Source Separation Research Articles

Mixed Source Separation of Partially Correlated Source Based on Analytic CMA

Mixed Source Separation of Partially Correlated Source Based on Analytic CMA

Heart Sound Classification Using Harmonic and Percussive Spectral Features from Phonocardiograms with a Deep ANN Approach

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, with a particularly high burden in India. Non-invasive methods like Phonocardiogram (PCG) analysis capture the acoustic activity of the heart. This holds significant potential for the early detection and diagnosis of heart conditions. However, the complexity and variability of PCG signals pose considerable challenges for accurate classification. Traditional methods of PCG signal analysis, including time-domain, frequency-domain, and time-frequency domain techniques, often fall short in capturing the intricate details necessary for reliable diagnosis. This study introduces an innovative approach that leverages harmonic–percussive source separation (HPSS) to extract distinct harmonic and percussive spectral features from PCG signals. These features are then utilized to train a deep feed-forward artificial neural network (ANN), classifying heart conditions as normal or abnormal. The methodology involves advanced digital signal processing techniques applied to PCG recordings from the PhysioNet 2016 dataset. The feature set comprises 164 attributes, including the Chroma STFT, Chroma CENS, Mel-frequency cepstral coefficients (MFCCs), and statistical features. These are refined using the ROC-AUC feature selection method to ensure optimal performance. The deep feed-forward ANN model was rigorously trained and validated on a balanced dataset. Techniques such as noise reduction and outlier detection were used to improve model training. The proposed model achieved a validation accuracy of 93.40% with sensitivity and specificity rates of 82.40% and 80.60%, respectively. These results underscore the effectiveness of harmonic-based features and the robustness of the ANN in heart sound classification. This research highlights the potential for deploying such models in non-invasive cardiac diagnostics, particularly in resource-constrained settings. It also lays the groundwork for future advancements in cardiac signal analysis.

Multiple independent components contribute to event-related potential correlates of conscious vision

Research has revealed two major event-related potential (ERP) markers of visual awareness: the earlier Visual Awareness Negativity (VAN, around 150–250 ms after stimulus onset), and the following Late Positivity (LP, around 300–500 ms after stimulus onset). Understanding the neural sources that give rise to VAN and LP is important in order to understand what kind of neural processes underlie conscious visual perception. Although the ERPs afford high temporal resolution, their spatial resolution is limited because multiple separate neural sources sum up at the scalp level. In the present study, we sought to characterize the locations and time-courses of independent neural sources underlying the ERP correlates of visual awareness by means of Independent Component Analysis (ICA). ICA allows identifying and localizing the temporal dynamics of different neural sources that contribute to the ERP correlates of conscious perception. The present results show that the cortical sources of VAN are localized to posterior areas including occipital and temporal cortex, while LP reflects a combination of multiple sources distributed among frontal, parietal and occipito-temporal cortex., Our findings suggest that conscious vision correlates with dynamically changing neural sources, developing in part in “accumulative fashion”: consciousness-related activity initially arises in few early sources and, subsequently, additional sources are engaged as a function of time.The results further suggest that even early latency neural sources that correlate with conscious perception may also associate with action-related processes.

Insights Into Brain Network Dynamics Across Ages Using Group-ICA Functional Parcellation

Aging is a natural and inevitable process in human life that involves changes in the brain. The brain becomes structurally, functionally, and interconnected differently. The evolution of brain activity and its anatomy follows separate paths, causing them to not always align. Independent Component Analysis (ICA), a Blind Source Separation (BSS) method, enables brain parcellation considering an individual's functional patterns. This is advantageous when studying brain function at different stages of life, allowing for a more comprehensive and flexible approach that accounts for age-related differences. This study aims to investigate the relationship between age and functional networks, exploring the differences in the functional parcellations of two different age groups and their networks. We propose a method utilizing group-ICA that identifies functional connectivity patterns to estimate coherent networks. We found variations in the distribution of the age-related networks and the brain portions they covered; some networks in old adults encompassed smaller areas in comparison to the networks in young adults.

Optimizing Waste Separation in Traditional Minority Communities: A Game Theory Approach for Sustainable Municipal Waste Management

Successful solid-waste management relies heavily on citizen involvement and cooperation, particularly through effective source separation. By ensuring that waste is sorted correctly at source, costs are reduced, the quality of recycled products is improved, and waste handling becomes more efficient—resulting in significant cost savings for municipal authorities (MAs) and mitigating causes of air pollution, water pollution, and soil contamination.This study explores enhancing waste separation in local authorities populated by traditional minority groups through stakeholder cooperation. The aim is to improve economic, social, and environmental utilities while identifying the mechanism that best maximizes the well-being of all players involved.Employing mixed methods and game-theory tools, we conduct twenty-one in-depth interviews with local minority leaders to define the parameters of the service function. The utility functions of all players serve as a basis for game-theory modeling that allow us to identify Nash equilibria, compare their efficiency, and formulate the mechanism optimally.The results of the study show that when an influential local player fosters cooperation and trust among residents, effective waste separation is achieved, enhancing the well-being of all involved.

Exploring Bounded Component Analysis Using an ℓ∞ Norm Criterion

In this paper we propose a new criterion for the Blind Source Separation (BSS) of antisparse bounded sources, based on the sum of the ℓ∞-norm of the sources. Based on the observation that the mixing process of bounded sources with any mixing matrix with unitary Frobenius norm will increase the ℓ∞-norm of the sources, unless it is the identity matrix, the minimization of the sum of the ℓ∞-norm of the sources can be used for the estimation of a separation matrix. To that, a Principle Component Analysis technique followed by a Givens Rotations based optimization method can be used for the separation of independent bounded sources. Also, the Givens Rotations based optimization method can be used for the separation of correlated bounded sources mixed by a rotation matrix. We theoretically analyze the proposed criterion and assess its performance through numerical simulations involving three distinct types of bounded signals. Our theoretical and experimental findings underscore the efficacy of the ℓ∞ norm as a suitable contrast function for antisparse bounded sources, showcasing its superior performance relative to a state-of-the-art algorithm.

Reducing electrocardiographic interference in the multichannel electromyogram to help muscle fatigue assessment in low-intensity contractions.

Surface electromyography (EMG) can be used in the rehabilitation of musculoskeletal disorders, for evaluating the coordination of muscles that stabilize a joint, or as an objective tool in assessing muscle fatigue. This latter may be achieved by evaluating the low-frequency content of the EMG. However, the electrocardiogram (ECG) interference is also recorded when EMG is acquired close to the heart. It may mask or even modify the information of interest in the EMG. Different signal processing techniques have been proposed to eliminate ECG artifacts from the EMG signals, the high-pass filter being the most used one. Nevertheless, this classic filtering approach would also attenuate EMG activities below 30 Hz, which contain information from low-intensity muscle contractions. This work addresses the automatic ECG attenuation when multichannel EMG is collected on the left pectoralis major muscle during a muscle fatigue test. The proposed ECG artifact mitigation extends a successful automatic template subtraction (TS) approach, which does not require an extra reference channel and is now applied to independent EMG source signal components extracted using a blind source separation technique (ICA, Independent Component Analysis). The automatic detection of ECG components was performed through two alternative measures: entropy and Kullback-Leibler divergence. While the ECG interference seems to hamper the detection of muscle fatigue in the low-contraction regime, the association ICA+TS preserved better the EMG low-frequency content, and the entropy-based automatic detection was found to be more suitable, avoiding possible errors that might arise from manual detection procedures.

Intracranial voltage profiles from untangled human deep sources reveal multisource composition and source allocation bias.

Intracranial potentials are used as functional biomarkers of neural networks. As potentials spread away from the source populations, they become mixed in the recordings. In humans, interindividual differences in the gyral architecture of the cortex pose an additional challenge, as functional areas vary in location and extent. We used source separation techniques to disentangle mixing potentials obtained by exploratory deep arrays implanted in epileptic patients of either sex to gain access to the number, location, relative contribution and dynamics of co-active sources. The unique spatial profiles of separated generators made it possible to discern dozens of independent cortical areas for each patient, whose stability maintained even during seizure, enabling the follow up of activity for days and across states. Through matching these profiles to MRI, we associated each with limited portions of sulci and gyri, and determined the local or remote origin of the corresponding sources. We also plotted source-specific 3D coverage across arrays. In average, individual recording sites are contributed to by 3-5 local and distant generators from areas up to several centimeters apart. During seizure, 13-85 % of generators were involved, and a few appeared anew. Significant bias in location assignment using raw potentials is revealed, including numerous false positives when determining the site of origin of a seizure. This is not amended by bipolar montage, which introduce additional errors of its own. In this way, source disentangling reveals the multisource nature and far intracranial spread of potentials in humans, while efficiently addressing patient-specific anatomofunctional cortical divergence.Significance Statement Field potentials are used to better localize zones showing normal and pathological activity. However, as potentials spread throughout the brain volume, they mix with others and make their place of origin uncertain, even when recorded intracranially. We used advanced algorithms to disentangle the activity of each these zones by their unique spatial profiles, which allowed us to determine the 3D outline of normal and epileptic areas and follow their activity for days. Dozens of independent sources per patient can be explored and precisely located. The findings show that standard stereoEEG recordings are contributed by 3-5 populations, which after separation will help to plan clinical intervention to break epileptic networks by more accurately marking epileptic foci and avoiding false positives.

Parameter-adaptive variational autoencoder for linear/nonlinear blind source separation

AbstractBlind source separation (BSS) serves as an important technique in the field of structural health monitoring (SHM), particularly for solving modal decomposition tasks. This study proposes a novel approach to both linear and nonlinear BSS problems in the Variational Autoencoder (VAE) framework, where the encoding and decoding processes of VAE are interpreted as procedures for inferring sources from observations and remixing these sources, respectively. In this way, the distribution of latent variables inferred by VAE is equivalent to the distribution of sources. We make improvements to the vanilla VAE to augment its effectiveness for BSS. First, we substitute standard normal distributions with trainable Gaussian processes (GP) as priors for latent variables and implement an exponential function as the activation function for adaptive parameters in the GP kernel functions. While the form of the priors is set as GP, the parameters of their kernel functions are not fixed but automatically converge to suitable values during the model training process. Additionally, a hyperparameter is introduced to balance the terms in the loss function. The proposed method is referred to as parameter-adaptive VAE (PAVAE). Then, upon different assumptions of the variances of sources, the proposed PAVAE is branched into two types: homoscedastic PAVAE (Ho-PAVAE) and heteroscedastic PAVAE (He-PAVAE). Through numerical and laboratory experiments, we demonstrate the effectiveness of the proposed method in solving BSS problems and their potential to underpin future research in SHM.

Modifying the Refuse Chute Design to Prevent Infection Spread: Engineering Analysis and Optimization

Considering the presence of airborne viruses, there is a need for renovation in refuse chutes, regarded as the first step in recycling household waste in buildings. This study aimed to revise the design of existing refuse chutes in light of the challenging experiences in waste management and public health during the coronavirus pandemic. This research primarily focused on the risks posed by various types of coronaviruses, such as the novel coronavirus (COVID-19) and acute respiratory syndrome (SARS and SARS-CoV), on stainless steel surfaces, with evidence of their survival under certain conditions. Refuse chutes are manufactured from stainless steel to resist the corrosive effects of waste. In examining the existing studies, it was observed that Casanova et al. and Chowdhury et al. found that the survival time of coronaviruses on stainless steel surfaces decreases as the temperature increases. Based on these studies, mechanical revisions have been made to the sanitation system of the refuse chute, thus increasing the washing water temperature. Additionally, through mechanical improvements, an automatic solution spray entry is provided before the intake doors are opened. Furthermore, to understand airflow and clarify flow parameters related to airborne infection transmission on residential floors in buildings equipped with refuse chutes, a computational fluid dynamics (CFD) analysis was conducted using a sample three-story refuse chute system. Based on the simulation results, a fan motor was integrated into the system to prevent pathogens from affecting users on other floors through airflow. Thus, airborne pathogens were periodically expelled into the atmosphere via a fan shortly before the intake doors were opened, supported by a PLC unit. Additionally, the intake doors were electronically interlocked, ensuring that all other intake doors remained locked while any single door was in use, thereby ensuring user safety. In a sample refuse chute, numerical calculations were performed to evaluate parameters such as the static suitability of the chute body thickness, static compliance of the chute support dimensions, chute diameter, chute thickness, fan airflow rate, ventilation duct diameter, minimum rock wool thickness for human contact safety, and the required number of spare containers. Additionally, a MATLAB code was developed to facilitate these numerical calculations, with values optimized using the Fmincon function. This allowed for the easy calculation of outputs for the new refuse chute systems and enabled the conversion of existing systems, evaluating compatibility with the new design for cost-effective upgrades. This refuse chute design aims to serve as a resource for readers in case of infection risks and contribute to the literature. The new refuse chute design supports the global circular economy (CE) model by enabling waste disinfection under pandemic conditions and ensuring cleaner source separation and collection for recycling. Due to its adaptability to different pandemic conditions including pathogens beyond coronavirus and potential new virus strains, the designed system is intended to contribute to the global health framework. In addition to the health measures described, this study calls for future research on how evolving global health conditions might impact refuse chute design.

