This is the authors' abstract. We don't add key points for this paper.
In this study, a wrist-worn hand gesture recognition system consisting of 8 new pressure-based force myography (pFMG) sensors is proposed for applications of human machine interface. The pneumatic sensing chamber of each pFMG sensor is optimized to fit the size of a wrist and adapt to detect the intensity of muscular activities at the wrist. The experimental characterization demonstrates that the newly designed pFMG sensor provides measurements of good repeatability, linearity, and stability. The offline analysis of hand gesture recognition (HGR) is performed to evaluate the classification performance for five common hand gestures using the proposed wristband. The results demonstrate a high classification accuracy of over 95% (highest accuracy ~99.4%). The findings also reveal that a smaller window size maintains high HGR performance for the proposed system, supporting low-latency and real-time applications. The study on the impact of sensor number shows that, using 4–6 sensors yields higher HGR accuracy than using 8 sensors, and even a configuration with just 3 sensors achieves comparable performance to that of 8 sensors. These results underscore the considerable potential of the pFMG-based wristband as a compact, cost-effective consumer device with broad application possibilities.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: