Movement direction decoding of local field potentials using time-evolving spatial patterns

Vijay Aditya Tadipatri; Ahmed H. Tewfik; James Ashe; Giuseppe Pellizzer; Rahul Gupta

doi:10.1109/NER.2011.5910569

Movement direction decoding of local field potentials using time-evolving spatial patterns

Vijay Aditya Tadipatri, Ahmed H. Tewfik, James Ashe, Giuseppe Pellizzer, Rahul Gupta

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

Abstract

A main disadvantage of using intra-cortical recordings for Brain Computer Interface (BCI) is their inherent non-stationarity and instability. Thus developing direction decoders for Local Field Potentials (LFP) that are robust over time becomes a difficult task. In this paper, we show the superior performance of qualitative information over the absolute power of the recorded signals by introducing a novel method, that uses time-evolving spatial patterns. This method over-performs the baseline method by 30% on an average over a two week testing period and provides a bit-rate of 0.98 per trial. Further, these spatial-patterns provide robustness against learning when new field-forces are introduced.

Original language	English (US)
Title of host publication	2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011
Pages	392-395
Number of pages	4
DOIs	https://doi.org/10.1109/NER.2011.5910569
State	Published - 2011
Externally published	Yes
Event	2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011 - Cancun, Mexico Duration: Apr 27 2011 → May 1 2011

Publication series

Name	2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011

Other

Other	2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011
Country/Territory	Mexico
City	Cancun
Period	4/27/11 → 5/1/11

Publisher link

10.1109/NER.2011.5910569

Find It

Find It at U of M Libraries

Cite this

Tadipatri, V. A., Tewfik, A. H., Ashe, J., Pellizzer, G., & Gupta, R. (2011). Movement direction decoding of local field potentials using time-evolving spatial patterns. In 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011 (pp. 392-395). Article 5910569 (2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011). https://doi.org/10.1109/NER.2011.5910569

Movement direction decoding of local field potentials using time-evolving spatial patterns. / Tadipatri, Vijay Aditya; Tewfik, Ahmed H.; Ashe, James et al.
2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011. 2011. p. 392-395 5910569 (2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011).

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

Tadipatri, VA, Tewfik, AH, Ashe, J, Pellizzer, G & Gupta, R 2011, Movement direction decoding of local field potentials using time-evolving spatial patterns. in 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011., 5910569, 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011, pp. 392-395, 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011, Cancun, Mexico, 4/27/11. https://doi.org/10.1109/NER.2011.5910569

@inproceedings{74fde830fc554c85983eacd9eac3fdbd,

title = "Movement direction decoding of local field potentials using time-evolving spatial patterns",

abstract = "A main disadvantage of using intra-cortical recordings for Brain Computer Interface (BCI) is their inherent non-stationarity and instability. Thus developing direction decoders for Local Field Potentials (LFP) that are robust over time becomes a difficult task. In this paper, we show the superior performance of qualitative information over the absolute power of the recorded signals by introducing a novel method, that uses time-evolving spatial patterns. This method over-performs the baseline method by 30% on an average over a two week testing period and provides a bit-rate of 0.98 per trial. Further, these spatial-patterns provide robustness against learning when new field-forces are introduced.",

author = "Tadipatri, {Vijay Aditya} and Tewfik, {Ahmed H.} and James Ashe and Giuseppe Pellizzer and Rahul Gupta",

year = "2011",

doi = "10.1109/NER.2011.5910569",

language = "English (US)",

isbn = "9781424441402",

series = "2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011",

pages = "392--395",

booktitle = "2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011",

note = "2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011 ; Conference date: 27-04-2011 Through 01-05-2011",

}

TY - GEN

T1 - Movement direction decoding of local field potentials using time-evolving spatial patterns

AU - Tadipatri, Vijay Aditya

AU - Tewfik, Ahmed H.

AU - Ashe, James

AU - Pellizzer, Giuseppe

AU - Gupta, Rahul

PY - 2011

Y1 - 2011

N2 - A main disadvantage of using intra-cortical recordings for Brain Computer Interface (BCI) is their inherent non-stationarity and instability. Thus developing direction decoders for Local Field Potentials (LFP) that are robust over time becomes a difficult task. In this paper, we show the superior performance of qualitative information over the absolute power of the recorded signals by introducing a novel method, that uses time-evolving spatial patterns. This method over-performs the baseline method by 30% on an average over a two week testing period and provides a bit-rate of 0.98 per trial. Further, these spatial-patterns provide robustness against learning when new field-forces are introduced.

AB - A main disadvantage of using intra-cortical recordings for Brain Computer Interface (BCI) is their inherent non-stationarity and instability. Thus developing direction decoders for Local Field Potentials (LFP) that are robust over time becomes a difficult task. In this paper, we show the superior performance of qualitative information over the absolute power of the recorded signals by introducing a novel method, that uses time-evolving spatial patterns. This method over-performs the baseline method by 30% on an average over a two week testing period and provides a bit-rate of 0.98 per trial. Further, these spatial-patterns provide robustness against learning when new field-forces are introduced.

UR - http://www.scopus.com/inward/record.url?scp=79960351398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960351398&partnerID=8YFLogxK

U2 - 10.1109/NER.2011.5910569

DO - 10.1109/NER.2011.5910569

M3 - Conference contribution

AN - SCOPUS:79960351398

SN - 9781424441402

T3 - 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011

SP - 392

EP - 395

BT - 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011

T2 - 2011 5th International IEEE/EMBS Conference on Neural Engineering, NER 2011

Y2 - 27 April 2011 through 1 May 2011

ER -

Movement direction decoding of local field potentials using time-evolving spatial patterns

Abstract

Publication series

Other

Publisher link

Find It

Other files and links

Fingerprint

Cite this