EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing

Jess McIntosh; Charlie McNeill; Mike Fraser; Frederic Kerber; Markus Lochtefeld; Antonio Krüger

doi:10.1145/2858036.2858093

EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing

Jess McIntosh, Charlie McNeill, Mike Fraser, Frederic Kerber, Markus Lochtefeld, Antonio Krüger

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

51 Citations (Scopus)

Abstract

Practical wearable gesture tracking requires that sensors align with existing ergonomic device forms. We show that combining EMG and pressure data sensed only at the wrist can support accurate classification of hand gestures. A pilot study with unintended EMG electrode pressure variability led to exploration of the approach in greater depth. The EMPress technique senses both finger movements and rotations around the wrist and forearm, covering a wide range of gestures, with an overall 10-fold cross validation classification accuracy of 96%. We show that EMG is especially suited to sensing finger movements, that pressure is suited to sensing wrist and forearm rotations, and their combination is significantly more accurate for a range of gestures than either technique alone. The technique is well suited to existing wearable device forms such as smart watches that are already mounted on the wrist.

Original language	English
Title of host publication	CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems
Publisher	Association for Computing Machinery
Pages	2332-2342
Number of pages	11
ISBN (Electronic)	9781450333627
DOIs	https://doi.org/10.1145/2858036.2858093
Publication status	Published - 31 May 2016
Event	34th Annual Conference on Human Factors in Computing Systems, CHI 2016 - San Jose, USA United States Duration: 7 May 2016 → 12 May 2016

Publication series

Name	Conference on Human Factors in Computing Systems - Proceedings
Publisher	CHI

Conference

Conference	34th Annual Conference on Human Factors in Computing Systems, CHI 2016
Country	USA United States
City	San Jose
Period	7/05/16 → 12/05/16

Keywords

Electromyography (EMG)
Force sensitive resistors
Hand gestures
Practical wearable device design
Pressure

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Access to Document

10.1145/2858036.2858093

Link to publication in Scopus

Fingerprint Dive into the research topics of 'EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing'. Together they form a unique fingerprint.

Mike Fraser
- mcf35@bath.ac.uk
- Department of Computer Science - Head of Department
- EPSRC Centre for Doctoral Training in Cyber Security
Person: Research & Teaching

Cite this

McIntosh, J., McNeill, C., Fraser, M., Kerber, F., Lochtefeld, M., & Krüger, A. (2016). EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing. In CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems (pp. 2332-2342). (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/2858036.2858093

EMPress : Practical hand gesture classification with wrist-mounted EMG and pressure sensing. / McIntosh, Jess; McNeill, Charlie; Fraser, Mike; Kerber, Frederic; Lochtefeld, Markus; Krüger, Antonio.

CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2016. p. 2332-2342 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

McIntosh, J, McNeill, C, Fraser, M, Kerber, F, Lochtefeld, M & Krüger, A 2016, EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing. in CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, pp. 2332-2342, 34th Annual Conference on Human Factors in Computing Systems, CHI 2016, San Jose, USA United States, 7/05/16. https://doi.org/10.1145/2858036.2858093

McIntosh J, McNeill C, Fraser M, Kerber F, Lochtefeld M, Krüger A. EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing. In CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2016. p. 2332-2342. (Conference on Human Factors in Computing Systems - Proceedings). https://doi.org/10.1145/2858036.2858093

McIntosh, Jess ; McNeill, Charlie ; Fraser, Mike ; Kerber, Frederic ; Lochtefeld, Markus ; Krüger, Antonio. / EMPress : Practical hand gesture classification with wrist-mounted EMG and pressure sensing. CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2016. pp. 2332-2342 (Conference on Human Factors in Computing Systems - Proceedings).

@inproceedings{82c079f273734aafb37755bf7bfd8010,

title = "EMPress: Practical hand gesture classification with wrist-mounted EMG and pressure sensing",

abstract = "Practical wearable gesture tracking requires that sensors align with existing ergonomic device forms. We show that combining EMG and pressure data sensed only at the wrist can support accurate classification of hand gestures. A pilot study with unintended EMG electrode pressure variability led to exploration of the approach in greater depth. The EMPress technique senses both finger movements and rotations around the wrist and forearm, covering a wide range of gestures, with an overall 10-fold cross validation classification accuracy of 96%. We show that EMG is especially suited to sensing finger movements, that pressure is suited to sensing wrist and forearm rotations, and their combination is significantly more accurate for a range of gestures than either technique alone. The technique is well suited to existing wearable device forms such as smart watches that are already mounted on the wrist.",

keywords = "Electromyography (EMG), Force sensitive resistors, Hand gestures, Practical wearable device design, Pressure",

author = "Jess McIntosh and Charlie McNeill and Mike Fraser and Frederic Kerber and Markus Lochtefeld and Antonio Kr{\"u}ger",

year = "2016",

month = may,

day = "31",

doi = "10.1145/2858036.2858093",

language = "English",

series = "Conference on Human Factors in Computing Systems - Proceedings",

publisher = "Association for Computing Machinery",

pages = "2332--2342",

booktitle = "CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems",

address = "USA United States",

note = "34th Annual Conference on Human Factors in Computing Systems, CHI 2016 ; Conference date: 07-05-2016 Through 12-05-2016",

}

TY - GEN

T1 - EMPress

T2 - 34th Annual Conference on Human Factors in Computing Systems, CHI 2016

AU - McIntosh, Jess

AU - McNeill, Charlie

AU - Fraser, Mike

AU - Kerber, Frederic

AU - Lochtefeld, Markus

AU - Krüger, Antonio

PY - 2016/5/31

Y1 - 2016/5/31

N2 - Practical wearable gesture tracking requires that sensors align with existing ergonomic device forms. We show that combining EMG and pressure data sensed only at the wrist can support accurate classification of hand gestures. A pilot study with unintended EMG electrode pressure variability led to exploration of the approach in greater depth. The EMPress technique senses both finger movements and rotations around the wrist and forearm, covering a wide range of gestures, with an overall 10-fold cross validation classification accuracy of 96%. We show that EMG is especially suited to sensing finger movements, that pressure is suited to sensing wrist and forearm rotations, and their combination is significantly more accurate for a range of gestures than either technique alone. The technique is well suited to existing wearable device forms such as smart watches that are already mounted on the wrist.

AB - Practical wearable gesture tracking requires that sensors align with existing ergonomic device forms. We show that combining EMG and pressure data sensed only at the wrist can support accurate classification of hand gestures. A pilot study with unintended EMG electrode pressure variability led to exploration of the approach in greater depth. The EMPress technique senses both finger movements and rotations around the wrist and forearm, covering a wide range of gestures, with an overall 10-fold cross validation classification accuracy of 96%. We show that EMG is especially suited to sensing finger movements, that pressure is suited to sensing wrist and forearm rotations, and their combination is significantly more accurate for a range of gestures than either technique alone. The technique is well suited to existing wearable device forms such as smart watches that are already mounted on the wrist.

KW - Electromyography (EMG)

KW - Force sensitive resistors

KW - Hand gestures

KW - Practical wearable device design

KW - Pressure

UR - http://www.scopus.com/inward/record.url?scp=84991055037&partnerID=8YFLogxK

U2 - 10.1145/2858036.2858093

DO - 10.1145/2858036.2858093

M3 - Conference contribution

AN - SCOPUS:84991055037

T3 - Conference on Human Factors in Computing Systems - Proceedings

SP - 2332

EP - 2342

BT - CHI '16: Proceedings, 34th Annual CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

Y2 - 7 May 2016 through 12 May 2016

ER -