In order to empower physical rehabilitation processes of motor disabled people, currently there is emergent efforts at scientific level aimed at developing new robotic devices such as exoskeletons. In physical therapy using robotic systems it is fundamental a high identification of human intentional movements to command such systems. To accomplish such movements identification or recognizing, in literature it have been widely used electromyographic signals (EMG) taking into account that such signals may reflect motion intention. This paper presents an evaluation of two algorithms implemented for identification of several human upper limb movements at forearm level. In the process of feature extraction of EMG signals, it were utilized the root mean square and auto-recursive model as signal characteristics. For pattern recognition were utilized two classifiers: linear discriminant analysis and an artificial neural network. All classifiers were evaluated using a set of SEMG signals and subsequently the same signals were contaminated by 60 Hz interference and white noise. Preliminary results show the robustness that presents the linear discriminant analysis method, which could be employed as part of a myoelectric control algorithm for a robotic upper limb exoskeleton.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.