A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification

Strahinja Dosen; Gauravkumar K. Patel; Claudio Castellini; Janne M. Hahne; Dario Farina

doi:10.1007/978-3-030-01845-0_204

A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification

Strahinja Dosen^*, Gauravkumar K. Patel, Claudio Castellini, Janne M. Hahne, Dario Farina

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

27 Downloads (Pure)

Abstract

The contemporary myoelectric prostheses are advanced mechatronic systems, but human-machine interfacing for robust control of these devices is still an open challenge. We present a novel method for the recognition of user intention based on pattern classification which is inspired by the natural coordination of multiple muscles during hand and wrist motions. The coordinated muscle activation produces a characteristic distribution of the amplitude features of the electromyography signals, and the novel method establishes the class boundaries to capture this natural distribution. The method has been tested in healthy subjects operating a prosthesis during a challenging functional task (bottle grasping, turning and releasing). The novel approach outperformed the commonly used benchmark (linear discriminant analysis), while using shorter training and fewer features. Further developments can, therefore, lead to a method that is suitable for practical implementation and allows robust and efficient control.

Original language	English
Title of host publication	Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018
Editors	Lorenzo Masia, Silvestro Micera, Metin Akay, José L. Pons
Number of pages	5
Publisher	Springer Publishing Company
Publication date	1 Jan 2019
Pages	1017-1021
ISBN (Print)	978-3-030-01844-3
ISBN (Electronic)	978-3-030-01845-0
DOIs	https://doi.org/10.1007/978-3-030-01845-0_204
Publication status	Published - 1 Jan 2019
Event	International Conference on Neurorehabilitation - Pisa, Italy Duration: 16 Oct 2018 → 20 Oct 2018 http://www.icnr2018.org

Conference

Conference	International Conference on Neurorehabilitation
Country/Territory	Italy
City	Pisa
Period	16/10/2018 → 20/10/2018
Internet address	http://www.icnr2018.org

Series	Biosystems and Biorobotics
Volume	21
ISSN	2195-3562

Access to Document

10.1007/978-3-030-01845-0_204

inProc.2018.Dosen.Cos_classificationAccepted author manuscript, 178 KB

Cite this

Dosen, S., Patel, G. K., Castellini, C., Hahne, J. M., & Farina, D. (2019). A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification. In L. Masia, S. Micera, M. Akay, & J. L. Pons (Eds.), Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018 (pp. 1017-1021). Springer Publishing Company. Biosystems and Biorobotics Vol. 21 https://doi.org/10.1007/978-3-030-01845-0_204

Dosen, Strahinja ; Patel, Gauravkumar K. ; Castellini, Claudio et al. / A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification. Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018. editor / Lorenzo Masia ; Silvestro Micera ; Metin Akay ; José L. Pons. Springer Publishing Company, 2019. pp. 1017-1021 (Biosystems and Biorobotics, Vol. 21).

@inproceedings{2e68c6a270e742208e315811621aace5,

title = "A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification",

abstract = "The contemporary myoelectric prostheses are advanced mechatronic systems, but human-machine interfacing for robust control of these devices is still an open challenge. We present a novel method for the recognition of user intention based on pattern classification which is inspired by the natural coordination of multiple muscles during hand and wrist motions. The coordinated muscle activation produces a characteristic distribution of the amplitude features of the electromyography signals, and the novel method establishes the class boundaries to capture this natural distribution. The method has been tested in healthy subjects operating a prosthesis during a challenging functional task (bottle grasping, turning and releasing). The novel approach outperformed the commonly used benchmark (linear discriminant analysis), while using shorter training and fewer features. Further developments can, therefore, lead to a method that is suitable for practical implementation and allows robust and efficient control.",

author = "Strahinja Dosen and Patel, {Gauravkumar K.} and Claudio Castellini and Hahne, {Janne M.} and Dario Farina",

