Toward a model-based predictive controller design in brain-computer interfaces

M. Kamrunnahar, N. S. Dias, S. J. Schiff

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

A first step in designing a robust and optimal model-based predictive controller (MPC) for brain-computer interface (BCI) applications is presented in this article. An MPC has the potential to achieve improved BCI performance compared to the performance achieved by current ad hoc, nonmodel-based filter applications. The parameters in designing the controller were extracted as model-based features from motor imagery task-related human scalp electroencephalography. Although the parameters can be generated from any model-linear or non-linear, we here adopted a simple autoregressive model that has well-established applications in BCI task discriminations. It was shown that the parameters generated for the controller design can as well be used for motor imagery task discriminations with performance (with 8-23% task discrimination errors) comparable to the discrimination performance of the commonly used features such as frequency specific band powers and the AR model parameters directly used. An optimal MPC has significant implications for high performance BCI applications.

Original languageEnglish (US)
Pages (from-to)1482-1492
Number of pages11
JournalAnnals of Biomedical Engineering
Volume39
Issue number5
DOIs
StatePublished - May 1 2011

Fingerprint

Brain computer interface
Controllers
Electroencephalography

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{421a6b08add44cbbbaa098e61298bd48,
title = "Toward a model-based predictive controller design in brain-computer interfaces",
abstract = "A first step in designing a robust and optimal model-based predictive controller (MPC) for brain-computer interface (BCI) applications is presented in this article. An MPC has the potential to achieve improved BCI performance compared to the performance achieved by current ad hoc, nonmodel-based filter applications. The parameters in designing the controller were extracted as model-based features from motor imagery task-related human scalp electroencephalography. Although the parameters can be generated from any model-linear or non-linear, we here adopted a simple autoregressive model that has well-established applications in BCI task discriminations. It was shown that the parameters generated for the controller design can as well be used for motor imagery task discriminations with performance (with 8-23{\%} task discrimination errors) comparable to the discrimination performance of the commonly used features such as frequency specific band powers and the AR model parameters directly used. An optimal MPC has significant implications for high performance BCI applications.",
author = "M. Kamrunnahar and Dias, {N. S.} and Schiff, {S. J.}",
year = "2011",
month = "5",
day = "1",
doi = "10.1007/s10439-011-0248-y",
language = "English (US)",
volume = "39",
pages = "1482--1492",
journal = "Annals of Biomedical Engineering",
issn = "0090-6964",
publisher = "Springer Netherlands",
number = "5",

}

Toward a model-based predictive controller design in brain-computer interfaces. / Kamrunnahar, M.; Dias, N. S.; Schiff, S. J.

In: Annals of Biomedical Engineering, Vol. 39, No. 5, 01.05.2011, p. 1482-1492.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Toward a model-based predictive controller design in brain-computer interfaces

AU - Kamrunnahar, M.

AU - Dias, N. S.

AU - Schiff, S. J.

PY - 2011/5/1

Y1 - 2011/5/1

N2 - A first step in designing a robust and optimal model-based predictive controller (MPC) for brain-computer interface (BCI) applications is presented in this article. An MPC has the potential to achieve improved BCI performance compared to the performance achieved by current ad hoc, nonmodel-based filter applications. The parameters in designing the controller were extracted as model-based features from motor imagery task-related human scalp electroencephalography. Although the parameters can be generated from any model-linear or non-linear, we here adopted a simple autoregressive model that has well-established applications in BCI task discriminations. It was shown that the parameters generated for the controller design can as well be used for motor imagery task discriminations with performance (with 8-23% task discrimination errors) comparable to the discrimination performance of the commonly used features such as frequency specific band powers and the AR model parameters directly used. An optimal MPC has significant implications for high performance BCI applications.

AB - A first step in designing a robust and optimal model-based predictive controller (MPC) for brain-computer interface (BCI) applications is presented in this article. An MPC has the potential to achieve improved BCI performance compared to the performance achieved by current ad hoc, nonmodel-based filter applications. The parameters in designing the controller were extracted as model-based features from motor imagery task-related human scalp electroencephalography. Although the parameters can be generated from any model-linear or non-linear, we here adopted a simple autoregressive model that has well-established applications in BCI task discriminations. It was shown that the parameters generated for the controller design can as well be used for motor imagery task discriminations with performance (with 8-23% task discrimination errors) comparable to the discrimination performance of the commonly used features such as frequency specific band powers and the AR model parameters directly used. An optimal MPC has significant implications for high performance BCI applications.

UR - http://www.scopus.com/inward/record.url?scp=79954445308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79954445308&partnerID=8YFLogxK

U2 - 10.1007/s10439-011-0248-y

DO - 10.1007/s10439-011-0248-y

M3 - Article

C2 - 21267657

AN - SCOPUS:79954445308

VL - 39

SP - 1482

EP - 1492

JO - Annals of Biomedical Engineering

JF - Annals of Biomedical Engineering

SN - 0090-6964

IS - 5

ER -