2018
DOI: 10.1109/tnsre.2018.2829913
|View full text |Cite
|
Sign up to set email alerts
|

Towards Wearable A-Mode Ultrasound Sensing for Real-Time Finger Motion Recognition

Abstract: It is evident that surface electromyography (sEMG) based human-machine interfaces (HMI) have inherent difficulty in predicting dexterous musculoskeletal movements such as finger motions. This paper is an attempt to investigate a plausible alternative to sEMG, ultrasound-driven HMI, for dexterous motion recognition due to its characteristic of detecting morphological changes of deep muscles and tendons. A multi-channel A-mode ultrasound lightweight device is adopted to evaluate the performance of finger motion … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
67
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
5
2

Relationship

3
4

Authors

Journals

citations
Cited by 112 publications
(75 citation statements)
references
References 49 publications
1
67
0
Order By: Relevance
“…In the part of gesture recognition, the performance of the SFO feature and the MSD feature was compared, in terms of the classification accuracy across variable force levels. While satisfying performance has been achieved by the SFO feature [4], we found that the MSD feature can further improve the classification performance in the presence of variable muscle contraction forces. As shown in Fig.…”
Section: A Methods Considerationsmentioning
confidence: 69%
See 3 more Smart Citations
“…In the part of gesture recognition, the performance of the SFO feature and the MSD feature was compared, in terms of the classification accuracy across variable force levels. While satisfying performance has been achieved by the SFO feature [4], we found that the MSD feature can further improve the classification performance in the presence of variable muscle contraction forces. As shown in Fig.…”
Section: A Methods Considerationsmentioning
confidence: 69%
“…Notice that most of above-mentioned ultrasound-related research was based on B-mode ultrasound imaging, which was cumbersome, expensive, and unrealistic to be wearable. Our pilot study has proven that wearable A-mode ultrasound can be used for dexterous finger motion recognition, confirming the ultrasound sensing's capability for wearable applications [4]. In this paper, we utilized A-mode ultrasound to evaluate the gesture recognition performance during variable muscle contraction forces and the simultaneous muscle force estimation precision, for the purpose of wearable ultrasound based PPR control.…”
Section: Introductionmentioning
confidence: 72%
See 2 more Smart Citations
“…Early studies have demonstrated that both discrete finger [15]/wrist motions [16] and continuous finger flexion [14]/wrist extension [17] can be decoded from Bmode ultrasound images, with better performance than sEMG [14]. Moreover, it is feasible to predict fine finger motions via one-dimensional A-mode ultrasound [18], [19], which is more lightweight and wearable compared to the bulky B-mode ultrasound. However, so far no study has concentrated on the prediction of simultaneous wrist/hand motion via ultrasound.…”
Section: Introductionmentioning
confidence: 99%