Multi-length windowed feature selection for surface EMG based hand motion recognition

Dalin Zhou; Yinfeng Fang; Zhaojie Ju; Honghai Liu

doi:10.1007/978-3-319-97586-3_24

Multi-length windowed feature selection for surface EMG based hand motion recognition

Dalin Zhou, Yinfeng Fang, Zhaojie Ju, Honghai Liu

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

196 Downloads (Pure)

Abstract

Feature selection for surface electromyography based hand motion recognition has been seen to retrieve an optimal or quasi-optimal feature subset for classification. This work aims to consider the influence of channel, feature and window length simultaneously with an emphasis on the multiple segmentation. The bacterial memetic algorithm is applied to select the feature candidates from time domain and autoregressive coefficients, which is measured by the inter-day hand motion recognition accuracy. The evaluation is conducted on a case study of 3 able-bodied subjects performing 9 hand motions in consecutive 7 days with 4 different window lengths adopted for the electromyographic data segmentation. Classification in combination with the multi-length windowed feature selection achieved an improved recognition accuracy in comparison with using solely the single-length windowed features in inter-day scenarios and indicated that complementary information to full length segmentation resides in the sub-windows, thus providing feasible feature combinations for conventional pattern recognition based solutions to prosthetic control.

Original language	English
Title of host publication	Intelligent Robotics and Applications
Subtitle of host publication	11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I
Editors	Zhiyong Chen, Alexandre Mendes, Yamin Yan, Shifeng Chen
Publisher	Springer
Pages	264-274
Number of pages	11
ISBN (Electronic)	978-3-319-97586-3
ISBN (Print)	978-3-319-97585-6
DOIs	https://doi.org/10.1007/978-3-319-97586-3_24
Publication status	Published - 20 Aug 2018
Event	11th International Conference on Intelligent Robotics and Applications - Australia, Newcastle, Australia Duration: 9 Aug 2018 → 11 Aug 2018 http://www.icira2018.org

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10984
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	11th International Conference on Intelligent Robotics and Applications
Abbreviated title	ICIRA 2018
Country/Territory	Australia
City	Newcastle
Period	9/08/18 → 11/08/18
Internet address	http://www.icira2018.org

Keywords

electromyography
hand motion recognition
window segmentation
feature selection
bacterial memetic algorithm

Access to Document

10.1007/978-3-319-97586-3_24

multi_length_windowed_7_
This is a post-peer-review, pre-copyedit version of an article published in Lecture Notes in Computer Science. The final authenticated version is available online at: http://dx.doi.org/10.1007/978-3-319-97586-3_24.
Accepted author manuscript (Post-print), 547 KB

Cite this

Zhou, D., Fang, Y., Ju, Z., & Liu, H. (2018). Multi-length windowed feature selection for surface EMG based hand motion recognition. In Z. Chen, A. Mendes, Y. Yan, & S. Chen (Eds.), Intelligent Robotics and Applications: 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I (pp. 264-274). (Lecture Notes in Computer Science; Vol. 10984). Springer. https://doi.org/10.1007/978-3-319-97586-3_24

Zhou, Dalin ; Fang, Yinfeng ; Ju, Zhaojie et al. / Multi-length windowed feature selection for surface EMG based hand motion recognition. Intelligent Robotics and Applications: 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I. editor / Zhiyong Chen ; Alexandre Mendes ; Yamin Yan ; Shifeng Chen. Springer, 2018. pp. 264-274 (Lecture Notes in Computer Science).

@inproceedings{734357796502498d9866b65def139a0b,

title = "Multi-length windowed feature selection for surface EMG based hand motion recognition",

abstract = "Feature selection for surface electromyography based hand motion recognition has been seen to retrieve an optimal or quasi-optimal feature subset for classification. This work aims to consider the influence of channel, feature and window length simultaneously with an emphasis on the multiple segmentation. The bacterial memetic algorithm is applied to select the feature candidates from time domain and autoregressive coefficients, which is measured by the inter-day hand motion recognition accuracy. The evaluation is conducted on a case study of 3 able-bodied subjects performing 9 hand motions in consecutive 7 days with 4 different window lengths adopted for the electromyographic data segmentation. Classification in combination with the multi-length windowed feature selection achieved an improved recognition accuracy in comparison with using solely the single-length windowed features in inter-day scenarios and indicated that complementary information to full length segmentation resides in the sub-windows, thus providing feasible feature combinations for conventional pattern recognition based solutions to prosthetic control.",

keywords = "electromyography, hand motion recognition, window segmentation, feature selection, bacterial memetic algorithm",

author = "Dalin Zhou and Yinfeng Fang and Zhaojie Ju and Honghai Liu",

year = "2018",

month = aug,

day = "20",

doi = "10.1007/978-3-319-97586-3_24",

language = "English",

isbn = "978-3-319-97585-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "264--274",

editor = "Zhiyong Chen and Alexandre Mendes and Yamin Yan and Shifeng Chen",

booktitle = "Intelligent Robotics and Applications",

note = "11th International Conference on Intelligent Robotics and Applications, ICIRA 2018 ; Conference date: 09-08-2018 Through 11-08-2018",

url = "http://www.icira2018.org",

}

Zhou, D, Fang, Y, Ju, Z & Liu, H 2018, Multi-length windowed feature selection for surface EMG based hand motion recognition. in Z Chen, A Mendes, Y Yan & S Chen (eds), Intelligent Robotics and Applications: 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I. Lecture Notes in Computer Science, vol. 10984, Springer, pp. 264-274, 11th International Conference on Intelligent Robotics and Applications, Newcastle, New South Wales, Australia, 9/08/18. https://doi.org/10.1007/978-3-319-97586-3_24

Multi-length windowed feature selection for surface EMG based hand motion recognition. / Zhou, Dalin; Fang, Yinfeng; Ju, Zhaojie et al.
Intelligent Robotics and Applications: 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I. ed. / Zhiyong Chen; Alexandre Mendes; Yamin Yan; Shifeng Chen. Springer, 2018. p. 264-274 (Lecture Notes in Computer Science; Vol. 10984).

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

TY - GEN

T1 - Multi-length windowed feature selection for surface EMG based hand motion recognition

AU - Zhou, Dalin

AU - Fang, Yinfeng

AU - Ju, Zhaojie

AU - Liu, Honghai

PY - 2018/8/20

Y1 - 2018/8/20

N2 - Feature selection for surface electromyography based hand motion recognition has been seen to retrieve an optimal or quasi-optimal feature subset for classification. This work aims to consider the influence of channel, feature and window length simultaneously with an emphasis on the multiple segmentation. The bacterial memetic algorithm is applied to select the feature candidates from time domain and autoregressive coefficients, which is measured by the inter-day hand motion recognition accuracy. The evaluation is conducted on a case study of 3 able-bodied subjects performing 9 hand motions in consecutive 7 days with 4 different window lengths adopted for the electromyographic data segmentation. Classification in combination with the multi-length windowed feature selection achieved an improved recognition accuracy in comparison with using solely the single-length windowed features in inter-day scenarios and indicated that complementary information to full length segmentation resides in the sub-windows, thus providing feasible feature combinations for conventional pattern recognition based solutions to prosthetic control.

AB - Feature selection for surface electromyography based hand motion recognition has been seen to retrieve an optimal or quasi-optimal feature subset for classification. This work aims to consider the influence of channel, feature and window length simultaneously with an emphasis on the multiple segmentation. The bacterial memetic algorithm is applied to select the feature candidates from time domain and autoregressive coefficients, which is measured by the inter-day hand motion recognition accuracy. The evaluation is conducted on a case study of 3 able-bodied subjects performing 9 hand motions in consecutive 7 days with 4 different window lengths adopted for the electromyographic data segmentation. Classification in combination with the multi-length windowed feature selection achieved an improved recognition accuracy in comparison with using solely the single-length windowed features in inter-day scenarios and indicated that complementary information to full length segmentation resides in the sub-windows, thus providing feasible feature combinations for conventional pattern recognition based solutions to prosthetic control.

KW - electromyography

KW - hand motion recognition

KW - window segmentation

KW - feature selection

KW - bacterial memetic algorithm

UR - http://www.scopus.com/inward/record.url?scp=85051858551&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-97586-3_24

DO - 10.1007/978-3-319-97586-3_24

M3 - Conference contribution

SN - 978-3-319-97585-6

T3 - Lecture Notes in Computer Science

SP - 264

EP - 274

BT - Intelligent Robotics and Applications

A2 - Chen, Zhiyong

A2 - Mendes, Alexandre

A2 - Yan, Yamin

A2 - Chen, Shifeng

PB - Springer

T2 - 11th International Conference on Intelligent Robotics and Applications

Y2 - 9 August 2018 through 11 August 2018

ER -

Zhou D, Fang Y, Ju Z , Liu H. Multi-length windowed feature selection for surface EMG based hand motion recognition. In Chen Z, Mendes A, Yan Y, Chen S, editors, Intelligent Robotics and Applications: 11th International Conference, ICIRA 2018, Newcastle, NSW, Australia, August 9–11, 2018, Proceedings, Part I. Springer. 2018. p. 264-274. (Lecture Notes in Computer Science). Epub 2018 Aug 3. doi: 10.1007/978-3-319-97586-3_24

Multi-length windowed feature selection for surface EMG based hand motion recognition

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this