Searcharxiv⌕ Search

arXiv subjects

Javier Escudero

Publications and source records attributed to Javier Escudero.

At least 37 records · Page 2Linked to original sources
arXiv2021

Higher order tensor decomposition for proportional myoelectric control based on muscle synergies

Muscle synergies have recently been utilised in myoelectric control systems. Thus far, all proposed synergy-based systems rely on matrix factorisation methods. However, this is limited in terms of task-dimensionality. Here, the potential application of higher-order tensor decomposition as a framework for proportional myoelectric control is demonstrated. A novel constrained Tucker decomposition (consTD) technique of synergy extraction is proposed for synergy-based myoelectric control model and compared with state-of-the-art matrix factorisation models. The extracted synergies were used to estimate control signals for the wrist's Degree of Freedom (DoF) through direct projection. The consTD model was able to estimate the control signals for each DoF by utilising all data in one 3rd-order tensor. This is contrast with matrix factorisation models where data are segmented for each DoF and then the synergies often have to be realigned. Moreover, the consTD method offers more information by providing additional shared synergies, unlike matrix factorisation methods. The extracted control signals were fed to a ridge regression to estimate the wrist's kinematics based on real glove data. The Coefficient of Determination (R2) for the reconstructed wrist position showed that the proposed consTD was higher than matrix factorisation methods. In sum, this study provides the first proof of concept for the use of higher-order tensor decomposition in proportional myoelectric control and it highlights the potential of tensors to provide an objective and direct approach to identify synergies.

eess.SP↗
arXiv2020

An Efficient Mixture of Deep and Machine Learning Models for COVID-19 and Tuberculosis Detection Using X-Ray Images in Resource Limited Settings

Clinicians in the frontline need to assess quickly whether a patient with symptoms indeed has COVID-19 or not. The difficulty of this task is exacerbated in low resource settings that may not have access to biotechnology tests. Furthermore, Tuberculosis (TB) remains a major health problem in several low- and middle-income countries and its common symptoms include fever, cough and tiredness, similarly to COVID-19. In order to help in the detection of COVID-19, we propose the extraction of deep features (DF) from chest X-ray images, a technology available in most hospitals, and their subsequent classification using machine learning methods that do not require large computational resources. We compiled a five-class dataset of X-ray chest images including a balanced number of COVID-19, viral pneumonia, bacterial pneumonia, TB, and healthy cases. We compared the performance of pipelines combining 14 individual state-of-the-art pre-trained deep networks for DF extraction with traditional machine learning classifiers. A pipeline consisting of ResNet-50 for DF computation and ensemble of subspace discriminant classifier was the best performer in the classification of the five classes, achieving a detection accuracy of 91.6+ 2.6% (accuracy + 95% Confidence Interval). Furthermore, the same pipeline achieved accuracies of 98.6+1.4% and 99.9+0.5% in simpler three-class and two-class classification problems focused on distinguishing COVID-19, TB and healthy cases; and COVID-19 and healthy images, respectively. The pipeline was computationally efficient requiring just 0.19 second to extract DF per X-ray image and 2 minutes for training a traditional classifier with more than 2000 images on a CPU machine. The results suggest the potential benefits of using our pipeline in the detection of COVID-19, particularly in resource-limited settings and it can run with limited computational resources.

eess.IV↗
arXiv2020

On the use of higher-order tensors to model muscle synergies

The muscle synergy concept provides the best framework to understand motor control and it has been recently utilised in many applications such as prosthesis control. The current muscle synergy model relies on decomposing multi-channel surface Electromyography (EMG) signals into a synergy matrix (spatial mode) and its weighting function (temporal mode). This is done using several matrix factorisation techniques, with Non-negative matrix factorisation (NMF) being the most prominent method. Here, we introduce a 4th-order tensor muscle synergy model that extends the current state of the art by taking spectral information and repetitions (movements) into account. This adds more depth to the model and provides more synergistic information. In particular, we illustrate a proof-of-concept study where the Tucker3 tensor decomposition model was applied to a subset of wrist movements from the Ninapro database. The results showed the potential of Tucker3 tensor factorisation in finding patterns of muscle synergies with information about the movements and highlights the differences between the current and proposed model.

eess.SP↗
arXiv2020

Consistency of Muscle Synergies Extracted via Higher-Order Tensor Decomposition Towards Myoelectric Control

In recent years, muscle synergies have been pro-posed for proportional myoelectric control. Synergies were extracted using matrix factorisation techniques (mainly non-negative matrix factorisation, NMF), which requires identification of synergies to tasks or movements. In addition, NMF methods were viable only with a task dimension of 2 degrees of freedoms(DoFs). Here, the potential use of a higher-order tensor model for myoelectric control is explored. We assess the ability of a constrained Tucker tensor decomposition to estimate consistent synergies when the task dimensionality is increased up to 3-DoFs. Synergies extracted from 3rd-order tensor of 1 and 3 DoFs were compared. Results showed that muscle synergies extracted via constrained Tucker decomposition were consistent with the increase of task-dimension. Hence, these results support the consideration of proportional 3-DoF myoelectric control based on tensor decompositions.

eess.SP↗
arXiv2020

Normalised Degree Variance

Finding graph indices which are unbiased to network size and density is of high importance both within a given field and across fields for enhancing comparability of modern network science studies. The degree variance is an important metric for characterising network degree heterogeneity. Here, we provide an analytically valid normalisation of degree variance to replace previous normalisations which are either invalid or not applicable to all networks. It is shown that this normalisation provides equal values for graphs and their complements; it is maximal in the star graph (and its complement); and its expected value is constant with respect to density for Erdös-Rényi (ER) random graphs of the same size. We strengthen these results with model observations in ER random graphs, random geometric graphs, scale-free networks, random hierarchy networks and resting-state brain networks, showing that the proposed normalisation is generally less affected by both network size and density than previous normalisation attempts. The closed form expression proposed also benefits from high computational efficiency and straightforward mathematical analysis. Analysis of 184 real-world binary networks across different disciplines shows that normalised degree variance is not correlated with average degree and is robust to node and edge subsampling. Comparisons across subdomains of biological networks reveals greater degree heterogeneity among brain connectomes and food webs than in protein interaction networks.

cs.SI↗
arXiv2019

Muscle Activity Analysis using Higher-Order Tensor Models: Application to Muscle Synergy Identification

Higher-order tensor decompositions have hardly been used in muscle activity analysis despite multichannel electromyography (EMG) datasets naturally occurring as multi-way structures. Here, we seek to demonstrate and discuss the potential of tensor decompositions as a framework to estimate muscle synergies from $3^{rd}$-order EMG tensors built by stacking repetitions of multi-channel EMG for several tasks. We compare the two most widespread tensor decomposition models -- Parallel Factor Analysis (PARAFAC) and Tucker -- in muscle synergy analysis of the wrist's three main Degree of Freedoms (DoFs) using the public first Ninapro database. Furthermore, we proposed a constrained Tucker decomposition (consTD) method for efficient synergy extraction building on the power of tensor decompositions. This method is proposed as a direct novel approach for shared and task-specific synergy estimation from two biomechanically related tasks. Our approach is compared with the current standard approach of repetitively applying non-negative matrix factorisation (NMF) to a series of movements. The results show that the consTD method is suitable for synergy extraction compared to PARAFAC and Tucker. Moreover, exploiting the multi-way structure of muscle activity, the proposed methods successfully identified shared and task-specific synergies for all three DoFs tensors. These were found to be robust to disarrangement with regard to task-repetition information, unlike the commonly used NMF. In summary, we demonstrate how to use tensors to characterise muscle activity and develop a new consTD method for muscle synergy extraction that could be used for shared and task-specific synergies identification. We expect that this study will pave the way for the development of novel muscle activity analysis methods based on higher-order techniques.

eess.SP↗
arXiv2019

Multiscale Fluctuation-based Dispersion Entropy and its Applications to Neurological Diseases

Fluctuation-based dispersion entropy (FDispEn) is a new approach to estimate the dynamical variability of the fluctuations of signals. It is based on Shannon entropy and fluctuation-based dispersion patterns. To quantify the physiological dynamics over multiple time scales, multiscale FDispEn (MFDE) is developed in this article. MFDE is robust to the presence of baseline wanders, or trends, in the data. We evaluate MFDE, compared with popular multiscale sample entropy (MSE), and the recently introduced multiscale dispersion entropy (MDE), on selected synthetic data and five neurological diseases' datasets: 1) focal and non-focal electroencephalograms (EEGs); 2) walking stride interval signals for young, elderly, and Parkinson's subjects; 3) stride interval fluctuations for Huntington's disease and amyotrophic lateral sclerosis; 4) EEGs for controls and Alzheimer's disease patients; and 5) eye movement data for Parkinson's disease and ataxia. MFDE dealt with the problem of undefined MSE values and, compared with MDE, led to more stable entropy values over the scale factors for pink noise. Overall, MFDE was the fastest and most consistent method for the discrimination of different states of neurological data, especially where the mean value of a time series considerably changes along the signal (e.g., eye movement data). This study shows that MFDE is a relevant new metric to gain further insights into the dynamics of neurological diseases recordings.

q-bio.NC↗
arXiv2018

Graph-Variate Signal Analysis

Incorporating graphs in the analysis of multivariate signals is becoming a standard way to understand the interdependency of activity recorded at different sites. The new research frontier in this direction includes the important problem of how to assess dynamic changes of signal activity. We address this problem in a novel way by defining the graph-variate signal alongside methods for its analysis. Essentially, graph-variate signal analysis leverages graphs of reliable connectivity information to filter instantaneous bivariate functions of the multivariate signal. This opens up a new and robust approach to analyse joint signal and network dynamics at sample resolution. Furthermore, our method can be formulated as instantaneous networks on which standard network analysis can be implemented. When graph connectivity is estimated from the multivariate signal itself, the appropriate consideration of instantaneous graph signal functions allows for a novel dynamic connectivity measure-- graphvariate dynamic (GVD) connectivity-- which is robust to spurious short-term dependencies. Particularly, we present appropriate functions for three pertinent connectivity metrics-- correlation, coherence and the phase-lag index. We show that our approach can determine signals with a single correlated couple against wholly uncorrelated data of up to 128 nodes in signal size (1 out of 8128 weighted edges). GVD connectivity is also shown to be more robust than i) other GSP approaches at detecting a randomly traveling spheroid on a 3D grid and ii) standard dynamic connectivity in determining differences in EEG restingstate and task-related activity. We also demonstrate its use in revealing hidden depth correlations from geophysical gamma ray data. We expect that the methods and framework presented will provide new approaches to data analysis in a variety of applied settings.

cs.SI↗
arXiv2018

Weighted network estimation by the use of topological graph metrics

Topological metrics of graphs provide a natural way to describe the prominent features of various types of networks. Graph metrics describe the structure and interplay of graph edges and have found applications in many scientific fields. In this work, graph metrics are used in network estimation by developing optimisation methods that incorporate prior knowledge of a network's topology. The derivatives of graph metrics are used in gradient descent schemes for weighted undirected network denoising, network completion, and network decomposition. The successful performance of our methodology is shown in a number of toy examples and real-world datasets. Most notably, our work establishes a new link between graph theory, network science and optimisation.

cs.DS↗
arXiv2018

Evaluation of matrix factorisation approaches for muscle synergy extraction

The muscle synergy concept provides a widely-accepted paradigm to break down the complexity of motor control. In order to identify the synergies, different matrix factorisation techniques have been used in a repertoire of fields such as prosthesis control and biomechanical and clinical studies. However, the relevance of these matrix factorisation techniques is still open for discussion since there is no ground truth for the underlying synergies. Here, we evaluate factorisation techniques and investigate the factors that affect the quality of estimated synergies. We compared commonly used matrix factorisation methods: Principal component analysis (PCA), Independent component analysis (ICA), Non-negative matrix factorization (NMF) and second-order blind identification (SOBI). Publicly available real data were used to assess the synergies extracted by each factorisation method in the classification of wrist movements. Synthetic datasets were utilised to explore the effect of muscle synergy sparsity, level of noise and number of channels on the extracted synergies. Results suggest that the sparse synergy model and a higher number of channels would result in better-estimated synergies. Without dimensionality reduction, SOBI showed better results than other factorisation methods. This suggests that SOBI would be an alternative when a limited number of electrodes is available but its performance was still poor in that case. Otherwise, NMF had the best performance when the number of channels was higher than the number of synergies. Therefore, NMF would be the best method for muscle synergy extraction.

eess.SP↗
arXiv2017

Tensor-driven extraction of developmental features from varying paediatric EEG datasets

Objective. Consistently changing physiological properties in developing children's brains challenges new data heavy technologies, like brain-computer interfaces (BCI). Advancing signal processing methods in such technologies to be more sensitive to developmental changes could help improve their function and usability in paediatric populations. Taking advantage of the multi-dimensional structure of EEG data through tensor analysis offers a framework to extract relevant developmental features present in paediatric resting-state EEG datasets. Methods. Three paediatric datasets from varying developmental states and populations were analyzed using a developed two-step constrained Parallel Factor (PARAFAC) tensor decomposition. The datasets included the Muir Maxwell Epilepsy Centre, Children's Hospital Boston-MIT and the Child Mind Institute, outlining two impaired and one healthy population, respectively. Within dataset cross-validation used support vector machines (SVM) for classification of out-of-fold data predicting subject age as a proxy measure of development. t-distributed Stochastic Neighbour Embedding (t-SNE) maps complemented classification analysis through visualization of the high-dimensional feature structures. Main Results. Development-sensitive features were successfully identified for the developmental conditions of each dataset. SVM classification accuracy and misclassification costs were improved significantly for both healthy and impaired paediatric populations. t-SNE maps revealed suitable tensor factorization was key in extracting developmental features. Significance. The described methods are a promising tool for incorporating the unique developmental features present throughout childhood EEG into new technologies like BCI and its applications.

