Robustness of Surface EMG Classifiers with Fixed-Point Decomposition on Reconfigurable Architecture

In this paper, we present a novel muscle synergy extraction method based on multivariate curve resolution–alternating least squares (MCR-ALS) to overcome the limitation of the nonnegative matrix factorization (NMF) method for extracting non-sparse muscle synergy, and we study its potential application for evaluating motor function of stroke survivors. Nonnegative matrix factorization (NMF) is the most widely used method for muscle synergy extraction. However, NMF is susceptible to components’ sparseness and usually provides inferior reliability, which significantly limits the promotion of muscle synergy. In this study, MCR-ALS was employed to extract muscle synergy from electromyography (EMG) data. Its performance was compared with two other matrix factorization algorithms, NMF and self-modeling mixture analysis (SMMA). Simulated data sets were utilized to explore the influences of the sparseness and noise on the extracted synergies. As a result, the synergies estimated by MCR-ALS were the most similar to true synergies as compared with SMMA and NMF. MCR-ALS was used to analyze the muscle synergy characteristics of upper limb movements performed by healthy (n = 11) and stroke (n = 5) subjects. The repeatability and intra-subject consistency were used to evaluate the performance of MCR-ALS. As a result, MCR-ALS provided much higher repeatability and intra-subject consistency as compared with NMF, which were important for the reliability of the motor function evaluation. The stroke subjects had lower intra-subject consistency and seemingly had more synergies as compared with the healthy subjects. Thus, MCR-ALS is a promising muscle synergy analysis method for motor function evaluation of stroke patients.

Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardware implementations, and some machine learning topics. Applications to biometric/bioinformatics and data mining are also included. Focusing on the prominent accomplishments and their practical aspects, academic and technical staff, graduate students and researchers will find that this provides a solid foundation and encompassing reference for the fields of neural networks, pattern recognition, signal processing, machine learning, computational intelligence, and data mining.

이 논문은 고차원의 데이터를 저 차원으로 줄이는 방법 중 하나인 특징추출에 대한 방법들의 특성을 비교한다. 비교대상 방법은 전통적인 PCA(Principal Component Analysis)방법과 시각피질의 특성을 보인다고 알려진 ICA(Independent Component Analysis), 국소기반인식을 구현한 NMF(Non-negative Matrix Factorization), 그리고 이의 성능을 개선한 sNMF(Sparse NMF)로 정하였다. 추출된 특징들의 특성을 시각적으로 확인하기 위하여 필기체 숫자 영상을 대상으로 특징추출을 수행하였으며, 인식기에 적용한 효과의 확인을 위하여 추출된 특징을 다층퍼셉트론에 학습시켜보았다. 각 방법의 특성을 비교한 결과는 응용하고자 하는 문제에서 어떤 특징을 추출하기 원하느냐에 따라 특징추출 방법을 선정할 때 유용할 것이다. In this paper, feature extraction methods, which is one field of reducing dimensions of high-dimensional data, are empirically investigated. We selected the traditional PCA(Principal Component Analysis), ICA(Independent Component Analysis), NMF(Non-negative Matrix Factorization), and sNMF(Sparse NMF) for comparisons. ICA has a similar feature with the simple cell of V1. NMF implemented a "parts-based representation in the brain" and sNMF is a improved version of NMF. In order to visually investigate the extracted features, handwritten digits are handled. Also, the extracted features are used to train multi-layer perceptrons for recognition test. The characteristic of each feature extraction method will be useful when applying feature extraction methods to many real-world problems.

Musculoskeletal models (MMs) driven by electromyography (EMG) signals have been used to predict human movements. Muscle excitations of MMs are generally the amplitude of EMG, which shows large variability even when repeating the same task. The general structure of muscle synergies has been proved to be consistent across test sessions, providing a perspective for extracting stable control information for MMs. Although non-negative matrix factorization (NMF) is a common method for extracting synergies, the factorization result of NMF is not unique. In this study, we proposed an improved NMF algorithm for extracting stable control information of MMs to predict hand and wrist motions. Specifically, we supplemented the Hadamard product and L2-norm regularization term to the objective function of NMF. The proposed NMF was utilized to identify stable muscle synergies. Then, the time-varying profile of each synergy was fed into a subject-specific MM for estimating joint motions. The results demonstrated that the proposed scheme significantly outperformed a traditional MM and an MM combined with the classic NMF (NMF-MM), with averaged R and NRMSE equal to \(0.89\pm 0.06\) and \(0.16\pm 0.04\). Further, the similarity between muscle synergies extracted from different training data revealed the proposed method’s effectiveness of identifying consistent control information for MMs. This study provides a novel model-based scheme for the estimation of continuous movements.KeywordsMusculoskeletal modelElectromyographyNon-negative matrix factorization algorithm

