Individualization of data-segment-related parameters for improvement of EEG signal classification in brain-computer interface

Hongbao Cao; Walter G. Besio; Steven Jones; Peng Zhou

doi:10.1007/s12209-010-0041-2

Individualization of data-segment-related parameters for improvement of EEG signal classification in brain-computer interface

Hongbao Cao, Walter G. Besio, Steven Jones, Peng Zhou

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects' EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.

Original language	English
Pages (from-to)	235-238
Number of pages	4
Journal	Transactions of Tianjin University
Volume	16
Issue number	3
DOIs	https://doi.org/10.1007/s12209-010-0041-2
State	Published - Jun 2010
Externally published	Yes

Keywords

Brain-computer interface (BCI)
Data segment
EEG classification
Parameter selection

Access to Document

10.1007/s12209-010-0041-2

Cite this

@article{b87e8ab8e8c7434c82f078819b594101,

title = "Individualization of data-segment-related parameters for improvement of EEG signal classification in brain-computer interface",

abstract = "In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects' EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.",

keywords = "Brain-computer interface (BCI), Data segment, EEG classification, Parameter selection",

author = "Hongbao Cao and Besio, {Walter G.} and Steven Jones and Peng Zhou",

year = "2010",

month = jun,

doi = "10.1007/s12209-010-0041-2",

language = "Ingl{\'e}s",

volume = "16",

pages = "235--238",

journal = "Transactions of Tianjin University",

issn = "1006-4982",

publisher = "Tianjin Daxue/Tianjin University",

number = "3",

}

TY - JOUR

T1 - Individualization of data-segment-related parameters for improvement of EEG signal classification in brain-computer interface

AU - Cao, Hongbao

AU - Besio, Walter G.

AU - Jones, Steven

AU - Zhou, Peng

PY - 2010/6

Y1 - 2010/6

N2 - In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects' EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.

AB - In electroencephalogram (EEG) modeling techniques, data segment selection is the first and still an important step. The influence of a set of data-segment-related parameters on feature extraction and classification in an EEG-based brain-computer interface (BCI) was studied. An auto search algorithm was developed to study four datasegment-related parameters in each trial of 12 subjects' EEG. The length of data segment (LDS), the start position of data (SPD) segment, AR order, and number of trials (NT) were used to build the model. The study showed that, compared with the classification ratio (CR) without parameter selection, the CR was increased by 20% to 30% with proper selection of these data-segment-related parameters, and the optimum parameter values were subject-dependent. This suggests that the data-segment-related parameters should be individualized when building models for BCI.

KW - Brain-computer interface (BCI)

KW - Data segment

KW - EEG classification

KW - Parameter selection

UR - http://www.scopus.com/inward/record.url?scp=77953760827&partnerID=8YFLogxK

U2 - 10.1007/s12209-010-0041-2

DO - 10.1007/s12209-010-0041-2

M3 - Artículo

AN - SCOPUS:77953760827

SN - 1006-4982

VL - 16

SP - 235

EP - 238

JO - Transactions of Tianjin University

JF - Transactions of Tianjin University

IS - 3

ER -

Individualization of data-segment-related parameters for improvement of EEG signal classification in brain-computer interface

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this