Source Separation Research Articles

Spectral Features Analysis for Print Quality Prediction in Additive Manufacturing: An Acoustics-Based Approach.

Quality prediction in additive manufacturing (AM) processes is crucial, particularly in high-risk manufacturing sectors like aerospace, biomedicals, and automotive. Acoustic sensors have emerged as valuable tools for detecting variations in print patterns by analyzing signatures and extracting distinctive features. This study focuses on the collection, preprocessing, and analysis of acoustic data streams from a Fused Deposition Modeling (FDM) 3D-printed sample cube (10 mm × 10 mm × 5 mm). Time and frequency-domain features were extracted at 10-s intervals at varying layer thicknesses. The audio samples were preprocessed using the Harmonic-Percussive Source Separation (HPSS) method, and the analysis of time and frequency features was performed using the Librosa module. Feature importance analysis was conducted, and machine learning (ML) prediction was implemented using eight different classifier algorithms (K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Trees (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LightGBM)) for the classification of print quality based on the labeled datasets. Three-dimensional-printed samples with varying layer thicknesses, representing two print quality levels, were used to generate audio samples. The extracted spectral features from these audio samples served as input variables for the supervised ML algorithms to predict print quality. The investigation revealed that the mean of the spectral flatness, spectral centroid, power spectral density, and RMS energy were the most critical acoustic features. Prediction metrics, including accuracy scores, F-1 scores, recall, precision, and ROC/AUC, were utilized to evaluate the models. The extreme gradient boosting algorithm stood out as the top model, attaining a prediction accuracy of 91.3%, precision of 88.8%, recall of 92.9%, F-1 score of 90.8%, and AUC of 96.3%. This research lays the foundation for acoustic based quality prediction and control of 3D printed parts using Fused Deposition Modeling and can be extended to other additive manufacturing techniques.

Acute intermittent hypoxia increases maximal motor unit discharge rates in people with chronic incomplete spinal cord injury.

Acute intermittent hypoxia (AIH) is an emerging technique for enhancing neuroplasticity and motor function in respiratory and limb musculature. Thus far, AIH-induced improvements in strength have been reported for upper and lower limb muscles after chronic incomplete cervical spinal cord injury (iSCI), but the underlying mechanisms have been elusive. We used high-density surface EMG (HDsEMG) to determine if motor unit discharge behaviour is altered after 15×60s exposures to 9% inspired oxygen, interspersed with 21% inspired oxygen (AIH), compared to breathing only 21% air (SHAM). We recorded HDsEMG from the biceps and triceps brachii of seven individuals with iSCI during maximal elbow flexion and extension contractions, and motor unit spike trains were identified using convolutive blind source separation. After AIH, elbow flexion and extension torque increased by 54% and 59% from baseline (P=0.003), respectively, whereas there was no change after SHAM. Across muscles, motor unit discharge rates increased by ∼4 pulses per second (P=0.002) during maximal efforts, from before to after AIH. These results suggest that excitability and/or activation of spinal motoneurons is augmented after AIH, providing a mechanism to explain AIH-induced increases in voluntary strength. Pending validation, AIH may be helpful in conjunction with other therapies to enhance rehabilitation outcomes after incomplete spinal cord injury, due to these enhancements in motor unit function and strength. KEY POINTS: Acute intermittent hypoxia (AIH) causes increases in muscular strength and neuroplasticity in people living with chronic incomplete spinal cord injury (SCI), but how it affects motor unit discharge rates is unknown. Motor unit spike times were identified from high-density surface electromyograms during maximal voluntary contractions and tracked from before to after AIH. Motor unit discharge rates were increased following AIH. These findings suggest that AIH can facilitate motoneuron function in people with incomplete SCI.

Source separation and classification using generative adversarial networks and weak class supervision

In this paper, we propose a decomposition-based weakly-supervised model that utilizes the class labels of the sources present in mixtures. We apply this weak class supervision approach to superimposed handwritten digit images using both non-negative matrix factorization (NMF) and generative adversarial networks (GANs). In this way, we can learn non-linear representations of the sources. The results of our experiments demonstrate that the proposed weakly-supervised methods are viable and mostly on par with the fully supervised baselines. The proposed joint classification and separation approach achieves a weakly-supervised source classification performance of 90.3 in terms of F1 score and outperforms the multi-label source classifier baseline of 68.2 when there are two sources. The separation performance of the proposed method is measured in terms of peak-signal-to-noise-ratio (PSNR) as 16 dB, outperforming the class-informed sparse NMF which achieves separation of two sources with a PSNR value of 13.9 dB. We show that it is possible to replace supervised training with weakly-supervised methods without performance penalty.

Source separation and anaerobic co-digestion of blackwater and food waste for biogas production and nutrient recovery.

Anaerobic co-digestion of source-separated blackwater (BW) and food and kitchen waste (FW) offers decentralized circular economy solutions by enabling local production of biogas and nutrient-rich byproducts. In this study, a 2 m3 pilot-scale continuously stirred tank reactor (CSTR) operated under mesophilic conditions was utilized for co-digestion of BW and FW. The process obtained a CH4 yield of 0.7 ± 0.2 m3/kg influent-volatile solid (VS), reaching a maximum yield of 1.1 ± 0.1 m3/kg influent-VS, with an average organic loading rate of 0.6 ± 0.1 kg-VS/m3/d and HRT of 25 days. The CH4 production rate averaged 0.4 ± 0.1 m3/m3/d, peaking at 0.6 ± 0.1 m3/m3/d. Treatment of digestate through flocculation followed by sedimentation recovered over 90% of ammonium nitrogen and potassium, and 80-85% of total phosphorus in the liquid fraction. This nutrient-rich liquid was used to cultivate Chlorella vulgaris, achieving a biomass concentration of 1.2 ± 0.1 g/L and 85 ± 3% and 78 ± 5% ammonium nitrogen and phosphorus removal efficiency, respectively. These findings not only highlight the feasibility of anaerobic co-digestion of source-separated BW and FW in local biogas production but also demonstrate the potential of microalgae cultivation as a sustainable approach to converting digestate into nutrient-rich algae biomass.

The whole is greater than the sum of its parts: improving music source separation by bridging networks

This paper presents the crossing scheme (X-scheme) for improving the performance of deep neural network (DNN)-based music source separation (MSS) with almost no increasing calculation cost. It consists of three components: (i) multi-domain loss (MDL), (ii) bridging operation, which couples the individual instrument networks, and (iii) combination loss (CL). MDL enables the taking advantage of the frequency- and time-domain representations of audio signals. We modify the target network, i.e., the network architecture of the original DNN-based MSS, by adding bridging paths for each output instrument to share their information. MDL is then applied to the combinations of the output sources as well as each independent source; hence, we called it CL. MDL and CL can easily be applied to many DNN-based separation methods as they are merely loss functions that are only used during training and do not affect the inference step. Bridging operation does not increase the number of learnable parameters in the network. Experimental results showed that the validity of Open-Unmix (UMX), densely connected dilated DenseNet (D3Net) and convolutional time-domain audio separation network (Conv-TasNet) extended with our X-scheme, respectively called X-UMX, X-D3Net and X-Conv-TasNet, by comparing them with their original versions. We also verified the effectiveness of X-scheme in a large-scale data regime, showing its generality with respect to data size. X-UMX Large (X-UMXL), which was trained on large-scale internal data and used in our experiments, is newly available at https://github.com/asteroid-team/asteroid/tree/master/egs/musdb18/X-UMX.

Online adaptation of fourier series-based acoustic transfer function model and its application to sound source localization and separation

In this paper, we propose an online adaptation method for Fourier series-based acoustic transfer function (FS-ATF) models for robot audition systems using microphone array signal processing. The ATF represents the characteristics of signal propagation from a sound source to a microphone, which is essential for sound source localization (SSL) and sound source separation (SSS). For practical applications in dynamically changing real-world environments, ATF models must satisfy two criteria: (1) they must be adaptable to changes in the acoustic environment; and (2) they must be lightweight to be suitable for resource-constrained systems, such as robots with limited memory and computational capacity. The proposed method addresses these challenges using Fourier series expansions for interpolation, which reduces the memory footprint of the ATF model and facilitates online adaptation to acoustic environmental changes. The experimental results demonstrate that the proposed online adaptation method both improves the SSL and SSS performance while reducing the size of the ATF model, which represents a significant improvement over existing online ATF adaptation methods.