The main goal of this work was to assess the performance of different initializations of matrix factorization algorithms for an accurate identification of muscle synergies. Currently, nonnegative matrix factorization (NNMF) is the most commonly used method to identify muscle synergies. However, it has been shown that NNMF performance might be affected by different kinds of initialization. The present study aims at optimizing the traditional NNMF initialization for data with partial or complete temporal dependencies. For this purpose, three different initializations are used: random, SVD-based, and sparse. NNMF was used to identify muscle synergies from simulated data as well as from experimental surface EMG signals. Simulated data were generated from synthetic independent and dependent synergy vectors (i.e., shared muscle components), whose activation coefficients were corrupted by simulating controlled degrees of correlation. Similarly, EMG data were artificially modified, making the extracted activation coefficients temporally dependent. By measuring the quality of identification of the original synergies underlying the data, it was possible to compare the performance of different initialization techniques. Simulation results demonstrate that sparse initialization performs significantly better than all other kinds of initialization in reconstructing muscle synergies, regardless of the correlation level in the data.

The purpose of this study was to determine the differences in muscle synergy between skilled and unskilled participants using various loading conditions for power clean. Nineteen participants (ten skilled and nine unskilled) performed power clean at 60–90% one repetition maximum (1RM), while measured 12 muscles across the entire body. The vertical impulse was calculated for the unweighting associated with the double-knee bend (DKB) manoeuvre in power clean. Muscle synergies were extracted using non-negative matrix factorization. The weighting of muscle synergies was subsequently compared between the two groups for all loads, and confidence intervals were calculated. The number of muscle synergies in both groups was three, and the functions of all muscle synergies were similar. Muscle synergy 1 involved the first pull, muscle synergy 2 involved the transition and the second pull, and muscle synergy 3 involved DKB. No significant difference in either muscle synergy was observed at 60–80% 1RM weight, while the 90% 1RM showed significantly active in the ankle plantar flexor and knee extensor muscles for muscle synergy 3, which involved DKB only in the skilled group. This indicates that increased joint stiffness during DKB may minimize unweighting. Unskilled individuals may acquire such muscle synergies to lift greater weights.

Nonnegative matrix factorization (NMF) is known as a parts-based linear representation for nonnegative data. This method has been applied for blind source separation (BSS) when the sources are nonnegative. This paper presents a new NMF method for independent component analysis (ICA), which is useful for BSS without the nonnegativity constraint. Using this method, we transform the sources by their cumulative distribution functions (CDFs) and perform the nonparametric quantization to construct a nonnegative matrix where each entry represents the joint probability density of two transformed signals. The NMF procedure is accordingly realized to find the ICA demixing matrix. The independence between sources is maximized towards attaining the uniformity in the joint probability density. In the experiments on the separation of signal and music signals, we show the effectiveness of the proposed NMF-ICA compared to the infomax ICA and FastICA algorithms.

This paper deals with the application of spatially localized, nonoverlapping features for face recognition. The analysis is carried out by using the features generated from two closely related techniques known as independent component analysis (ICA) and nonnegative matrix factorization (NMF). A set of statistically independent basis vectors with sparse features is derived from ICA. Likewise, NMF is used to yield sparse representation of localized features to represent distributed parts over a human face. Similarities between reconstructed faces of test images and a set of synthesised face representations from the basis vectors derived from an image database using the two techniques are measured. The strengths and weaknesses of each method in the context of face recognition are discussed.

Muscle synergies are defined as coordinated recruitment of groups of muscles with specific activation balances and time profiles aimed at generating task-specific motor commands. While muscle synergies in postural control have been investigated primarily in reactive balance conditions, the neuromechanical contribution of muscle synergies during voluntary control of upright standing is still unclear. In this study, muscle synergies were investigated during the generation of isometric force at the trunk during the maintenance of standing posture. Participants were asked to maintain the steady-state upright standing posture while pulling forces of different magnitudes were applied at the level at the waist in eight horizontal directions. Muscle synergies were extracted by nonnegative matrix factorization from sixteen lower limb and trunk muscles. An average of 5-6 muscle synergies were sufficient to account for a wide variety of EMG waveforms associated with changes in the magnitude and direction of pulling forces. A cluster analysis partitioned the muscle synergies of the participants into a large group of clusters according to their similarity, indicating the use of a subjective combination of muscles to generate a multidirectional force vector in standing. Furthermore, we found a participant-specific distribution in the values of cosine directional tuning parameters of synergy amplitude coefficients, suggesting the existence of individual neuromechanical strategies to stabilize the whole-body posture. Our findings provide a starting point for the development of novel diagnostic tools to assess muscle coordination in postural control and lay the foundation for potential applications of muscle synergies in rehabilitation.

The sit-to-stand motion is a common movement in daily life and understanding the mechanism of the sit-to-stand motion is important. Our previous study shows that four muscle synergies can characterize the sit-to-stand motion, and they have specific roles, such as upper body flexion, rising from a chair, body extension, and posture stabilization. The time-varying weight of these synergies are changed to achieve adaptive movement. However, the relationship between sensory input and the activation of the muscle synergies is not completely understood. In this paper, we aim to clarify how vestibular and visual inputs affect the muscle synergy in sit-to-stand motion. To address this, we conducted experiments as follows. Muscle activity, body kinematics, and ground reaction force were measured for the sit-to-stand motion under three different conditions: control, visual-disturbance, and vestibular-disturbance conditions. Under the control condition, the participants stood without any intervention. Under the visual-disturbance condition, the participants wore convex lens glasses and performed the sit-to-stand motion in a dark room. Under the vestibular-disturbance condition, a caloric test was performed. Muscle synergies were calculated for these three conditions using non-negative matrix factorization. We examined whether the same four muscle synergies were employed under each condition, and the changes in the time-varying coefficients were determined. These experiments were conducted on seven healthy, young participants. It was found that four muscle synergies could explain the muscle activity in the sit-to-stand motion under the three conditions. However, there were significant differences in the time-varying weight coefficients. When the visual input was disturbed, a larger amplitude was found for the muscle synergy that activated mostly in the final posture stabilization phase of the sit-to-stand motion. Under vestibular-disturbance condition, a longer activation was observed for the synergies that extended the entire body and led to posture stabilization. The results implied that during human sit-to-stand motion, visual input has less contribution to alter or correct activation of muscle synergies until the last phase. On the other hand, duration of muscle synergies after the buttocks leave are prolonged in order to adapt to the unstable condition in which sense of verticality is decreased under vestibular-disturbance.