year = "2019",

month = jan,

day = "1",

doi = "10.1007/978-3-030-01845-0_204",

language = "English",

isbn = "978-3-030-01844-3",

series = "Biosystems and Biorobotics",

publisher = "Springer Publishing Company",

pages = "1017--1021",

editor = "Masia, {Lorenzo } and Silvestro Micera and Metin Akay and Pons, {Jos{\'e} L. }",

booktitle = "Proceedings of the 4th International Conference on NeuroRehabilitation",

address = "United States",

note = "International Conference on Neurorehabilitation, ICNR ; Conference date: 16-10-2018 Through 20-10-2018",

url = "http://www.icnr2018.org",

}

Dosen, S, Patel, GK, Castellini, C, Hahne, JM & Farina, D 2019, A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification. in L Masia, S Micera, M Akay & JL Pons (eds), Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018. Springer Publishing Company, Biosystems and Biorobotics, vol. 21, pp. 1017-1021, International Conference on Neurorehabilitation, Pisa, Italy, 16/10/2018. https://doi.org/10.1007/978-3-030-01845-0_204

A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification. / Dosen, Strahinja; Patel, Gauravkumar K.; Castellini, Claudio et al.

Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018. ed. / Lorenzo Masia; Silvestro Micera; Metin Akay; José L. Pons. Springer Publishing Company, 2019. p. 1017-1021 (Biosystems and Biorobotics, Vol. 21).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification

AU - Dosen, Strahinja

AU - Patel, Gauravkumar K.

AU - Castellini, Claudio

AU - Hahne, Janne M.

AU - Farina, Dario

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The contemporary myoelectric prostheses are advanced mechatronic systems, but human-machine interfacing for robust control of these devices is still an open challenge. We present a novel method for the recognition of user intention based on pattern classification which is inspired by the natural coordination of multiple muscles during hand and wrist motions. The coordinated muscle activation produces a characteristic distribution of the amplitude features of the electromyography signals, and the novel method establishes the class boundaries to capture this natural distribution. The method has been tested in healthy subjects operating a prosthesis during a challenging functional task (bottle grasping, turning and releasing). The novel approach outperformed the commonly used benchmark (linear discriminant analysis), while using shorter training and fewer features. Further developments can, therefore, lead to a method that is suitable for practical implementation and allows robust and efficient control.

AB - The contemporary myoelectric prostheses are advanced mechatronic systems, but human-machine interfacing for robust control of these devices is still an open challenge. We present a novel method for the recognition of user intention based on pattern classification which is inspired by the natural coordination of multiple muscles during hand and wrist motions. The coordinated muscle activation produces a characteristic distribution of the amplitude features of the electromyography signals, and the novel method establishes the class boundaries to capture this natural distribution. The method has been tested in healthy subjects operating a prosthesis during a challenging functional task (bottle grasping, turning and releasing). The novel approach outperformed the commonly used benchmark (linear discriminant analysis), while using shorter training and fewer features. Further developments can, therefore, lead to a method that is suitable for practical implementation and allows robust and efficient control.

UR - http://www.scopus.com/inward/record.url?scp=85055321650&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-01845-0_204

DO - 10.1007/978-3-030-01845-0_204

M3 - Article in proceeding

AN - SCOPUS:85055321650

SN - 978-3-030-01844-3

T3 - Biosystems and Biorobotics

SP - 1017

EP - 1021

BT - Proceedings of the 4th International Conference on NeuroRehabilitation

A2 - Masia, Lorenzo

A2 - Micera, Silvestro

A2 - Akay, Metin

A2 - Pons, José L.

PB - Springer Publishing Company

T2 - International Conference on Neurorehabilitation

Y2 - 16 October 2018 through 20 October 2018

ER -

Dosen S, Patel GK, Castellini C, Hahne JM, Farina D. A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification. In Masia L, Micera S, Akay M, Pons JL, editors, Proceedings of the 4th International Conference on NeuroRehabilitation : ICNR2018. Springer Publishing Company. 2019. p. 1017-1021. (Biosystems and Biorobotics, Vol. 21). doi: 10.1007/978-3-030-01845-0_204

A Novel Physiologically-Inspired Method for Myoelectric Prosthesis Control Using Pattern Classification

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this