Segmentation by data point classification applied to forearm surface EMG

Jonathan Feng Shun Lin; Ali Akbar Samadani; Dana Kulić

doi:10.1007/978-3-319-33681-7_13

Segmentation by data point classification applied to forearm surface EMG

Jonathan Feng Shun Lin, Ali Akbar Samadani, Dana Kulić

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

4 Citations (Scopus)

Abstract

Recent advances in wearable technologies have led to the development of new modalities for human-machine interaction such as gesture-based interaction via surface electromyograph (EMG). An important challenge when performing EMG gesture recognition is to temporally segment the individual gestures from continuously recorded time-series data. This paper proposes an approach for EMG data segmentation, by formulating the segmentation problem as a classification task, where a classifier is used to label each data point as either a segment point or a non-segment point. The proposed EMG segmentation approach is used to recognize 9 hand gestures from forearm EMG data of 10 participants and a balanced accuracy of 83% is achieved.

Original language	English
Title of host publication	Smart City 360
Subtitle of host publication	First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers
Editors	Alberto Leon-Garcia, Radim Lenort, David Holman, David Staš, Veronika Krutilova, Pavel Wicher, Dagmar Cagáňová, Daniela Špirková, Julius Golej, Kim Nguyen
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	153-165
Number of pages	13
ISBN (Electronic)	9783319336817
ISBN (Print)	9783319336800
DOIs	https://doi.org/10.1007/978-3-319-33681-7_13
Publication status	Published - 2016
Externally published	Yes
Event	International Conference on Sustainable Solutions Beyond Mobility of Goods 2015 - Bratislava, Slovakia Duration: 13 Oct 2015 → 14 Oct 2015

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering
Publisher	Springer
Volume	166
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	International Conference on Sustainable Solutions Beyond Mobility of Goods 2015
Abbreviated title	SustainableMoG 2015
Country/Territory	Slovakia
City	Bratislava
Period	13/10/15 → 14/10/15

Keywords

Classifiers
Motion segmentation
Pattern recognition
Surface electromyography

Access to Document

10.1007/978-3-319-33681-7_13

Cite this

Lin, J. F. S., Samadani, A. A., & Kulić, D. (2016). Segmentation by data point classification applied to forearm surface EMG. In A. Leon-Garcia, R. Lenort, D. Holman, D. Staš, V. Krutilova, P. Wicher, D. Cagáňová, D. Špirková, J. Golej, & K. Nguyen (Eds.), Smart City 360: First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers (pp. 153-165). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 166). Springer. https://doi.org/10.1007/978-3-319-33681-7_13

Lin, Jonathan Feng Shun ; Samadani, Ali Akbar ; Kulić, Dana. / Segmentation by data point classification applied to forearm surface EMG. Smart City 360: First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers. editor / Alberto Leon-Garcia ; Radim Lenort ; David Holman ; David Staš ; Veronika Krutilova ; Pavel Wicher ; Dagmar Cagáňová ; Daniela Špirková ; Julius Golej ; Kim Nguyen. Cham Switzerland : Springer, 2016. pp. 153-165 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering).

@inproceedings{a48e39e56aed4b30af7f6ff237316ea1,

title = "Segmentation by data point classification applied to forearm surface EMG",

abstract = "Recent advances in wearable technologies have led to the development of new modalities for human-machine interaction such as gesture-based interaction via surface electromyograph (EMG). An important challenge when performing EMG gesture recognition is to temporally segment the individual gestures from continuously recorded time-series data. This paper proposes an approach for EMG data segmentation, by formulating the segmentation problem as a classification task, where a classifier is used to label each data point as either a segment point or a non-segment point. The proposed EMG segmentation approach is used to recognize 9 hand gestures from forearm EMG data of 10 participants and a balanced accuracy of 83% is achieved.",

keywords = "Classifiers, Motion segmentation, Pattern recognition, Surface electromyography",

author = "Lin, {Jonathan Feng Shun} and Samadani, {Ali Akbar} and Dana Kuli{\'c}",

year = "2016",

doi = "10.1007/978-3-319-33681-7_13",

language = "English",

isbn = "9783319336800",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering",

publisher = "Springer",

pages = "153--165",

editor = "Alberto Leon-Garcia and Radim Lenort and David Holman and David Sta{\v s} and Veronika Krutilova and Pavel Wicher and Dagmar Cag{\'a}{\v n}ov{\'a} and Daniela {\v S}pirkov{\'a} and Julius Golej and Kim Nguyen",

booktitle = "Smart City 360",

note = "International Conference on Sustainable Solutions Beyond Mobility of Goods 2015, SustainableMoG 2015 ; Conference date: 13-10-2015 Through 14-10-2015",

