Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface

Jun Yao*, Julius P A Dewald

*Corresponding author for this work

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

Abstract

This paper focuses on the problem of how time-frequency representation influences the generalization ability of the 'synthesized time-frequency spatial pattern (TFSP)' algorithm in Brain Computer Interface (BCI) for classification. TFSP methods use time-frequency analysis to extract features in both time and frequency domains. Different time-frequency analysis methods have been used before. However, it is still unknown how these different approaches influence the generalization ability. We compared the performance of three different TFSP methods in classifying 3 stroke survivors' intention in hand opening and closing. Each of these TFSP methods uses different time-frequency analysis approaches with different time-frequency resolutions. Our results show that a high resolution in time-frequency resolution doesn't guarantee better generalization ability. It seems that although large redundancy in feature reduces the generalization ability of TFSP method, certain redundancy is necessary for achieving high generalization ability.

Original languageEnglish (US)
Title of host publicationProceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Subtitle of host publicationEngineering the Future of Biomedicine, EMBC 2009
PublisherIEEE Computer Society
Pages6473-6476
Number of pages4
ISBN (Print)9781424432967
DOIs
StatePublished - Jan 1 2009
Event31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 - Minneapolis, MN, United States
Duration: Sep 2 2009Sep 6 2009

Other

Other31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009
CountryUnited States
CityMinneapolis, MN
Period9/2/099/6/09

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Aptitude
Redundancy

ASJC Scopus subject areas

  • Cell Biology
  • Developmental Biology
  • Biomedical Engineering
  • Medicine(all)

Cite this

Yao, J., & Dewald, J. P. A. (2009). Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface. In Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 (pp. 6473-6476). [5333583] IEEE Computer Society. https://doi.org/10.1109/IEMBS.2009.5333583
Yao, Jun ; Dewald, Julius P A. / Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface. Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009. IEEE Computer Society, 2009. pp. 6473-6476
@inproceedings{38e656b52caa4f5e81fa675157f2f668,
title = "Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface",
abstract = "This paper focuses on the problem of how time-frequency representation influences the generalization ability of the 'synthesized time-frequency spatial pattern (TFSP)' algorithm in Brain Computer Interface (BCI) for classification. TFSP methods use time-frequency analysis to extract features in both time and frequency domains. Different time-frequency analysis methods have been used before. However, it is still unknown how these different approaches influence the generalization ability. We compared the performance of three different TFSP methods in classifying 3 stroke survivors' intention in hand opening and closing. Each of these TFSP methods uses different time-frequency analysis approaches with different time-frequency resolutions. Our results show that a high resolution in time-frequency resolution doesn't guarantee better generalization ability. It seems that although large redundancy in feature reduces the generalization ability of TFSP method, certain redundancy is necessary for achieving high generalization ability.",
author = "Jun Yao and Dewald, {Julius P A}",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/IEMBS.2009.5333583",
language = "English (US)",
isbn = "9781424432967",
pages = "6473--6476",
booktitle = "Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society",
publisher = "IEEE Computer Society",
address = "United States",

}

Yao, J & Dewald, JPA 2009, Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface. in Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009., 5333583, IEEE Computer Society, pp. 6473-6476, 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009, Minneapolis, MN, United States, 9/2/09. https://doi.org/10.1109/IEMBS.2009.5333583

Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface. / Yao, Jun; Dewald, Julius P A.

Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009. IEEE Computer Society, 2009. p. 6473-6476 5333583.

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

TY - GEN

T1 - Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface

AU - Yao, Jun

AU - Dewald, Julius P A

PY - 2009/1/1

Y1 - 2009/1/1

N2 - This paper focuses on the problem of how time-frequency representation influences the generalization ability of the 'synthesized time-frequency spatial pattern (TFSP)' algorithm in Brain Computer Interface (BCI) for classification. TFSP methods use time-frequency analysis to extract features in both time and frequency domains. Different time-frequency analysis methods have been used before. However, it is still unknown how these different approaches influence the generalization ability. We compared the performance of three different TFSP methods in classifying 3 stroke survivors' intention in hand opening and closing. Each of these TFSP methods uses different time-frequency analysis approaches with different time-frequency resolutions. Our results show that a high resolution in time-frequency resolution doesn't guarantee better generalization ability. It seems that although large redundancy in feature reduces the generalization ability of TFSP method, certain redundancy is necessary for achieving high generalization ability.

AB - This paper focuses on the problem of how time-frequency representation influences the generalization ability of the 'synthesized time-frequency spatial pattern (TFSP)' algorithm in Brain Computer Interface (BCI) for classification. TFSP methods use time-frequency analysis to extract features in both time and frequency domains. Different time-frequency analysis methods have been used before. However, it is still unknown how these different approaches influence the generalization ability. We compared the performance of three different TFSP methods in classifying 3 stroke survivors' intention in hand opening and closing. Each of these TFSP methods uses different time-frequency analysis approaches with different time-frequency resolutions. Our results show that a high resolution in time-frequency resolution doesn't guarantee better generalization ability. It seems that although large redundancy in feature reduces the generalization ability of TFSP method, certain redundancy is necessary for achieving high generalization ability.

UR - http://www.scopus.com/inward/record.url?scp=77951015730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951015730&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2009.5333583

DO - 10.1109/IEMBS.2009.5333583

M3 - Conference contribution

SN - 9781424432967

SP - 6473

EP - 6476

BT - Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - IEEE Computer Society

ER -

Yao J, Dewald JPA. Impact of time-frequency representation to the generalization ability of synthesized time-frequency spatial patterns algorithm in brain computer interface. In Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009. IEEE Computer Society. 2009. p. 6473-6476. 5333583 https://doi.org/10.1109/IEMBS.2009.5333583