Sparse linear regression with elastic net regularization for brain-computer interfaces

John W. Kelly; Alan D. Degenhart; Daniel P. Siewiorek; Asim Smailagic; Wei Wang

doi:10.1109/EMBC.2012.6346911

Sparse linear regression with elastic net regularization for brain-computer interfaces

John W. Kelly, Alan D. Degenhart, Daniel P. Siewiorek, Asim Smailagic, Wei Wang

Section of Neuroradiology

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

13 Scopus citations

Abstract

This paper demonstrates the feasibility of decoding neuronal population signals using a sparse linear regression model with an elastic net penalty. In offline analysis of real electrocorticographic (ECoG) neural data the elastic net achieved a timepoint decoding accuracy of 95% for classifying hand grasps vs. rest, and 82% for moving a cursor in 1-D space towards a target. These results were superior to those obtained using ₂-penalized and unpenalized linear regression, and marginally better than ₁-penalized regression. Elastic net and the ₁-penalty also produced sparse feature sets, but the elastic net did not eliminate correlated features, which could result in a more stable decoder for brain-computer interfaces.

Original language	English
Title of host publication	2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012
Pages	4275-4278
Number of pages	4
DOIs	https://doi.org/10.1109/EMBC.2012.6346911
State	Published - 2012
Event	34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012 - San Diego, CA, United States Duration: Aug 28 2012 → Sep 1 2012

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)	1557-170X

Conference

Conference	34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012
Country/Territory	United States
City	San Diego, CA
Period	08/28/12 → 09/1/12

Keywords

brain-computer interfaces
elastic net
feature selection
neural signals
sparse linear regression

Access to Document

10.1109/EMBC.2012.6346911

Cite this

Kelly, J. W., Degenhart, A. D., Siewiorek, D. P., Smailagic, A., & Wang, W. (2012). Sparse linear regression with elastic net regularization for brain-computer interfaces. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012 (pp. 4275-4278). Article 6346911 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2012.6346911

Kelly, John W. ; Degenhart, Alan D. ; Siewiorek, Daniel P. et al. / Sparse linear regression with elastic net regularization for brain-computer interfaces. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012. 2012. pp. 4275-4278 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{f870d0236a18498493beb4ae535192d5,

title = "Sparse linear regression with elastic net regularization for brain-computer interfaces",

abstract = "This paper demonstrates the feasibility of decoding neuronal population signals using a sparse linear regression model with an elastic net penalty. In offline analysis of real electrocorticographic (ECoG) neural data the elastic net achieved a timepoint decoding accuracy of 95% for classifying hand grasps vs. rest, and 82% for moving a cursor in 1-D space towards a target. These results were superior to those obtained using 2-penalized and unpenalized linear regression, and marginally better than 1-penalized regression. Elastic net and the 1-penalty also produced sparse feature sets, but the elastic net did not eliminate correlated features, which could result in a more stable decoder for brain-computer interfaces.",

keywords = "brain-computer interfaces, elastic net, feature selection, neural signals, sparse linear regression",

author = "Kelly, {John W.} and Degenhart, {Alan D.} and Siewiorek, {Daniel P.} and Asim Smailagic and Wei Wang",

year = "2012",

doi = "10.1109/EMBC.2012.6346911",

language = "English",

isbn = "9781424441198",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

pages = "4275--4278",

booktitle = "2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012",

note = "34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012 ; Conference date: 28-08-2012 Through 01-09-2012",

}

Kelly, JW, Degenhart, AD, Siewiorek, DP, Smailagic, A & Wang, W 2012, Sparse linear regression with elastic net regularization for brain-computer interfaces. in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012., 6346911, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, pp. 4275-4278, 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012, San Diego, CA, United States, 08/28/12. https://doi.org/10.1109/EMBC.2012.6346911

Sparse linear regression with elastic net regularization for brain-computer interfaces. / Kelly, John W.; Degenhart, Alan D.; Siewiorek, Daniel P. et al.
2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012. 2012. p. 4275-4278 6346911 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

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

TY - GEN

T1 - Sparse linear regression with elastic net regularization for brain-computer interfaces

AU - Kelly, John W.

AU - Degenhart, Alan D.

AU - Siewiorek, Daniel P.

AU - Smailagic, Asim

AU - Wang, Wei

PY - 2012

Y1 - 2012

N2 - This paper demonstrates the feasibility of decoding neuronal population signals using a sparse linear regression model with an elastic net penalty. In offline analysis of real electrocorticographic (ECoG) neural data the elastic net achieved a timepoint decoding accuracy of 95% for classifying hand grasps vs. rest, and 82% for moving a cursor in 1-D space towards a target. These results were superior to those obtained using 2-penalized and unpenalized linear regression, and marginally better than 1-penalized regression. Elastic net and the 1-penalty also produced sparse feature sets, but the elastic net did not eliminate correlated features, which could result in a more stable decoder for brain-computer interfaces.

AB - This paper demonstrates the feasibility of decoding neuronal population signals using a sparse linear regression model with an elastic net penalty. In offline analysis of real electrocorticographic (ECoG) neural data the elastic net achieved a timepoint decoding accuracy of 95% for classifying hand grasps vs. rest, and 82% for moving a cursor in 1-D space towards a target. These results were superior to those obtained using 2-penalized and unpenalized linear regression, and marginally better than 1-penalized regression. Elastic net and the 1-penalty also produced sparse feature sets, but the elastic net did not eliminate correlated features, which could result in a more stable decoder for brain-computer interfaces.

KW - brain-computer interfaces

KW - elastic net

KW - feature selection

KW - neural signals

KW - sparse linear regression

UR - http://www.scopus.com/inward/record.url?scp=84880933444&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2012.6346911

DO - 10.1109/EMBC.2012.6346911

M3 - Conference contribution

C2 - 23366872

AN - SCOPUS:84880933444

SN - 9781424441198

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 4275

EP - 4278

BT - 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012

T2 - 34th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2012

Y2 - 28 August 2012 through 1 September 2012

ER -

Kelly JW, Degenhart AD, Siewiorek DP, Smailagic A, Wang W. Sparse linear regression with elastic net regularization for brain-computer interfaces. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2012. 2012. p. 4275-4278. 6346911. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC.2012.6346911

Sparse linear regression with elastic net regularization for brain-computer interfaces

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this