A Review of Strategies and Technologies for Sustainable Decentralized Wastewater Treatment

The traditional model of centralized wastewater treatment is facing substantial strain due to a confluence of global challenges. Consequently, it is imperative to evaluate the impediments and potential advantages associated with the deployment of decentralized wastewater (DW) treatment technologies and systems. Decentralized wastewater (DW) treatment represents a sustainable approach to managing and purifying wastewater across both urban and rural settings. This literature review provides a detailed examination of current advancements and challenges associated with DW treatment technologies. It specifically addresses their operational efficiency, long-term sustainability, and practical implementation across diverse environments. This review critically analyzes recent studies that highlight innovative methodologies, including the deployment of constructed wetlands, anaerobic digestion processes, and predictive models enhanced by artificial intelligence. A critical focus is placed on the ecological and economic advantages of source separation and resource recovery from wastewater streams. The issue of emerging contaminants, such as microplastics, antibiotics, and steroids, is also discussed, emphasizing the continued need for innovation in treatment technologies. Findings from various life cycle assessments are presented to illustrate the environmental impact and feasibility of decentralized systems relative to centralized alternatives. This comprehensive analysis offers valuable insights into the future trajectories of wastewater treatment research and implementation.

End-to-end underwater acoustic source separation model based on EDBG-GALR

In practical work scenarios, it is common for multiple vessels to be present in close proximity within the same water area. In such cases, the acoustic signals emitted by these vessels often overlap, causing interference and reducing the accuracy of vessel identification. This paper proposes an improved GALR end-to-end underwater acoustic source separation algorithm, with ECA-DE (Efficient Channel Attention-Deep Encoder) and Bi-GRU (Bidirectional Gated Recurrent Unit), which consists of an encoder, separation blocks, and a decoder (EDBG-GALR). Addressing the issue of GALR encoder’s limited expressiveness due to its single-layer one-dimensional convolutional layer, we introduce a new deep encoder, ECA-DE, to enhance the encoder’s capability to process temporal signals and improve the efficiency of the separator’s input. Additionally, we integrate Bi-GRU into the GALR separation block’s local modeling module to enhance the local modeling ability of sequence features, thereby reducing the model’s computational and parameter requirements. Experimental results demonstrate that the proposed EDBG-GALR method can effectively separate mixed multi-target signals into multiple single-target signals, achieving a maximum scale-invariant signal-to-noise ratio (SI-SNR) improvement of 3.32 dB and a signal distortion ratio (SDR) improvement of 3.38 dB over baseline methods. These results highlight the practical applicability of EDBG-GALR in complex underwater environments.

The effectiveness of stage-matched interventions in changing waste source separation behaviour: Evidence from a consecutive quasi-experiment.

In many developing countries, inefficient waste source separation poses a significant challenge to sustainable waste management systems, hindering progress towards a circular economy. Previous research has shown mixed results regarding the effectiveness of informational interventions and has not thoroughly evaluated regulatory measures. This study innovatively employs a quasi-experimental design, enhanced by successive surveys, to assess the impact of targeted interventions on behavioural changes in waste separation practices. Utilizing the Health Action Process Approach, we introduced three interventions - posters, educational lectures and a supervision policy - over 8 weeks among university students. Our results indicate stepwise improvements in waste separation accuracy: posters modestly increased awareness without significantly altering behaviours; educational lectures led to a 40% increase in the food waste separation rate and supervision achieved over 90% separation purity, but with an increase in 'fly-dumping'. The interventions incurred costs of 36, 60 and 365 RMB per capita annually. This research underlines the importance of customized informational interventions and the costs and challenges of initial regulatory measures in waste management, offering crucial empirical evidence and insights for creating impactful environmental behaviour change interventions.

