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

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

2 Citations (Scopus)

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%).

Original language	English
Title of host publication	3rd International Winter Conference on Brain-Computer Interface, BCI 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781479974948
DOIs	https://doi.org/10.1109/IWW-BCI.2015.7073021
Publication status	Published - 2015 Mar 30
Event	2015 3rd International Winter Conference on Brain-Computer Interface, BCI 2015 - Gangwon-Do, Korea, Republic of Duration: 2015 Jan 12 → 2015 Jan 14

Other

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

Keywords

common spatial pattern
EEG classification
motor imagery
nonnegative matrix factorization
random forest

ASJC Scopus subject areas

Human-Computer Interaction
Cognitive Neuroscience
Sensory Systems

Access to Document

10.1109/IWW-BCI.2015.7073021

Cite this

Nonnegative matrix factorization common spatial pattern in brain machine interface. / Tsubakida, H.; Shiratori, T.; Ishiyama, Atsushi et al.
3rd International Winter Conference on Brain-Computer Interface, BCI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7073021.

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

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

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this