Source Separation Research Articles

Multi-resolution Analysis Based Time-Domain Audio Source Separation with Optimized U-NET Model

Multi-resolution Analysis Based Time-Domain Audio Source Separation with Optimized U-NET Model

A Radar Compound Jamming Recognition Method Based on Blind Source Separation

A Radar Compound Jamming Recognition Method Based on Blind Source Separation

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.

Different sustained and induced alpha oscillations emerge in the human auditory cortex during sound processing

Alpha oscillations in the auditory cortex have been associated with attention and the suppression of irrelevant information. However, their anatomical organization and interaction with other neural processes remain unclear. Do alpha oscillations function as a local mechanism within most neural sources to regulate their internal excitation/inhibition balance, or do they belong to separated inhibitory sources gating information across the auditory network? To address this question, we acquired intracerebral electrophysiological recordings from epilepsy patients during rest and tones listening. Thanks to independent component analysis, we disentangled the different neural sources and labeled them as “oscillatory” if they presented strong alpha oscillations at rest, and/or “evoked” if they displayed a significant evoked response to the stimulation. Our results show that 1) sources are condition-specific and segregated in the auditory cortex, 2) both sources have a high-gamma response followed by an induced alpha suppression, 3) only oscillatory sources present a sustained alpha suppression during all the stimulation period. We hypothesize that there are two different alpha oscillations in the auditory cortex: an induced bottom-up response indicating a selective engagement of the primary cortex to process the stimuli, and a sustained suppression reflecting a general disinhibited state of the network to process sensory information.

Occupancy Map Guided Attributes Artifacts Removal for Video-Based Point Cloud Compression

Point clouds offer realistic 3D representations of objects and scenes at the expense of large data volumes. To represent such data compactly in real-world applications, Video-Based Point Cloud Compression (V-PCC) converts their texture into 2D attributes and occupancy maps before applying lossy video compression. Unfortunately, the coding artifacts introduced in the decoded attribute maps eventually degrade the quality of the reconstructed point cloud, thereby influencing its immersive experience. This article proposes a deep learning-based attribute map enhancement method that fully leverages the occupancy map's guidance. The design philosophy is that the cross-modality guidance from occupancy can be leveraged as critical information to enhance the attribute. Therefore, instead of treating attribute and occupancy as two separate sources of signals, occupancy serves as an indispensable auxiliary, such that the proposed framework explicitly provides the model with abundant clues by conducting local feature modification and global dependencies aggregation. In particular, the proposed framework is compatible with existing V-PCC bitstreams and can be feasibly incorporated into the standardized decoder pipeline. Extensive evaluations show the effectiveness of the proposed framework in attribute enhancement, with equivalently 6.0% Bjontegaard Delta-rate (BD-rate) savings obtained.

A new deep learning forward BSS (D-FBSS) algorithm for acoustic noise reduction and speech enhancement

To enhance the speech signal in noisy environments, a Forward Blind Source Separation (FBSS) structure is frequently employed. This structure retrieves speech signal at the output from two noisy observations at the input. However, most speech enhancement methods based on FBSS use manual Voice Activity Detection (VAD) system. In this work, we propose a new algorithm based on FBSS and a Deep Neural Network (DNN) system for automatic VAD (denoted DVAD). This algorithm uses a multi-classification mechanism to identify various types of noise, and a deep DVAD for each specific type. We constructed, in the first part, the DNN models using the TIMIT database with various types of noise. The dataset was subsequently partitioned into three segments: 75% for training, 15% for validation, and the remaining portion for testing purposes. After preparing the recordings, we combined them with six different types of noise from another collection called NOISEX-92. In the second part, we integrated the DVAD system in the FBSS to cancel the noise component from noisy observations. This algorithm yields better results even under negative SNR environments. We show the efficiency of the proposed algorithm in terms of objective and subjective criteria.

A neuronal marker of eye contact spontaneously activated in neurotypical subjects but not in autistic spectrum disorders

Attention to faces and eye contact are key behaviors for establishing social bonds in humans. In Autism Spectrum Disorders (ASD), a disturbance in neurodevelopment, impaired face processing and gaze avoidance are key clinical features for ASD diagnosis. The biological alterations underlying these impairments are not yet clearly established. Using high-density electroencephalography coupled with multi-variate pattern classification and group blind source separation methods we searched for face- and-face components-related neural signals that could best discriminate visual processing of neurotypical subjects (N = 38) from ASD participants (N = 27). We isolated a face-specific neural signal in the superior temporal sulcus peaking at 240 msec after face-stimulus onset. A machine learning algorithm applied on the extracted neural component reached 74% decoding accuracy at the same latencies, discriminating the neurotypical population from ASD subjects in whom this signal was weak. By manipulating attention on different parts of the face, we also found that the power of the evoked signal in neurotypical subjects varied depending on the region observed: it was strong when the eye region fell on the fovea to decrease on regions further away and outside the stimulus face. Such face and face-components selective neural modulations were not found in ASD, although they did show typical early face-related P100 and N170 signals. These results show that specialized cortical mechanisms for face perception show higher responses for eyes when attention is focused on gaze and that these mechanisms may be particularly affected in autism spectrum disorders.

