Blind Source Separation Algorithm Research Articles

Recent advances in photoacoustic blind source spectral unmixing approaches and the enhanced detection of endogenous tissue chromophores

Recently, the development of learning-based algorithms has shown a crucial role to extract features of vital importance from multi-spectral photoacoustic imaging. In particular, advances in spectral photoacoustic unmixing algorithms can identify tissue biomarkers without a priori information. This has the potential to enhance the diagnosis and treatment of a large number of diseases. Here, we investigated the latest progress within spectral photoacoustic unmixing approaches. We evaluated the sensitivity of different unsupervised Blind Source Separation (BSS) techniques such as Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Non-negative Matrix Factorization (NNMF) to distinguish absorbers from spectral photoacoustic imaging. Besides, the performance of a recently developed superpixel photoacoustic unmixing (SPAX) framework has been also examined in detail. Near-infrared spectroscopy (NIRS) has been used to validate the performance of the different unmixing algorithms. Although the NNMF has shown superior unmixing performance than PCA and ICA in terms of correlation and processing time, this is still prone to unmixing misinterpretation due to spectral coloring artifact. Thus, the SPAX framework, which also compensates for the spectral coloring effect, has shown improved sensitivity and specificity of the unmixed components. In addition, the SPAX also reveals the most and less prominent tissue components from sPAI at a volumetric scale in a data-driven way. Phantom experimental measurements and in vivo studies have been conducted to benchmark the performance of the BSS algorithms and the SPAX framework.

Fast Multimodulus Blind Deconvolution Algorithms

A novel class of fast Multi-Modulus algorithms (fastMMA) for Blind Source Separation (BSS) and deconvolution are presented in this work. These are obtained through a fast fixed-point optimization rule used to minimize the Multi-Modulus (MM) criterion. Here, two BSS versions are provided to separate the sources either by finding the separation matrix at once or by separating a single source each time using a fast deflation technique. Further, the latter method is extended to cover systems of convolutive nature. Interestingly, these algorithms are implicitly shown to belong to the fixed step-size gradient descent family, henceforth, an algebraic variable step-size is proposed to make these algorithms converge even much faster. Apart from being computationally and performance-wise attractive, the new algorithms are free of any user-defined parameters.

Blind Source Separation with Multi-Objective Optimization for Denoising

Blind Source Separation is an optimization method frequently used in statistical signal processing applications. There are many application areas such as ambient listening, denoising, signal detection, and so on. In this study, a new Strength Pareto Evolutionary Algorithm 2-based signal separation method is proposed, which combines Multi-Objective Optimization and Blind Source Separation algorithms. The proposed method has been tested for denoising, which is widely used in biomedical signal processing. That is, the Electrocardiogram (ECG) and White Gaussian Noise are mixed together with normally distributed random numbers and the original signals of the mixed signals are obtained again. To evaluate the performance of the proposed method and others (Multi-Objective Blind Source Separation and Independent Component Analysis), the Signal-to-Noise Ratio (SNR) of the ECG signal obtained from mixed signals has been measured. As a result of the simulation studies, it is seen that the performance of the proposed method is satisfactory.

Research on Music Signal Processing Based on a Blind Source Separation Algorithm

The isolation of mixed music signals is beneficial to the extraction and identification of music signal features and to enhance music signal quality. This paper briefly introduced the mathematical model for separating blind source from mixed music signals and the traditional Independent Component Analysis (ICA) algorithm. The separation algorithm was optimized by the complex neural network. The traditional and optimized ICA algorithms were simulated in MATLAB software. It was found that the time-domain waveform of the signal isolated by the improved ICA-based separation algorithm was closer to the source signal. The similarity coefficient matrix, signal-to-interference ratio, performance index, and iteration time of the improved ICA-based algorithm was 62.3, 0.0011, and 0.87 s, respectively, which were all superior to the traditional ICA algorithm. The novelty of this paper is setting the initial iterative matrix of the ICA algorithm with the complex neural network.

An outlier detection-based method for artifact removal of few-channel EEGs

Objective. The electroencephalogram (EEG) is one of the most important brain-imaging tools. The few-channel EEG is more suitable and affordable for practical use as a wearable device. Removing artifacts from collected EEGs is a prerequisite for accurately interpreting brain function and state. Previous studies proposed methods combining signal decomposition with the blind source separation (BSS) algorithms, but most of them used threshold-based criteria for artifact rejection, resulting in a lack of effectiveness in removing specific artifacts and the excessive suppression of brain activities. In this study, we proposed an outlier detection-based method for artifact removal under the few-channel condition. Approach. The underlying components (sources) were extracted using the decomposition-BSS schema. Based on our assumptions that in the feature space, the artifact-related components are dispersed, while the components related to brain activities are closely distributed, the artifact-related components were identified and rejected using one-class support vector machine. The assumptions were validated by visualizing the distribution of clusters of components. Main results. In quantitative analyses with semisimulated data, the proposed method outperformed the threshold-based methods for various artifacts, including muscle artifact, ocular artifact, and power line noise. With a real dataset and an event-related potential dataset, the proposed method demonstrated good performance in real-life situations. Significance. This study provided a fully data-driven and adaptive method for removing various artifacts in a single process without excessive suppression of brain activities.

Heart-lung sound separation by nonnegative matrix factorization and deep learning

Auscultation is an ordinary way to diagnose cardiovascular and respiratory diseases. The heart-lung sound (HLS) from the stethoscope is a mixture of heart sound (HS) and lung sound (LS). The first and most crucial step is to differentiate between HS and LS from the mixture signal. This paper proposes an unsupervised single-channel blind source separation (BSS) algorithm based on nonnegative matrix factorization (NMF) and deep learning (DL). Firstly, HS signals are extracted by the multi-constrained NMF (MCNMF) decomposition algorithm and K-means & SVM (KS) clustering method proposed in this paper, and different types of HS signals are classified by a convolutional neural network (CNN). Then, the HLS is separated by the embedding space centroid network (ECNet) proposed in our study. The method outperforms the known state-of-the-art techniques in all evaluation metrics SNR, SDR, SIR, SAR, and correlation coefficient. Our algorithm has two advantages: 1) this study is the first to combine NMF and DL for the HLS separation. MCNMF with selected constraints can have a more substantial sparsity effect that improves the decomposition accuracy. KS clustering algorithm can distinguish the HS component from the LS component in two clustering results. By mapping classified HLS into an embedding space, the ECNet demonstrates excellent separation results. 2) HS extraction and classification first, then HLS separation. Because our method exploits more detailed information from HS types in HLS before BSS, the ECNet can outperform other HLS separation methods.

Semi-Blind Source Separation with Learned Constraints

Blind source separation (BSS) algorithms are unsupervised methods, which are the cornerstone of hyperspectral data analysis by allowing for physically meaningful data decompositions. BSS problems being ill-posed, the resolution requires efficient regularization schemes to better distinguish between the sources and yield interpretable solutions. For that purpose, we investigate a semi-supervised source separation approach in which we combine a projected alternating least-square algorithm with a learning-based regularization scheme. In this article, we focus on constraining the mixing matrix to belong to a learned manifold by making use of generative models. Altogether, we show that this allows for an innovative BSS algorithm, with improved accuracy, which provides physically interpretable solutions. The proposed method, coined sGMCA, is tested on realistic hyperspectral astrophysical data in challenging scenarios involving strong noise, highly correlated spectra and unbalanced sources. The results highlight the significant benefit of the learned prior to reduce the leakages between the sources, which allows an overall better disentanglement.

Biologically plausible single-layer networks for nonnegative independent component analysis.

An important problem in neuroscience is to understand how brains extract relevant signals from mixtures of unknown sources, i.e., perform blind source separation. To model how the brain performs this task, we seek a biologically plausible single-layer neural network implementation of a blind source separation algorithm. For biological plausibility, we require the network to satisfy the following three basic properties of neuronal circuits: (i) the network operates in the online setting; (ii) synaptic learning rules are local; and (iii) neuronal outputs are nonnegative. Closest is the work by Pehlevan et al.(Neural Comput 29:2925-2954, 2017), which considers nonnegative independent component analysis (NICA), a special case of blind source separation that assumes the mixture is a linear combination of uncorrelated, nonnegative sources. They derive an algorithm with a biologically plausible 2-layer network implementation. In this work, we improve upon their result by deriving 2 algorithms for NICA, each with a biologically plausible single-layer network implementation. The first algorithm maps onto a network with indirect lateral connections mediated by interneurons. The second algorithm maps onto a network with direct lateral connections and multi-compartmental output neurons.

Robust approach for blind separation of noisy mixtures of independent and dependent sources

The framework of this article is to introduce a new efficient Blind Source Separation (BSS) method that handles mixtures of noise-contaminated independent / dependent sources. In order to achieve that, one can minimize a criterion that fuses a separating part, based on Kullback–Leibler divergence to set apart the observed mixtures of either dependent or independent sources, with a regularization part that employs the bilateral total variation (BTV) for the purpose of denoising the observations. The proposed algorithm utilizes a primal-dual algorithm to remove the noise, while a gradient descent method is implemented to retrieve the source signals. Our algorithm has shown its effectiveness and efficiency toward the noisy dependent / independent sources and also surpassed the standard BSS algorithms through different experimental results.

Speech enhancement system design is based on FastICA blind source separation algorithm

Based on the analysis of existing speech enhancement based on the drawbacks of the traditional algorithm is adopted in the system is proposed based on FastICA blind source separation algorithm design of speech enhancement algorithm, and the transplanted to embedded speech enhancement system. The system real-time speech enhancement, by four element microphone arrays is used to sample the space of sound signal and through the built-in speech enhancement algorithm to the voice source signal and noise source signal separation, capable of suppressing co channel noise, active noise and residual background noise. Based on the test results of the algorithm on PC platform, the system meets the design requirements and the effect is good.

A New Robust Adaptive Algorithm for Second Order Blind Source Separation

This paper deals with the adaptive blind source separation problem in presence of impulsive noise. New algorithms extending the well known SOBI method from batch to adaptive scheme are introduced. At first, the standard Gaussian noise case is considered, leading to our first algorithm referred to as Adaptive SOBI (A-SOBI). Later on, a robust version of A-SOBI, referred to as RA-SOBI is derived to handle the impulsive noise case. RA-SOBI relies on robust subspace tracking for the whitening stage together with robust correlation estimation for the separation stage. All proposed algorithms are of relatively low complexity and allow to achieve good separation quality as illustrated by our simulation results.

Respiration and heart rates measurement using 77GHz FMCW radar with blind source separation algorithm.

This paper presents a blind source separation based signal processing method of measuring respiration and heartbeat rates using frequency modulated continues wave (FMCW) radar with working frequency range 77GHz-81GHz. To improve signal quality, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method is used in preprocessing stage to first decompose the phase signal into several intrinsic mode functions (IMFs) and then the phase signal is reconstructed by adding the selected IMFs. The accurate measurement results can be obtained by the proposed method both in separating respiratory and heartbeat signals of one person (the average deviations are 1.1 beat per minute and 6.8 beat per minute respectively), and in separating respiratory signals of two persons.

A Method Applied in Anomaly Detection of Impurities Adhering to Pipes of Coriolis Mass Flowmeter

The Coriolis mass flowmeter (CMF) is widely used to measure mass flow, mainly in petrochemical, medical, pharmaceutical, food manufacturing, and other industries. The measuring tube is the crucial component of CMF, which affects the measurement accuracy and causes losses to the production of enterprises. Wall-mounted failure of the measuring tube affects measurement accuracy. A real-time detection method based on acceleration sensor array signal processing and pattern recognition are proposed to detect such failure. Two acceleration sensors are arranged outside the CMF to compose a five-channel sensor array. The signals of the multichannel array are decomposed through a blind source separation algorithm, and array signal features are extracted by a wavelet scattering network. Support vector data description (SVDD) is used to detect the hanging state of CMF at last. The experimental results show that the proposed method can be used to detect the CMF wall-mounted failure in real-time with an accuracy of 89.59%, and the method can reduce production losses.

Sound Quality Control Based on CEEMD Blind Source Separation and FELMS Algorithm

The reduction in sound pressure level is the focus of noise reduction in construction machinery, but the sound quality parameters can better describe the operator’s subjective perception of noise. This paper proposes a sound quality control method for the cab, which is based on complementary ensemble empirical mode decomposition for signal decomposition and reconstruction and an adaptive control algorithm error filter. Firstly, a subjective and objective prediction model was created to identify the target parameters for the sound quality control in the cab. Secondly, the noise was reconstructed based on a complementary ensemble empirical mode decomposition method, thus evaluating the influence of each component on the sound quality and determining the frequency interval. Lastly, the active sound quality control was completed based on the variable step size filter-error least mean square algorithm. The experiments were performed in the cab of a mini-excavator to verify the method’s effectiveness. It was verified that the loudness peak drops by 0.95 sones under stationary idle working conditions. The results demonstrate that the above methods play a guiding role in the actual application of sound quality control for the cab of construction machinery.

