Blind Source Separation Method Research Articles

Spatial decomposition of ultrafast ultrasound images to identify motor unit activity – A comparative study with intramuscular and surface EMG

The smallest voluntarily controlled structure of the human body is the motor unit (MU), comprised of a motoneuron and its innervated fibres. MUs have been investigated in neurophysiology research and clinical applications, primarily using electromyographic (EMG) techniques. Nonetheless, EMG (both surface and intramuscular) has a limited detection volume. A recent alternative approach to detect MUs is ultrafast ultrasound (UUS) imaging. The possibility of identifying MU activity from UUS has been shown by blind source separation (BSS) of UUS images, using optimal separation spatial filters. However, this approach has yet to be fully compared with EMG techniques for a large population of unique MU spike trains. Here we identify individual MU activity in UUS images using the BSS method for 401 MU spike trains from eleven participants based on concurrent recordings of either surface or intramuscular EMG from forces up to 30% of the maximum voluntary contraction (MVC) force. We assessed the BSS method’s ability to identify MU spike trains from direct comparison with the EMG-derived spike trains as well as twitch areas and temporal profiles from comparison with the spike-triggered-averaged UUS images when using the EMG-derived spikes as triggers. We found a moderate rate of correctly identified spikes (53.0 ± 16.0%) with respect to the EMG-identified firings. However, the MU twitch areas and temporal profiles could still be identified accurately, including at 30% MVC force. These results suggest that the current BSS methods for UUS can accurately identify the location and average twitch of a large pool of MUs in UUS images, providing potential avenues for studying neuromechanics from a large cross-section of the muscle. On the other hand, more advanced methods are needed to address the convolutive and partly non-linear summation of velocities for recovering the full spike trains.

Tracking gaze position from EEG: Exploring the possibility of an EEG-based virtual eye-tracker.

Ocular artifact has long been viewed as an impediment to the interpretation of electroencephalogram (EEG) signals in basic and applied research. Today, the use of blind source separation (BSS) methods, including independent component analysis (ICA) and second-order blind identification (SOBI), is considered an essential step in improving the quality of neural signals. Recently, we introduced a method consisting of SOBI and a discriminant and similarity (DANS)-based identification method, capable of identifying and extracting eye movement-related components. These recovered components can be localized within ocular structures with a high goodness of fit (>95%). This raised the possibility that such EEG-derived SOBI components may be used to build predictive models for tracking gaze position. As proof of this new concept, we designed an EEG-based virtual eye-tracker (EEG-VET) for tracking eye movement from EEG alone. The EEG-VET is composed of a SOBI algorithm for separating EEG signals into different components, a DANS algorithm for automatically identifying ocular components, and a linear model to transfer ocular components into gaze positions. The prototype of EEG-VET achieved an accuracy of 0.920° and precision of 1.510° of a visual angle in the best participant, whereas an average accuracy of 1.008°±0.357° and a precision of 2.348°±0.580° of a visual angle across all participants (N=18). This work offers a novel approach that readily co-registers eye movement and neural signals from a single-EEG recording, thus increasing the ease of studying neural mechanisms underlying natural cognition in the context of free eye movement.

Study of modeling questions in a first-year university mathematics online course

The training of non-specialists, particularly engineers, in mathematics requires designing specific didactic proposals that make the importance of mathematics evident. One approach to creating such proposals consists in analyzing the mathematics used in authentic contexts of engineering research and then effectuating a didactic transposition to mathematics teaching. To this end, in this research, we use elements of the anthropological theory of the didactic and the methodology of didactic engineering. Initially, we analyze the blind source separation method, a case of inverse modeling widely used in numerous engineering contexts (e.g., telecommunications, acoustics, geophysics, biosignal analysis). More specifically, we examine the algorithm based on the Amathbf{x}=mathbf{b} matrix model and its use in a signal processing context. Based on this analysis, we designed a didactic device that focuses the study on a simulated signal mixture of pure tones and implemented it in two first-year university mathematics courses in the virtual modality. This article reports the results of the students’ first approximation to mathematical modeling activity in a setting of authentic research in engineering using a blind source separation method.

Improvement of independent vector analysis for closely spaced sources

Independent vector analysis (IVA) is one of the most widely-used blind source separation methods. Theoretically, its performance is not affected by the location of the sound source, however, in practical applications with the presence of diffuse noise, the separation performance severely degrades when sources are closely spaced. In this technical note, the reason for this deterioration is explored and an effective modification of IVA cost function is proposed to compensate for the separation performance in closely-spaced source scenarios. Numerous experiments validate the effectiveness of the proposed method with its application to auxiliary function-based IVA.

An Improved Underdetermined Blind Source Separation Method for Insufficiently Sparse Sources

An Improved Underdetermined Blind Source Separation Method for Insufficiently Sparse Sources

DWT-BSS: Blind Source Separation applied to EEG signals by extracting wavelet transform’s approximation coefficients

The Electroencephalogram (EEG) signal is widely contaminated by a physiological artifact, such as muscle activity, heart rhythm, and eye movement. The researcher has proposed a number of methods to clean the EEG signal. A group of these methods is called Blind Source Separation (BSS). In this paper, we suggest an approach that combines the BSS methods and the Discrete Wavelet Transform (DWT) algorithm, in order to evaluate the BSS methods after applying them to the approximation coefficients extracted using the DWT. The aim of this work is to identify which BSS algorithms, using which family of wavelet and at which decomposition level, would provide excellent performance. We used the Spearman Correlation Coefficient (SCC) to rate our methods. The technique that performs the best, as evaluated by the SCC between the generated component and the approximation coefficient obtained from the Horizontal EOG results, is AMICA, which obtains a value of 0.81 for levels 2 while using the wavelet symlet at scales 7 and 11. With a value of 0.70 and the use of the wavelet Daubechies at scale 9 and Coiflets at scales 2 and 5 for level 1, AMICA also has the best SCC value calculated between the separated component and the approximation coefficient recovered from the Vertical EOG. While employing the wavelet symlets at scales 5, 7, 8, and 11. for level 2, and level 3 when using the wavelet symlets at scales 1 and 2.

Detection of Jamming Attacks via Source Separation and Causal Inference

Jamming attacks to hinder communication capabilities are becoming a critical aspect of wireless networks. A challenging issue is the detection of reactive jammers that perform spectrum sensing and attack the network only when legitimate communication is in progress. In this scenario, we introduce a novel framework for reactive jamming detection using a patrol of radio-frequency (RF) sensors external to the network to be protected. The solution relies on two key components: i) a novel underdetermined blind source separation (UBSS) method that, starting from the signal mixtures observed by the RF patrollers, is capable of separating the jamming temporal profile from the network nodes’ transmission profiles; ii) a new jamming detection based on causal inference called all-versus-one transfer entropy (AvOTE). The framework is then applied to a case study where the victim network is a Long Range (LoRa)-based internet of things (IoT) system with star topology. The solution outperforms a state-of-the-art method and an approach that attempts to find the causal relationship via time series correlation, exhibiting very good performance in the presence of shadowing. Indeed, a detection probability of 90% is achieved with a false alarm probability of 6% in the presence of nuisances such as collisions and severe shadowing.

A novel physiological signal denoising method coupled with multispectral adaptive wavelet denoising(MAWD) and unsupervised source counting algorithm(USCA)

In order to improve the quality of physiological signals, a combined study of blind source separation and wavelet thresholding methods was conducted, resulting in the proposal of a multispectral adaptive wavelet denoising (MAWD) method. This method was employed in conjunction with an improved unsupervised source counting algorithm (USCA). To evaluate the effectiveness of the proposed approach, three methods were used to calculate signal-to-noise ratio (SNR) and root mean square error (RMSE): soft thresholding, hard thresholding, and adaptive thresholding. The results demonstrated that the proposed method exhibited strong applicability under soft thresholding. Specifically, compared to hard thresholding, the enhanced signal using soft thresholding showed an approximately 44.2% increase in SNR and a 28.8% decrease in RMSE, along with a 1.4% reduction in processing time. Moreover, when compared to adaptive thresholding, soft thresholding exhibited approximately 706% improvement in SNR, a 16.7% decrease in RMSE, and a 3.0% reduction in processing time. Multiple experiments were conducted to determine the optimal peak detection threshold range for USCA, which was found to be within the interval [0.001, 0.0001]. This range facilitated the separation of more sources, thereby enhancing the separation effectiveness and accuracy. To substantiate the effectiveness of the USCA method, tests were conducted on publicly available datasets of EMG, ECG, and EEG signals, all of which consistently demonstrated the advantages of this approach. Data AvailabilityThe authors do not have permission to share data.

Investigation of Modal Identification of Frame Structures Using Blind Source Separation Technique Based on Vibration Data

This paper investigates system identification algorithms for modal identification of frame structures, such as a suspension bridge and an overhead transmission line-crossing frame, using ambient vibration measurements. The modal identification procedures include two novel blind source separation (BSS) algorithms, complexity pursuit method (CP) and generalized eigen decomposition method (GED), based on modern signal processing technology. Here, the frequency response function (FRF) method is introduced as an important reference to verify the effectiveness of the CP algorithm and GED algorithm. The effectiveness and accuracy of both types of algorithms are verified by numerical simulations and experiments on a suspension bridge. In addition, an engineering application of these two BSS methods is successfully implemented in an overhead transmission line-crossing frame. The results show that the two novel BSS learning rules (CP and GED) are capable of successfully identifying modal parameters of the civil structure under ambient excitation.

LOCUS: A REGULARIZED BLIND SOURCE SEPARATION METHOD WITH LOW-RANK STRUCTURE FOR INVESTIGATING BRAIN CONNECTIVITY.

Network-oriented research has been increasingly popular in many scientific areas. In neuroscience research, imaging-based network connectivity measures have become the key for understanding brain organizations, potentially serving as individual neural fingerprints. There are major challenges in analyzing connectivity matrices, including the high dimensionality of brain networks, unknown latent sources underlying the observed connectivity, and the large number of brain connections leading to spurious findings. In this paper we propose a novel blind source separation method with low-rank structure and uniform sparsity (LOCUS) as a fully data-driven decomposition method for network measures. Compared with the existing method that vectorizes connectivity matrices ignoring brain network topology, LOCUS achieves more efficient and accurate source separation for connectivity matrices using low-rank structure. We propose a novel angle-based uniform sparsity regularization that demonstrates better performance than the existing sparsity controls for low-rank tensor methods. We propose a highly efficient iterative node-rotation algorithm that exploits the block multiconvexity of the objective function to solve the nonconvex optimization problem for learning LOCUS. We illustrate the advantage of LOCUS through extensive simulation studies. Application of LOCUS to Philadelphia Neurodevelopmental Cohort neuroimaging study reveals biologically insightful connectivity traits which are not found using the existing method.

The Single-channel blind source separation based on VMD and Tukey M estimation for rolling bearing composite fault diagnosis

Rolling bearing is one of the core components in rotating machinery, and its running status directly affects the operation of the whole equipment. Faults of rolling bearings in the actual working process are often multiple faults. To effectively separate fault sources, the blind source separation method is used for the compound fault diagnosis of rolling bearings. Because of the impact of the number of artificially limited decompositions and quadratic penalty factor on VMD in the decomposition process, and the slow convergence and low accuracy in the objective function of traditional FastICA operation, the VMD algorithm based on the energy loss coefficient and the information entropy is proposed, which adaptively determines the number of modal components and the quadratic penalty factor; The Tukey M estimation is selected as the objective convergence function of the FastICA algorithm to improve its robustness. First, VMD is used to decompose the signal; Secondly, the original signal and the decomposed IMF component are reconstructed, the covariance matrix and the singular value decomposition are constructed, the number of fault sources is estimated by the proximity dominance method, and the decomposed IMF components are filtered through correlation analysis and kurtosis index to build a multi-channel feature set; Finally, the constructed multi-channel feature set is input to the FastICA algorithm based on the Tukey M estimation for the separation of fault source signals to achieve composite fault diagnosis. The compound fault experiment shows that the proposed method in this paper can effectively realize the blind source separation of rolling bearing fault features to realize the compound fault diagnosis in different positions.

Underdetermined Blind Source Separation Method Based on a Two-Stage Single-Source Point Screening

Underdetermined blind source separation is a signal processing technique that is more suitable for practical applications and aims to separate the source signals from the mixed signals. The mixing matrix estimation is a major step in the underdetermined blind source separation. Since the current methods for estimating the mixing matrix have the disadvantages of insufficient accuracy or weak noise immunity, a two-stage single-source point screening that combines the cosine angle algorithm and the L1-norm optimization algorithm is proposed. During the first stage, the first-stage single-source points are extracted from the original mixed signals using the cosine angle algorithm. During the second stage, based on the L1-norm optimization algorithm, the reference single-source points are extracted from the original mixed signals. The reference single-source points are then clustered to obtain the clustering center, which is defined as the reference center. In combination with the reference center, the deviation and interference points in the first-stage single-source points are eliminated by the cosine distance. The remaining signal points are considered as the second-stage single-source points, which are clustered to obtain the mixing matrix estimation. Experiments on simulated and speech signals show that the proposed method can obtain more accurate and robust mixing matrix estimation, leading to better separation of the source signals.

Construction of semi-supervised spatial projections to identify the source of beta- and high frequency oscillations in Parkinson's disease.

Traditional deep brain stimulation (DBS) treatment for Parkinson's disease (PD) targets the placement of DBS leads into subthalamic nucleus (STN). Extraction of neurobiomarkers from STN local field potential activity can be used for the optimization of DBS. Beta (12-30 Hz) and high frequency oscillations (200-450 Hz, HFO) of STN and their phase-amplitude coupling have been previously correlated with symptom severity in PD. The typical approach is to take bipolar derivations of electrode contacts in order to enhance recordings of local brain activity and suppress noise levels. This approach can often cancel the signals in correlated neighboring contacts and create ambiguity in which monopolar contact to select for the identification of the main source of the oscillatory signal. To improve local specificity and help identify the source of beta and HFO in terms of electrode contact, we propose a semi supervised blind-source separation method. This approach presents a novel perspective to investigate electrophysiology by projecting the recorded channels into a subspace of virtual channels. We show the contribution of each channel to the identified source and correlate the spatial information with imaging and postoperative programming parameters. We anticipate such a source identification strategy can be used in the future to investigate the distribution of beta and HFO on individual contacts of the DBS lead and can improve the interpretation of these signals.

Automatic Optimization of Multichannel Electrode Configurations for Robust Fetal Heart Rate Detection by Blind Source Separation.

Fetal heart rate (fHR) evaluation is fundamental to guarantee timely medical intervention in case of pregnancy complications. Due to the limitations of traditional cardiotocography, multichannel electrophysiological recording was proposed as a viable alternative, which requires Blind Source Separation (BSS) techniques. Yet effective and reliable separation of the fetal ECG remains challenging due to multiple noise sources and the effects of varying fetal position. In this work, we demonstrate that the adopted electrode configuration plays a key role in the effectiveness of BSS and propose guidelines for optimal electrode positioning. Moreover, a model is proposed to automatically predict the most suited configuration for accurate BSS-based fHR estimation with a minimal number of leads, to facilitate practical implementation. We compared fHR estimation accuracy with different electrode configurations on in-silico data, identifying the optimal configuration for a recent BSS method. Based on features extracted from raw signals, we proposed a support vector regression model to automatically identify the best electrode configuration in terms of fHR estimation accuracy and to dynamically adjust it to varying fetal presentation. Evaluation was performed on real and synthetic data. Guidelines for the optimal electrode configuration are proposed by using 4 leads. Prediction of configuration quality shows 80.9% accuracy; the optimal configurat- ion is recognized in 92.2% of the subjects. The proposed method successfully predicts the quality of the configurations, demonstrating the impact of the electrode configuration on the BSS performance. The method holds potential for long-term fetal monitoring, by dynamically choosing the optimal configuration.