q-bio.NC↗
arXiv2017

Accounting for the Complex Hierarchical Topology of EEG Phase-Based Functional Connectivity in Network Binarisation

Research into binary network analysis of brain function faces a methodological challenge in selecting an appropriate threshold to binarise edge weights. For EEG phase-based functional connectivity, we test the hypothesis that such binarisation should take into account the complex hierarchical structure found in functional connectivity. We explore the density range suitable for such structure and provide a comparison of state-of-the-art binarisation techniques, the recently proposed Cluster-Span Threshold (CST), minimum spanning trees, efficiency-cost optimisation and union of shortest path graphs, with arbitrary proportional thresholds and weighted networks. We test these techniques on weighted complex hierarchy models by contrasting model realisations with small parametric differences. We also test the robustness of these techniques to random and targeted topological attacks.We find that the CST performs consistenty well in state-of-the-art modelling of EEG network topology, robustness to topological network attacks, and in three real datasets, agreeing with our hypothesis of hierarchical complexity. This provides interesting new evidence into the relevance of considering a large number of edges in EEG functional connectivity research to provide informational density in the topology.

q-bio.NC↗
arXiv2017

Amplitude- and Frequency-based Dispersion Patterns and Entropy

Permutation patterns-based approaches, such as permutation entropy (PerEn), have been widely and successfully used to analyze data. However, these methods have two main shortcomings. First, when a series is symbolized based on permutation patterns, repetition as an unavoidable phenomenon in data is not took in to account. Second, they consider only the order of amplitude values and so, some information regarding the amplitude values themselves may be ignored. To address these deficiencies, we have very recently introduced dispersion patterns and subsequently, dispersion entropy (DispEn). In this paper, we investigate the effect of different linear and non-linear mapping approaches, used in the algorithm of DispEn, on the characterization of signals. We also inspect the sensitivity of different parameters of DispEn to noise. Moreover, we introduce frequency-based DispEn (FDispEn) as a measure to deal with only the frequency of time series. The results suggest that DispEn and FDispEn with the log-sigmoid mapping approach, unlike PerEn, can detect outliers. Furthermore, the original and frequency-based forbidden dispersion patterns are introduced to discriminate deterministic from stochastic time series. The computation times show that DispEn and FDispEn are considerably faster than PerEn. Finally, we find that DispEn and FDispEn outperform PerEn to distinguish various dynamics of biomedical signals. Due to their advantages over existing entropy methods, DispEn and FDispEn are expected to be widely used for the characterization of a wide variety of real-world time series.

cs.IT↗
arXiv2017

Refined Multiscale Fuzzy Entropy based on Standard Deviation for Biomedical Signal Analysis

Multiscale entropy (MSE) has been a prevalent algorithm to quantify the complexity of fluctuations in the local mean value of biomedical time series. Recent developments in the field have tried to improve the MSE by reducing its variability in large scale factors. On the other hand, there has been recent interest in using other statistical moments than the mean, i.e. variance, in the coarse-graining step of the MSE. Building on these trends, here we introduce the so-called refined composite multiscale fuzzy entropy based on the standard deviation (RCMFEσ) to quantify the dynamical properties of spread over multiple time scales. We demonstrate the dependency of the RCMFEσ, in comparison with other multiscale approaches, on several straightforward signal processing concepts using a set of synthetic signals. We also investigate the complementarity of using the standard deviation instead of the mean in the coarse-graining process using magnetoencephalograms in Alzheimer disease and publicly available electroencephalograms recorded from focal and non-focal areas in epilepsy. Our results indicate that RCMFEσ offers complementary information to that revealed by classical coarse-graining approaches and that it has superior performance to distinguish different types of physiological activity.

cs.CE↗
arXiv2017

Refined Composite Multiscale Dispersion Entropy and its Application to Biomedical Signals

Multiscale entropy (MSE) is a widely-used tool to analyze biomedical signals. It was proposed to overcome the deficiencies of conventional entropy methods when quantifying the complexity of time series. However, MSE is undefined for very short signals and slow for real-time applications because of the use of sample entropy (SampEn). To overcome these shortcomings, we introduce multiscale dispersion entropy (DisEn - MDE) as a very fast and powerful method to quantify the complexity of signals. MDE is based on our recently developed DisEn, which has a computation cost of O(N), compared with O(N2) for SampEn. We also propose the refined composite MDE (RCMDE) to improve the stability of MDE. We evaluate MDE, RCMDE, and refined composite MSE (RCMSE) on synthetic signals and find that these methods have similar behaviors but the MDE and RCMDE are significantly faster than MSE and RCMSE, respectively. The results also illustrate that RCMDE is more stable than MDE for short and noisy signals, which are common in biomedical applications. To evaluate the proposed methods on real signals, we employ three biomedical datasets, including focal and non-focal electroencephalograms (EEGs), blood pressure recordings in Fantasia database, and resting-state EEGs activity in Alzheimer's disease (AD). The results again demonstrate a similar behavior of RCMSE, MDE and RCMDE, although the RCMDE and MDE are significantly faster and lead to larger differences between physiological conditions known to alter the complexity of the physiological recordings. To sum up, MDE and RCMDE are expected to be useful for the analysis of physiological signals thanks to their ability to distinguish different types of dynamics.

cs.IT↗
arXiv2017

Complex tensor factorisation with PARAFAC2 for the estimation of brain connectivity from the EEG

Objective: The coupling between neuronal populations and its magnitude have been shown to be informative for various clinical applications. One method to estimate brain connectivity is with electroencephalography (EEG) from which the cross-spectrum between different sensor locations is derived. We wish to test the efficacy of tensor factorisation in the estimation of brain connectivity. Methods: Complex tensor factorisation based on PARAFAC2 is used to decompose the EEG into scalp components described by the spatial, spectral, and complex trial profiles. An EEG model in the complex domain was derived that shows the suitability of PARAFAC2. A connectivity metric was also derived on the complex trial profiles of the extracted components. Results: Results on a benchmark EEG dataset confirmed that PARAFAC2 can estimate connectivity better than traditional tensor analysis such as PARAFAC within a range of signal-to-noise ratios. The analysis of EEG from patients with mild cognitive impairment or Alzheimer's disease showed that PARAFAC2 identifies loss of brain connectivity better than traditional approaches and agreeing with prior pathological knowledge. Conclusion: The complex PARAFAC2 algorithm is suitable for EEG connectivity estimation since it allows to extract meaningful coupled sources and provides better estimates than complex PARAFAC. Significance: A new paradigm that employs complex tensor factorisation has demonstrated to be successful in identifying brain connectivity and the location of couples sources for both a benchmark and a real-world EEG dataset. This can enable future applications and has the potential to solve some the issues that deteriorate the performance of traditional connectivity metrics.

cs.CE↗
arXiv2017

Multivariate Multiscale Dispersion Entropy of Biomedical Times Series

Objective: Due to the non-linearity of numerous biomedical signals, non-linear analysis of multi-channel time series, notably multivariate multiscale entropy (mvMSE), has been extensively used in biomedical signal processing. However, mvMSE has three drawbacks: 1) mvMSE values are either undefined or unreliable for short signals; 2) mvMSE is not fast enough for real-time applications; and 3) the computation of mvMSE for signals with a large number of channels requires the storage of a huge number of elements. Methods: To deal with these problems and improve the stability of mvMSE, we introduce multivariate multiscale dispersion entropy (MDE - mvMDE) as an extension of our recently developed MDE, to quantify the complexity of multivariate time series. Results: We assess mvMDE, in comparison with mvMSE and multivariate multiscale fuzzy entropy (mvMFE), on correlated and uncorrelated multi-channel noise signals, bivariate autoregressive processes, and three biomedical datasets. The results show that mvMDE takes into account dependencies in patterns across both the time and spatial domains. The mvMDE, mvMSE, and mvMFE methods are consistent in that they lead to similar conclusions about the underlying physiological conditions. However, the proposed mvMDE discriminates various physiological states of the biomedical recordings better than mvMSE and mvMFE. In addition, for both the short and long time series, the mvMDE-based results are noticeably more stable than the mvMSE- and mvMFE-based ones. Conclusion: For short multivariate time series, mvMDE, unlike mvMSE, does not result in undefined values. Furthermore, mvMDE is noticeably faster than mvMFE and mvMSE and also needs to store a considerably smaller number of elements. Significance: Due to its ability to detect different kinds of dynamics of multivariate signals, mvMDE has great potential to analyse various physiological signals.

q-bio.QM↗