Improved Estimation of End-Milling Parameters from Acoustic Emission Signals Using a Microphone Array Assisted by AI Modelling.

This paper presents the implementation of a measurement system that uses a four microphone array and a data-driven algorithm to estimate depth of cut during end milling operations. The audible range acoustic emission signals captured with the microphones are combined using a spectral subtraction and a blind source separation algorithm to reduce the impact of noise and reverberation. Afterwards, a set of features are extracted from these signals which are finally fed into a nonlinear regression algorithm assisted by machine learning techniques for the contactless monitoring of the milling process. The main advantages of this algorithm lie in relatively simple implementation and good accuracy in its results, which reduce the variance of the current noncontact monitoring systems. To validate this method, the results have been compared with the values obtained with a precision dynamometer and a geometric model algorithm obtaining a mean error of 1% while maintaining an STD below 0.2 mm.

High-Capacity Space-Division Multiplexing Communications With Silicon Photonic Blind Source Separation

Space-division multiplexing is a widely used technique to improve data-carrying capacities in both wireless and optical communication systems. However, tightly packed spatial channels cause severe crosstalk. High data rates and large channel counts impose severe constraints on resolving the crosstalk using traditional digital signal processing algorithms and electronic circuits. In order to solve these issues, this paper presents a silicon photonic system combining high-speed silicon photonic devices with a novel blind source separation (BSS) algorithm. We first demonstrate using photonic BSS to undo modal crosstalk in a short-reach multimode optical fiber interconnect for intra-data-center communications. The proposed photonic BSS system inherits the advantages of photonic matrix processor and the “blindness” of BSS, leading to superior energy and cost efficiency and reduced latency, while allowing to recover the signals using a sub-Nyquist sampling rate and in a free-running mode, and offering unmatched agility in signal format and data rate. The feasibility of using photonic processors for mode crosstalk equalization has been recently demonstrated, assisted with training sequences. Our approach, photonic BSS, in contrast, can tackle the more difficult problem of making the receiver transparent to any data rate and modulation format, and workable with slow and cost-effective electronics. In addition, we find that photonic BSS has a much better scaling law for space-division multiplexing (SDM)-based communication systems than digital signal processing (DSP). When compared to state-of-the-art DSP, photonic BSS can reduce system power consumption, speed, and latency by several orders of magnitude, particularly for high-capacity communications with high data rates per channel and a large number of channels. Photonic BSS has the added advantages of being agnostic to transmission content, making it exceptional at protecting communication privacy. This paper also discusses our previous work in demonstrating photonic BSS for privacy protection in wireless multiple-in multiple-out (MIMO) communications using silicon photonic micoring resonator (MRR) weight banks.

Evaluation of decomposition parameters for high-density surface electromyogram using fast independent component analysis algorithm

The surface electromyogram (sEMG) signal reveals the electrical neuromuscular activities and offers theoretical and clinical information. Recently, exploring motoneuron discharge events at the microscopic level through decomposition has been proposed as a promising analysis approach, which can surpass traditional global sEMG-based analysis method in some aspects. However, computational efficiency is an essential issue when discharge events of individual motor unit are decomposed using blind source separation algorithms. Therefore, choosing proper parameters of decomposition algorithms for different research purposes is important. Accordingly, we have systematically investigated the influences between computation time and decomposition performance for fast independent component analysis (FastICA)-based sEMG decomposition algorithm under different value selections of five decomposition parameters, namely the percentage of eliminated channels, extension factor, the number of decomposition iteration loops, the number of maximum inner loops in each iteration and sampling frequency. We employed high-density sEMG signals from 14 intact subjects during muscle contractions of four-digit extension and flexion at different force levels (20% and 50% maximum voluntary contraction) and a public dataset for sEMG decomposition. According to obtained results, we offer four preference suggestions (less computation time, more motor units, higher accuracy and trade-off). Results show that the trade-off values with consideration of decomposition performance and computation time are recommended as 25% of channels with minimal root mean square, extension factor of 4, 200 iteration loop numbers of decomposition, 20 maximum inner loop numbers and 2048 sampling frequency. Overall, this paper provides a guide for researchers to determine proper decomposition parameters for sEMG decomposition-related works.