Blind Separation of Skin Chromophores from Multispectral Dermatological Images.

Background/Objectives: Based on Blind Source Separation and the use of multispectral imaging, the new approach we propose in this paper aims to improve the estimation of the concentrations of the main skin chromophores (melanin, oxyhemoglobin and deoxyhemoglobin), while considering shading as a fully-fledged source. Methods: In this paper, we demonstrate that the use of the Infra-Red spectral band, in addition to the traditional RGB spectral bands of dermatological images, allows us to model the image provided by each spectral band as a mixture of the concentrations of the three chromophores in addition to that of the shading, which are estimated through four steps using Blind Source Separation. Results: We studied the performance of our new method on a database of real multispectral dermatological images of melanoma by proposing a new quantitative performances measurement criterion based on mutual information. We then validated these performances on a database of multispectral dermatological images that we simulated using our own new protocol. Conclusions: All the results obtained demonstrated the effectiveness of our new approach for estimating the concentrations of the skin chromophores from a multispectral dermatological image, compared to traditional approaches that consist of using only the RGB image by neglecting shading.

Main lobe deceptive jamming suppression based on blind source separation and energy detection for monopulse radar

AbstractMain lobe deceptive jamming always causes the serious degradation of signal detection ability and angle measurement precision of monopulse radar. In recent years, the Blind Source Separation (BSS) method has been adopted to suppress the main lobe jamming. However, the separation results of BSS have the problem of amplitude ambiguity, which will cause the radar using monopulse angle measurement fail to measure the angle parameters after jamming suppression. To tackle this problem, a novel main lobe jamming suppression method is proposed based on BSS and energy detection. Firstly, the models of target echoes and jamming in the sum and difference beam receiving channels are derived. Secondly, the target echoes and interferences are separated by the Joint Approximate Diagonalisation of Eigenmatrices (JADE) algorithm, and then the unperturbed signal segments in the mixed signal are extracted by energy detection, thereby obtaining the precise ratio of the sum and difference channels to complete the angle measurement. Performance of the method was verified by numerical simulation. The results show that the proposed method can achieve interference suppression while accurately estimating the angle parameter of the target.

Non-stationary mechanical sound source separation: An all-neural beamforming network driven by time–frequency convolution and self-attention

To tackle the challenging task of extracting target signal features amidst significant interference from complex, time-varying non-stationary noise in industrial scenarios, we propose a novel time-domain all-neural beamforming network tailored for non-stationary mechanical sound source separation, named TFANBNet. Leveraging time–frequency convolution and self-attention, TFANBNet promised robust performance in challenging acoustic environments. First, the proposed time–frequency convolution module employs parameterized complex-valued convolutional layers to simulate time–frequency transformations, thereby implicitly extracting time–frequency features. Then, the proposed adaptive attention transformer network enhances local attention interaction by integrating intermediate features, effectively enhancing long-range context modeling. Third, the beamforming module utilizes deep neural networks for beamforming weight estimation, replacing conventional noise covariance matrix computations, which have inherent performance limitations. Finally, the experimental results on the multi-channel spatial reverberation dataset synthesized from the MIMII dataset show that the proposed TFANBNet yields superior separation performance and generalization capabilities compared to the considered competitive methods.

Self-gated free-running 5D whole-heart MRI using blind source separation for automated cardiac motion extraction.

