Across-subject offline decoding of motor imagery from MEG and EEG

Research output: Contribution to journalArticleScientificpeer-review

Standard

Across-subject offline decoding of motor imagery from MEG and EEG. / Halme, Hanna-Leena; Parkkonen, Lauri.

In: Scientific Reports, Vol. 8, No. 1, 10087, 01.12.2018, p. 1-12.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{1ff66eda2c65403dbd0d1507aed585ce,
title = "Across-subject offline decoding of motor imagery from MEG and EEG",
abstract = "Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects' data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l1 - or l2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6{\%} for MEG, 67.7{\%} for EEG) were obtained using multi-task learning (MTL) with logistic regression and l2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7{\%}) accuracy. In conclusion, MTL and training with other subject's MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.",
author = "Hanna-Leena Halme and Lauri Parkkonen",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41598-018-28295-z",
language = "English",
volume = "8",
pages = "1--12",
journal = "Scientific Reports",
issn = "2045-2322",
number = "1",

}

RIS - Download

TY - JOUR

T1 - Across-subject offline decoding of motor imagery from MEG and EEG

AU - Halme, Hanna-Leena

AU - Parkkonen, Lauri

PY - 2018/12/1

Y1 - 2018/12/1

N2 - Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects' data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l1 - or l2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject's MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.

AB - Long calibration time hinders the feasibility of brain-computer interfaces (BCI). If other subjects' data were used for training the classifier, BCI-based neurofeedback practice could start without the initial calibration. Here, we compare methods for inter-subject decoding of left- vs. right-hand motor imagery (MI) from MEG and EEG. Six methods were tested on data involving MEG and EEG measurements of healthy participants. Inter-subject decoders were trained on subjects showing good within-subject accuracy, and tested on all subjects, including poor performers. Three methods were based on Common Spatial Patterns (CSP), and three others on logistic regression with l1 - or l2,1 -norm regularization. The decoding accuracy was evaluated using (1) MI and (2) passive movements (PM) for training, separately for MEG and EEG. With MI training, the best accuracies across subjects (mean 70.6% for MEG, 67.7% for EEG) were obtained using multi-task learning (MTL) with logistic regression and l2,1-norm regularization. MEG yielded slightly better average accuracies than EEG. With PM training, none of the inter-subject methods yielded above chance level (58.7%) accuracy. In conclusion, MTL and training with other subject's MI is efficient for inter-subject decoding of MI. Passive movements of other subjects are likely suboptimal for training the MI classifiers.

UR - http://www.scopus.com/inward/record.url?scp=85049696269&partnerID=8YFLogxK

U2 - 10.1038/s41598-018-28295-z

DO - 10.1038/s41598-018-28295-z

M3 - Article

VL - 8

SP - 1

EP - 12

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 10087

ER -

ID: 26688167