Blind Source Separation Method Research Articles

Ship-Radiated Noise Separation in Underwater Acoustic Environments Using a Deep Time-Domain Network

Ship-radiated noise separation is critical in both military and economic domains. However, due to the complex underwater environments with multiple noise sources and reverberation, separating ship-radiated noise poses a significant challenge. Traditionally, underwater acoustic signal separation has employed blind source separation methods based on independent component analysis. Recently, the separation of underwater acoustic signals has been approached as a deep learning problem. This involves learning the features of ship-radiated noise from training data. This paper introduces a deep time-domain network for ship-radiated noise separation by leveraging the power of parallel dilated convolution and group convolution. The separation layer employs parallel dilated convolution operations with varying expansion factors to better extract low-frequency features from the signal envelope while preserving detailed information. Additionally, we use group convolution to reduce the expansion of network size caused by parallel convolution operations, enabling the network to maintain a smaller size and computational complexity while achieving good separation performance. The proposed approach is demonstrated to be superior to the other common networks in the DeepShip dataset through comprehensive comparisons.

Improvements of EEG Signal Quality: A Hybrid Method of Blind Source Separation and Variational Mode Destruction to Reduce Artifacts

The electroencephalogram (EEG) is a crucial tool for studying brain activity; yet it frequently encounters artifacts that distort meaningful neural signals. This paper addresses the challenge of artifact removal through a unique hybrid method, combining Variational Mode Decomposition (VMD) techniques with Blind Source Separation (BSS) algorithms. VMD, recognized for its adaptability to non-linear and non-stationary EEG data, as well as its ability to alleviate mode mixing and the “endpoint effect,” which serves as an effective preprocessing step. The paper evaluates the performance of two integrated BSS algorithms, AMICA and AMUSE, across various criteria. Comparisons across metrics such as Euclidean distance, Spearman correlation coefficient, and Root Mean Square Error reveal similar performance between AMICA and AMUSE. However, a distinct divergence is evident in the Signal to Artifact Ratio (SAR). When employed with VMD, AMICA demonstrates superiority in effectively discerning and segregating brain signals from artifacts, which gives a mean value of 1.0924. This study introduces a potent hybrid VMDBSS approach for enhancing EEG signal quality. The findings emphasize the notable impact of AMICA, particularly in achieving optimal results in artifact removal, as indicated by its superior performance in SAR. The abstract concludes by underlining the significance of these results, emphasizing AMICA’s pivotal role in achieving the highest measurable evaluation value, making it a compelling choice for researchers and practitioners in EEG signal processing.

Research on heart and lung sound separation method based on DAE–NMF–VMD

Auscultation is the most effective method for diagnosing cardiovascular and respiratory diseases. However, stethoscopes typically capture mixed signals of heart and lung sounds, which can affect the auscultation effect of doctors. Therefore, the efficient separation of mixed heart and lung sound signals plays a crucial role in improving the diagnosis of cardiovascular and respiratory diseases. In this paper, we propose a blind source separation method for heart and lung sounds based on deep autoencoder (DAE), nonnegative matrix factorization (NMF) and variational mode decomposition (VMD). Firstly, DAE is employed to extract highly informative features from the heart and lung sound signals. Subsequently, NMF clustering is applied to group the heart and lung sounds based on their distinct periodicities, achieving the separation of the mixed heart and lung sounds. Finally, variational mode decomposition is used for denoising the separated signals. Experimental results demonstrate that the proposed method effectively separates heart and lung sound signals and exhibits significant advantages in terms of standardized evaluation metrics when compared to contrast methods.

Utilizing data-driven algorithms for blind modal parameter identification of structures from output-only video measurements

