Language-model assisted brain computer interface for typing: A comparison of matrix and rapid serial visual presentation

Mohammad Moghadamfalahi, Umut Orhan, Murat Akcakaya, Hooman Nezamfar, Melanie Fried-Oken, Deniz Erdogmus

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Noninvasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) popularly utilize event-related potential (ERP) for intent detection. Specifically, for EEG-based BCI typing systems, different symbol presentation paradigms have been utilized to induce ERPs. In this manuscript, through an experimental study, we assess the speed, recorded signal quality, and system accuracy of a language-model-Assisted BCI typing system using three different presentation paradigms: A 4 7 matrix paradigm of a 28-character alphabet with row-column presentation (RCP) and single-character presentation (SCP), and rapid serial visual presentation (RSVP) of the same. Our analyses show that signal quality and classification accuracy are comparable between the two visual stimulus presentation paradigms. In addition, we observe that while the matrix-based paradigm can be generally employed with lower inter-Trial-interval (ITI) values, the best presentation paradigm and ITI value configuration is user dependent. This potentially warrants offering both presentation paradigms and variable ITI options to users of BCI typing systems.

Original languageEnglish (US)
Article number7058364
Pages (from-to)910-920
Number of pages11
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume23
Issue number5
DOIs
StatePublished - Sep 1 2015

Fingerprint

Brain-Computer Interfaces
Brain computer interface
Language
Electroencephalography
User-Computer Interface
Enterprise resource planning
Evoked Potentials

Keywords

  • Brain-computer interface
  • event-related potential
  • matrix speller
  • P300
  • RSVP keyboard

ASJC Scopus subject areas

  • Neuroscience(all)
  • Computer Science Applications
  • Biomedical Engineering

Cite this

Language-model assisted brain computer interface for typing : A comparison of matrix and rapid serial visual presentation. / Moghadamfalahi, Mohammad; Orhan, Umut; Akcakaya, Murat; Nezamfar, Hooman; Fried-Oken, Melanie; Erdogmus, Deniz.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 23, No. 5, 7058364, 01.09.2015, p. 910-920.

Research output: Contribution to journalArticle

Moghadamfalahi, Mohammad ; Orhan, Umut ; Akcakaya, Murat ; Nezamfar, Hooman ; Fried-Oken, Melanie ; Erdogmus, Deniz. / Language-model assisted brain computer interface for typing : A comparison of matrix and rapid serial visual presentation. In: IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2015 ; Vol. 23, No. 5. pp. 910-920.
@article{8f97482e9bcb46bfafe56f552ace5113,
title = "Language-model assisted brain computer interface for typing: A comparison of matrix and rapid serial visual presentation",
abstract = "Noninvasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) popularly utilize event-related potential (ERP) for intent detection. Specifically, for EEG-based BCI typing systems, different symbol presentation paradigms have been utilized to induce ERPs. In this manuscript, through an experimental study, we assess the speed, recorded signal quality, and system accuracy of a language-model-Assisted BCI typing system using three different presentation paradigms: A 4 7 matrix paradigm of a 28-character alphabet with row-column presentation (RCP) and single-character presentation (SCP), and rapid serial visual presentation (RSVP) of the same. Our analyses show that signal quality and classification accuracy are comparable between the two visual stimulus presentation paradigms. In addition, we observe that while the matrix-based paradigm can be generally employed with lower inter-Trial-interval (ITI) values, the best presentation paradigm and ITI value configuration is user dependent. This potentially warrants offering both presentation paradigms and variable ITI options to users of BCI typing systems.",
keywords = "Brain-computer interface, event-related potential, matrix speller, P300, RSVP keyboard",
author = "Mohammad Moghadamfalahi and Umut Orhan and Murat Akcakaya and Hooman Nezamfar and Melanie Fried-Oken and Deniz Erdogmus",
year = "2015",
month = "9",
day = "1",
doi = "10.1109/TNSRE.2015.2411574",
language = "English (US)",
volume = "23",
pages = "910--920",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Language-model assisted brain computer interface for typing

T2 - A comparison of matrix and rapid serial visual presentation

AU - Moghadamfalahi, Mohammad

AU - Orhan, Umut

AU - Akcakaya, Murat

AU - Nezamfar, Hooman

AU - Fried-Oken, Melanie

AU - Erdogmus, Deniz

PY - 2015/9/1

Y1 - 2015/9/1

N2 - Noninvasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) popularly utilize event-related potential (ERP) for intent detection. Specifically, for EEG-based BCI typing systems, different symbol presentation paradigms have been utilized to induce ERPs. In this manuscript, through an experimental study, we assess the speed, recorded signal quality, and system accuracy of a language-model-Assisted BCI typing system using three different presentation paradigms: A 4 7 matrix paradigm of a 28-character alphabet with row-column presentation (RCP) and single-character presentation (SCP), and rapid serial visual presentation (RSVP) of the same. Our analyses show that signal quality and classification accuracy are comparable between the two visual stimulus presentation paradigms. In addition, we observe that while the matrix-based paradigm can be generally employed with lower inter-Trial-interval (ITI) values, the best presentation paradigm and ITI value configuration is user dependent. This potentially warrants offering both presentation paradigms and variable ITI options to users of BCI typing systems.

AB - Noninvasive electroencephalography (EEG)-based brain-computer interfaces (BCIs) popularly utilize event-related potential (ERP) for intent detection. Specifically, for EEG-based BCI typing systems, different symbol presentation paradigms have been utilized to induce ERPs. In this manuscript, through an experimental study, we assess the speed, recorded signal quality, and system accuracy of a language-model-Assisted BCI typing system using three different presentation paradigms: A 4 7 matrix paradigm of a 28-character alphabet with row-column presentation (RCP) and single-character presentation (SCP), and rapid serial visual presentation (RSVP) of the same. Our analyses show that signal quality and classification accuracy are comparable between the two visual stimulus presentation paradigms. In addition, we observe that while the matrix-based paradigm can be generally employed with lower inter-Trial-interval (ITI) values, the best presentation paradigm and ITI value configuration is user dependent. This potentially warrants offering both presentation paradigms and variable ITI options to users of BCI typing systems.

KW - Brain-computer interface

KW - event-related potential

KW - matrix speller

KW - P300

KW - RSVP keyboard

UR - http://www.scopus.com/inward/record.url?scp=84949792551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949792551&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2015.2411574

DO - 10.1109/TNSRE.2015.2411574

M3 - Article

C2 - 25775495

AN - SCOPUS:84949792551

VL - 23

SP - 910

EP - 920

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 5

M1 - 7058364

ER -