An Evaluation of Non-Contact Photoplethysmography-Based Methods for Remote Respiratory Rate Estimation.

The respiration rate (RR) is one of the physiological signals deserving monitoring for assessing human health and emotional states. However, traditional devices, such as the respiration belt to be worn around the chest, are not always a feasible solution (e.g., telemedicine, device discomfort). Recently, novel approaches have been proposed aiming at estimating RR in a less invasive yet reliable way, requiring the acquisition and processing of contact or remote Photoplethysmography (contact reference and remote-PPG, respectively). The aim of this paper is to address the lack of systematic evaluation of proposed methods on publicly available datasets, which currently impedes a fair comparison among them. In particular, we evaluate two prominent families of PPG processing methods estimating Respiratory Induced Variations (RIVs): the first encompasses methods based on the direct extraction of morphological features concerning the RR; and the second group includes methods modeling respiratory artifacts adopting, in the most promising cases, single-channel blind source separation. Extensive experiments have been carried out on the public BP4D+ dataset, showing that the morphological estimation of RIVs is more reliable than those produced by a single-channel blind source separation method (both in contact and remote testing phases), as well as in comparison with a representative state-of-the-art Deep Learning-based approach for remote respiratory information estimation.

Underdetermined Blind Source Separation Method for Speech Signals Based on SOM-DPC and Compressed Sensing

Underdetermined blind source separation has received increasing attention in recent years as an effective method for speech-signal processing. Hence, a self-organizing mapping-density peak clustering and compressed sensing approach, which is a two-step approach, is proposed herein to improve the accuracy of underdetermined blind source separation. The approach features the following two aspects: (1) A mixing matrix estimation method based on self-organizing mapping and density peak clustering, which can intuitively determine the number of source signals, remove outliers, and determine the column vector of the mixing matrix based on local density; (2) a compressed sensing-based source signal reconstruction method, which can exploit the sparsity of signals in the frequency domain and use a hierarchical coupling method to reconstruct the source signal accurately and efficiently under the premise that the prior knowledge of the signal is unknown. The proposed method does not require the number of source signals and exhibits excellent performance under different noise conditions. Theoretical analysis and experimental results demonstrate the effectiveness of the proposed method.

Extracting the Invisible: Mesial Temporal Source Detection in Simultaneous EEG and SEEG Recordings.

Epileptic source detection relies mainly on visual expertise of scalp EEG signals, but it is recognised that epileptic discharges can escape to this expertise due to a deep localization of the brain sources that induce a very low, even negative, signal to noise ratio. In this methodological study, we aimed to investigate the feasibility of extracting deep mesial temporal sources that were invisible in scalp EEG signals using blind source separation (BSS) methods (infomax ICA, extended infomax ICA, and JADE) combined with a statistical measure (kurtosis). We estimated the effect of different methodological and physiological parameters that could alter or improve the extraction. Using nine well-defined mesial epileptic networks (1949 spikes) obtained from seven patients and simultaneous EEG-SEEG recordings, the first independent component extracted from the scalp EEG signals was validated in mean from 46 to 80% according to the different parameters. The three BSS methods equally performed (no significant difference) and no influence of the number of scalp electrodes used was found. At the opposite, the number and amplitude of spikes included in the averaging before the extraction modified the performance. Anyway, despite their invisibility in scalp EEG signals, this study demonstrates that deep source extraction is feasible under certain conditions and with the use of common signal analysis toolboxes. This finding confirms the crucial need to continue the signal analysis of scalp EEG recordings which contains subcortical signals that escape to expert visual analysis but could be found by signal processing.

The Influence Assessment of Artifact Subspace Reconstruction on the EEG Signal Characteristics

EEG signals may be affected by physiological and non-physiological artifacts hindering the analysis of brain activity. Blind source separation methods such as independent component analysis (ICA) are effective ways of improving signal quality by removing components representing non-brain activity. However, most ICA-based artifact removal strategies have limitations, such as individual differences in visual assessment of components. These limitations might be reduced by introducing automatic selection methods for ICA components. On the other hand, new fully automatic artifact removal methods are developed. One of such method is artifact subspace reconstruction (ASR). ASR is a component-based approach, which can be used automatically and with small calculation requirements. The ASR was originally designed to be run not instead of, but in addition to ICA. We compared two automatic signal quality correction approaches: the approach based only on ICA method and the approach where ASR was applied additionally to ICA and run before the ICA. The case study was based on the analysis of data collected from 10 subjects performing four popular experimental paradigms, including resting-state, visual stimulation and oddball task. Statistical analysis of the signal-to-noise ratio showed a significant difference, but not between ICA and ASR followed by ICA. The results show that both methods provided a signal of similar quality, but they were characterised by different usabilities.

Toward a generalizable deep CNN for neural drive estimation across muscles and participants

Objective. High-density electromyography (HD-EMG) decomposition algorithms are used to identify individual motor unit (MU) spike trains, which collectively constitute the neural code of movements, to predict motor intent. This approach has advanced from offline to online decomposition, from isometric to dynamic contractions, leading to a wide range of neural-machine interface applications. However, current online methods need offline retraining when applied to the same muscle on a different day or to a different person, which limits their applications in a real-time neural-machine interface. We proposed a deep convolutional neural network (CNN) framework for neural drive estimation, which takes in frames of HD-EMG signals as input, extracts general spatiotemporal properties of MU action potentials, and outputs the number of spikes in each frame. The deep CNN can generalize its application without retraining to HD-EMG data recorded in separate sessions, muscles, or participants. Approach. We recorded HD-EMG signals from the vastus medialis and vastus lateralis muscles from five participants while they performed isometric contractions during two sessions separated by ∼20 months. We identified MU spike trains from HD-EMG signals using a convolutive blind source separation (BSS) method, and then used the cumulative spike train (CST) of these MUs and the HD-EMG signals to train and validate the deep CNN. Main results. On average, the correlation coefficients between CST from the BSS and that from deep CNN were for leave-one-out across-sessions-and-muscles validation and for leave-one-out across-participants validation. When trained with more than four datasets, the performance of deep CNN saturated at for cross validations across muscles, sessions, and participants. Significance. We can conclude that the deep CNN is generalizable across the aforementioned conditions without retraining. We could potentially generate a robust deep CNN to estimate neural drive to muscles for neural-machine interfaces.

Statistically Dependent Blind Signal Separation under Relaxed Sparsity

Most traditional blind source separation (BSS) methods are based on the basic assumption that source signals are mutually independent. However, many signals in the real world are often interrelated to each other. In this paper, a novel BSS method is proposed for dependent signals which only relies on the relaxed sparsity of sources. Under this constraint, the column vector of high-dimensional observed signals would be distributed in a specific subspace. According to the representation relation in time-frequency (TF) domain, each column vector of observed signal is uniquely clustered into the subspace, to which it belongs. Furthermore, the estimation of source signals is calculated by the inverse matrix or the pseudo-inverse matrix of the mixing matrix. It is also demonstrated mathematically and experimentally that under relaxed sparsity conditions, proposed subspace clustering methods is promising and hopeful to solve the dependent BSS (DBSS) problems.