Neural decoding using a nonlinear generative model for brain-computer interface

Henrique Dantas, Spencer Kellis, V. John Mathews, Bradley Greger

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

6 Citations (Scopus)

Abstract

Kalman filters have been used to decode neural signals and estimate hand kinematics in many studies. However, most prior work assumes a linear system model, an assumption that is almost certainly violated by neural systems. In this paper, we show that adding nonlinearities to the decoding algorithm improves the accuracy of tracking hand movements using neural signal acquired via a 32-channel micro-electrocorticographic (μECoG) grid placed over the arm and hand representations in the motor cortex. Experimental comparisons indicate that a Kalman filter with a fifth order polynomial generative model relating the hand kinematics signals to the neural signals improved the mean-square tracking performance in the hand movements over a conventional Kalman filter employing a linear system model. This finding is in accord with the current neurophysiological understanding of the decoded signals.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4683-4687
Number of pages5
ISBN (Print)9781479928927
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 - Florence, Italy
Duration: May 4 2014May 9 2014

Other

Other2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
CountryItaly
CityFlorence
Period5/4/145/9/14

Fingerprint

Brain computer interface
Kalman filters
Decoding
Linear systems
Kinematics

Keywords

  • Brain-Computer Interface
  • Neural decoding
  • Nonlinear Kalman Filter

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Dantas, H., Kellis, S., Mathews, V. J., & Greger, B. (2014). Neural decoding using a nonlinear generative model for brain-computer interface. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 4683-4687). [6854490] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2014.6854490

Neural decoding using a nonlinear generative model for brain-computer interface. / Dantas, Henrique; Kellis, Spencer; Mathews, V. John; Greger, Bradley.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 4683-4687 6854490.

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

Dantas, H, Kellis, S, Mathews, VJ & Greger, B 2014, Neural decoding using a nonlinear generative model for brain-computer interface. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6854490, Institute of Electrical and Electronics Engineers Inc., pp. 4683-4687, 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014, Florence, Italy, 5/4/14. https://doi.org/10.1109/ICASSP.2014.6854490
Dantas H, Kellis S, Mathews VJ, Greger B. Neural decoding using a nonlinear generative model for brain-computer interface. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 4683-4687. 6854490 https://doi.org/10.1109/ICASSP.2014.6854490
Dantas, Henrique ; Kellis, Spencer ; Mathews, V. John ; Greger, Bradley. / Neural decoding using a nonlinear generative model for brain-computer interface. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 4683-4687
@inproceedings{4f8e781dc02f41a39227bf2eac37049e,
title = "Neural decoding using a nonlinear generative model for brain-computer interface",
abstract = "Kalman filters have been used to decode neural signals and estimate hand kinematics in many studies. However, most prior work assumes a linear system model, an assumption that is almost certainly violated by neural systems. In this paper, we show that adding nonlinearities to the decoding algorithm improves the accuracy of tracking hand movements using neural signal acquired via a 32-channel micro-electrocorticographic (μECoG) grid placed over the arm and hand representations in the motor cortex. Experimental comparisons indicate that a Kalman filter with a fifth order polynomial generative model relating the hand kinematics signals to the neural signals improved the mean-square tracking performance in the hand movements over a conventional Kalman filter employing a linear system model. This finding is in accord with the current neurophysiological understanding of the decoded signals.",
keywords = "Brain-Computer Interface, Neural decoding, Nonlinear Kalman Filter",
author = "Henrique Dantas and Spencer Kellis and Mathews, {V. John} and Bradley Greger",
year = "2014",
doi = "10.1109/ICASSP.2014.6854490",
language = "English (US)",
isbn = "9781479928927",
pages = "4683--4687",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Neural decoding using a nonlinear generative model for brain-computer interface

AU - Dantas, Henrique

AU - Kellis, Spencer

AU - Mathews, V. John

AU - Greger, Bradley

PY - 2014

Y1 - 2014

N2 - Kalman filters have been used to decode neural signals and estimate hand kinematics in many studies. However, most prior work assumes a linear system model, an assumption that is almost certainly violated by neural systems. In this paper, we show that adding nonlinearities to the decoding algorithm improves the accuracy of tracking hand movements using neural signal acquired via a 32-channel micro-electrocorticographic (μECoG) grid placed over the arm and hand representations in the motor cortex. Experimental comparisons indicate that a Kalman filter with a fifth order polynomial generative model relating the hand kinematics signals to the neural signals improved the mean-square tracking performance in the hand movements over a conventional Kalman filter employing a linear system model. This finding is in accord with the current neurophysiological understanding of the decoded signals.

AB - Kalman filters have been used to decode neural signals and estimate hand kinematics in many studies. However, most prior work assumes a linear system model, an assumption that is almost certainly violated by neural systems. In this paper, we show that adding nonlinearities to the decoding algorithm improves the accuracy of tracking hand movements using neural signal acquired via a 32-channel micro-electrocorticographic (μECoG) grid placed over the arm and hand representations in the motor cortex. Experimental comparisons indicate that a Kalman filter with a fifth order polynomial generative model relating the hand kinematics signals to the neural signals improved the mean-square tracking performance in the hand movements over a conventional Kalman filter employing a linear system model. This finding is in accord with the current neurophysiological understanding of the decoded signals.

KW - Brain-Computer Interface

KW - Neural decoding

KW - Nonlinear Kalman Filter

UR - http://www.scopus.com/inward/record.url?scp=84905270901&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905270901&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2014.6854490

DO - 10.1109/ICASSP.2014.6854490

M3 - Conference contribution

AN - SCOPUS:84905270901

SN - 9781479928927

SP - 4683

EP - 4687

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -