Exploring the LIMB Position Effect on Wearable-Ultrasound-Based Gesture Recognition

Despite the prosperous development of the ultrasound-based human-machine interface, its reliability in the practical applications is still unevaluated. This paper gives priority to exploring the limb position effect on the ultrasound-based gesture recognition, where wearable A-mode ultrasound is utilized instead of its cumbersome B-mode counterpart. An online experiment under eight different limb positions is conducted to validate the performance of the ultrasound-based gesture recognition, with eight able-bodied subjects employed. Results show that the influence of limb movement on the ultrasound-based gesture recognition is not significant. Overall, the real-time motion completion rate and motion recognition accuracy are 97.1% and 94.5% across different limb positions, albeit only training at a natural limb position. Moreover, it takes only 177 ms for the system to successfully recognize the intended motions across various limb positions. These results demonstrate the reliability of the ultrasound-based gesture interaction, paving the way for its practical applications.