EEG Classification with a Sequential Decision-Making Method in Motor Imagery BCI

Rong Liu, Yongxuan Wang, Geoffrey I. Newman, Nitish V Thakor, Sarah Ying

Research output: Contribution to journalArticle

Abstract

To develop subject-specific classifier to recognize mental states fast and reliably is an important issue in brain-computer interfaces (BCI), particularly in practical real-time applications such as wheelchair or neuroprosthetic control. In this paper, a sequential decision-making strategy is explored in conjunction with an optimal wavelet analysis for EEG classification. The subject-specific wavelet parameters based on a grid-search method were first developed to determine evidence accumulative curve for the sequential classifier. Then we proposed a new method to set the two constrained thresholds in the sequential probability ratio test (SPRT) based on the cumulative curve and a desired expected stopping time. As a result, it balanced the decision time of each class, and we term it balanced threshold SPRT (BTSPRT). The properties of the method were illustrated on 14 subjects' recordings from offline and online tests. Results showed the average maximum accuracy of the proposed method to be 83.4% and the average decision time of 2.77s, when compared with 79.2% accuracy and a decision time of 3.01s for the sequential Bayesian (SB) method. The BTSPRT method not only improves the classification accuracy and decision speed comparing with the other nonsequential or SB methods, but also provides an explicit relationship between stopping time, thresholds and error, which is important for balancing the speed-accuracy tradeoff. These results suggest that BTSPRT would be useful in explicitly adjusting the tradeoff between rapid decision-making and error-free device control.

Original languageEnglish (US)
Article number1750046
JournalInternational Journal of Neural Systems
Volume27
Issue number8
DOIs
StatePublished - Dec 1 2017

Fingerprint

Brain computer interface
Electroencephalography
Classifiers
Decision making
Wheelchairs
Wavelet analysis

Keywords

  • Brain-computer interface (BCI)
  • classification
  • decision-making
  • motor imagery

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

EEG Classification with a Sequential Decision-Making Method in Motor Imagery BCI. / Liu, Rong; Wang, Yongxuan; Newman, Geoffrey I.; Thakor, Nitish V; Ying, Sarah.

In: International Journal of Neural Systems, Vol. 27, No. 8, 1750046, 01.12.2017.

Research output: Contribution to journalArticle

Liu, Rong ; Wang, Yongxuan ; Newman, Geoffrey I. ; Thakor, Nitish V ; Ying, Sarah. / EEG Classification with a Sequential Decision-Making Method in Motor Imagery BCI. In: International Journal of Neural Systems. 2017 ; Vol. 27, No. 8.
@article{93a498bbff1748cf9e76c9b962b95aaa,
title = "EEG Classification with a Sequential Decision-Making Method in Motor Imagery BCI",
abstract = "To develop subject-specific classifier to recognize mental states fast and reliably is an important issue in brain-computer interfaces (BCI), particularly in practical real-time applications such as wheelchair or neuroprosthetic control. In this paper, a sequential decision-making strategy is explored in conjunction with an optimal wavelet analysis for EEG classification. The subject-specific wavelet parameters based on a grid-search method were first developed to determine evidence accumulative curve for the sequential classifier. Then we proposed a new method to set the two constrained thresholds in the sequential probability ratio test (SPRT) based on the cumulative curve and a desired expected stopping time. As a result, it balanced the decision time of each class, and we term it balanced threshold SPRT (BTSPRT). The properties of the method were illustrated on 14 subjects' recordings from offline and online tests. Results showed the average maximum accuracy of the proposed method to be 83.4{\%} and the average decision time of 2.77s, when compared with 79.2{\%} accuracy and a decision time of 3.01s for the sequential Bayesian (SB) method. The BTSPRT method not only improves the classification accuracy and decision speed comparing with the other nonsequential or SB methods, but also provides an explicit relationship between stopping time, thresholds and error, which is important for balancing the speed-accuracy tradeoff. These results suggest that BTSPRT would be useful in explicitly adjusting the tradeoff between rapid decision-making and error-free device control.",
keywords = "Brain-computer interface (BCI), classification, decision-making, motor imagery",
author = "Rong Liu and Yongxuan Wang and Newman, {Geoffrey I.} and Thakor, {Nitish V} and Sarah Ying",
year = "2017",
month = "12",
day = "1",
doi = "10.1142/S0129065717500460",
language = "English (US)",
volume = "27",
journal = "International Journal of Neural Systems",
issn = "0129-0657",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "8",

}

TY - JOUR

T1 - EEG Classification with a Sequential Decision-Making Method in Motor Imagery BCI

AU - Liu, Rong

AU - Wang, Yongxuan

AU - Newman, Geoffrey I.

AU - Thakor, Nitish V

AU - Ying, Sarah

PY - 2017/12/1

Y1 - 2017/12/1

N2 - To develop subject-specific classifier to recognize mental states fast and reliably is an important issue in brain-computer interfaces (BCI), particularly in practical real-time applications such as wheelchair or neuroprosthetic control. In this paper, a sequential decision-making strategy is explored in conjunction with an optimal wavelet analysis for EEG classification. The subject-specific wavelet parameters based on a grid-search method were first developed to determine evidence accumulative curve for the sequential classifier. Then we proposed a new method to set the two constrained thresholds in the sequential probability ratio test (SPRT) based on the cumulative curve and a desired expected stopping time. As a result, it balanced the decision time of each class, and we term it balanced threshold SPRT (BTSPRT). The properties of the method were illustrated on 14 subjects' recordings from offline and online tests. Results showed the average maximum accuracy of the proposed method to be 83.4% and the average decision time of 2.77s, when compared with 79.2% accuracy and a decision time of 3.01s for the sequential Bayesian (SB) method. The BTSPRT method not only improves the classification accuracy and decision speed comparing with the other nonsequential or SB methods, but also provides an explicit relationship between stopping time, thresholds and error, which is important for balancing the speed-accuracy tradeoff. These results suggest that BTSPRT would be useful in explicitly adjusting the tradeoff between rapid decision-making and error-free device control.

AB - To develop subject-specific classifier to recognize mental states fast and reliably is an important issue in brain-computer interfaces (BCI), particularly in practical real-time applications such as wheelchair or neuroprosthetic control. In this paper, a sequential decision-making strategy is explored in conjunction with an optimal wavelet analysis for EEG classification. The subject-specific wavelet parameters based on a grid-search method were first developed to determine evidence accumulative curve for the sequential classifier. Then we proposed a new method to set the two constrained thresholds in the sequential probability ratio test (SPRT) based on the cumulative curve and a desired expected stopping time. As a result, it balanced the decision time of each class, and we term it balanced threshold SPRT (BTSPRT). The properties of the method were illustrated on 14 subjects' recordings from offline and online tests. Results showed the average maximum accuracy of the proposed method to be 83.4% and the average decision time of 2.77s, when compared with 79.2% accuracy and a decision time of 3.01s for the sequential Bayesian (SB) method. The BTSPRT method not only improves the classification accuracy and decision speed comparing with the other nonsequential or SB methods, but also provides an explicit relationship between stopping time, thresholds and error, which is important for balancing the speed-accuracy tradeoff. These results suggest that BTSPRT would be useful in explicitly adjusting the tradeoff between rapid decision-making and error-free device control.

KW - Brain-computer interface (BCI)

KW - classification

KW - decision-making

KW - motor imagery

UR - http://www.scopus.com/inward/record.url?scp=85031904386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031904386&partnerID=8YFLogxK

U2 - 10.1142/S0129065717500460

DO - 10.1142/S0129065717500460

M3 - Article

C2 - 29046111

AN - SCOPUS:85031904386

VL - 27

JO - International Journal of Neural Systems

JF - International Journal of Neural Systems

SN - 0129-0657

IS - 8

M1 - 1750046

ER -