Affordable and real-time antimicrobial resistance prediction from multimodal electronic health records

The spread of antimicrobial resistance (AMR) leads to challenging complications and losses of human lives plus medical resources, with a high expectancy of deterioration in the future if the problem is not controlled. From a machine learning perspective, data-driven models could aid clinicians and microbiologists by anticipating the resistance beforehand. Our study serves as the first attempt to harness deep learning (DL) techniques and the multimodal data available in electronic health records (EHR) for predicting AMR. In this work, we utilize and preprocess the MIMIC-IV database extensively to produce separate structured input sources for time-invariant and time-series data customized to the AMR task. Then, a multimodality fusion approach merges the two modalities with clinical notes to determine resistance based on an antibiotic or a pathogen. To efficiently predict AMR, our approach builds the foundation for deploying multimodal DL techniques in clinical practice, leveraging the existing patient data.

Blind Source Separation of Electromagnetic Signals Based on Swish-Tasnet

Blind Source Separation of Electromagnetic Signals Based on Swish-Tasnet

Peronia peronii as a bio-indicator to assess the toxicity of waterpipe tobacco leachates in aquatic and sediment media.

This study was aimed to survey toxicity of waterpipe wastes leachates on Peronia peronii in aquatic and sediment environments as two exposure media. For this, leachates of four tobacco types including burnt traditional tobacco (BTT), fresh traditional tobacco (FTT), burnt fruit-flavored tobacco (BFT) and fresh fruit-flavored tobacco (FFT)) were prepared and used to assess their toxic effects on P. peronei in two aquatic and sediment media. The in-vivo toxic effects of five different concentrations of waterpipe tobacco waste leachates on P. peronii were evaluated. The LC50 values of BTTs leachates to P. peronii were 17.50, 16.05, 11.31 and 9.38g/L at exposure times of 24, 48, 72 and 96h, respectively in aquatic media. These values for BFTs leachates were 14.86, 12.38, 9.53 and 7.46g/L at exposure times of 24, 48, 72 and 96h, respectively. In the case of sediment media, the LC50 values of BTTs leachates were 15.33, 13.70, 9.09 and 6.70g/L at exposure times of 24, 48, 72 and 96h, respectively while these values for BFTs leachates were 12.00, 10.32, 8.20 and 5.65g/L. Fruit-flavored tobacco leachates had significantly higher toxicity than traditional tobacco leachates for P. peronii. The findings also showed significant differences between the LC50 values of different leachates in different media of water and sediment. The results demonstrated that even small amount of tobacco waste (~ 5 to 6g/L) can lead to P. peronii mortality and may also pose a hazard to other aquatic and benthic organisms. The results obtained from the present study can be used as a baseline data to assess local effects causing from unsafe disposal of post-consumption tobacco waste in beach areas. In addition, these findings can lead to encouraging decision-makers to focus more on the types of tobacco waste in the municipal solid waste management system and to implement a source separation process for these wastes.

Exact evaluation of large-charge correlation functions in nonrelativistic conformal field theory

The large-charge master field which generates all n-point correlation functions with an insertion of large charge Q in nonrelativistic conformal field theory is obtained. This field is used to compute Schrödinger-invariant n-point correlation functions of large-charge operators via a direct evaluation of the path integral. Conformal dimensions are found to agree with calculations based on the state-operator correspondence. The master field solution exhibits an emergent harmonic trap whose frequency is a function of the Euclidean time. The large-charge effective action with operator insertions describes a droplet of superfluid matter whose spatial size scales with the time separation of sources. The solution is used to compute Schrödinger symmetry breaking corrections in the large-charge effective field theory (EFT) due to a finite scattering length in the fundamental theory of fermions near unitarity. The scaling of these effects in the large-charge power counting scheme is established, and the size of the effects is quantified using input from quantum Monte Carlo simulations of the near-unitary gas, as well as from the large-N expansion at large charge. Published by the American Physical Society 2024

Unveiling MOA-2007-BLG-192: An M Dwarf Hosting a Likely Super-Earth

We present an analysis of high-angular-resolution images of the microlensing target MOA-2007-BLG-192 using Keck adaptive optics and the Hubble Space Telescope. The planetary host star is robustly detected as it separates from the background source star in nearly all of the Keck and Hubble data. The amplitude and direction of the lens–source separation allows us to break a degeneracy related to the microlensing parallax and source radius crossing time. Thus, we are able to reduce the number of possible binary-lens solutions by a factor of ∼2, demonstrating the power of high-angular-resolution follow-up imaging for events with sparse light-curve coverage. Following Bennett et al., we apply constraints from the high-resolution imaging on the light-curve modeling to find host star and planet masses of M host = 0.28 ± 0.04 M ☉ and mp=12.49−8.03+65.47M⊕ at a distance from Earth of D L = 2.16 ± 0.30 kpc. This work illustrates the necessity for the Nancy Grace Roman Galactic Exoplanet Survey to use its own high-resolution imaging to inform light-curve modeling for microlensing planets that the mission discovers.

EF‐CorrCA: A multi‐modal EEG‐fNIRS subject independent model to assess speech quality on brain activity using correlated component analysis

AbstractAn investigation on the effect of mental activity in quality perception is presented using simultaneous measurement of electroencephalography (EEG) and functional near‐infrared spectroscopy (fNIRS), in a subject‐independent approach. Building a subject‐independent model is a harder problem due to noise and high EEG variability between individuals, correlated components analysis (CorrCA) have been proposed to extract significant correlated components for a single subject that experiences multiple identical trials; this is done by identifying spatio‐temporal patterns of activity that are well preserved across trials. The aim is to build a model based on neurophysiological data to assess text‐to‐speech quality. In order to build a subject independent model, we extended the use of CorrCA such that it can be applied to the subject independent model. The authors used two preprocessing steps, namely the subject dependent and the stimulus dependent preprocessing. The second preprocessing used the denoising source separation (DSS) to remove noise/artefact that are subject specific. The discrete convolution is used for data fusion and the support vector machine for regression. With the proposed model, the fusion of EEG and fNIRS performs better than single modality. Using our defined regression accuracy metrics, the authors obtained accuracy of 81.346% for overall impression, 83.28% for valence and 89.714% for arousal. The model compete the baseline that is subject dependent.

SA-UCBSS: Sparsity-Based Adaptive Underdetermined Convolutive Blind Source Separation

Blind source separation is the process of separating unknown source signals based only on the received mixing signals when the source signal cannot be accurately known. Traditional methods are mainly based on linear approximate transformation models that often have large systematic errors in high reverberation environments, resulting in poor separation performance. To avoid these limitations, a sparsity-based adaptive underdetermined convolutive blind source separation (SA-UCBSS) algorithm is proposed by unifying a convolutive approximate transformation model and an Lp(0<p≤1)-norm regularisation penalty. A crosstalk canceller is designed for room impulse response pretreatment with p-norm optimisation to eliminate audible echoes, and a sparse optimisation scheme is designed for the parameter initialisation to accelerate the convergence of the iterative recovery process. Subsequently, a convolutive approximate transformation model is built to achieve a more accurate estimation of the mixing system. The SA-UCBSS algorithm is proposed to achieve better source separation by adaptively tuning the value of parameter p. Experimental results including BSS of the synthesised and live-recorded speech convolutive mixtures showed that the SA-UCBSS algorithm had superior separating properties and better robustness than several popular algorithms.