Event Abstract Back to Event Comparing independent component analysis and non-negative matrix factorisation in the identification of event-related brain dynamics Sandra Ortega-Martorell1*, Ivan Olier2, Alfredo Vellido3, Paulo J. Lisboa4 and Wael El-Deredy2 1 Universitat Autònoma de Barcelona, Spain 2 University of Manchester, United Kingdom 3 Universitat Politècnica de Catalunya, Spain 4 Liverpool John Moores University, United Kingdom Matrix factorisation methods (such as principal and independent component analysis - PCA, ICA-, or singular value decomposition SVD) are commonly used for decomposing EEG data into factors from which the likely (latent) generating sources could be inferred or identified (Jung et al., 2000; Hoang et al., 2004). Since such factorisations are non-unique, different methods impose different constraints or priors in order to obtain a solution (e.g. components must be orthogonal in PCA, whereas independent in ICA). In non-negative matrix factorisation NMF (Paatero & Tapper,1994; Lee & Seung, 1999), the data matrix, X, is factorised into two non-negative matrices, W and H, whose product provides a good approximation of the original (X ≈ WH). Iterative methods are used to minimise the divergence between X and the product of W and H. In this study, a least squares method (Paatero & Tapper,1994 ) was used. We compared NMF and ICA in terms of: i. Their ability to identify eye movement artifacts in high density EEG electrode arrays. ii. Specificity in the separation of different event related brain dynamics from simultaneously activated sensory modalities. iii. Their computational cost, to assess their suitability for real time processing for the purposes of BCI applications. We used EEG recordings from 15 subjects as in (Brown et al., 2008). NMF was as good as ICA for identifying eye movement and separating different events. The former was much better, though, in the resolution of the components obtained. Computationally, NMF was marginally more efficient than FastICA. Keywords: Brain Signals, EEG Conference: XI International Conference on Cognitive Neuroscience (ICON XI), Palma, Mallorca, Spain, 25 Sep - 29 Sep, 2011. Presentation Type: Poster Presentation Topic: Poster Sessions: Modeling and Analysis of Brain Signals Citation: Ortega-Martorell S, Olier I, Vellido A, Lisboa PJ and El-Deredy W (2011). Comparing independent component analysis and non-negative matrix factorisation in the identification of event-related brain dynamics. Conference Abstract: XI International Conference on Cognitive Neuroscience (ICON XI). doi: 10.3389/conf.fnhum.2011.207.00082 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 16 Nov 2011; Published Online: 25 Nov 2011. * Correspondence: Dr. Sandra Ortega-Martorell, Universitat Autònoma de Barcelona, Barcelona, Spain, S.OrtegaMartorell@ljmu.ac.uk Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Sandra Ortega-Martorell Ivan Olier Alfredo Vellido Paulo J Lisboa Wael El-Deredy Google Sandra Ortega-Martorell Ivan Olier Alfredo Vellido Paulo J Lisboa Wael El-Deredy Google Scholar Sandra Ortega-Martorell Ivan Olier Alfredo Vellido Paulo J Lisboa Wael El-Deredy PubMed Sandra Ortega-Martorell Ivan Olier Alfredo Vellido Paulo J Lisboa Wael El-Deredy Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Understanding the muscle synergies shared between pedaling and walking is crucial for elucidating the mechanisms of human motor control and establishing highly individualized rehabilitation strategies. This study investigated how pedaling direction and speed influence the recruitment of walking-like muscle synergies. Twelve healthy male participants pedaled at three speeds (60 RPM, 30 RPM, and 80 RPM) in two rotational directions (forward and backward). Additionally, they completed walking tasks at three different speeds (slow, comfortable, and fast). Surface electromyography (EMG) was recorded on 10 lower limb muscles during movement, and muscle synergies were extracted from each condition using non-negative matrix factorization. The similarities between the muscle synergies during walking and each pedaling condition were examined using cosine similarity. The results confirmed that the composition of muscle synergies during pedaling varied depending on the rotational direction and speed. Furthermore, one to three muscle synergies, similar to those observed during walking, were recruited in each pedaling condition, with specific synergies dependent on direction and speed. For instance, synergy involving the quadriceps and hip extensors was predominantly observed during pedaling at 30 RPM, regardless of the direction of rotation. Meanwhile, synergy involving the hamstrings was more pronounced during forward pedaling at 60 RPM and backward pedaling at 80 RPM. These findings suggest that walking-like muscle synergies can be selectively recruited during pedaling, depending on the rotational direction and speed.

We investigated muscle activity, ground reaction forces, and center of mass (CoM) acceleration in two different postural behaviors for standing balance control in humans to determine whether common neural mechanisms are used in different postural tasks. We compared nonstepping responses, where the base of support is stationary and balance is recovered by returning CoM back to its initial position, with stepping responses, where the base of support is enlarged and balance is recovered by pushing the CoM away from the initial position. In response to perturbations of the same direction, these two postural behaviors resulted in different muscle activity and ground reaction forces. We hypothesized that a common pool of muscle synergies producing consistent task-level biomechanical functions is used to generate different postural behaviors. Two sets of support-surface translations in 12 horizontal-plane directions were presented, first to evoke stepping responses and then to evoke nonstepping responses. Electromyographs in 16 lower back and leg muscles of the stance leg were measured. Initially (∼100-ms latency), electromyographs, CoM acceleration, and forces were similar in nonstepping and stepping responses, but these diverged in later time periods (∼200 ms), when stepping occurred. We identified muscle synergies using non-negative matrix factorization and functional muscle synergies that quantified correlations between muscle synergy recruitment levels and biomechanical outputs. Functional muscle synergies that produce forces to restore CoM position in nonstepping responses were also used to displace the CoM during stepping responses. These results suggest that muscle synergies represent common neural mechanisms for CoM movement control under different dynamic conditions: stepping and nonstepping postural responses.

Sit-to-Stand (STS) is an important movement in daily life and could be difficult for older people. Assist robot is expected to provide STS support. STS movement does not only require kinetic coordination, but also muscle coordination. Thus, understanding the muscle coordination during STS with robot assistance is a key issue of human-robot-interaction. The purpose of this study is to reveal the effect of assist robot on muscle coordination during STS through muscle synergy theory. Six subjects did self-performed and robot-assist STSs in total ten times. Surface electromyogram (EMG) of eight muscles was measured to extract muscle synergy using non-negative matrix factorization (NMF). As a result, two muscle synergies appeared in self-performed STS. There were three muscle synergies when STS was assisted by the robot. The spatial patterns of muscle synergies for lower limb muscles differed with and without robot assistance. Using the robot delayed the activation of muscle synergy at the temporal pattern.

No evidence of expertise-related changes in muscle synergies during rowing