An Innovative Nonlinear Bounded Component Analysis Algorithm Based on Multivariate Nonlinear Chirp Mode Decomposition

In complex and diverse practical application scenarios, the challenge of blind source separation under underdetermined and nonlinear conditions is often encountered. To address this challenge, this paper proposes an innovative underdetermined nonlinear bounded component analysis method. This method first employs Multivariate Nonlinear Chirp Mode Decomposition (MNCMD) to process and reconstruct the observed signals, transforming the original underdetermined problem into a positive definite problem. Subsequently, Gaussianization techniques are introduced as a means of nonlinear compensation, successfully converting the nonlinear model into an analyzable linear model, laying a solid foundation for subsequent signal separation. Finally, the signal is separated by the bounded component analysis method, which does not require the source signals to be independent of each other. To validate the effectiveness and superiority of the proposed algorithm, detailed simulation experiments were designed and implemented. The experimental results demonstrate that compared to traditional underdetermined blind source separation algorithms, the algorithm presented in this paper exhibits significant advantages in terms of universality, convergence speed, separation accuracy, and robustness. Furthermore, this paper successfully applies the algorithm to the blind extraction of fetal electrocardiogram (FECG) signals from real datasets. The experimental results show that the algorithm can rapidly and effectively extract clearer and more accurate FECG signals, demonstrating its great potential and value in practical applications.

A Method for Multimodal IVA Fusion Within a MISA Unified Model Reveals Markers of Age, Sex, Cognition, and Schizophrenia in Large Neuroimaging Studies.

With the increasing availability of large-scale multimodal neuroimaging datasets, it is necessary to develop data fusion methods which can extract cross-modal features. A general framework, multidataset independent subspace analysis (MISA), has been developed to encompass multiple blind source separation approaches and identify linked cross-modal sources in multiple datasets. In this work, we utilized the multimodal independent vector analysis (MMIVA) model in MISA to directly identify meaningful linked features across three neuroimaging modalities-structural magnetic resonance imaging (MRI), resting state functional MRI and diffusion MRI-in two large independent datasets, one comprising of control subjects and the other including patients with schizophrenia. Results show several linked subject profiles (sources) that capture age-associated decline, schizophrenia-related biomarkers, sex effects, and cognitive performance. For sources associated with age, both shared and modality-specific brain-age deltas were evaluated for association with non-imaging variables. In addition, each set of linked sources reveals a corresponding set of cross-modal spatial patterns that can be studied jointly. We demonstrate that the MMIVA fusion model can identify linked sources across multiple modalities, and that at least one set of linked, age-related sources replicates across two independent and separately analyzed datasets. The same set also presented age-adjusted group differences, with schizophrenia patients indicating lower multimodal source levels. Linked sets associated with sex and cognition are also reported for the UK Biobank dataset.

Blind source separation algorithm for biomedical signal based on lie group manifold

Independent Component Analysis (ICA) is a powerful tool for solving blind source separation problem in biomedical engineering. The traditional ICA algorithm ignores the Lie group structure of constrained matrix manifold. In this paper, a gradient descent algorithm on Lie group manifold is proposed based on the geometric framework of optimization algorithm on Riemann manifold. Firstly, the orthogonal constraint separation matrices are regarded as a Lie group manifold, and the gradient of ICA objective function on the Lie group manifold is given by using Riemann metric; Secondly, the geodesic equation of the current iteration point along the gradient descent direction is calculated; Finally, a new iteration point is obtained by moving a certain step along the geodesic line, meanwhile, the step length can be adjusted adaptively. Simulation results show that the gradient algorithm on Lie group manifold is feasible for blind Source Separation, and its performance (convergence speed, stability and error) is better than other algorithms.

Mixed Source Separation of Partially Correlated Source Based on Analytic CMA

Mixed Source Separation of Partially Correlated Source Based on Analytic CMA

Application of the Theory of Planned Behavior to predict waste source separation

Appropriate solid municipal waste management is an important topic in the EU. Abiding by the amended EU Waste Framework Directive and the amended EU Landfill Directive, Greece has set ambitious goals for waste reuse and recycling and for landfill minimization in its recent National Waste Management Plans. These goals however can only be reached through the improvement of the mixed recyclable waste scheme (the “blue bin” scheme for paper/carton, plastic and metal) and the establishment of collection containers for separate waste streams (separately for biodegradable waste, for glass, for paper/carton and for the rest). Active participation of citizens in waste source separation is paramount for this program. As such, the determinants that favor waste source separation intention were measured in approximately 1600 residents in the city of Thessaloniki in Northern Greece, through the application of the Theory of Planned Behavior (TPB). The determinant of Moral Norms (MN) was included in the basic model [that contains the determinants Attitude (ATT), Subjective Norms (SN) and Perceived Behavioral Control (PBC)]. Each determinant was measured through four or five declarations while the Behavioral Intention (BI) contained ten subsections. The model was able to satisfactorily predict the intention of the respondents to perform waste source separation. Specifically, the model successfully predicted respondents' intention to engage in waste source separation, explaining 36 % of the variance, indicating that a moderate amount of variance can be explained by the constructs. There was a significant direct effect of ATT (β = 0.486, p < 0.001), SN (β = 0.091, p < 0.05), and PBC (β = 0.091, p < 0.05) on BI. Additionally, MN showed statistically significant mediating effects; a mediating effect on BI via ATT (β = 0.479; p < 0.01), via SN (β = 0.046; p = 0.015), and via PBC (β = 0.057; p = 0.017) was noted. Implications of these results on waste separation policies include the following: launching comprehensive public education campaigns to reshape positive attitudes, improving infrastructure to strengthen the real or perceived behavioral control of citizens experience, increasing “peer pressure” via community engagement activities, such as recycling workshops, clean-up drives, and competitions. The important role of moral obligations in the community should be underlined and it may be the long-term key solution; educational programs and campaigns should emphasize the moral obligation of waste separation and integrating environmental ethics into school programs can instill these values from a young age.

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.

Audio-visual correspondences based joint learning for instrumental playing source separation

Sound source separation is usually challenged by the identification of intermittently static sounding objects in realistic scenarios, especially when the sound generation is intrinsically related to variational motion as instrumental playing. Current solutions based on audio-visual learning have demonstrated a capability to enhance the sound source by modality interaction, but the training sample deficiency caused by unreliable pair-wise annotation still limits the separation performance to be further improved. Inspired by the sound-motion connection in realistic symphony scenario, in this work, a two-stage audio-visual network is proposed for instrumental audio separation. With a coarse-grained to fine-grained separation, a Patch-level Channel Audio-Visual Interaction (PCAVI) module is also introduced for elegant association between features of audio-motion modalities. By designing a regularization loss to compensate the imbalance of audio-visual feature distribution, a novel circulant learning is proposed to achieve more accurate and reliable performance. Substantial experiments have demonstrated that the proposed two-stage audio-visual instrumental audio separation network outperforms the motion-free methods on the MUSIC dataset, and achieves strong audio separation results in challenging real-world symphony scenarios.

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.

Visually Guided Sound Source Separation With Audio-Visual Predictive Coding.

The framework of visually guided sound source separation generally consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. An ongoing trend in this field has been to tailor involved visual feature extractor for informative visual guidance and separately devise module for feature fusion, while utilizing U-Net by default for sound analysis. However, such a divide-and-conquer paradigm is parameter-inefficient and, meanwhile, may obtain suboptimal performance as jointly optimizing and harmonizing various model components is challengeable. By contrast, this article presents a novel approach, dubbed audio-visual predictive coding (AVPC), to tackle this task in a parameter-efficient and more effective manner. The network of AVPC features a simple ResNet-based video analysis network for deriving semantic visual features, and a predictive coding (PC)-based sound separation network that can extract audio features, fuse multimodal information, and predict sound separation masks in the same architecture. By iteratively minimizing the prediction error between features, AVPC integrates audio and visual information recursively, leading to progressively improved performance. In addition, we develop a valid self-supervised learning strategy for AVPC via copredicting two audio-visual representations of the same sound source. Extensive evaluations demonstrate that AVPC outperforms several baselines in separating musical instrument sounds, while reducing the model size significantly. Code is available at: https://github.com/zjsong/Audio-Visual-Predictive-Coding.

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.

Technical, Economic, and Environmental Study with ANN-based Optimization of A Biomass-powered Versatile/Sustainable Polygeneration System with Carbon Capture/Utilization Approach

This study delineates the development and evaluation of a power generation cycle characterized by the absence of carbon dioxide emissions, achieved through the direct combustion of oxygen and natural gas, a system commonly known as the Graz cycle. The analysis incorporates both thermodynamic and economic dimensions. In this system, hydrogen (H2) was initially produced from two separate sources to enable the conversion of carbon dioxide (CO2), sourced from the Graz cycle, into methane. The predominant method for hydrogen production is through the biomass gasification system, complemented by the use of hydrogen separation membranes. The solid oxide electrolyzer cell serves as the secondary source, wherein the necessary electrical energy is supplied by photovoltaic collectors. This research employs a robust methodological framework to undertake a comprehensive analysis of economic variables, with the objective of providing an accurate depiction of empirical conditions in the real world. This study conducts a comprehensive analysis of all relevant costs within the specified framework. A series of ANN-centered optimization analyses was performed to ascertain conditions that concurrently optimize the economic and thermodynamic dimensions of the system.