<p><em>Objective:</em> 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. As an alternative HMI approach, ultrasound (US) has been receiving increasing attention as an alternative to EMG. Here, we developed a novel 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. </p> <p><em>Methods:</em> US and motion capture data was recorded while participants performed wrist and hand movements in up to four degrees of freedom (DoFs). A linear regression model was then used to predict the hand kinematics from the US (or sEMG, for comparison) features. The model was also implemented in real-time for a 3-DoF pointer control with minimal training data. </p> <p><em>Results:</em> In offline analysis, the wearable US system achieved an average of 0.94 in the prediction of four DoFs of the wrist and hand. sEMG reached a performance of   = 0.60. </p> <p><em>Conclusion:</em> The newly proposed A-mode US bracelet setup and processing pipeline can regress hand kinematics for up to four DoFs with higher accuracies than other previously published interfaces based on sEMG or US data. The system allowed real-time control with minimal training data </p> <p><em>Significance:</em> Wearable US technology may provide a new generation of HMIs that use muscular deformation to estimate limb movements. The proposed US system here provided robust proportional and simultaneous control over multiple DoFs. </p>

<p><em>Objective:</em> 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. </p> <p><br></p> <p><em>Methods:</em> 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. </p> <p><br></p> <p><em>Results:</em> In the offline analysis, the wearable US system achieved an average  R²of 0.94 in the prediction of four DoFs of the wrist and hand while sEMG reached a performance of R²  = 0.60. In online control, the participants achieved an average 93% completion rate of the targets. </p> <p><br></p> <p><em>Conclusion: </em>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<em>.</em> </p> <p><br></p> <p><em>Significance:</em> 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. </p>

<p><em>Objective:</em> 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. As an alternative HMI approach, ultrasound (US) has been receiving increasing attention as an alternative to EMG. Here, we developed a novel 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. </p> <p><em>Methods:</em> US and motion capture data was recorded while participants performed wrist and hand movements in up to four degrees of freedom (DoFs). A linear regression model was then used to predict the hand kinematics from the US (or sEMG, for comparison) features. The model was also implemented in real-time for a 3-DoF pointer control with minimal training data. </p> <p><em>Results:</em> In offline analysis, the wearable US system achieved an average of 0.94 in the prediction of four DoFs of the wrist and hand. sEMG reached a performance of   = 0.60. </p> <p><em>Conclusion:</em> The newly proposed A-mode US bracelet setup and processing pipeline can regress hand kinematics for up to four DoFs with higher accuracies than other previously published interfaces based on sEMG or US data. The system allowed real-time control with minimal training data </p> <p><em>Significance:</em> Wearable US technology may provide a new generation of HMIs that use muscular deformation to estimate limb movements. The proposed US system here provided robust proportional and simultaneous control over multiple DoFs. </p>