Towards wearable A-mode ultrasound sensing for real-time finger motion recognition

Xingchen Yang; Xueli Sun; Dalin Zhou; Yuefeng Li; Honghai Liu

doi:10.1109/TNSRE.2018.2829913

Towards wearable A-mode ultrasound sensing for real-time finger motion recognition

Xingchen Yang, Xueli Sun, Dalin Zhou, Yuefeng Li, Honghai Liu

School of Computing

Research output: Contribution to journal › Article › peer-review

1005 Downloads (Pure)

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 recognition; an experiment is designed for both widely acceptable offline and online algorithms with eight able-bodied subjects employed. The experiment result presents that the offline recognition accuracy is up to 98.83% ± 0.79%. The real-time motion completion rate is 95.4% ± 8.7% and online motion selection time is 0.243 ± 0.127 s. The outcomes confirm the feasibility of A-mode ultrasound based wearable HMI as well as its prosperous applications in prosthetic devices, virtual reality and remote manipulation.

Original language	English
Pages (from-to)	1199-1208
Journal	IEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume	26
Issue number	6
Early online date	25 Apr 2018
DOIs	https://doi.org/10.1109/TNSRE.2018.2829913
Publication status	Early online - 25 Apr 2018

Access to Document

10.1109/TNSRE.2018.2829913

FINAL VERSION
© © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 1.75 MB

https://ieeexplore.ieee.org/document/8347147/

Data availability statement for 'Towards wearable A-mode ultrasound sensing for real-time finger motion recognition'.
Yang, X. (Creator), Sun, X. (Creator), Zhou, D. (Creator), Li, Y. (Creator) & Liu, H. (Creator), Institute of Electrical and Electronics Engineers Inc., 25 Apr 2018
DOI: 10.1109/TNSRE.2018.2829913, https://ieeexplore.ieee.org/document/8347147/figures
Dataset

Cite this

@article{32cb4129e36c41dda825b035dc15763e,

title = "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 recognition; an experiment is designed for both widely acceptable offline and online algorithms with eight able-bodied subjects employed. The experiment result presents that the offline recognition accuracy is up to 98.83% ± 0.79%. The real-time motion completion rate is 95.4% ± 8.7% and online motion selection time is 0.243 ± 0.127 s. The outcomes confirm the feasibility of A-mode ultrasound based wearable HMI as well as its prosperous applications in prosthetic devices, virtual reality and remote manipulation.",

author = "Xingchen Yang and Xueli Sun and Dalin Zhou and Yuefeng Li and Honghai Liu",

year = "2018",

month = apr,

day = "25",

doi = "10.1109/TNSRE.2018.2829913",

language = "English",

volume = "26",

pages = "1199--1208",

journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",

issn = "1534-4320",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Towards wearable A-mode ultrasound sensing for real-time finger motion recognition

AU - Yang, Xingchen

AU - Sun, Xueli

AU - Zhou, Dalin

AU - Li, Yuefeng

AU - Liu, Honghai

PY - 2018/4/25

Y1 - 2018/4/25

N2 - 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 recognition; an experiment is designed for both widely acceptable offline and online algorithms with eight able-bodied subjects employed. The experiment result presents that the offline recognition accuracy is up to 98.83% ± 0.79%. The real-time motion completion rate is 95.4% ± 8.7% and online motion selection time is 0.243 ± 0.127 s. The outcomes confirm the feasibility of A-mode ultrasound based wearable HMI as well as its prosperous applications in prosthetic devices, virtual reality and remote manipulation.

AB - 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 recognition; an experiment is designed for both widely acceptable offline and online algorithms with eight able-bodied subjects employed. The experiment result presents that the offline recognition accuracy is up to 98.83% ± 0.79%. The real-time motion completion rate is 95.4% ± 8.7% and online motion selection time is 0.243 ± 0.127 s. The outcomes confirm the feasibility of A-mode ultrasound based wearable HMI as well as its prosperous applications in prosthetic devices, virtual reality and remote manipulation.

U2 - 10.1109/TNSRE.2018.2829913

DO - 10.1109/TNSRE.2018.2829913

M3 - Article

SN - 1534-4320

VL - 26

SP - 1199

EP - 1208

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

IS - 6

ER -

Towards wearable A-mode ultrasound sensing for real-time finger motion recognition

Abstract

Access to Document

Fingerprint

Datasets

Data availability statement for 'Towards wearable A-mode ultrasound sensing for real-time finger motion recognition'.

Cite this