The ability to predict wrist and hand motions simultaneously is essential for natural controls of hand protheses. In this paper, we propose a novel method that includes subclass discriminant analysis (SDA) and principal component analysis for the simultaneous prediction of wrist rotation (pronation/supination) and finger gestures using wearable ultrasound. We tested the method on eight finger gestures with concurrent wrist rotations. Results showed that SDA was able to achieve accurate classification of both finger gestures and wrist rotations under dynamic wrist rotations. When grouping the wrist rotations into three subclasses, about 99.2 ±1.2% of finger gestures and 92.8 ± 1.4% of wrist rotations can be accurately classified. Moreover, we found that the first principal component (PC1) of the selected ultrasound features was linear to the wrist rotation angle regardless of finger gestures. We further used PC1 in an online tracking task for continuous wrist control and demonstrated that a wrist tracking precision (R 2 ) of 0.954 ± 0.012 and a finger gesture classification accuracy of 96.5 ± 1.7% can be simultaneously achieved, with only two minutes of user training. Our proposed simultaneous wrist/hand control scheme is training-efficient and robust, paving the way for musculaturedriven artificial hand control and rehabilitation treatment.Index Terms-Subclass discriminant analysis, principal component analysis, simultaneous wrist/hand control, wearable ultrasound sensing.
It is evident that the prevailing solution, myoelectric pattern recognition for prosthetic manipulation, constrains gesture-based interaction due to the lack of proportional control information such as exerted force. This paper reports an attempt, named simultaneous gesture recognition and muscle contraction force estimation, to realize proportional pattern recognition (PPR) control taking advantage of arm muscle deformation via wearable ultrasound sensing. We experiment with eight types of predefined hand motions, with a range of 0 -60% maximum voluntary contraction (MVC) using a wearable multi-channel Amode ultrasound system. The experiment result demonstrates that above 93.7% of gestures are correctly recognized during dynamic muscle contraction forces (0 -60% MVC), albeit only training at a slight force level (<6% MVC). Besides, the adopted non-parametric Gaussian process regression estimates the muscle contraction forces accurately synchronously, with average coefficient of determination (R 2 ) and normalized root-mean-square error (nRMSE) of 0.927 and 0.102, respectively. These research outcomes demonstrate the feasibility of ultrasound-based PPR control, paving the way for musculature-driven applications including finer prosthetic control, remote manipulation and rehabilitation treatment.
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.