In structural dynamics and vibration analysis, modal identification plays a pivotal role in understanding and characterizing the dynamic behavior of complex systems. Traditional modal analysis techniques heavily rely on accurate sensor placement and knowledge of the excitation forces, which may not always be feasible or practical in real-world scenarios. Recently, non-contact video-based modal analysis methods for structures with arbitrary complexity using computer vision techniques have gained much importance. But these methods need to know ahead of time where the structure's natural frequency ranges are, and they use steerable pyramids, which are complicated multi-scale image decomposition filters. To address these issues, a blind modal identification technique is suggested to extract the modal parameters (modal frequency and mode shapes) from the recorded structural vibration video signal. The proposed algorithm for unsupervised machine learning is the Non-Negative Matrix Factorization (NNMF) method, which is combined with the Generalized Complexity Pursuit (GCP) method for blind source separation. The NNMF algorithm is directly applied to the raw pixel-time series made from the video data to get the temporal components, which are then separated using GCP to find the individual modal frequencies and mode shapes. The above algorithm is first validated on a numerical model and then implemented on laboratory scale models (cantilever, single-degree, and multi-degree frame models). Finally, the proposed methodology is implemented on real-world recorded structural vibration videos to determine its noise sensitivity, such as the Tacoma Narrows bridge and the London Millennium footbridge. The modal parameters extracted are compared with those from the available literature for validation. The estimation errors obtained from all the validations are well below 1%, which makes the technique quite suitable and reliable for structural vibration monitoring by identifying and reproducing complex vibration modes.

Tensor decomposition meets blind source separation

In this paper, we investigate the problem of blind source separation (BSS) through the lens of tensor decomposition (TD). Two fundamental connections between TD and BSS are established, forming the basis for two novel tensor-based BSS methods, namely TenSOFO and TCBSS. The former is designed for a joint individual differences in scaling (INDSCAL) decomposition, addressing instantaneous (linear) BSS tasks; while the latter efficiently performs a constrained block term decomposition (BTD), aligning with the design of convolutive BSS. Leveraging the benefits of the alternating direction method of multipliers and the strengths of tensor representations, both TenSOFO and TCBSS prove to be effective in BSS. Our experimental results demonstrate the effectiveness of these two proposed methods in addressing both TD and BSS tasks, particularly when compared to state-of-the-art algorithms.

Flux Contribution and Geometry of Charge Exchange Emission in the Starburst Galaxy M82

Recent X-ray studies of starburst galaxies have found that charge exchange (CX) commonly occurs between outflowing hot plasma and cold gas, possibly from swept-up clouds. However, the total CX flux and the regions where CX occurs have been poorly understood. We present an analysis of XMM-Newton observations of M82, a prototype starburst galaxy, aiming to investigate these key properties of CX emission. We have used a blind source separation method in an image analysis of CCD data, which identified a component with the enhanced O–K lines expected from the CX process. Analyzing the XMM-Newton/RGS spectra from the regions identified by the image analysis, we have detected a high forbidden-to-resonance ratio of the O vii Heα triplet as well as several emission lines from K-shell transitions of C, N, and O that are enhanced by the CX process. CX is less responsible for the emission lines of Ne and Mg, and accurate estimation of the CX contribution is confirmed to be crucial in measuring chemical abundances. The temperature of the plasma acting as an electron receiver in the CX process is significantly lower compared to that of the plasma components responsible for most of the X-rays. From the low temperature and an estimation of the CX-emitting volume, we find that the CX primarily occurs in a limited region at interfaces between plasma and gas whose temperatures rapidly decrease due to thermal conduction.

Towards vision-based structural modal identification at low frame rate using blind source separation

With increasing availability of cost-effective and high-resolution cameras, their use as a non-contact sensing tool has rapidly progressed for structural health monitoring. The cameras offer unique capabilities to provide full-field measurement with high spatial density at low cost. However, extracting high-density temporal data is challenging, as a high-speed camera increases the monitoring cost with high-rate data processing. Recently, motion magnification (MM) has shown significant success in analyzing low-amplitude motion of structural systems. However, previous studies observed that MM methodology performs poorly at low frame rates for modal identifications. In this paper, the influence of low frame rate on phased-based motion magnification (PMM) has been investigated. A novel technique is proposed by combining PMM with zero mean-normalization cross-correlation tracker to determine vibrational responses, and then the spatial Wigner-Ville spectrum-based time-frequency blind source separation method is explored for modal identification using the extracted vibrational responses obtained from the video data. The experimental data of a lumped mass experimental model and a steel bridge is used to test the accuracy of the proposed method. The original and motion-magnified image response data is compared with accelerometer data for modal identification. The proposed method is able to extract the modal parameters with high accuracy for motion-magnified images, even for low frame rates.

Sex differences in laterality of motor unit firing behavior of the first dorsal interosseous muscle in strength-matched healthy young males and females.

The purpose of this study was to compare laterality in motor unit firing behavior between females and males. Twenty-seven subjects (14 females) were recruited for this study. The participants performed ramp up and hold isometric index finger abduction at 10, 30, and 60% of their maximum voluntary contraction (MVC). High-density surface electromyography (HD-sEMG) signals were recorded in the first dorsal interosseous (FDI) muscle and decomposed into individual motor unit (MU) firing behavior using a convolution blind source separation method. In total, 769 MUs were detected (females, n = 318 and males, n = 451). Females had a significantly higher discharge rate than males at each relative torque level (10%: male dominant hand, 13.4 ± 2.7 pps vs. female dominant hand, 16.3 ± 3.4 pps; 30%: male dominant hand, 16.1 ± 3.9 pps vs. female dominant hand, 20.0 ± 5.0 pps; and 60%: male dominant hand, 19.3 ± 3.8 vs. female dominant hand, 25.3 ± 4.8 pps; p < 0.0001). The recruitment threshold was also significantly higher in females than in males at 30 and 60% MVC. Furthermore, males exhibited asymmetrical discharge rates at 30 and 60% MVC and recruitment thresholds at 30 and 60% MVC, whereas no asymmetry was observed in females. In the FDI muscle, compared to males, females exhibited different neuromuscular strategies with higher discharge rates and recruitment thresholds and no asymmetrical MU firing behavior. Notably, the findings that sex differences in neuromuscular activity also occur in healthy individuals provide important information for understanding the pathogenesis of various diseases.

Nonlinear spatio-temporal filter to reduce crosstalk in bipolar electromyogram

Objective. The wide detection volume of surface electromyogram (EMG) makes it prone to crosstalk, i.e. the signal from other muscles than the target one. Removing this perturbation from bipolar recordings is an important open problem for many applications. Approach. An innovative nonlinear spatio-temporal filter is developed to estimate the EMG generated by the target muscle by processing noisy signals from two bipolar channels, placed over the target and the crosstalk muscle, respectively. The filter is trained on some calibration data and then can be applied on new signals. Tests are provided in simulations (considering different thicknesses of the subcutaneous tissue, inter-electrode distances, locations of the EMG channels, force levels) and experiments (from pronator teres and flexor carpi radialis of 8 healthy subjects). Main results. The proposed filter allows to reduce the effect of crosstalk in all investigated conditions, with a statistically significant reduction of its root mean squared of about 20%, both in simulated and experimental data. Its performances are also superior to those of a blind source separation method applied to the same data. Significance. The proposed filter is simple to be applied and feasible in applications in which single bipolar channels are placed over the muscles of interest. It can be useful in many fields, such as in gait analysis, tests of myoelectric fatigue, rehabilitation with EMG biofeedback, clinical studies, prosthesis control.

Study on weak sound signal separation and pattern recognition under strong background noise in marine engineering

The extraction of weak acoustic signals under strong background noise is of great significance in the applications of target identification and localization. In this paper, the pulse signal with high randomness is set as the weak signal sound source, random noise and sine sound are used as the background noise. Under the condition of a signal-to-noise ratio of −20 dB, combined with blind source separation and neural network methods, the collected observation signals are subjected to weak sound signal separation and recognition research. The optimization method of centralization and scaling processing is used to eliminate the unfavorable influence of the uncertainty of the separated signal amplitude caused by the blind source separation method on the pattern recognition. The recognition result is verified by the combination of “weak impulse acoustic signal” and “random noise signal,” and the output vector (0.99 0.01 0.01) approaches (1 0 0), which is recognized as impulse acoustic signal. By combining blind source separation and neural network methods, the separation and identification of weak pulse signals under the condition of a signal-to-noise ratio of −20 dB can be achieved.

Early pseudoprogression and progression lesions in glioblastoma patients are both metabolically heterogeneous.

The standard treatment in glioblastoma includes maximal safe resection followed by concomitant radiotherapy plus chemotherapy and adjuvant temozolomide. The first follow-up study to evaluate treatment response is performed 1 month after concomitant treatment, when contrast-enhancing regions may appear that can correspond to true progression or pseudoprogression. We retrospectively evaluated 31 consecutive patients at the first follow-up after concomitant treatment to check whether the metabolic pattern assessed with multivoxel MRS was predictive of treatment response 2 months later. We extracted the underlying metabolic patterns of the contrast-enhancing regions with a blind-source separation method and mapped them over the reference images. Pattern heterogeneity was calculated using entropy, and association between patterns and outcomes was measured with Cramér's V. We identified three distinct metabolic patterns-proliferative, necrotic, and responsive, which were associated with status 2 months later. Individually, 70% of the patients showed metabolically heterogeneous patterns in the contrast-enhancing regions. Metabolic heterogeneity was not related to the regions' size and only stable patients were less heterogeneous than the rest. Contrast-enhancing regions are also metabolically heterogeneous 1 month after concomitant treatment. This could explain the reported difficulty in finding robust pseudoprogression biomarkers.

Clutter rejection in passive non-line-of-sight imaging via blind multispectral unmixing.

Passive non-line-of-sight imaging methods that utilize scattered light to "look around corners" are often hindered by unwanted sources that overwhelm the weaker desired signal. Recent approaches to mitigate these "clutter" sources have exploited dependencies in the spectral content, or color, of the scattered light. A particularly successful method utilized blind source separation methods to isolate the desired imaging signal with minimal prior information. This current paper quantifies the efficacy of several preconditioning and unmixing algorithms when blind source separation methods are employed for passive multispectral non-line-of-sight imaging. Using an OLED television monitor as the source of both the desired signals and clutter, we conducted multiple controlled experiments to test these methods under a variety of scene conditions. We conclude that the preconditioner is a vital component as it greatly decreases the power and correlation of the clutter. Additionally, the choice of unmixing algorithm significantly impacts the reconstruction quality. By optimizing these two components, we find that effective image retrieval can be obtained even when the clutter signals are as much as 670 times stronger than the desired image.

CW_ICA: an efficient dimensionality determination method for independent component analysis.

Independent component analysis (ICA) is a widely used blind source separation method for signal pre-processing. The determination of the number of independent components (ICs) is crucial for achieving optimal performance, as an incorrect choice can result in either under-decomposition or over-decomposition. In this study, we propose a robust method to automatically determine the optimal number of ICs, named the column-wise independent component analysis (CW_ICA). CW_ICA divides the mixed signals into two blocks and applies ICA separately to each block. A quantitative measure, derived from the rank-based correlation matrix computed from the ICs of the two blocks, is utilized to determine the optimal number of ICs. The proposed method is validated and compared with the existing determination methods using simulation and scalp EEG data. The results demonstrate that CW_ICA is a reliable and robust approach for determining the optimal number of ICs. It offers computational efficiency and can be seamlessly integrated with different ICA methods.

Earth's core variability from magnetic and gravity field observations

Abstract. The motions of the liquid within the Earth's outer core lead to magnetic field variations together with mass distribution changes. As the core is not accessible for direct observation, our knowledge of the Earth’s liquid core dynamics only relies on indirect information sources. Mainly generated by the core dynamics, the surface geomagnetic field provides information about the variations of the fluid motion at the top of the core. The dynamic of the fluid core is also associated with mass distribution changes inside the core and produces gravitational field time fluctuations. By applying several statistical blind source separation methods to both the gravity and magnetic field time series, we investigate the common space–time variabilities. We report several robust interannual oscillations shared by the two observation sets. Among those, a common mode of around 7 years looks very significant. Whereas the nature of the driving mechanism of the coupled variability remains unclear, the spatial and temporal properties of the common signal are compatible with a core origin.

Robust second-order stationary spatial blind source separation using generalized sign matrices

Consider a spatial blind source separation model in which the observed multivariate spatial data are assumed to be a linear mixture of latent stationary spatially uncorrelated random fields. The objective is to recover an unknown mixing procedure as well as the latent random fields. Recently, spatial blind source separation methods that are based on the simultaneous diagonalization of two or more scatter matrices were proposed. In cases involving uncontaminated data, such methods can solve the blind source separation problem, however, in the presence of outlying observations, these methods perform poorly. We propose a robust blind source separation method that employs robust global and local covariance matrices based on generalized spatial signs in simultaneous diagonalization. Simulation studies are employed to illustrate the robustness and efficiency of the proposed methods in various scenarios.

A novel semi-blind source separation framework towards maximum signal-to-interference ratio

For the independence-based blind source separation (BSS) methods, effective modeling of the source signals is important. When applying the auxiliary function techniques, different source models normally result in different forms of the weighted covariance matrices, which in turn are used to compute the demixing filters. This paper proposes a new algorithmic framework termed minimum variance independent component analysis (MVICA), which is rigorously derived from the conventional BSS methods by determining the weighted covariance matrices with the maximum signal-to-interference ratio (SIR) criterion.The maximum-SIR weighted covariance matrix is approximately proved to be the interference covariance matrix. A deep neural network-supported implementation of the proposed MVICA algorithm is subsequently presented. Furthermore, we give a revealing insight into the relationships between MVICA and the existing speech separation approaches including conventional BSS methods and several mainstream beamforming techniques. Experimental results show the superiority of MVICA over the state-of-the-art BSS techniques and beamformers under various conditions, in terms of not only SIR but also signal-to-distortion ratio, speech intelligibility and perceptual quality and automatic speech recognition accuracy.

A comparative study of blind source separation methods

A comparative study of blind source separation methods

Enhancing second-order blind identification for underdetermined operational modal analysis through bandlimited source separation

Blind source separation (BSS) has been demonstrated to be a promising method for operational modal analysis (OMA). However, the conventional BSS-based modal identification methods can only handle the determined or overdetermined identification where the number of sensors must equal or exceed that of active modes, limiting their wider application. Furthermore, the existing methods for underdetermined BSS require sparsity assumption of sources, optimization of model parameters, or structural prior information, undermining the non-parametric and “blind” properties of BSS. This paper proposes a novel method for underdetermined OMA. Firstly, the bandlimited source separation using sinc-dictionaries is performed to efficiently transform the underdetermined problem into several determined or overdetermined ones. An improved second-order blind identification (SOBI) involving Hilbert transform and random time-lagged covariances is then applied for each bandlimited signal to recover modal responses and mode shapes. To attenuate noise, an adaptive singular spectrum analysis (SSA) can be optionally applied to the recovered modal responses for the highly noisy systems. Finally, the natural frequencies and damping ratios are estimated by the single-degree-of-freedom (SDOF) fitting technique. Several numerical examples, an experimental frame case, and a field test of a pedestrian bridge are studied to verify the effectiveness of the proposed strategy.

A novel subject-wise dictionary learning approach using multi-subject fMRI spatial and temporal components

The conventional dictionary learning (DL) algorithms aim to adapt the dictionary/sparse code to individual functional magnetic resonance imaging (fMRI) data. Thus, lacking the capability to consolidate the spatiotemporal diversities offered by other subjects. Considering that subject-wise (sw) data matrix can be decomposed into the sparse linear combination of multi-subject (MS) time courses and MS spatial maps, two new algorithms, sw sequential DL (swsDL) and sw block DL (swbDL), have been proposed. They are based on the novel framework, defined by the mixing model, where base matrices prepared by operating a computationally fast sparse spatiotemporal blind source separation method over multiple subjects are employed to adapt the mixing matrices to sw training data. They solve the optimization models formulated using l_0/l_1-norm penalization/constraints through dictionary/sparse code pair update and alternating minimization approach. They are unique because no existing sparse DL method can incorporate MS spatiotemporal components while updating sw atoms/sparse codes, which can eventually be assembled using neuroscience knowledge to extract group-level dynamics. Various fMRI datasets are used to evaluate and compare the performance of the proposed algorithms with existing state-of-the-art algorithms. Specifically, overall, a 14% increase in the mean correlation value and 39% reduction in the mean computation time exhibited by swsDL and swbDL, respectively, over the adaptive consistent sequential dictionary algorithm.

Blind source separation of electromagnetic signals based on deep focusing U-Net

The unintentional electromagnetic radiation of digital electronic devices during operation can cause information leakage and threaten the information security of the system. In order to explore the leakage level of important information, it is necessary to separate the electromagnetic leakage signal from the complex environmental electromagnetic wave, so the blind source separation technology is studied.Traditional blind source separation methods are mainly unsupervised learning methods, and their separation results are not as expected. In recent years, deep learning technology based on supervised learning has achieved good results in speech separation and other fields, indicating that it is a feasible method.In order to solve the problem of separating source signals from mixed electromagnetic radiation signals and reducing noise interference in electromagnetic safety detection. this paper proposes a Deep Focusing U-Net neural network, which makes the model pay more attention to the features at deeper layer. The network is applied to the blind separation of LCD electromagnetic leakage signals, and the good separation performance proves the effectiveness of this method.