To compare two blind source separation (BSS) techniques to principal component analysis and the electrocardiogram for the identification of cardiac triggers in self-gated free-running 5D whole-heart MRI. To ascertain the precision and robustness of the techniques, they were compared in three different noise and contrast regimes. The repeated superior-inferior (SI) projections of a 3D radial trajectory were used to extract the physiological signals in three cardiac MRI cohorts: (1) 9 healthy volunteers without contrast agent injection at 1.5T, (2) 30 ferumoxytol-injected congenital heart disease patients at 1.5T, and (3) 12 gadobutrol-injected patients with suspected coronary artery disease at 3T. Self-gated cardiac triggers were extracted with the three algorithms (principal component analysis [PCA], second-order blind identification [SOBI], and independent component analysis [ICA]) and the difference with the electrocardiogram triggers was calculated. PCA and SOBI triggers were retained for image reconstruction. The image sharpness was ascertained on whole-heart 5D images obtained with PCA and SOBI and compared among the three cohorts. SOBI resulted in smaller trigger differences in Cohorts 1 and 3 compared to PCA (p < 0.01) and in all cohorts compared to ICA (p < 0.04). In Cohorts 1 and 3, the sharpness increased significantly in the reconstructed images when using SOBI instead of PCA (p < 0.03), but not in Cohort 2 (p = 0.4). We have shown that SOBI results in more precisely extracted self-gated triggers than PCA and ICA. The validation across three diverse cohorts demonstrates the robustness of the method against acquisition variability.

Modelling multivariate spatio-temporal data with identifiable variational autoencoders

Modelling multivariate spatio-temporal data with complex dependency structures is a challenging task but can be simplified by assuming that the original variables are generated from independent latent components. If these components are found, they can be modelled univariately. Blind source separation aims to recover the latent components by estimating the unknown linear or nonlinear unmixing transformation based on the observed data only. In this paper, we extend recently introduced identifiable variational autoencoder to the nonlinear nonstationary spatio-temporal blind source separation setting and demonstrate its performance using comprehensive simulation studies. Additionally, we introduce two alternative methods for the latent dimension estimation, which is a crucial task in order to obtain the correct latent representation. Finally, we illustrate the proposed methods using a meteorological application, where we estimate the latent dimension and the latent components, interpret the components, and show how nonstationarity can be accounted and prediction accuracy can be improved by using the proposed nonlinear blind source separation method as a preprocessing method.

A sustainable network design for municipal solid waste management considering waste-to-energy conversion under uncertainty

This research proposes a sustainable municipal solid waste management (MSWM) system to address population growth, consumerism, and resource scarcity. It introduces a two-phase decision structure combining multi-attribute decision-making (MADM) tools. Phase one develops a hybrid risk-oriented fuzzy MADM tool for selecting optimal waste-to-energy technologies, considering environmental and technological factors. Phase two uses a fuzzy bi-objective multi-period mixed-integer linear programming model to design the MSWM supply chain efficiently under uncertainty. A case study in North Tehran demonstrates the framework’s practical applicability and effectiveness in real-world scenarios, highlighting that effective source separation boosts recycling, reduces costs, and provides social benefits. Sensitivity analyses offer insights to enhance waste segregation practices. The study emphasizes integrating economic, environmental, and social sustainability in waste management decision-making. By offering a novel, holistic approach, this research addresses existing gaps in systematic decision-making processes and provides a robust tool for municipalities to optimize strategies under uncertainty.

DOA-informed switching independent vector extraction and beamforming for speech enhancement in underdetermined situations

This paper proposes novel methods for extracting a single Speech signal of Interest (SOI) from a multichannel observed signal in underdetermined situations, i.e., when the observed signal contains more speech signals than microphones. It focuses on extracting the SOI using prior knowledge of the SOI’s Direction of Arrival (DOA). Conventional beamformers (BFs) and Blind Source Separation (BSS) with spatial regularization struggle to suppress interference speech signals in such situations. Although Switching Minimum Power Distortionless Response BF (Sw-MPDR) can handle underdetermined situations using a switching mechanism, its estimation accuracy significantly decreases when it relies on a steering vector determined by the SOI’s DOA. Spatially-Regularized Independent Vector Extraction (SRIVE) can robustly enhance the SOI based solely on its DOA using spatial regularization, but its performance degrades in underdetermined situations. This paper extends these conventional methods to overcome their limitations. First, we introduce a time-varying Gaussian (TVG) source model to Sw-MPDR to effectively enhance the SOI based solely on the DOA. Second, we introduce the switching mechanism to SRIVE to improve its speech enhancement performance in underdetermined situations. These two proposed methods are called Switching weighted MPDR (Sw-wMPDR) and Switching SRIVE (Sw-SRIVE). We experimentally demonstrate that both surpass conventional methods in enhancing the SOI using the DOA in underdetermined situations.