High Performance Wearable Ultrasound as a Human-Machine Interface for Wrist and Hand Kinematic Tracking.

OBJECTIVE: Non-invasive human machine interfaces (HMIs) have high potential in medical, entertainment, and industrial applications. Traditionally, surface electromyography (sEMG) has been used to track muscular activity and infer motor intention. Ultrasound (US) has received increasing attention as an alternative to sEMG-based HMIs. Here, we developed a portable US armband system with 24 channels and a multiple receiver approach, and compared it with existing sEMG- and US-based HMIs on movement intention decoding. METHODS: US and motion capture data was recorded while participants performed wrist and hand movements of four degrees of freedom (DoFs) and their combinations. A linear regression model was used to offline predict hand kinematics from the US (or sEMG, for comparison) features. The method was further validated in real-time for a 3-DoF target reaching task. RESULTS: In the offline analysis, the wearable US system achieved an average [Formula: see text] of 0.94 in the prediction of four DoFs of the wrist and hand while sEMG reached a performance of [Formula: see text]= 0.60. In online control, the participants achieved an average 93% completion rate of the targets. CONCLUSION: When tailored for HMIs, the proposed US A-mode system and processing pipeline can successfully regress hand kinematics both in offline and online settings with performances comparable or superior to previously published interfaces. SIGNIFICANCE: Wearable US technology may provide a new generation of HMIs that use muscular deformation to estimate limb movements. The wearable US system allowed for robust proportional and simultaneous control over multiple DoFs in both offline and online settings.

Simultaneous and proportional control of wrist and hand degrees of freedom with kinematic prediction models from high-density EMG.

To improve intuitive control and reduce training time for active upper limb prostheses, we developed a myocontrol system for 3 degrees of freedom (DoFs) of the hand and wrist. In an offline study, we systematically investigated movement sets used to train this system, to identify the optimal compromise between training time and performance. High-density surface electromyography (HDsEMG) and optical marker motion capture were recorded concurrently from the lower arms of 8 subjects performing a series of wrist and hand movements activating DoFs individually, sequentially, and simultaneously. The root mean square (RMS) feature extracted from the EMG signal and kinematics obtained from motion capture were used to train regression and classification models to predict the kinematics of wrist movements and opening and closing of the hand, respectively. Results showed successful predictions of kinematics when training with the complete training set (r2 = 0.78 for wrist regression and recall = 0.85 for hand closing/opening classification). In further analysis, the training set was substantially reduced by removing the simultaneous movements. This led to a statistically significant, but relatively small reduction of the effectiveness of the wrist controller (r2 = 0.70, p<0.05), without changes for the hand controller (closing recall = 0.83). Reducing the training time and complexity needed to control a prosthesis with simultaneous wrist control as well as detection of intention to close the hand can lead to improved uptake of upper limb prosthetics.