Covariate shift adaptation in EMG pattern recognition for prosthetic device control

Marina M C Vidovic, Liliana P. Paredes, Han Jeong Hwang, Sebastian Amsüss, Jaspar Pahl, Janne M. Hahne, Bernhard Graimann, Dario Farina, Klaus Muller

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

5 Citations (Scopus)

Abstract

Ensuring robustness of myocontrol algorithms for prosthetic devices is an important challenge. Robustness needs to be maintained under nonstationarities, e.g. due to electrode shifts after donning and doffing, sweating, additional weight or varying arm positions. Such nonstationary behavior changes the signal distributions - a scenario often referred to as covariate shift. This circumstance causes a significant decrease in classification accuracy in daily life applications. Re-training is possible but it is time consuming since it requires a large number of trials. In this paper, we propose to adapt the EMG classifier by a small calibration set only, which is able to capture the relevant aspects of the nonstationarities, but requires re-training data of only very short duration. We tested this strategy on signals acquired across 5 days in able-bodied individuals. The results showed that an estimator that shrinks the training model parameters towards the calibration set parameters significantly increased the classifier performance across different testing days. Even when using only one trial per class as re-training data for each day, the classification accuracy remained > 92% over five days. These results indicate that the proposed methodology can be a practical means for improving robustness in pattern recognition methods for myocontrol.

Original languageEnglish
Title of host publication2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4370-4373
Number of pages4
ISBN (Print)9781424479290
DOIs
Publication statusPublished - 2014 Nov 2
Externally publishedYes
Event2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 - Chicago, United States
Duration: 2014 Aug 262014 Aug 30

Other

Other2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
CountryUnited States
CityChicago
Period14/8/2614/8/30

Fingerprint

Prosthetics
Calibration
Pattern recognition
Classifiers
Equipment and Supplies
Sweating
Electrodes
Weights and Measures
Testing

ASJC Scopus subject areas

  • Health Informatics
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Vidovic, M. M. C., Paredes, L. P., Hwang, H. J., Amsüss, S., Pahl, J., Hahne, J. M., ... Muller, K. (2014). Covariate shift adaptation in EMG pattern recognition for prosthetic device control. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014 (pp. 4370-4373). [6944592] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2014.6944592

Covariate shift adaptation in EMG pattern recognition for prosthetic device control. / Vidovic, Marina M C; Paredes, Liliana P.; Hwang, Han Jeong; Amsüss, Sebastian; Pahl, Jaspar; Hahne, Janne M.; Graimann, Bernhard; Farina, Dario; Muller, Klaus.

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 4370-4373 6944592.

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

Vidovic, MMC, Paredes, LP, Hwang, HJ, Amsüss, S, Pahl, J, Hahne, JM, Graimann, B, Farina, D & Muller, K 2014, Covariate shift adaptation in EMG pattern recognition for prosthetic device control. in 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014., 6944592, Institute of Electrical and Electronics Engineers Inc., pp. 4370-4373, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014, Chicago, United States, 14/8/26. https://doi.org/10.1109/EMBC.2014.6944592
Vidovic MMC, Paredes LP, Hwang HJ, Amsüss S, Pahl J, Hahne JM et al. Covariate shift adaptation in EMG pattern recognition for prosthetic device control. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 4370-4373. 6944592 https://doi.org/10.1109/EMBC.2014.6944592
Vidovic, Marina M C ; Paredes, Liliana P. ; Hwang, Han Jeong ; Amsüss, Sebastian ; Pahl, Jaspar ; Hahne, Janne M. ; Graimann, Bernhard ; Farina, Dario ; Muller, Klaus. / Covariate shift adaptation in EMG pattern recognition for prosthetic device control. 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 4370-4373
@inproceedings{d605612442384ee98f3bb0f50df469a0,
title = "Covariate shift adaptation in EMG pattern recognition for prosthetic device control",
abstract = "Ensuring robustness of myocontrol algorithms for prosthetic devices is an important challenge. Robustness needs to be maintained under nonstationarities, e.g. due to electrode shifts after donning and doffing, sweating, additional weight or varying arm positions. Such nonstationary behavior changes the signal distributions - a scenario often referred to as covariate shift. This circumstance causes a significant decrease in classification accuracy in daily life applications. Re-training is possible but it is time consuming since it requires a large number of trials. In this paper, we propose to adapt the EMG classifier by a small calibration set only, which is able to capture the relevant aspects of the nonstationarities, but requires re-training data of only very short duration. We tested this strategy on signals acquired across 5 days in able-bodied individuals. The results showed that an estimator that shrinks the training model parameters towards the calibration set parameters significantly increased the classifier performance across different testing days. Even when using only one trial per class as re-training data for each day, the classification accuracy remained > 92{\%} over five days. These results indicate that the proposed methodology can be a practical means for improving robustness in pattern recognition methods for myocontrol.",
author = "Vidovic, {Marina M C} and Paredes, {Liliana P.} and Hwang, {Han Jeong} and Sebastian Ams{\"u}ss and Jaspar Pahl and Hahne, {Janne M.} and Bernhard Graimann and Dario Farina and Klaus Muller",
year = "2014",
month = "11",
day = "2",
doi = "10.1109/EMBC.2014.6944592",
language = "English",
isbn = "9781424479290",
pages = "4370--4373",
booktitle = "2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Covariate shift adaptation in EMG pattern recognition for prosthetic device control

AU - Vidovic, Marina M C

AU - Paredes, Liliana P.

AU - Hwang, Han Jeong

AU - Amsüss, Sebastian

AU - Pahl, Jaspar

AU - Hahne, Janne M.

AU - Graimann, Bernhard

AU - Farina, Dario

AU - Muller, Klaus

PY - 2014/11/2

Y1 - 2014/11/2

N2 - Ensuring robustness of myocontrol algorithms for prosthetic devices is an important challenge. Robustness needs to be maintained under nonstationarities, e.g. due to electrode shifts after donning and doffing, sweating, additional weight or varying arm positions. Such nonstationary behavior changes the signal distributions - a scenario often referred to as covariate shift. This circumstance causes a significant decrease in classification accuracy in daily life applications. Re-training is possible but it is time consuming since it requires a large number of trials. In this paper, we propose to adapt the EMG classifier by a small calibration set only, which is able to capture the relevant aspects of the nonstationarities, but requires re-training data of only very short duration. We tested this strategy on signals acquired across 5 days in able-bodied individuals. The results showed that an estimator that shrinks the training model parameters towards the calibration set parameters significantly increased the classifier performance across different testing days. Even when using only one trial per class as re-training data for each day, the classification accuracy remained > 92% over five days. These results indicate that the proposed methodology can be a practical means for improving robustness in pattern recognition methods for myocontrol.

AB - Ensuring robustness of myocontrol algorithms for prosthetic devices is an important challenge. Robustness needs to be maintained under nonstationarities, e.g. due to electrode shifts after donning and doffing, sweating, additional weight or varying arm positions. Such nonstationary behavior changes the signal distributions - a scenario often referred to as covariate shift. This circumstance causes a significant decrease in classification accuracy in daily life applications. Re-training is possible but it is time consuming since it requires a large number of trials. In this paper, we propose to adapt the EMG classifier by a small calibration set only, which is able to capture the relevant aspects of the nonstationarities, but requires re-training data of only very short duration. We tested this strategy on signals acquired across 5 days in able-bodied individuals. The results showed that an estimator that shrinks the training model parameters towards the calibration set parameters significantly increased the classifier performance across different testing days. Even when using only one trial per class as re-training data for each day, the classification accuracy remained > 92% over five days. These results indicate that the proposed methodology can be a practical means for improving robustness in pattern recognition methods for myocontrol.

UR - http://www.scopus.com/inward/record.url?scp=84929471501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929471501&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2014.6944592

DO - 10.1109/EMBC.2014.6944592

M3 - Conference contribution

SN - 9781424479290

SP - 4370

EP - 4373

BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -