Classifying the intent of novel users during human locomotion using powered lower limb prostheses

Aaron J. Young, Ann M. Simon, Nicholas P. Fey, Levi J. Hargrove

Research output: Chapter in Book/Report/Conference proceedingConference contribution

21 Citations (Scopus)

Abstract

Intent recognition systems using pattern recognition technology to control powered lower-limb prostheses are promising for seamlessly changing between locomotion modes - such as transitioning from level walking to stair ascent. These transitions can be accomplished by training an algorithm to recognize the patterns of mechanical and/or myoelectric signals an amputee generates during and between different locomotion modes. While low error rates can be achieved with this method, it typically requires a substantial amount of training data to be gathered. To alleviate this burden, this study investigated training a user-independent classifier from a pool of lower limb amputees performing level walking, ramps and stairs on a powered prosthesis and tested generalization of the classifier to a novel subject. The effect of using the amputee's EMG signals in combination with the mechanical sensors on the leg was also evaluated for this user-independent classifier. Generalization was poor to a novel subject - 48% overall recognition rate with EMG and 62% without (mechanical sensors only). However, an important system improvement could be made by including a few level walking trials of the novel subject (only a few minutes of data collection) in the training data, the overall recognition rate improved to 86% with EMG and 83% without.

Original languageEnglish (US)
Title of host publication2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
Pages311-314
Number of pages4
DOIs
StatePublished - Dec 1 2013
Event2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013 - San Diego, CA, United States
Duration: Nov 6 2013Nov 8 2013

Other

Other2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
CountryUnited States
CitySan Diego, CA
Period11/6/1311/8/13

Fingerprint

Prosthetics
Pattern recognition systems
Stairs
Classifiers
Sensors

ASJC Scopus subject areas

  • Artificial Intelligence
  • Mechanical Engineering

Cite this

Young, A. J., Simon, A. M., Fey, N. P., & Hargrove, L. J. (2013). Classifying the intent of novel users during human locomotion using powered lower limb prostheses. In 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013 (pp. 311-314). [6695934] https://doi.org/10.1109/NER.2013.6695934

Classifying the intent of novel users during human locomotion using powered lower limb prostheses. / Young, Aaron J.; Simon, Ann M.; Fey, Nicholas P.; Hargrove, Levi J.

2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. p. 311-314 6695934.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Young, AJ, Simon, AM, Fey, NP & Hargrove, LJ 2013, Classifying the intent of novel users during human locomotion using powered lower limb prostheses. in 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013., 6695934, pp. 311-314, 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013, San Diego, CA, United States, 11/6/13. https://doi.org/10.1109/NER.2013.6695934
Young AJ, Simon AM, Fey NP, Hargrove LJ. Classifying the intent of novel users during human locomotion using powered lower limb prostheses. In 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. p. 311-314. 6695934 https://doi.org/10.1109/NER.2013.6695934
Young, Aaron J. ; Simon, Ann M. ; Fey, Nicholas P. ; Hargrove, Levi J. / Classifying the intent of novel users during human locomotion using powered lower limb prostheses. 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. pp. 311-314
@inproceedings{bbcaef66ab63458f82488d1044a65acc,
title = "Classifying the intent of novel users during human locomotion using powered lower limb prostheses",
abstract = "Intent recognition systems using pattern recognition technology to control powered lower-limb prostheses are promising for seamlessly changing between locomotion modes - such as transitioning from level walking to stair ascent. These transitions can be accomplished by training an algorithm to recognize the patterns of mechanical and/or myoelectric signals an amputee generates during and between different locomotion modes. While low error rates can be achieved with this method, it typically requires a substantial amount of training data to be gathered. To alleviate this burden, this study investigated training a user-independent classifier from a pool of lower limb amputees performing level walking, ramps and stairs on a powered prosthesis and tested generalization of the classifier to a novel subject. The effect of using the amputee's EMG signals in combination with the mechanical sensors on the leg was also evaluated for this user-independent classifier. Generalization was poor to a novel subject - 48{\%} overall recognition rate with EMG and 62{\%} without (mechanical sensors only). However, an important system improvement could be made by including a few level walking trials of the novel subject (only a few minutes of data collection) in the training data, the overall recognition rate improved to 86{\%} with EMG and 83{\%} without.",
author = "Young, {Aaron J.} and Simon, {Ann M.} and Fey, {Nicholas P.} and Hargrove, {Levi J.}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/NER.2013.6695934",
language = "English (US)",
isbn = "9781467319690",
pages = "311--314",
booktitle = "2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013",

}

TY - GEN

T1 - Classifying the intent of novel users during human locomotion using powered lower limb prostheses

AU - Young, Aaron J.

AU - Simon, Ann M.

AU - Fey, Nicholas P.

AU - Hargrove, Levi J.

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Intent recognition systems using pattern recognition technology to control powered lower-limb prostheses are promising for seamlessly changing between locomotion modes - such as transitioning from level walking to stair ascent. These transitions can be accomplished by training an algorithm to recognize the patterns of mechanical and/or myoelectric signals an amputee generates during and between different locomotion modes. While low error rates can be achieved with this method, it typically requires a substantial amount of training data to be gathered. To alleviate this burden, this study investigated training a user-independent classifier from a pool of lower limb amputees performing level walking, ramps and stairs on a powered prosthesis and tested generalization of the classifier to a novel subject. The effect of using the amputee's EMG signals in combination with the mechanical sensors on the leg was also evaluated for this user-independent classifier. Generalization was poor to a novel subject - 48% overall recognition rate with EMG and 62% without (mechanical sensors only). However, an important system improvement could be made by including a few level walking trials of the novel subject (only a few minutes of data collection) in the training data, the overall recognition rate improved to 86% with EMG and 83% without.

AB - Intent recognition systems using pattern recognition technology to control powered lower-limb prostheses are promising for seamlessly changing between locomotion modes - such as transitioning from level walking to stair ascent. These transitions can be accomplished by training an algorithm to recognize the patterns of mechanical and/or myoelectric signals an amputee generates during and between different locomotion modes. While low error rates can be achieved with this method, it typically requires a substantial amount of training data to be gathered. To alleviate this burden, this study investigated training a user-independent classifier from a pool of lower limb amputees performing level walking, ramps and stairs on a powered prosthesis and tested generalization of the classifier to a novel subject. The effect of using the amputee's EMG signals in combination with the mechanical sensors on the leg was also evaluated for this user-independent classifier. Generalization was poor to a novel subject - 48% overall recognition rate with EMG and 62% without (mechanical sensors only). However, an important system improvement could be made by including a few level walking trials of the novel subject (only a few minutes of data collection) in the training data, the overall recognition rate improved to 86% with EMG and 83% without.

UR - http://www.scopus.com/inward/record.url?scp=84897691606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897691606&partnerID=8YFLogxK

U2 - 10.1109/NER.2013.6695934

DO - 10.1109/NER.2013.6695934

M3 - Conference contribution

AN - SCOPUS:84897691606

SN - 9781467319690

SP - 311

EP - 314

BT - 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013

ER -