}

Lin, JFS, Samadani, AA & Kulić, D 2016, Segmentation by data point classification applied to forearm surface EMG. in A Leon-Garcia, R Lenort, D Holman, D Staš, V Krutilova, P Wicher, D Cagáňová, D Špirková, J Golej & K Nguyen (eds), Smart City 360: First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, vol. 166, Springer, Cham Switzerland, pp. 153-165, International Conference on Sustainable Solutions Beyond Mobility of Goods 2015, Bratislava, Slovakia, 13/10/15. https://doi.org/10.1007/978-3-319-33681-7_13

Segmentation by data point classification applied to forearm surface EMG. / Lin, Jonathan Feng Shun; Samadani, Ali Akbar; Kulić, Dana.
Smart City 360: First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers. ed. / Alberto Leon-Garcia; Radim Lenort; David Holman; David Staš; Veronika Krutilova; Pavel Wicher; Dagmar Cagáňová; Daniela Špirková; Julius Golej; Kim Nguyen. Cham Switzerland: Springer, 2016. p. 153-165 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering; Vol. 166).

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

TY - GEN

T1 - Segmentation by data point classification applied to forearm surface EMG

AU - Lin, Jonathan Feng Shun

AU - Samadani, Ali Akbar

AU - Kulić, Dana

PY - 2016

Y1 - 2016

N2 - Recent advances in wearable technologies have led to the development of new modalities for human-machine interaction such as gesture-based interaction via surface electromyograph (EMG). An important challenge when performing EMG gesture recognition is to temporally segment the individual gestures from continuously recorded time-series data. This paper proposes an approach for EMG data segmentation, by formulating the segmentation problem as a classification task, where a classifier is used to label each data point as either a segment point or a non-segment point. The proposed EMG segmentation approach is used to recognize 9 hand gestures from forearm EMG data of 10 participants and a balanced accuracy of 83% is achieved.

AB - Recent advances in wearable technologies have led to the development of new modalities for human-machine interaction such as gesture-based interaction via surface electromyograph (EMG). An important challenge when performing EMG gesture recognition is to temporally segment the individual gestures from continuously recorded time-series data. This paper proposes an approach for EMG data segmentation, by formulating the segmentation problem as a classification task, where a classifier is used to label each data point as either a segment point or a non-segment point. The proposed EMG segmentation approach is used to recognize 9 hand gestures from forearm EMG data of 10 participants and a balanced accuracy of 83% is achieved.

KW - Classifiers

KW - Motion segmentation

KW - Pattern recognition

KW - Surface electromyography

UR - http://www.scopus.com/inward/record.url?scp=84978229468&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-33681-7_13

DO - 10.1007/978-3-319-33681-7_13

M3 - Conference Paper

AN - SCOPUS:84978229468

SN - 9783319336800

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering

SP - 153

EP - 165

BT - Smart City 360

A2 - Leon-Garcia, Alberto

A2 - Lenort, Radim

A2 - Holman, David

A2 - Staš, David

A2 - Krutilova, Veronika

A2 - Wicher, Pavel

A2 - Cagáňová, Dagmar

A2 - Špirková, Daniela

A2 - Golej, Julius

A2 - Nguyen, Kim

PB - Springer

CY - Cham Switzerland

T2 - International Conference on Sustainable Solutions Beyond Mobility of Goods 2015

Y2 - 13 October 2015 through 14 October 2015

ER -

Lin JFS, Samadani AA, Kulić D. Segmentation by data point classification applied to forearm surface EMG. In Leon-Garcia A, Lenort R, Holman D, Staš D, Krutilova V, Wicher P, Cagáňová D, Špirková D, Golej J, Nguyen K, editors, Smart City 360: First EAI International Summit, Smart City 360° Bratislava, Slovakia and Toronto, Canada, October 13–16, 2015 Revised Selected Papers. Cham Switzerland: Springer. 2016. p. 153-165. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering). doi: 10.1007/978-3-319-33681-7_13

Segmentation by data point classification applied to forearm surface EMG

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this