Rojas, M.; Alonso, J.F.; Jordanic, M.; Romero, S.; Mañanas, M.A. Revista iberoamericana de automática e informática industrial Vol. 14, num. 4, p. 406-411 DOI: 10.1016/j.riai.2017.07.006 Data de publicació: 2017-10-01 Article en revista
La identificación de tareas y estimación del movimiento voluntario basados en electromiografía (EMG) constituyen un problema conocido que involucra diferentes áreas en sistemas expertos, particularmente la de reconocimiento de patrones, con muchas aplicaciones posibles en dispositivos de asistencia y rehabilitación. La información que proporciona puede resultar útil para el control de exoesqueletos o brazos robóticos utilizados en terapias activas. La tecnología emergente de electromiografía de alta densidad (HD-EMG) abre nuevas posibilidades para extraer información neural y ya ha sido reportado que la distribución espacial de mapas de intensidad HD-EMG es una característica valiosa en la identificación de tareas isométricas (contracciones que no producen cambio en la longitud del músculo). Este estudio explora la utilización de la distribución espacial de la actividad mioeléctrica y lleva a cabo identificación de tareas durante ejercicios dinámicos a diferentes velocidades que son mucho más cercanos a los que se utilizan habitualmente en las terapias de rehabilitación. Con este objetivo, se registraron señales HD-EMG en un grupo de sujetos sanos durante la realización de un conjunto de tareas isométricas y dinámicas del miembro superior. Los resultados indican que la distribución espacial es una característica muy útil en la identificación, no solo de contracciones isométricas sino también de contracciones dinámicas, mejorando la eficiencia y naturalidad del control de dispositivos de rehabilitación para que se adapte mejor al usuario.
Estimation of neuromuscular intention using electromyography (EMG) and pattern recognition is still an open problem. One of the reasons is that the pattern-recognition approach is greatly influenced by temporal changes in electromyograms caused by the variations in the conductivity of the skin and/or electrodes, or physiological changes such as muscle fatigue. This paper proposes novel features for task identification extracted from the high-density electromyographic signal (HD-EMG) by applying the mean shift channel selection algorithm evaluated using a simple and fast classifier-linear discriminant analysis. HD-EMG was recorded from eight subjects during four upper-limb isometric motor tasks (flexion/extension, supination/pronation of the forearm) at three different levels of effort. Task and effort level identification showed very high classification rates in all cases. This new feature performed remarkably well particularly in the identification at very low effort levels. This could be a step towards the natural control in everyday applications where a subject could use low levels of effort to achieve motor tasks. Furthermore, it ensures reliable identification even in the presence of myoelectric fatigue and showed robustness to temporal changes in EMG, which could make it suitable in long-term applications.
Jordanic, M.; Rojas, M.; Mañanas, M.A.; Alonso, J.F. Journal of neural engineering Vol. 13, num. 4, p. 046002-1-046002-10 DOI: 10.1088/1741-2560/13/4/046002 Data de publicació: 2016-05-17 Article en revista
Objective. The development of modern assistive and rehabilitation devices requires reliable and easy-to-use methods to extract neural information for control of devices. Group-specific pattern recognition identifiers are influenced by inter-subject variability. Based on high-density EMG (HD-EMG) maps, our research group has already shown that inter-subject muscle activation patterns exist in a population of healthy subjects. The aim of this paper is to analyze muscle activation patterns associated with four tasks (flexion/extension of the elbow, and supination/pronation of the forearm) at three different effort levels in a group of patients with incomplete Spinal Cord Injury (iSCI). Approach. Muscle activation patterns were evaluated by the automatic identification of these four isometric tasks along with the identification of levels of voluntary contractions. Two types of classifiers were considered in the identification: linear discriminant analysis and support vector machine. Main results. Results show that performance of classification increases when combining features extracted from intensity and spatial information of HD-EMG maps (accuracy = 97.5%). Moreover, when compared to a population with injuries at different levels, a lower variability between activation maps was obtained within a group of patients with similar injury suggesting stronger task-specific and effort-level-specific co-activation patterns, which enable better prediction results. Significance. Despite the challenge of identifying both the four tasks and the three effort levels in patients with iSCI, promising results were obtained which support the use of HD-EMG features for providing useful information regarding motion and force intention
Background: Recent studies show that spatial distribution of High Density surface EMG maps (HD-EMG) improves the identification of tasks and their corresponding contraction levels. However, in patients with incomplete spinal cord injury (iSCI), some nerves that control muscles are damaged, leaving some muscle parts without an innervation. Therefore, HD-EMG maps in patients with iSCI are affected by the injury and they can be different for every patient. The objective of this study is to investigate the spatial distribution of intensity in HD-EMG recordings to distinguish co-activation patterns for different tasks and effort levels in patients with iSCI. These patterns are evaluated to be used for extraction of motion intention.; Method: HD-EMG was recorded in patients during four isometric tasks of the forearm at three different effort levels. A linear discriminant classifier based on intensity and spatial features of HD-EMG maps of five upper-limb muscles was used to identify the attempted tasks. Task and force identification were evaluated for each patient individually, and the reliability of the identification was tested with respect to muscle fatigue and time interval between training and identification. Results: Three feature sets were analyzed in the identification: 1) intensity of the HD-EMG map, 2) intensity and center of gravity of HD-EMG maps and 3) intensity of a single differential EMG channel (gold standard).; Results show that the combination of intensity and spatial features in classification identifies tasks and effort levels properly (Acc = 98.8 %; S = 92.5 %; P = 93.2 %; SP = 99.4 %) and outperforms significantly the other two feature sets (p < 0.05).; Conclusion: In spite of the limited motor functionality, a specific co-activation pattern for each patient exists for both intensity, and spatial distribution of myoelectric activity. The spatial distribution is less sensitive than intensity to myoelectric changes that occur due to fatigue, and other time-dependent influences.
Common non-invasive measurements of muscle fatigue during dynamic contractions are based on the surface electromyography (SEMG). However, these measurements include movement artefacts such as the change of muscle length and the movement of electrodes. These artefacts significantly contribute to the non-stationary properties of the measured SEMG signal. Consequently, the measurements of the muscle fatigue employ various sensors and signal-processing methods. In this paper, we present a method for the estimation of the fatigue which uses an accelerometer to determine the SEMG segments within which the movement artefacts are resolved and the wide-sense stationarity holds. The fatigue is then estimated by the median frequencies of their power spectra. To illustrate the features of the proposed method, we apply it to the biceps curl exercise.
Jordanic, M.; Molnar, G.; Magjarevic, R. International Convention on Information and Communication Technology, Electronics and Microelectronics p. 108-112 Data de presentació: 2011 Presentació treball a congrés
The continuous-time detection of movement is a time-domain operation. It usually requires lowpass filters ensuring small waveform distortion. To achieve small time-domain distortion, the filters approximating linear phase, such as Bessel and Gaussian filter, are often used. However, these filters have poor selectivity. Both, high selectivity and nearly linear phase are obtained by using the filters with symmetric impulse response. In this paper, we propose a simple method for the detection of movement, which uses this type of filter. We illustrate the features of the method in the measurement of the movements during biceps curl exercise. The method proved to be robust with high accuracy of the detection. Furthermore, it is suitable for application in physical rehabilitation where variety of changes in motoric functions can be detected.