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
Y1 - 2007
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 -