Skip to content

Ultrasound feature evaluation for robustness to sensor shift in ultrasound sensor based hand motion recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pattern Recognition based approaches have offered great promise in the field of bio-signal controlled prosthesis. Traditionally Surface Electromyography based Approaches (SEMG) have been used to satisfy the purpose of providing Bio-Signal control in upper extremity Prosthesis. Although these methods have been shown to be robust, there still exists issues in performance within clinical environments. In recent years, Ultrasound signal based methods have seen growing interest within the field of motion Recognition, largely due to the increased resolution, deeper muscle observation, and reduced cross-talk that can be achieved in comparison to SEMG methods. However, the methods to be applied for hand Motion recognition are still only just beginning to be explored. In this paper, we shall investigate the applicability of SEMG feature extraction techniques to Ultrasound based hand motion recognition and the subsequent impact of Sensor shift on these features. The results of this study indicate that SEMG feature extraction techniques have excellent single location accuracy in Ultrasound based Hand motion recognition. However this paper more visibly presents the strong impact of Sensor Shift on A-Mode ultrasound based hand motion Recognition, and finally presents which feature extraction methods are most robust to this shift.

Original languageEnglish
Title of host publicationTowards Autonomous Robotic Systems
Subtitle of host publication20th Annual Conference, TAROS 2019, London, UK, July 3–5, 2019, Proceedings, Part I
EditorsKaspar Althoefer, Jelizaveta Konstantinova, Ketao Zhang
Number of pages11
ISBN (Electronic)978-3-030-23807-0
ISBN (Print)978-3-030-23806-3
Publication statusPublished - 28 Jun 2019
Event20th Annual Conference on Towards Autonomous Robotic Systems - London, United Kingdom
Duration: 3 Jul 20195 Jul 2019

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameLecture Notes in Artificial Intelligence
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference20th Annual Conference on Towards Autonomous Robotic Systems
Abbreviated titleTAROS 2019
CountryUnited Kingdom


  • TAROS2019_103_final_v7

    Rights statement: This is a post-peer-review, pre-copyedit version of an article published in Towards Autonomous Robotic Systems. TAROS 2019. The final authenticated version is available online at:

    Accepted author manuscript (Post-print), 577 KB, PDF document

Related information

Relations Get citation (various referencing formats)

ID: 14911373