Blind Source Separation Research Articles

Use of a rugged mid-infrared spectrometer for in situ process analysis of liquids

The widespread application of mid-infrared (MIR) spectroscopy for process monitoring is currently limited by the poor transmission of MIR light through fibre optics. In this work, the performance of a novel and robust MIR spectrometer has been evaluated for practical deployment in a pilot plant or production environment. The spectrometer utilises a Sagnac interferometer design containing no moving parts and is directly attached to an attenuated total reflectance probe, eliminating the need for fibre optics. The quantitative performance of the spectrometer for the in situ analysis of ternary solvent mixtures was assessed. The predictions obtained by partial least squares were accurate (root mean square error of prediction of < 1% w/w) and comparable to those of a benchmark Michelson-based spectrometer with a fibre-coupled probe, which is more amenable to process development in a laboratory or pilot plant. Calibration transfer between the two spectrometers was performed using the spectral space transformation method to mimic the scenario of the scale-up of a process from the laboratory to pilot scale or from a pilot plant to production scale, where the two different MIR instruments might be deployed. The ability to perform in situ reaction monitoring with the robust Sagnac-based spectrometer was then demonstrated. Spectra acquired during an esterification reaction were resolved using multivariate curve resolution, to produce concentration profiles of each component. These results demonstrate the suitability of this rugged spectrometer for quantitative in situ monitoring of liquid processes, opening up new opportunities for process monitoring in the MIR region.

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.

Complex emotion processing and early life adversity in the Healthy Brain Network sample

ObjectiveEarly life adversity (ELA) has shown to have negative impacts on mental health. One possible mechanism is through alterations in neural emotion processing. We sought to characterize how multiple indices of ELA were related to naturalistic neural socio-emotional processing. MethodIn 521 5–15-year-old participants from the Healthy Brain Network Biobank, we identified scenes that elicited activation of the Default Mode Network (DMN), Ventral Attention Network (VAN), Cingulo-Opercular Network (CON) and amygdala, all of which are networks shown to be associated with ELA. We used linear regression to examine associations between activation and ELA: negative parenting, social status, financial insecurity, neighborhood disadvantage, negative experiences, and parent psychopathology. ResultsWe found DMN, VAN, CON and amygdala activation during sad/emotional, bonding, action, conflict, sad, or fearful scenes. Greater inconsistent discipline was associated with greater VAN activation during sad or emotional scenes. ConclusionFindings suggest that the DMN, VAN, CON networks and the amygdala support socio-emotional processing consistent with prior literature. Individuals who experienced inconsistent discipline may have greater sensitivity to parent–child separation signals. Since no other ELA–activation associations were found, it is possible that unpredictability may be more strongly associated with complex neural emotion processing than socio-economic status or negative life events.

Analytical Figures of Merit in Univariate, Multivariate, and Multiway Calibration: What Have We Learned? What Do We Still Need to Learn?

ABSTRACTAn overview of the status of the research in analytical figures of merit is provided, including all calibration scenarios from univariate to multivariate and multiway analytical protocols. Both linear and nonlinear multivariate models are considered. Starting with the simplest multivariate model, inverse least‐squares regression, the basic concepts of sensitivity, sample leverage, and limit of detection are introduced. The extension to other multivariate models is discussed, as well as to nonlinear models based on radial basis functions, kernel partial least‐squares, and multilayer feed‐forward artificial neural networks. Finally, multiway calibration models are discussed, including multilinear decomposition models such as parallel factor analysis (PARAFAC) and multivariate curve resolution–alternating least‐squares (MCR‐ALS). In the latter case, recent developments concerning the pervasive phenomenon of rotational ambiguity are discussed. Unfinished works and areas where further research efforts are needed to develop closed‐form expressions and to fully understand their meaning are included.

A Mobius transformation-based liftoff effect reduction method for crack classification and prediction in eddy current testing

In eddy current (EC) defect evaluation, accurate determination of the crack depth is crucial. The lift-off signal on the complex impedance plane is not necessarily horizontal and mostly arc-shaped, which makes it difficult to separate from crack signals, which can have various orientations depending on probe characteristics and frequencies. Phase rotation is normally used to align the lift-off signal to the real axis and defect signal is read from the imaginary axis. However, this approach proves challenging to separate lift-off and defect signals within the complex plane in many cases.To address this issue, this study proposes and implements a Mobius transformation that linearizes the arc-shaped lift-off signals on the complex plane, enabling more accurate extraction of crack signals unaffected by lift-off signal height. Furthermore, it is demonstrated through k-nearest neighbors (kNN) that the transformed crack signals can still be effectively quantified.

A Highly Sensitive, Conductive, and Flexible Hydrogel Sponge as a Discriminable Multimodal Sensor for Deep‐Learning‐Assisted Gesture Language Recognition

AbstractFlexible multimodal sensors have gained increasing popularity for applications in healthcare and extreme environment operations owing to their all‐around environmental perception and data acquisition capabilities. However, fabricating a magnetism‐mechanics‐humidity multimodal sensor that possesses high sensitivity without signal overlapping while in a facile methodology remains a great challenge. Herein, a highly sensitive, conductive, and flexible hydrogel sponge sensor with discriminable magnetism, mechanics, and humidity sensing capability is proposed, which shows stable pore size (19.30 µm) and satisfactory mechanical properties based on the synergistic hydrogen bonding among sodium alginate, poly(vinyl alcohol) and glycerol. The proposed sensors can not only display favorable humidity sensing ability with rapid response/recovery time (2.5/4 s) but also possess enhanced sensitivities (a gauge factor of 0.46 T−1 for magnetic field, −1.16 kPa−1 for pressure), superior stability and durability (over 8000 cycles). Benefiting from the separated capacitive and resistive response signals, the sensors can precisely distinguish the magnetic, mechanical, and humidity stimuli without cross‐talk. Further, the sensor arrays assisted by the deep learning algorithm are developed to realize gesture language recognition with a high accuracy of 99.17%. It can be believed that this high‐performance sensor will have good prospects in future soft electronics and human‐machine interaction systems.

Self‐Powered Wearable Pressure Sensors for Detection and Separation of Signals for Various Human Movements

A detailed study on the dynamic response of mountable pressure sensors is presented, with a focus on foot pressure sensors integrated with carbon nanotube (CNT)‐coated cotton fibers. The research explores the sensor's sensitivity to pressure changes, repeatability, hysteresis, and durability through rigorous modeling and experimental validation. Computational simulations using Python and experimental data demonstrate the sensor's nonlinear conductance response to applied force, attributed to the varying contact area and number of contact points among the fibers. Long‐term outdoor exposure tests confirm the material's resilience, maintaining electrical conductivity and structural integrity. The study also demonstrates the sensor's ability to monitor human activities like walking, running, stair climbing, and jumping, as well as detecting muscle movements during swallowing, coughing, and speech, highlighting potential applications in health monitoring and artificial voice synthesis. The MRMR algorithm is used for feature selection to distinguish activities, demonstrating the sensor's potential for activity recognition. Additionally, a piezoelectric sensor on the pressure sensors estimates harvested electric power to power wearable devices. This work contributes to the advancement of self‐powered wearable pressure sensors to monitor real‐time human activity, with implications for healthcare, sports performance, and assistive technologies.

Small sample composite fault diagnosis of hydraulic bearings based on improved VME algorithm and mRVM

The working environment of rolling bearings is complex. Once a fault occurs, various parts will affect each other and produce a compound fault. Traditional methods often use signal separation algorithms to separate different types of signals for fault diagnosis, but it is difficult to analyze specific faults efficiently and accurately. To solve this problem, this paper combines variational mode decomposition (VMD), Laplace energy index (LE) and variational mode extraction (VME) for signal extraction. Multi-class relevance vector machine (mRVM) and DS evidence theory are used for intelligent fault diagnosis, focusing on the context of small sample data. First, the VMD-LE-VME method is used to extract effective fault information from the fault signal and obtain multi-domain features. Then, the multi-domain features are input into mRVM for fault identification. Finally, the classification results are fused through DS evidence theory to obtain the final classification results. The effectiveness and superiority of this method in processing small sample data are verified by experiments.

Evaluation of new Li2CaSiO4:Eu/ scintillation plastic phoswich for combined alpha-beta and gamma-neutron detectors

A phoswich-type detector element based on a new light inorganic scintillation material, Li2CaSiO4:Eu2+, and a plastic scintillator, EJ-200, was evaluated for separation of signals of neutrons, β-, α-particles and γ-rays. It has been shown that the use of scintillators in a phoswich with a quite large difference in the scintillation kinetics, by two orders of magnitude, despite the effect of excitation of inorganic material luminescence by scintillation of plastic, provides reliable discrimination of signals from the layers of the phoswich detector. The developed approach to constructing a detecting element can find applications for discrimination of α- and β-particles, as well as neutrons and γ-rays in combined α/β and γ-neutron detectors for radiometry and dosimetry. The separation of signals and measurement of the response when recording interaction products in the reverse β-decay reaction are of particular interest.

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.

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.

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.

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.

Systematic optimization of UCNPs-LFA for Helicobacter pylori nucleic acid detection at point-of-care.

Helicobacter pylori (Hp) prevail globally as the primary cause of gastritis, gastric ulcer, and potential gastric cancer, highlighting the need for rapid and precise point-of-care (POC) detection of Hp nucleic acid. Upconversion nanoparticle-based lateral flow assay (UCNPs-LFA) exhibit great potential in POC detection, due to their high optical stability and absence of background fluorescence. However, insufficient sensitivity for nucleic acid detection remains a key challenge. This study systematically optimizes UCNPs-LFA by focusing on target capture, signal transduction, signal separation, and signal analysis, to enhance its detection capabilities for Hp nucleic acid. The optimized UCNPs-LFA platform features a significantly decreased detection limit, a broadened detection range, and high reliability. Results demonstrate that the limit of detection (LOD) is 25 fM, a 105-fold improvement over the initial platform. This systematic optimization strategy is versatile and can be applied to optimize other nanoparticle-based LFAs.

Identification methodology for MIMO Hammerstein nonlinear model with process noise

In this paper, we present a methodology for identifying the multi-input–multi-output (MIMO) Hammerstein nonlinear model under colored noise. The Hammerstein model presented comprises neural fuzzy models (NFMs) as its static nonlinear block and rational transfer functions (RTF) model as its dynamic linear block. The hybrid signals consisting of separable signals and random signals are utilized to deal with the MIMO Hammerstein model identification issue, and the separable signals to implement separation identification of MIMO Hammerstein model is introduced, that is, the two blocks are separately identified. First, parameters of the linear block are estimated applying correlation function-based least squares method in the presence of measurable input–output of Gaussian signals, which can efficiently weaken the process noise interference. Second, estimate of noise parameters vector is introduced to solve the unknown noise vector in the information matrix, then a recursive extended least squares method is developed for identifying parameters of nonlinear block and colored noise model based on available input–output of random signals. The validity and precision of the presented methodology are demonstrated applying a numerical simulation and a nonlinear process, and it is known from the research results that compared with existing identification techniques, the methodology utilized achieved higher identification accuracy.

Nanozyme-Based Pump-free Microfluidic Chip for Colorectal Cancer Diagnosis via Circulating Cancer Stem Cell Detection.

Circulating cancer stem cells (CCSCs) are subpopulations of cancer cells with high tumorigenicity, chemoresistance, and metastatic potential, which are also major drivers of disease progression. Herein, to achieve the prediction of tumor diagnosis and progression in colorectal cancer (CRC), a new, automated, and portable lateral displacement patterned pump-free (LP) microfluidic chip (LP-chip) with the CoPt3 nanozyme was established for CCSC capture and detection in peripheral blood and feces samples ex vivo. In this design, CoPt3@HA probes with functions of magnetic separation and colorimetric signal transduction by peroxidase-mimicking activity were applied for the capture of CCSCs and signal output in clinical samples. The generated colors of polydopamine (PDA) were quantifiable through the smartphone APP and visualizable by the naked eye in the test line (T line) and control line (C line) of the LP-chip. In the optimal experimental conditions, the CCSC concentration was sensitive to change in the range 0-105 cells mL-1, with a detection limit of 3 cells mL-1 (S/N = 3). Preliminary studies of clinical samples suggest that the platform has the potential for prediction of colorectal cancer progression and poor prognosis. Overall, the LP-chip provides potential strategies for timely diagnosis, therapeutic monitoring, and recurrence prediction to improve home-based patient care.

A Non-Invasive Fetal QRS Complex Detection Method Based on a Multi-Feature Fusion Neural Network

Fetal heart monitoring, as a crucial part of fetal monitoring, can accurately reflect the fetus’s health status in a timely manner. To address the issues of high computational cost, inability to observe fetal heart morphology, and insufficient accuracy associated with the traditional method of calculating the fetal heart rate using a four-channel maternal electrocardiogram (ECG), a method for extracting fetal QRS complexes from a single-channel non-invasive fetal ECG based on a multi-feature fusion neural network is proposed. Firstly, a signal entropy data quality detection algorithm based on the blind source separation method is designed to select maternal ECG signals that meet the quality requirements from all channel ECG data, followed by data preprocessing operations such as denoising and normalization on the signals. After being segmented by the sliding window method, the maternal ECG signals are calculated as data in four modes: time domain, frequency domain, time–frequency domain, and data eigenvalues. Finally, the deep neural network using three multi-feature fusion strategies—feature-level fusion, decision-level fusion, and model-level fusion—achieves the effect of quickly identifying fetal QRS complexes. Among the proposed networks, the one with the best performance has an accuracy of 95.85% and sensitivity of 97%.

7324 Regulation of Super Enhancers by Phosphorylated Progesterone Receptors Drives Breast Cancer Stem Cell Expansion

Abstract Disclosure: N. Gillis: None. C.A. Lange: None. Current treatments for estrogen receptor (ER) positive breast cancer largely target rapidly dividing tumor cells. However, aggressive breast cancers often contain long-lived and weakly proliferative cancer stem cells (CSCs) that readily escape treatments aimed at cycling cells. We previously reported that progesterone receptors (PR) and their target genes aid the growth of these CSCs and help them evade anti-estrogen therapy. As proliferation and stemness are directed by separate signaling pathways that lead to the expression of distinct gene programs, it's crucial to understand how PR facilitates this cellular transformation at the genomic level. Establishing a gene expression program that may limit proliferation but encourages stemness requires coordination between transcription factors and their coregulators to alter the nuclear microenvironment and chromatin landscape.To reveal these mechanisms, we profiled PR and ER genomic binding using CUT&amp;RUN in the T47D luminal breast cancer cell line grown in ultra-low attachment (3D) mammosphere conditions. Our analysis of genomic binding profiles displayed a pattern of PR/ER co-occupancy at distant sites more than 10 kilobases away from the nearest transcriptional start site. We used Rank Ordering of Super Enhancer (ROSE) analysis on these PR/ER binding sites to predict which are likely super enhancer elements capable of coordinating the regulation of multi-gene subsets. We employed a genetic approach to directly test the function of novel enhancer sites linked to PR-target genes by disrupting the PR/ER binding with a dCas9-KRAB construct directed to the predicted enhancer elements. We propose that abnormal growth factor signaling in breast cancer cells permits PR/ER complex formation which promotes expression of genes that induce endocrine resistance and CSC expansion through regulation of super enhancer elements. Further studies to elucidate these mechanisms are ongoing. Understanding the intricacies of PR/ER crosstalk is the crucial next step in developing new therapies that target PR-driven processes in ER+ breast cancers. Presentation: 6/3/2024