Muscle synergy analysis is a useful tool for the evaluation of the motor control strategies and for the quantification of motor performance. Among the parameters that can be extracted, most of the information is included in the rank of the modular control model (i.e. the number of muscle synergies that can be used to describe the overall muscle coordination). Even though different criteria have been proposed in literature, an objective criterion for the model order selection is needed to improve reliability and repeatability of MSA results. In this paper, we propose an Akaike Information Criterion (AIC)-based method for model order selection when extracting muscle synergies via the original Gaussian Non-Negative Matrix Factorization algorithm. The traditional AIC definition has been modified based on a correction of the likelihood term, which includes signal dependent noise on the neural commands, and a Discrete Wavelet decomposition method for the proper estimation of the number of degrees of freedom of the model, reduced on a synergy-by-synergy and event-by-event basis. We tested the performance of our method in comparison with the most widespread ones, proving that our criterion is able to yield good and stable performance in selecting the correct model order in simulated EMG data. We further evaluated the performance of our AIC-based technique on two distinct experimental datasets confirming the results obtained with the synthetic signals, with performances that are stable and independent from the nature of the analysed task, from the signal quality and from the subjective EMG pre-processing steps.

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.

Recent studies have highlighted the possibility of using surface electromyographic (EMG) signals to develop human–computer interfaces that are also able to recognize complex motor tasks involving the hand as the handwriting of digits. However, the automatic recognition of words from EMG information has not yet been studied. The aim of this study is to investigate the feasibility of using combined forearm and wrist EMG probes for solving the handwriting recognition problem of 30 words with consolidated machine-learning techniques and aggregating state-of-the-art features extracted in the time and frequency domains. Six healthy subjects, three females and three males aged between 25 and 40 years, were recruited for the study. Two tests in pattern recognition were conducted to assess the possibility of classifying fine hand movements through EMG signals. The first test was designed to assess the feasibility of using consolidated myoelectric control technology with shallow machine-learning methods in the field of handwriting detection. The second test was implemented to assess if specific feature extraction schemes can guarantee high performances with limited complexity of the processing pipeline. Among support vector machine, linear discriminant analysis, and K-nearest neighbours (KNN), the last one showed the best classification performances in the 30-word classification problem, with a mean accuracy of 95% and 85% when using all the features and a specific feature set known as TDAR, respectively. The obtained results confirmed the validity of using combined wrist and forearm EMG data for intelligent handwriting recognition through pattern recognition approaches in real scenarios.

Background: The above-knee amputation of a lower limb is a severe impairment that affects significantly the ability to walk; considering this, a complex adaptation strategy at the neuromuscular level is needed in order to be able to move safely with a prosthetic knee. In literature, it has been demonstrated that muscle activity during walking can be described via the activation of a small set of muscle synergies. The analysis of the composition and the time activation profiles of such synergies have been found to be a valid tool for the description of the motor control schemes in pathological subjects. Methods: In this study, we used muscle synergy analysis techniques to characterize the differences in the modular motor control schemes between a population of 14 people with trans-femoral amputation and 12 healthy subjects walking at two different (slow and normal self-selected) speeds. Muscle synergies were extracted from a 12 lower-limb muscles sEMG recording via non-negative matrix factorization. Equivalence of the synergy vectors was quantified by a cross-validation procedure, while differences in terms of time activation coefficients were evaluated through the analysis of the activity in the different gait sub-phases. Results: Four synergies were able to reconstruct the muscle activity in all subjects. The spatial component of the synergy vectors did not change in all the analysed populations, while differences were present in the activity during the sound limb’s stance phase. Main features of people with trans-femoral amputation’s muscle synergy recruitment are a prolonged activation of the module composed of calf muscles and an additional activity of the hamstrings’ module before and after the prosthetic heel strike. Conclusions: Synergy-based results highlight how, although the complexity and the spatial organization of motor control schemes are the same found in healthy subjects, substantial differences are present in the synergies’ recruitment of people with trans femoral amputation. In particular, the most critical task during the gait cycle is the weight transfer from the sound limb to the prosthetic one. Future studies will integrate these results with the dynamics of movement, aiming to a complete neuro-mechanical characterization of people with trans-femoral amputation’s walking strategies that can be used to improve the rehabilitation therapies.

Goal: The goal of this manuscript is to investigate the optimal methods for extracting muscle synergies from a sit-to-stand test; in particular, the performance in identifying the modular structures from signals of different length is characterized. Methods: Surface electromyography signals have been recorded from instrumented sit-to-stand trials. Muscle synergies have then been extracted from signals of different duration ( i.e. 5 times sit to stand and 30 seconds sit to stand) from different portions of a complete sit-to-stand-to-sit cycle. Performance have then been characterized using cross-validation procedures. Moreover, an optimal method based on a modified Akaike Information Criterion measure is applied on the signal for selecting the correct number of synergies from each trial. Results: Results show that it is possible to identify correctly muscle synergies from relatively short signals in a sit-to-stand experiment. Moreover, the information about motor control structures is identified with a higher consistency when only the sit-to-stand phase of the complete cycle is considered. Conclusions : Defining a set of optimal methods for the extraction of muscle synergies from a clnical test such as the sit-to-stand is of key relevance to ensure the applicability of any synergy-related analysis in the clinical practice, without requiring knowledge of the technical signal processing methods and the underlying features of the signal.