![]() According to recent studies, better efficiency of classifications is usually achieved through a combination of multiple feature sets. The feature set extracted from the time- and frequency-domains has received widespread interest as a powerful tool for hand movement recognition applications. Therefore, whether the muscle synergy patterns could be broadened to hand gesture recognition left an interesting topic. Synergistic muscular activity is generally a neural-controlled strategy with high robustness for limb movement and muscle synergy patterns were successfully used for complex movement evaluations. However, the robustness of this recognition is difficult to be maintained because these parameters are often affected by factors such as muscle fatigue, electrode shift, etc. Therefore, the recognition of hand gestures is principally based on the myoelectric feature vectors, using characteristic parameters extracted from the corresponding sEMG signals. The difference in the muscle contraction pattern that controls finger movements will alter the sEMG characteristic parameters in the time- or frequency- domain. Surface electromyography (sEMG) signals from multi-tendon forearm muscles can reflect the finger movement pattern, which is useful to finger motion classification applications such as sign language recognition or an electromyography (EMG)-driven robotic hand exoskeleton. Generally, hand finger movements are controlled by the skeletal muscle of the forearms. Hand motion analysis is one of the most essential topics in rehabilitation for understanding and restoring human motor function, as the hand is very frequently used in our daily lives. We showed that muscle synergies can be well applied to gesture recognition. By augmenting the number of participants, the mean recognition rate remained at more than 96% and reflected high robustness. The results showed that the synergistic features of forearm muscles could be successfully clustered in the feature space, which enabled hand gestures to be recognized with high efficiency. A non-negative matrix factorization (NMF) algorithm was employed to decompose the pre-treated six-channel sEMG data to obtain the muscle synergy matrixes, in which the weights of each muscle channel determined the feature set for hand gesture classification. Five healthy participants executed five gestures of daily life (pinch, fist, open hand, grip, and extension) and the sEMG activity was acquired from six forearm muscles. We aimed to study whether the muscle synergies could be used for gesture recognition. Currently, surface electromyography (sEMG) features of the forearm multi-tendon muscles are widely used in gesture recognition, however, there are few investigations on the inherent physiological mechanism of muscle synergies.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |