Nonnegative matrix factorization common spatial pattern in brain machine interface

H. Tsubakida; T. Shiratori; Atsushi Ishiyama; Y. Ono

doi:10.1109/IWW-BCI.2015.7073021

Nonnegative matrix factorization common spatial pattern in brain machine interface

H. Tsubakida, T. Shiratori, Atsushi Ishiyama, Y. Ono

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Fast and accurate discrimination of Electroencephalography (EEG) data is necessary for controlling brain machine interface. This paper introduces a novel method to discriminate 2-class motor imagery states (left and right hand) using nonnegative matrix factorization (NMF), common spatial pattern (CSP) and random forest. Conventionally CSP is used after extracting frequency band segment of EEG signal, which is called bandpass-filtered CSP (BPCSP). Especially filter bank CSP (FBCSP) has been extensively used to extract feature vectors from EEG data. However in these methods, the range of frequency band needed to be specified in advance and the performance depends on the selected frequency band. Our new method can decide the frequency band automatically by using NMF (NMFCSP). After the feature vectors were extracted from EEG data, random forests (RF) method was adopted as a classification algorithm. The mean accuracy rate of 2-class classifier using NMFCSP was 78.8±3.27%. This is higher than the accuracy rate of BPCSP (64.4±8.53%) and FBCSP (68.4±6.81%).

本文言語	English
ホスト出版物のタイトル	3rd International Winter Conference on Brain-Computer Interface, BCI 2015
出版社	Institute of Electrical and Electronics Engineers Inc.
ISBN（印刷版）	9781479974948
DOI	https://doi.org/10.1109/IWW-BCI.2015.7073021
出版ステータス	Published - 2015 3月 30
イベント	2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015 - Gangwon-Do, Korea, Republic of 継続期間: 2015 1月 12 → 2015 1月 14

Other

Other	2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015
国/地域	Korea, Republic of
City	Gangwon-Do
Period	15/1/12 → 15/1/14

ASJC Scopus subject areas

人間とコンピュータの相互作用
認知神経科学
感覚系

文献へのアクセス

10.1109/IWW-BCI.2015.7073021

他のファイルとリンク

引用スタイル

Tsubakida, H, Shiratori, T, Ishiyama, A & Ono, Y 2015, Nonnegative matrix factorization common spatial pattern in brain machine interface. in 3rd International Winter Conference on Brain-Computer Interface, BCI 2015., 7073021, Institute of Electrical and Electronics Engineers Inc., 2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015, Gangwon-Do, Korea, Republic of, 15/1/12. https://doi.org/10.1109/IWW-BCI.2015.7073021

@inproceedings{838c3ceb4aa54452ab0fc5a3b011aa21,

title = "Nonnegative matrix factorization common spatial pattern in brain machine interface",

abstract = "Fast and accurate discrimination of Electroencephalography (EEG) data is necessary for controlling brain machine interface. This paper introduces a novel method to discriminate 2-class motor imagery states (left and right hand) using nonnegative matrix factorization (NMF), common spatial pattern (CSP) and random forest. Conventionally CSP is used after extracting frequency band segment of EEG signal, which is called bandpass-filtered CSP (BPCSP). Especially filter bank CSP (FBCSP) has been extensively used to extract feature vectors from EEG data. However in these methods, the range of frequency band needed to be specified in advance and the performance depends on the selected frequency band. Our new method can decide the frequency band automatically by using NMF (NMFCSP). After the feature vectors were extracted from EEG data, random forests (RF) method was adopted as a classification algorithm. The mean accuracy rate of 2-class classifier using NMFCSP was 78.8±3.27%. This is higher than the accuracy rate of BPCSP (64.4±8.53%) and FBCSP (68.4±6.81%).",

keywords = "common spatial pattern, EEG classification, motor imagery, nonnegative matrix factorization, random forest",

author = "H. Tsubakida and T. Shiratori and Atsushi Ishiyama and Y. Ono",

year = "2015",

month = mar,

day = "30",

doi = "10.1109/IWW-BCI.2015.7073021",

language = "English",

isbn = "9781479974948",

booktitle = "3rd International Winter Conference on Brain-Computer Interface, BCI 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015 ; Conference date: 12-01-2015 Through 14-01-2015",

}

TY - GEN

T1 - Nonnegative matrix factorization common spatial pattern in brain machine interface

AU - Tsubakida, H.

AU - Shiratori, T.

AU - Ishiyama, Atsushi

AU - Ono, Y.

PY - 2015/3/30

Y1 - 2015/3/30

N2 - Fast and accurate discrimination of Electroencephalography (EEG) data is necessary for controlling brain machine interface. This paper introduces a novel method to discriminate 2-class motor imagery states (left and right hand) using nonnegative matrix factorization (NMF), common spatial pattern (CSP) and random forest. Conventionally CSP is used after extracting frequency band segment of EEG signal, which is called bandpass-filtered CSP (BPCSP). Especially filter bank CSP (FBCSP) has been extensively used to extract feature vectors from EEG data. However in these methods, the range of frequency band needed to be specified in advance and the performance depends on the selected frequency band. Our new method can decide the frequency band automatically by using NMF (NMFCSP). After the feature vectors were extracted from EEG data, random forests (RF) method was adopted as a classification algorithm. The mean accuracy rate of 2-class classifier using NMFCSP was 78.8±3.27%. This is higher than the accuracy rate of BPCSP (64.4±8.53%) and FBCSP (68.4±6.81%).

AB - Fast and accurate discrimination of Electroencephalography (EEG) data is necessary for controlling brain machine interface. This paper introduces a novel method to discriminate 2-class motor imagery states (left and right hand) using nonnegative matrix factorization (NMF), common spatial pattern (CSP) and random forest. Conventionally CSP is used after extracting frequency band segment of EEG signal, which is called bandpass-filtered CSP (BPCSP). Especially filter bank CSP (FBCSP) has been extensively used to extract feature vectors from EEG data. However in these methods, the range of frequency band needed to be specified in advance and the performance depends on the selected frequency band. Our new method can decide the frequency band automatically by using NMF (NMFCSP). After the feature vectors were extracted from EEG data, random forests (RF) method was adopted as a classification algorithm. The mean accuracy rate of 2-class classifier using NMFCSP was 78.8±3.27%. This is higher than the accuracy rate of BPCSP (64.4±8.53%) and FBCSP (68.4±6.81%).

KW - common spatial pattern

KW - EEG classification

KW - motor imagery

KW - nonnegative matrix factorization

KW - random forest

UR - http://www.scopus.com/inward/record.url?scp=84927944669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927944669&partnerID=8YFLogxK

U2 - 10.1109/IWW-BCI.2015.7073021

DO - 10.1109/IWW-BCI.2015.7073021

M3 - Conference contribution

AN - SCOPUS:84927944669

SN - 9781479974948

BT - 3rd International Winter Conference on Brain-Computer Interface, BCI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015

Y2 - 12 January 2015 through 14 January 2015

ER -

Nonnegative matrix factorization common spatial pattern in brain machine interface

抄録

Other

ASJC Scopus subject areas

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル