Worldwide 17 million people are left with impairment to their upper or lower limb following stroke. Functional electrical stimulation (FES) is a method of artificially activating muscles using electrical pulses and is the most common rehabilitation technology. A significant body of clinical research confirms that successful rehabilitation requires FES to be applied in a way that supports voluntary intention during repeated attempts at functional tasks. Electromyography (EMG) measures the voluntary contraction of muscles and has been used to directly control FES in openloop, however it is limited by poor accuracy. On the other hand, model-based feedback control can provide high accuracy, but does not explicitly promote voluntary intention. A new dynamic model of the muscle activation, generated by combined voluntary nerve signals and FES, is developed in this paper. It includes both nonlinear recruitment and linear activation dynamics. An efficient identification procedure is then formulated which can be applied to people with stroke. A model-based hybrid EMG/FES control scheme is then derived based on the model structure, allowing tracking and volitional intention support to be simultaneously optimized for the first time. Exploiting the repeated nature of rehabilitation, the control framework is then extended to further improve tracking accuracy. That is achieved by learning from experience through iterative learning control. The framework is experimentally tested with results confirming it can deliver greater performance compared to existing FES approaches, which do not consider voluntary action in the model or controller.
Upper limb amputation is a significant limitation for achieving routine activities. Myoelectric signals detected by electrodes well-known as Electromyography (EMG) have been targeted to control upper limb prostheses of such lost limbs. Unfortunately, the acquisition, processing and use of such myoelectric signals are sophisticated. Furthermore, it necessarily requires complex computation to fulfil accuracy, robustness, and time-consumption execution for the real-time prosthesis application. Thus, machine learning schemes for pattern recognition are a potential approach to improve the traditional control for hand prostheses due to the movement of users and muscle contraction. This paper presents real-time hand posture recognition based on three hand postures using surface EMG (sEMG) signals. sEMG signals are acquired by the electrode channel and simultaneously collected while making a hand posture. Performance evaluation relies on classification accuracy and time consumption. The performance of six real-time recognition models is evaluated which combine two projection techniques and three classifiers. Results indicate that EMG-based pattern recognition (EMG-PR) control outperforms the traditional control for hand prostheses in real-time application. The highest classification accuracy is approximately 96%, whereas the lowest time consumption is 4 ms. In addition, the accuracy is dropped when the number of electrodes decreases nearly to 3%. These outcomes can apply to real-time hand prostheses to alleviate the limited prostheses available.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations 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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.