal Noise Rate region while maintaining its performance; ET-2-FC two-phase decoding saves approximately 25% decoding time complexity while improving the BER by about 0.18 dB and FER by about 0.23 dB.

Research on frequency shift signal detection algorithm for jointless track circuits based on improved relaxation algorithm

The accuracy of ZPW-2000 frequency shift signal demodulation is related to the safety and efficiency of high-speed trains. This paper proposed a kind of ZPW-2000 frequency-shift signal detection algorithm based on improved Relaxation algorithm (ZFSD-IR) to address the issue of low accuracy in detecting ZPW-2000 frequency shift signal under strong noise interference, as the traditional fast Fourier transform (FFT) spectrum analysis methods are susceptible to fence effects and spectrum leakage effects. Firstly, the principle of ZPW-2000 jointless track circuit was analyzed, and then the ideal and simplified models of ZPW-2000 frequency shift signal were established, respectively. Finally, the simulation experiments were conducted on ZPW-2000 frequency shift signal detection under different sampling durations and signal-to-noise ratios (SNR). The effectiveness of the proposed algorithm was verified through comparative analysis with the traditional algorithms. The research results indicated that the ZFSD-IR algorithm has better accuracy in carrier-frequency and low-frequency estimation than traditional algorithms, and can achieve accurate detection of ZPW-2000 frequency shift signal under the lower SNR conditions. It has high detection accuracy and good anti-interference ability, ensuring the safe operation of high-speed trains.

Early clinical efficacy study on the efficacy of a three-stage conservative Chinese medicine external treatment for acute lateral ankle ligament injuries

To evaluate the clinical effect of a new three-phase Chinese medicine (CM) external treatment for acute lateral ankle ligament injuries. From July to December 2023, 64 patients with acute lateral ankle ligament injuries were randomly assigned to receive either the new three-phase CM external treatment combined with the POLICE(protect, optimal loading, ice, compression, elevation) treatment (observation group) or the POLICE treatment (control group), with 32 cases in each group. The observation group consisted of 17 males and 15 females, with an average age of(30.59±3.10) years old ranging from 25 to 36 years old, while the control group included 14 males and 18 females, with an average age of(30.03±3.19) years old ranging from 24 to 37 years old. Visual analogue scale (VAS) evaluation and Figure of 8 measurement were used to evaluate the degree of ankle joint pain and swelling of the subjects at the initial enrollment and after 1 week and sixth weeks of treatment. At the same time, the American Orthopaedic Foot and Ankle Society (AOFAS) and Karlsson Ankle Function Score System were used to evaluate the improvement of ankle joint function in patients at all stages. MRI imaging was employed to observe the degree of biological healing of the anterior talofibular ligament, with the signal to noise ratio(SNR) indicating the level of healing. A lower SNR suggests better ligament healing, as it represents lower water content in the ligament. All patients completed a 6-week follow-up. There was no significant difference in VAS, AOFAS score and Karlsson score between the two groups before treatment (P>0.05). After 1 week and 6 weeks of treatment, the VAS, AOFAS score and Karlsson score of the two groups were significantly improved (P<0.05). After 1 week of treatment, the VAS score of the observation group (3.21±0.87) was lower than that of the control group (4.21±1.50), and the difference was statistically significant (P<0.05). After 1 weeks of treatment, the AOFAS and Karlsson scores [(50.84±4.70) points, (49.97±4.00) points] of the observation group were higher than those [(46.91±5.56) points, (46.66±5.36) points]of the control group (P<0.05). MRI images showed that after 6 weeks of treatment, the SNR value of the observation group was significantly lower than that of the control group, and the difference was statistically significant(SNR of the observation group was 75.25±16.59, the contral gruop was 85.81±15.55), (P<0.05). Compared with the control group, the new three-phase CM external treatment is significantly effective in reducing pain and swelling, enhancing ligament repair quality, and promoting functional recovery of the ankle joint in patients with acute lateral malleolar ligament injuries.

Weighted joint LRTs for cooperative spectrum sensing using K-means clustering

In this paper, a blind centralized cooperative spectrum sensing (CSS) with soft decision fusion is considered. The fusion center (FC) constructs the energy vector from the collaborating secondary nodes. The energy feature is assumed to be an efficient measure, as it is widely used and directly correlates with the strength of the received signal. The K-means clustering algorithm is employed to extract descriptive statistical features about the distributions of the absence and presence of the primary user (PU) signal, such as the mean and non-centrality parameter. In the framework of this statistical analysis, the signal-to-noise ratio (SNR) at each node is easily estimated and examined. Equal, selective, and weighted combining techniques are applied to develop three joint likelihood ratio test (JLRT)-based algorithms. These algorithms are implemented in the context of simple hypothesis testing, where the distribution of the data is fully specified. Furthermore, they are justified by the Neyman-Pearson theorem, which constructs the most powerful test for a given significance level. The proposed selective and weighted JLRT approaches are based on the estimated SNRs at each sensor, reflecting their reliability. Several comparison scenarios between the proposed algorithms, K-means, fuzzy c-means (FCM), and OR-rule are simulated over Rayleigh fading channel with low average SNR and few samples. The simulation results reveal that the proposed tests outperform other CSS techniques. Additionally, asymptotic theoretical expressions for probability of detection and the probability of false alarm are derived, which show high agreement with the simulated results.

Adaptive stochastic resonance enhanced weak linear frequency modulated signal perception in low signal-to-noise ratio environments

Abstract The linear frequency modulated (LFM) signal has gained extensive utilization in radar, sonar and covert communication system due to its large time-bandwidth product, high-precision distance measurement and low detection probability. The perception of weak LMF signals holds significant importance yet encounters substantial challenges within the increasing complexity of the electromagnetic environments. Consequently, this paper proposes an adaptive stochastic resonance (ASR) enhanced approach for perceiving weak LFM signals in low signal-to-noise ratio (SNR) conditions. This approach initially commences a pioneering study on the quantitative synergistic resonance mechanism among LFM signals, random noise, and nonlinear stochastic resonance (SR) systems. Subsequently, the ASR system’s implementation becomes straightforward through the adaptive adjustment of SR system parameters according to the LFM signal and noise characteristics. This implementation leverages the inherent property of noise energy transfer to signal energy, facilitating the enhancement of ordered weak signals via random noise. Following the enhancement of the output signal by the ASR system, the Wigner–Ville distribution (WVD) transform’s time-frequency concentration property is employed to extract the time-frequency characteristics. Building on the WVD transform, the Radon transform with linear integral projection is applied to further harness the time-frequency domain energy concentration, thereby achieving the effective perception of weak LFM signals. Finally, the effectiveness of the proposed method in improving the perception performance of weak LFM signal in very low SNR conditions is verified through numerical simulations. It is anticipated that this method will have potential application value in fields such as radar, sonar, and communication under complex electromagnetic environments.

Super-Resolution Processing for Multiple Aperture Antenna to Suppress Multipath

Angle estimation for low-altitude targets above the sea surface is a challenging problem due to multipath interference from surface reflection signals, and various approaches have been proposed. This paper proposes a matrix pencil method with multiple apertures. The matrix pencil method effectively responds to dynamic scenarios because it performs better when using a single snapshot than other methods. Also, employing multiple apertures is more economical than using one large aperture. Therefore, we propose a computationally efficient approach using this method and structures. The proposed two-stage MP method incrementally improves the resolution in two stages: in stage 1, we extract the denoised signals at each aperture level, and in stage 2, we further improve the resolution with those signals. In comparison with the angular resolution defined by the half-power beamwidth (HPBW) of a uniform linear array (ULA) antenna with an equivalent number of arrays, the proposed method demonstrated a superior resolution of less than 0.087 of the HPBW at a high signal-to-noise ratio (SNR) of 40 dB, and less than 0.31 of it even at a relatively low SNR of 15 dB, based on 90% of the resolving probability. For the multipath problem, the proposed scheme has the advantage of not requiring prior geometric information, and its performance is demonstrated through simulations to be better than the adaptive beamforming method and the composite monopulse method.

Acoustic leak localization for water distribution network through time-delay-based deep learning approach

Water leakage within water distribution networks (WDNs) presents significant challenges, encompassing infrastructure damage, economic losses, and public health risks. Traditional methods for leak localization based on acoustic signals encounter inherent limitations due to environmental noise and signal distortions. In response to this crucial issue, this study introduces an innovative approach that utilizes deep learning-based techniques to estimate time delay for leak localization. The research findings reveal that while the Res1D-CNN model demonstrates inferior performance compared to the GCC-SCOT and BCC under high signal-to-noise ratio (SNR) conditions, it exhibits robust capabilities and higher accuracy in low SNR scenarios. The proposed method's efficacy was empirically validated through field measurements. This advancement in acoustic leak localization holds the potential to significantly improve fault diagnosis and maintenance systems, thereby enabling efficient management of WDNs.

DOA Estimation Method for Vector Hydrophones Based on Sparse Bayesian Learning.

Through extensive literature review, it has been found that sparse Bayesian learning (SBL) is mainly applied to traditional scalar hydrophones and is rarely applied to vector hydrophones. This article proposes a direction of arrival (DOA) estimation method for vector hydrophones based on SBL (Vector-SBL). Firstly, vector hydrophones capture both sound pressure and particle velocity, enabling the acquisition of multidimensional sound field information. Secondly, SBL accurately reconstructs the received vector signal, addressing challenges like low signal-to-noise ratio (SNR), limited snapshots, and coherent sources. Finally, precise DOA estimation is achieved for multiple sources without prior knowledge of their number. Simulation experiments have shown that compared with the OMP, MUSIC, and CBF algorithms, the proposed method exhibits higher DOA estimation accuracy under conditions of low SNR, small snapshots, multiple sources, and coherent sources. Furthermore, it demonstrates superior resolution when dealing with closely spaced signal sources.

Investigating the Influence of Wavelength-Specific Textured Backgrounds in Background Oriented Schlieren (BOS) Imaging

This study investigates the influence of wavelength-specific textured backgrounds on the effectiveness of Background-Oriented Schlieren (BOS) imaging, focusing on wavelengths from 400 nm to 670 nm at intervals of 30 nm intervals and multiple captured recordings for each background wavelength interval. By analyzing the signal-to-noise ratio (SNR) computationally, and the image gradient magnitude, we aimed to determine the optimal wavelengths for capturing turbulence and determine the effectiveness of colored backgrounds in natural external environments for schlieren. The SNR, calculating the ratio of mean signal intensity to noise standard deviation, revealed the highest value at 550 nm (SNR = 22.8), indicating maximized clarity. Similarly, image gradient magnitude, computed using the Sobel operator to assess spatial intensity changes, peaked at 550 nm (G=52.3), confirming effective turbulence visualization. Our findings align with the Bayer color filter trend, suggesting that the green spectrum is particularly advantageous for BOS imaging. Deviations at 490 nm and 580 nm, characterized by lower SNR and gradient magnitude, could be attributed to atmospheric scattering, refractive index overlap, or slight digital video capture differences., highlighting environmental factors that can influence imaging performance and value variation. These insights emphasize the importance of wavelength selection and background design in real-world BOS applications, suggesting that while 550 nm provides optimal results, further refinement may enhance the effectiveness of other wavelengths.

SiPM-based LiDAR with multipulse sequence modulation and multithreshold signal processing.

A light detection and range technology (LiDAR) system that enables rapid ranging under extremely low signal-to-noise ratios (SNRs) during daylight conditions based on a SiPM (silicon photomultiplier) detector is proposed. The system emits a sequence of modulated laser pulses by controlling the semiconductor laser and then processes the SiPM response signals using dynamic multithreshold. The experimental result shows that, under extremely low SNR of daylight, the system achieves a 100% success rate in continuous ranging of a low reflectivity target at 125 m, with a ranging precision of less than 20 cm and a ranging time of less than 10 µs. Our system provides a significant reference value for achieving high-speed, noise-resistant, miniaturized, practical, and low-cost LiDAR based on a SiPM.

Post-Estimation Shrinkage in Full and Selected Linear Regression Models in Low-Dimensional Data Revisited.

The fit of a regression model to new data is often worse due to overfitting. Analysts use variable selection techniques to develop parsimonious regression models, which may introduce bias into regression estimates. Shrinkage methods have been proposed to mitigate overfitting and reduce bias in estimates. Post-estimation shrinkage is an alternative to penalized methods. This study evaluates effectiveness of post-estimation shrinkage in improving prediction performance of full and selected models. Through a simulation study, results were compared with ordinary least squares (OLS) and ridge in full models, and best subset selection (BSS) and lasso in selected models. We focused on prediction errors and the number of selected variables. Additionally, we proposed a modified version of the parameter-wise shrinkage (PWS) approach named non-negative PWS (NPWS) to address weaknesses of PWS. Results showed that no method was superior in all scenarios. In full models, NPWS outperformed global shrinkage, whereas PWS was inferior to OLS. In low correlation with moderate-to-high signal-to-noise ratio (SNR), NPWS outperformed ridge, but ridge performed best in small sample sizes, high correlation, and low SNR. In selected models, all post-estimation shrinkage performed similarly, with global shrinkage slightly inferior. Lasso outperformed BSS and post-estimation shrinkage in small sample sizes, low SNR, and high correlation but was inferior when the opposite was true. Our study suggests that, with sufficient information, NPWS is more effective than global shrinkage in improving prediction accuracy of models. However, in high correlation, small sample sizes, and low SNR, penalized methods generally outperform post-estimation shrinkage methods.

Impact of Model Knowledge on Acoustic Emission Source Localization Accuracy

Reliable and precise damage localization in mechanical structures is of high importance in the context of structural health monitoring (SHM). The acoustic emission (AE) method has already shown its excellent suitability for damage localization. However, low signal-to-noise ratios (SNRs) are often prevalent in SHM, thus an increase in localization accuracy and robustness is still in demand. The present study faces this task through the integration of various model knowledge for AE source localization. The basis of the presented algorithm is the consideration of the dispersive behavior of elastic waves in thin-walled structures. The continuous wavelet transform (CWT) is used to obtain time-frequency representations of the signals, where frequency-dependent values for time-of-arrival (TOA) are extracted. Furthermore, the algorithm incorporates the knowledge that all sensors receive signals with the same time and location of origin, as well as the slightly different sensitivity of the theoretically equal sensors. The final localization results are achieved by a two parameter grid search optimization. The algorithm is experimentally tested on a large aluminum plate with four piezoelectric wafer active sensors (PWASs) arranged in an array of 100 mm × 100 mm. The mean localization error of pencil lead breaks at ten different positions within the sensor array is used as an accuracy measure. It is shown that as more of the described model knowledge is incorporated into the localization, the accuracy increases. With the final algorithm, the mean localization error is more than halved compared to AE localization based on classical TOA estimation. Although the experiment described is conducted under laboratory conditions, the remarkable increase in accuracy suggests that AE source localization may be successful even at low SNR as typical for operational conditions.

Noise-robust automated sudden damage detection using blind source separation enhanced by variational mode decomposition and support vector machine based on shapelet transform

Compared to parametric counterparts, non-parametric (aka, model-free) damage detection methods have no requirements of accurate models, with the potential of autonomous monitoring of various complex structures. However, noises, or low signal-to-noise ratio (SNR), are one of the main challenges. This study is aimed at improving blind source separation (BSS)-based damage detection method, one of the most advanced non-parametric methods, in both aspects of noise robustness and autonomous operation. In particular, the measured acceleration responses are processed by variational mode decomposition (VMD) and wavelet transform (WT) in sequential, acting as the input for a BSS model. The BSS is then solved by independent component analysis (ICA), which approves to be more noise-robust compared to the state-of-the-art counterparts. Furthermore, shapelet transform is applied to extract the universal shape-based spike-like feature from the BSS model for training a support vector machine (SVM) model, applicable to different structures; it finally automates the sudden damage detection process and enables online monitoring. The effectiveness of the proposed method is illustrated by a numerical example and an experimental test, and demonstrated by a real-world seismic-excited structure. The results show that both single and multiple sudden damages can be automatically detected with high accuracy. Compared with the existing BSS methods, the proposed BSS method is more capable to detect small damages at relatively low SNR. In addition, the classification accuracy of SVM is also improved when shapelet-based feature is used for training, which reduces the malfunction of automated damage detection as shown by the numerical example. Therefore, the proposed strategy has the potential for rapid condition assessment of structures during rare/extreme events, before engineers are sent for further post-event inspection.

Monoenergetic reconstructions and iodine density maps for visualization of coronary artery stents using 8-cm dual-layer detector spectral computed tomography: an in vitro phantom study.

The effectiveness of coronary computed tomography (CT) angiography in assessing stent restenosis is hindered by heavy metal artifacts. This study aimed to evaluate the image quality of monoenergetic reconstructions and iodine density map for coronary stent imaging using an 8-cm dual-layer detector spectral CT. In this study, 8 stents with a diameter <3 mm (group A) and 10 with a diameter ≥3 mm (group B) were placed in plastic tubes filled with iodinated contrast media and scanned. The internal diameter of the prepared stents was then measured by intravascular ultrasound. The reconstructed images included iodine density maps, conventional images, and different energy levels. The visualization of the stent lumen and stent structure was subjectively assessed using a 4-point Likert scale. The objective evaluation was performed using the in-stent lumen signal-to-noise ratio (SNRis), non-stent lumen SNR (SNRns), internal diameter difference (IDD), and blooming artifact index (BAI). The Friedman test and analysis of variance were used for multiple comparisons. For lumen visualization, the optimal monoenergetic images received the highest score for both group A (2.56±0.51) and group B (3.1±0.55). Multiple comparisons showed that there were significant differences between the optimal monoenergetic images and iodine density maps. However, for stent structure, iodine density maps received the highest score for group A (3.0±0.52) and group B (3.8±0.41). For quantitative assessment, the optimal monoenergetic images had the highest SNRis and SNRns, while the iodine density maps had the lowest SNRis and SNRns. For IDD and BAI, the iodine density maps yielded the smallest value. The monoenergetic images on the second-generation dual-layer detector CT provide better visualization of the lumen and higher SNR. However, iodine density maps are superior for evaluating stent structure and IDD and BAI compared to monoenergetic and conventional reconstructions.

A high-resolution method for direction of arrival estimation based on an improved self-attention module.

The high-resolution direction of arrival (DOA) estimation is a prominent research issue in underwater acoustics. The existing high-resolution methods include subspace methods and sparse representation methods. However, the performance of subspace methods suffers from low signal-to-noise ratio (SNR) and limited snapshots conditions, and the computational complexity of sparse representation methods is too high. The neural network methods are emerging high-resolution methods. However, insufficient support for big data is frequently observed in underwater acoustics, and conventional network structures present challenges in further enhancing performance. To address the aforementioned problems, we propose a neural network method based on an improved self-attention module to achieve high accuracy and robust DOA estimation. First, we design a multi-head self-attention module with large-scale convolutional kernels and residual structures to improve the estimated accuracy. Second, we propose an improved input feature to enhance the robustness to non-uniform noise and unequal-intensity targets. The simulations demonstrate that the proposed method exhibits superior angle resolution compared to sparse representation methods under the same simulation conditions. The proposed method demonstrates exceptional accuracy and robustness in DOA estimation under challenging conditions of low SNR, limited snapshots, and unequal-intensity targets. The experimental results further prove the effectiveness of the proposed method.

A hybrid denoising method for low-field nuclear magnetic resonance data

Low-field nuclear magnetic resonance (NMR) has broad application prospects in the exploration and development of unconventional oil and gas reservoirs. However, NMR instruments tend to acquire echo signals with relatively low signal-to-noise ratio (SNR), resulting in poor accuracy of T2 spectrum inversion. It is crucial to preprocess the low SNR data with denoising methods before inversion. In this paper, a hybrid NMR data denoising method combining empirical mode decomposition-singular value decomposition (EMD-SVD) was proposed. Firstly, the echo data were decomposed with the EMD method to low- and high-frequency intrinsic mode function (IMF) components as well as a residual. Next, the SVD method was employed for the high-frequency IMF components denoising. Finally, the low-frequency IMF components, the denoised high-frequency IMF components, and the residual are summed to form the denoised signal. To validate the effectiveness and feasibility of the EMD-SVD method, numerical simulations, experimental data, and NMR log data processing were conducted. The results indicate that the inverted NMR spectra with the EMD-SVD denoising method exhibit higher quality compared to the EMD method and the SVD method.

A complex-valued convolutional fusion-type multi-stream spatiotemporal network for automatic modulation classification

Automatic Modulation Classification (AMC) is crucial in non-cooperative communication systems as it facilitates the identification of interference signals with minimal prior knowledge. Although there have been significant advancements in Deep Learning (DL) within the field of AMC, leveraging the inherent relationships between In-phase (I) and Quadrature-phase (Q) components, and enhance recognition accuracy under low signal-to-noise ratio (SNR) conditions remains a challenge. This study introduces a complex-valued convolutional fusion-type multi-stream spatiotemporal network (CC-MSNet) for AMC, which combines spatial and temporal feature extraction modules for modulation recognition. Experimental results demonstrate that the CC-MSNet performs well on three benchmark datasets, RML2016.10a, RML2016.10b, and RML2016.04c, with average recognition accuracy of 62.86%, 65.08%, and 71.12%. It also performs excellently in low SNR environments below 0dB, significantly outperforming other networks.