A Blind Source Separation Method Using Denoising Strategy Based on ICEEMDAN and Improved Wavelet Threshold

Traditional blind source separation (BSS) methods often want no additional noise effects. But in practice, noise is ubiquitous, and there are even cases with low signal-to-noise ratios (SNR). Unfortunately, these blind source separation methods have a significant impact on system performance in the presence of noise. This study proposes a blind source separation method to eliminate noise and extract signal information to the maximum extent. The method is based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and improved wavelet threshold (IWT) hierarchical decomposition to improve the signal separation effect. First, the signal is decomposed via ICEEMDAN to obtain the noise-dominated and information-dominated intrinsic mode function (IMF) components. Then, the noise-dominated IMF components are again decomposed by ICEEMDAN, and each component’s scale function is obtained via detrended fluctuation analysis (DFA). Next, the noise-dominated IMF components generated in the second decomposition round undergo an improved wavelet threshold denoising to obtain useful signal information. Finally, the information-dominated IMF components generated in the two rounds of decomposition and the resulting signal of wavelet denoising yield a reconstructed signal, which is then decomposed using the BSS algorithm to obtain the source signal. The experimental results demonstrate that the proposed method can accurately extract signal information and can better separate the source signal than the existing algorithm.

An Advanced Scheme for Range Ambiguity Suppression of Spaceborne SAR Based on Blind Source Separation

Due to the minimum antenna area constrain of synthetic aperture radar (SAR), high-resolution and wide-swath (HRWS) imaging is difficult to be achieved using classical modes, such as scan, spotlight, and so on. Range ambiguity is one of the main technical challenges limiting HRWS imaging in spaceborne SAR. Insipred by the cocktail party effect, an advanced scheme based on blind source separation is put forward to suppress the range ambiguity of spaceborne SAR in this paper. In the scheme, multiple subantennas are used to collect multiple echo data sets, which are given different patterns. In this way, the echo signal of the desired region and that of the ambiguous region are weighted using different coefficients. During postprocessing, a detailed flow with the blind source separation algorithm is proposed to separate the desired echoes from those data sets. To verify the scheme, point target and scene simulations based on GF3 are carried out. The results indicate that the range ambiguity can be reduced by more than 15 dB using the proposed scheme, the processing flow is effective, and the scheme has a good performance without increasing the complexity of the system design under the current SAR system conditions. The scheme has the potential to be adopted in future spaceborne SAR missions.

Switching Independent Vector Analysis and its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms

This paper develops a framework that can accurately perform denoising, dereverberation, and source separation using a relatively small number of microphones. It has been empirically confirmed that Independent Vector Analysis (IVA) can blindly separate <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$N$</tex-math></inline-formula> sources from their sound mixture even with diffuse noise when a sufficiently large number ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$=M$</tex-math></inline-formula> ) of microphones are available (i.e., <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$M\gg N)$</tex-math></inline-formula> . However, the estimation accuracy is seriously degraded when the number of microphones, or more specifically <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$M-N$</tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$(\geq 0)$</tex-math></inline-formula> , decreases. To overcome this IVA limitation, we propose switching IVA (swIVA) in this paper. With swIVA, the time frames of an observed signal with time-varying characteristics are clustered into several groups, each of which can be well handled by IVA with a small number of microphones, and thus accurate estimation can be achieved by individually applying IVA to each group. Conventionally, a switching mechanism was introduced into a Minimum-Variance Distortionless Response (MVDR) beamformer, and this paper extends the mechanism to work with a blind source separation algorithm. To incorporate dereverberation capability, we further extend swIVA to a blind Convolutional beamforming algorithm (swCIVA) that integrates swIVA and switching Weighted Prediction Error-based dereverberation (swWPE) in a jointly optimal way. With swCIVA, two different time-varying characteristics of an observed signal are captured for dereverberation and source separation to achieve effective estimation. We show that both swIVA and swCIVA can be optimized effectively based on blind signal processing, and their performance can be further improved using a spatial guide for initialization. Experiments demonstrate that both the proposed methods largely outperformed conventional IVA and its convolutional beamforming extension (CIVA) in terms of objective signal quality and automatic speech recognition scores when using relatively few microphones.