Decomposição de sinais eletromiográficos de superfície utilizando Modelos ocultos de Markov

Abstract

The detection of physiological signals from the Motor System (electromyographic signals), studied by electromyography, is being utilized in the practice clinic to guide the therapist in a more precise and accurate diagnosis of motor disorders. In this context, the process of decomposition of electromyographic signals (EMG) that includes the identification and classification of Motor Unit Action Potential (MUAP) of EMG signals, is very import to help the therapist in the evaluation of motor disorders The EMG decomposition is a complex task due to the features of the EMG features depend on the electrode type (needle or surface), its placement related to the muscle, the contraction level and the health of the Neuromuscular System. To date the majority of research on EMG decomposition utilizes EMG signals acquired by needle electrodes, due to their advantages in processing this type of signal. However, relatively little research has been conducted using surface based EMG signals. As such this thesis aims to contribute to the clinical practice and Biofeedback therapies by presenting a system permitting the decomposition of surface EMG signal via the use of Hidden Markov Models. This process is supported by the use of Differential Evolution and Spectral Clustering techniques. The developed system presented coherent results in: a) Identification of the number of Motor Units actives in the EMG signal; b) Presentation of the morphological patterns of MUAPs in the EMG signal; c) Identification of the firing sequence of the Motor Units. The Techniques utilized in this work have not yet been applied in the field of EMG decomposition and, in the end of this work, it was proved that they are excellent techniques for the surface EMG decomposition. The model proposed in this work is an advance in the research of decomposition of surface EMG signals.