Dual input single Output quadratic Boost converter for DC microgrid

DC-DC converters play a critical role in various applications, including DC microgrids, electrical vehicles, data centres and aerospace power systems. This article provides a description of a non-isolated Dual Input Single Output Quadratic Boost DC-DC Converter (DISOQBC) designed for DC microgrids. PV module and battery are low dc voltage power generators. DC microgrid requires high voltage for its operation effectively. By utilizing the proposed converter, the PV module and battery are integrated with separate sources. Achieving a high efficiency and voltage conversion ratio, the proposed converter is distinguished by low components used. The operation of the converter, component design, steady state analysis, and small-signal model has been reported. The proposed converter's benefits include the converter's ability to handle more than one source, deliver more gain than the conventional converter, simple control and reduced losses. The outcome of simulating the converter validates the proposed converter's theoretical operation. The laboratory prototype is ultimately employed to validate and verify the performance of the proposed DISOQBC.

A High-Performance Anti-Noise Algorithm for Arrhythmia Recognition.

In recent years, the incidence of cardiac arrhythmias has been on the rise because of changes in lifestyle and the aging population. Electrocardiograms (ECGs) are widely used for the automated diagnosis of cardiac arrhythmias. However, existing models possess poor noise robustness and complex structures, limiting their effectiveness. To solve these problems, this paper proposes an arrhythmia recognition system with excellent anti-noise performance: a convolutionally optimized broad learning system (COBLS). In the proposed COBLS method, the signal is convolved with blind source separation using a signal analysis method based on high-order-statistic independent component analysis (ICA). The constructed feature matrix is further feature-extracted and dimensionally reduced using principal component analysis (PCA), which reveals the essence of the signal. The linear feature correlation between the data can be effectively reduced, and redundant attributes can be eliminated to obtain a low-dimensional feature matrix that retains the essential features of the classification model. Then, arrhythmia recognition is realized by combining this matrix with the broad learning system (BLS). Subsequently, the model was evaluated using the MIT-BIH arrhythmia database and the MIT-BIH noise stress test database. The outcomes of the experiments demonstrate exceptional performance, with impressive achievements in terms of the overall accuracy, overall precision, overall sensitivity, and overall F1-score. Specifically, the results indicate outstanding performance, with figures reaching 99.11% for the overall accuracy, 96.95% for the overall precision, 89.71% for the overall sensitivity, and 93.01% for the overall F1-score across all four classification experiments. The model proposed in this paper shows excellent performance, with 24 dB, 18 dB, and 12 dB signal-to-noise ratios.

Matrix-based project dataset parsers

There are several existing project datasets, which involve separate data sources for simulated and real projects, individual and multiprojects, and single- and multimodal attributes. In addition, their file structures are heterogeneous; therefore, scholars can usually use only one dataset to test a proposed scheduling or resource allocation algorithm. Since the internal structures of these projects are also very different, it is difficult to ensure that an algorithm optimized for a given type of project will also perform well on projects with other structures. The proposed parsing method supports researchers in:•reading several types of projects: simulated, real, individual, and multiprojects, as well as single- and multimodal attributes;•considering the priorities of activities and the flexibility of their dependencies, which is essential for modeling the structural flexibility employed by agile, hybrid, and extreme project management approaches;•building a large project database for testing and comparing different scheduling and resource allocation algorithms.

Separation and Extraction of Compound-Fault Signal Based on Multi-Constraint Non-Negative Matrix Factorization.

To solve the separation of multi-source signals and detect their features from a single channel, a signal separation method using multi-constraint non-negative matrix factorization (NMF) is proposed. In view of the existing NMF algorithm not performing well in the underdetermined blind source separation, the β-divergence constraints and determinant constraints are introduced in the NMF algorithm, which can enhance local feature information and reduce redundant components by constraining the objective function. In addition, the Sine-bell window function is selected as the processing method for short-time Fourier transform (STFT), and it can preserve the overall feature distribution of the original signal. The original vibration signal is first transformed into time-frequency domain with the STFT, which describes the local characteristic of the signal from the time-frequency distribution. Then, the multi-constraint NMF is applied to reduce the dimensionality of the data and separate feature components in the low dimensional space. Meanwhile, the parameter WK is constructed to filter the reconstructed signal that recombined with the feature component in the time domain. Ultimately, the separated signals will be subjected to envelope spectrum analysis to detect fault features. The simulated and experimental results indicate the effectiveness of the proposed approach, which can realize the separation of multi-source signals and their fault diagnosis of bearings. In addition, it is also confirmed that the proposed method, juxtaposed with the NMF algorithm of the traditional objective function, is more applicable for compound fault diagnosis of the rotating machinery.

Implementation of Sound Direction Detection and Mixed Source Separation in Embedded Systems.

In recent years, embedded system technologies and products for sensor networks and wearable devices used for monitoring people's activities and health have become the focus of the global IT industry. In order to enhance the speech recognition capabilities of wearable devices, this article discusses the implementation of audio positioning and enhancement in embedded systems using embedded algorithms for direction detection and mixed source separation. The two algorithms are implemented using different embedded systems: direction detection developed using TI TMS320C6713 DSK and mixed source separation developed using Raspberry Pi 2. For mixed source separation, in the first experiment, the average signal-to-interference ratio (SIR) at 1 m and 2 m distances was 16.72 and 15.76, respectively. In the second experiment, when evaluated using speech recognition, the algorithm improved speech recognition accuracy to 95%.

The Preparation and Properties of a Hydrogen-Sensing Field-Effect Transistor with a Gate of Nanocomposite C-Pd Film

The objective of this paper is to evaluate the effect of a nanostructured C-Pd film deposited in the gate area of a field-effect transistor (FET) with a carbon–palladium composite gate (C-Pd/FET) on the hydrogen-sensing properties of the transistor. The method of preparing a field-effect transistor (FET) with a C-Pd film deposited as a gate and the properties of such a transistor and the film itself are presented. The C-Pd film deposited by PVD method on the gate area serves as an active layer. The PVD process was carried out in a dynamic vacuum of 10−5 mbar from two separated sources—one containing fullerenes (C60) and the other containing palladium acetate. Scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS, EDX) and electrical property studies were used to the characterize C-Pd films and FET/C-Pd structures. SEM observations revealed the topography of C-Pd films and FET/C-Pd transistors. EDS/EDX microanalysis was applied to visualize the arrangement of elements on the studied surfaces. The changes in electrical properties (resistance and relative resistance) due to the presence of hydrogen were studied in a designed and computerized experimental set-up. The enhanced properties of the FET/C-Pd transistor are demonstrated in terms of hydrogen detection.

Separation of ventilation and perfusion of electrical impedance tomography image streams using multi-dimensional ensemble empirical mode decomposition

Objective. In the future, thoracic electrical impedance tomography (EIT) monitoring may include continuous and simultaneous tracking of both breathing and heart activity. However, an effective way to decompose an EIT image stream into physiological processes as ventilation-related and cardiac-related signals is missing.Approach. This study analyses the potential of Multi-dimensional Ensemble Empirical Mode Decomposition by application of the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and a novel frequency-based combination criterion for detrending, denoising and source separation of EIT image streams, collected from nine healthy male test subjects with similar age and constitution.Main results. In this paper, a novel approach to estimate the lung, the heart and the perfused regions of an EIT image is proposed, which is based on the Root Mean Square Error between the index of maximal respiratory and cardiac variation to their surroundings. The summation of the indexes of the respective regions reveals physiologically meaningful time signals, separated into the physiological bandwidths of ventilation and heart activity at rest. Moreover, the respective regions were compared with the relative thorax movement and photoplethysmogram (PPG) signal. In linear regression analysis and in the Bland–Altman plot, the beat-to-beat time course of both the ventilation-related signal and the cardiac-related signal showed a high similarity with the respective reference signal.Significance. Analysis of the data reveals a fair separation of ventilatory and cardiac activity realizing the aimed source separation, with optional detrending and denoising. For all performed analyses, a feasible correlation of 0.587 to 0.905 was found between the cardiac-related signal and the PPG signal.