Echo state networks for motor control of human ECoG neuroprosthetics

Aysegul Gunduz; Mustafa C. Ozturk; Justin C. Sanchez; Jose C. Principe

doi:10.1109/CNE.2007.369722

Echo state networks for motor control of human ECoG neuroprosthetics

Aysegul Gunduz, Mustafa C. Ozturk, Justin C. Sanchez, Jose C. Principe

Biomedical Engineering

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

6 Scopus citations

Abstract

Towards non-invasive neuroprosthetic systems for motor control, electrocorticogram (ECoG) recordings provide an intermediate step from microwire single neuron recordings to electroencephalograms. Preprocessing modalities that emphasize amplitude modulation and temporal power in the ECoG are employed to build human brain-machine interfaces, which have been previously shown to modulate with hand behavior by means of linear filters, though, with limited accuracy. We improve the online decoding performance of the amplitude modulation across the recording spectra by employing echo state networks (ESNs) which provide nonlinear mappings without compromising training complexity and filter order compared to basic linear filters and other neural networks. Preliminary results show an increase of 15% in the average correlation of ESN outputs with actual hand trajectories compared to linear mappings.

Original language	English (US)
Title of host publication	Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering
Pages	514-517
Number of pages	4
DOIs	https://doi.org/10.1109/CNE.2007.369722
State	Published - Sep 25 2007
Event	3rd International IEEE EMBS Conference on Neural Engineering - Kohala Coast, HI, United States Duration: May 2 2007 → May 5 2007

Publication series

Name	Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

Other

Other	3rd International IEEE EMBS Conference on Neural Engineering
Country	United States
City	Kohala Coast, HI
Period	5/2/07 → 5/5/07

ASJC Scopus subject areas

Biotechnology
Bioengineering
Neuroscience (miscellaneous)

Access to Document

10.1109/CNE.2007.369722

Fingerprint Dive into the research topics of 'Echo state networks for motor control of human ECoG neuroprosthetics'. Together they form a unique fingerprint.

Cite this

Echo state networks for motor control of human ECoG neuroprosthetics. / Gunduz, Aysegul; Ozturk, Mustafa C.; Sanchez, Justin C.; Principe, Jose C.

Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering. 2007. p. 514-517 4227327 (Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering).

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

Gunduz, A, Ozturk, MC, Sanchez, JC & Principe, JC 2007, Echo state networks for motor control of human ECoG neuroprosthetics. in Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering., 4227327, Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering, pp. 514-517, 3rd International IEEE EMBS Conference on Neural Engineering, Kohala Coast, HI, United States, 5/2/07. https://doi.org/10.1109/CNE.2007.369722

@inproceedings{066b6d3347e842d68f6860a40fbe6be1,

title = "Echo state networks for motor control of human ECoG neuroprosthetics",

abstract = "Towards non-invasive neuroprosthetic systems for motor control, electrocorticogram (ECoG) recordings provide an intermediate step from microwire single neuron recordings to electroencephalograms. Preprocessing modalities that emphasize amplitude modulation and temporal power in the ECoG are employed to build human brain-machine interfaces, which have been previously shown to modulate with hand behavior by means of linear filters, though, with limited accuracy. We improve the online decoding performance of the amplitude modulation across the recording spectra by employing echo state networks (ESNs) which provide nonlinear mappings without compromising training complexity and filter order compared to basic linear filters and other neural networks. Preliminary results show an increase of 15% in the average correlation of ESN outputs with actual hand trajectories compared to linear mappings.",

author = "Aysegul Gunduz and Ozturk, {Mustafa C.} and Sanchez, {Justin C.} and Principe, {Jose C.}",

year = "2007",

month = sep,

day = "25",

doi = "10.1109/CNE.2007.369722",

language = "English (US)",

isbn = "1424407923",

series = "Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering",

pages = "514--517",

booktitle = "Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering",

note = "3rd International IEEE EMBS Conference on Neural Engineering ; Conference date: 02-05-2007 Through 05-05-2007",

}

TY - GEN

T1 - Echo state networks for motor control of human ECoG neuroprosthetics

AU - Gunduz, Aysegul

AU - Ozturk, Mustafa C.

AU - Sanchez, Justin C.

AU - Principe, Jose C.

PY - 2007/9/25

Y1 - 2007/9/25

N2 - Towards non-invasive neuroprosthetic systems for motor control, electrocorticogram (ECoG) recordings provide an intermediate step from microwire single neuron recordings to electroencephalograms. Preprocessing modalities that emphasize amplitude modulation and temporal power in the ECoG are employed to build human brain-machine interfaces, which have been previously shown to modulate with hand behavior by means of linear filters, though, with limited accuracy. We improve the online decoding performance of the amplitude modulation across the recording spectra by employing echo state networks (ESNs) which provide nonlinear mappings without compromising training complexity and filter order compared to basic linear filters and other neural networks. Preliminary results show an increase of 15% in the average correlation of ESN outputs with actual hand trajectories compared to linear mappings.

AB - Towards non-invasive neuroprosthetic systems for motor control, electrocorticogram (ECoG) recordings provide an intermediate step from microwire single neuron recordings to electroencephalograms. Preprocessing modalities that emphasize amplitude modulation and temporal power in the ECoG are employed to build human brain-machine interfaces, which have been previously shown to modulate with hand behavior by means of linear filters, though, with limited accuracy. We improve the online decoding performance of the amplitude modulation across the recording spectra by employing echo state networks (ESNs) which provide nonlinear mappings without compromising training complexity and filter order compared to basic linear filters and other neural networks. Preliminary results show an increase of 15% in the average correlation of ESN outputs with actual hand trajectories compared to linear mappings.

UR - http://www.scopus.com/inward/record.url?scp=34548805856&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548805856&partnerID=8YFLogxK

U2 - 10.1109/CNE.2007.369722

DO - 10.1109/CNE.2007.369722

M3 - Conference contribution

AN - SCOPUS:34548805856

SN - 1424407923

SN - 9781424407927

T3 - Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

SP - 514

EP - 517

BT - Proceedings of the 3rd International IEEE EMBS Conference on Neural Engineering

T2 - 3rd International IEEE EMBS Conference on Neural Engineering

Y2 - 2 May 2007 through 5 May 2007

ER -