EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing

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

doi:10.1145/2858036.2858093

EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing

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

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

89 Citations (Scopus)

4408 Downloads (Pure)

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	Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16)
Publisher	Association for Computing Machinery (ACM)
Pages	2332-2342
Number of pages	11
ISBN (Print)	9781450333627
DOIs	https://doi.org/10.1145/2858036.2858093
Publication status	Published - 7 May 2016
Event	34th Annual CHI Conference on Human Factors in Computing Systems, CHI 2016: chi4good - San Jose, United States Duration: 7 May 2016 → 12 May 2016 Conference number: 34 https://chi2016.acm.org/wp/

Conference

Conference	34th Annual CHI Conference on Human Factors in Computing Systems, CHI 2016
Abbreviated title	CHI 2016
Country/Territory	United States
City	San Jose
Period	7/05/16 → 12/05/16
Other	For those who are finding out about CHI – pronounced kai – for the first time, CHI is a place to see, discuss and learn about the future of how people interact with technology. At any minute you might experience a new gesture interface for tablets, learn how developing countries use mobile phones for maternal health, play soccer against someone 3000 miles away, or debate the future of online education. You’ll meet with top researchers from universities, corporations and startups from across the world, as well as the brightest student scientists, designers, and researchers. It’s a place to find your community, to talk about your toughest problems, and to find your next job.
Internet address	https://chi2016.acm.org/wp/

Keywords

Hand Gestures
Electromyography (EMG)
Pressure
Force Sensitive Resistors
Practical Wearable Device Design

Access to Document

10.1145/2858036.2858093

Jess McIntosh - EMPress
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via ACM at http://dl.acm.org/citation.cfm?id=2858093&CFID=803798395&CFTOKEN=17436186. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 2.09 MB

Handle.net

Persistent link

Professor Mike Fraser
- Mike.Fraserbristol.acuk
- Engineering Faculty Office - Head of School
- School of Computer Science - Professor of Human-Computer Interaction
Person: Academic , Professional and Administrative

Cite this

McIntosh, J., McNeill, C., Fraser, M. C., Kerber, F., Löchtefeld, M., & Krüger, A. (2016). EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing. In Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16) (pp. 2332-2342). Association for Computing Machinery (ACM). https://doi.org/10.1145/2858036.2858093

@inproceedings{621068a730f346acb7dfe07e1f364358,

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 moreaccurate 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 = "Hand Gestures, Electromyography (EMG), Pressure, Force Sensitive Resistors, Practical Wearable Device Design",

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

year = "2016",

month = may,

day = "7",

doi = "10.1145/2858036.2858093",

language = "English",

isbn = "9781450333627",

pages = "2332--2342",

booktitle = "Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16)",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "34th Annual CHI Conference on Human Factors in Computing Systems, CHI 2016 : chi4good, CHI 2016 ; Conference date: 07-05-2016 Through 12-05-2016",

url = "https://chi2016.acm.org/wp/",

}

McIntosh, J, McNeill, C, Fraser, MC, Kerber, F, Löchtefeld, M & Krüger, A 2016, EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing. in Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16). Association for Computing Machinery (ACM), pp. 2332-2342, 34th Annual CHI Conference on Human Factors in Computing Systems, CHI 2016, San Jose, California, United States, 7/05/16. 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 C et al.
Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16). Association for Computing Machinery (ACM), 2016. p. 2332-2342.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - EMPress

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

AU - McIntosh, Jess

AU - McNeill, Charlie

AU - Fraser, Mike C

AU - Kerber, Frederic

AU - Löchtefeld, Markus

AU - Krüger, Antonio

N1 - Conference code: 34

PY - 2016/5/7

Y1 - 2016/5/7

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 moreaccurate 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 moreaccurate 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 - Hand Gestures

KW - Electromyography (EMG)

KW - Pressure

KW - Force Sensitive Resistors

KW - Practical Wearable Device Design

U2 - 10.1145/2858036.2858093

DO - 10.1145/2858036.2858093

M3 - Conference Contribution (Conference Proceeding)

SN - 9781450333627

SP - 2332

EP - 2342

BT - Proceedings of the 34th Annual ACM Conference on Human Factors in Computing Systems (CHI'16)

PB - Association for Computing Machinery (ACM)

Y2 - 7 May 2016 through 12 May 2016

ER -

EMPress: Practical Hand Gesture Classification with Wrist-Mounted EMG and Pressure Sensing

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Profiles

Professor Mike Fraser

Cite this