Towards a brain computer interface based on the N2pc event-related potential

Hani Awni, James J.S. Norton, Stephen Umunna, Kara D Federmeier, Timothy Wolfe Bretl

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Research over the last decade has shown that brain-computer interfaces (BCI) based on electroencephalography (EEG) can provide an alternative input paradigm for both clinical and healthy populations. Currently, the majority of BCI paradigms rely on a limited number of brain potentials; thus there remain many EEG signals to be explored for BCI applications. One such signal is the N2pc event-related potential (ERP). The N2pc is an ERP elicited 150ms to 350ms post-stimulus onset in response to target detection in visual search tasks. During this time window, target detection causes a negative deflection in the ERPs measured contralaterally to the target, allowing the lateralization of the target to be determined. Here we explore the feasibility of an N2pc-based BCI paradigm by analyzing the classification performance of participants based on data collected during an N2pc elicitation task. We quantify performance as a function of two variables; channel selection and the number of trials averaged together to obtain the ERP. Preliminary results indicate that with as few as three trials, the N2pc can be classified at nearly 90% accuracy in some individuals. These results could directly lead to the development of a new BCI paradigm, which we plan to realize in future work through the construction of a speller interface.

Original languageEnglish (US)
Title of host publication2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
Pages1021-1024
Number of pages4
DOIs
StatePublished - Dec 1 2013
Event2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013 - San Diego, CA, United States
Duration: Nov 6 2013Nov 8 2013

Publication series

NameInternational IEEE/EMBS Conference on Neural Engineering, NER
ISSN (Print)1948-3546
ISSN (Electronic)1948-3554

Other

Other2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013
CountryUnited States
CitySan Diego, CA
Period11/6/1311/8/13

Fingerprint

Brain computer interface
Electroencephalography
Target tracking
Enterprise resource planning
Bioelectric potentials
Brain

ASJC Scopus subject areas

  • Artificial Intelligence
  • Mechanical Engineering

Cite this

Awni, H., Norton, J. J. S., Umunna, S., Federmeier, K. D., & Bretl, T. W. (2013). Towards a brain computer interface based on the N2pc event-related potential. In 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013 (pp. 1021-1024). [6696110] (International IEEE/EMBS Conference on Neural Engineering, NER). https://doi.org/10.1109/NER.2013.6696110

Towards a brain computer interface based on the N2pc event-related potential. / Awni, Hani; Norton, James J.S.; Umunna, Stephen; Federmeier, Kara D; Bretl, Timothy Wolfe.

2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. p. 1021-1024 6696110 (International IEEE/EMBS Conference on Neural Engineering, NER).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Awni, H, Norton, JJS, Umunna, S, Federmeier, KD & Bretl, TW 2013, Towards a brain computer interface based on the N2pc event-related potential. in 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013., 6696110, International IEEE/EMBS Conference on Neural Engineering, NER, pp. 1021-1024, 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013, San Diego, CA, United States, 11/6/13. https://doi.org/10.1109/NER.2013.6696110
Awni H, Norton JJS, Umunna S, Federmeier KD, Bretl TW. Towards a brain computer interface based on the N2pc event-related potential. In 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. p. 1021-1024. 6696110. (International IEEE/EMBS Conference on Neural Engineering, NER). https://doi.org/10.1109/NER.2013.6696110
Awni, Hani ; Norton, James J.S. ; Umunna, Stephen ; Federmeier, Kara D ; Bretl, Timothy Wolfe. / Towards a brain computer interface based on the N2pc event-related potential. 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013. 2013. pp. 1021-1024 (International IEEE/EMBS Conference on Neural Engineering, NER).
@inproceedings{c4a893c663fb40dea5dbfe45bd3a015d,
title = "Towards a brain computer interface based on the N2pc event-related potential",
abstract = "Research over the last decade has shown that brain-computer interfaces (BCI) based on electroencephalography (EEG) can provide an alternative input paradigm for both clinical and healthy populations. Currently, the majority of BCI paradigms rely on a limited number of brain potentials; thus there remain many EEG signals to be explored for BCI applications. One such signal is the N2pc event-related potential (ERP). The N2pc is an ERP elicited 150ms to 350ms post-stimulus onset in response to target detection in visual search tasks. During this time window, target detection causes a negative deflection in the ERPs measured contralaterally to the target, allowing the lateralization of the target to be determined. Here we explore the feasibility of an N2pc-based BCI paradigm by analyzing the classification performance of participants based on data collected during an N2pc elicitation task. We quantify performance as a function of two variables; channel selection and the number of trials averaged together to obtain the ERP. Preliminary results indicate that with as few as three trials, the N2pc can be classified at nearly 90{\%} accuracy in some individuals. These results could directly lead to the development of a new BCI paradigm, which we plan to realize in future work through the construction of a speller interface.",
author = "Hani Awni and Norton, {James J.S.} and Stephen Umunna and Federmeier, {Kara D} and Bretl, {Timothy Wolfe}",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/NER.2013.6696110",
language = "English (US)",
isbn = "9781467319690",
series = "International IEEE/EMBS Conference on Neural Engineering, NER",
pages = "1021--1024",
booktitle = "2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013",

}

TY - GEN

T1 - Towards a brain computer interface based on the N2pc event-related potential

AU - Awni, Hani

AU - Norton, James J.S.

AU - Umunna, Stephen

AU - Federmeier, Kara D

AU - Bretl, Timothy Wolfe

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Research over the last decade has shown that brain-computer interfaces (BCI) based on electroencephalography (EEG) can provide an alternative input paradigm for both clinical and healthy populations. Currently, the majority of BCI paradigms rely on a limited number of brain potentials; thus there remain many EEG signals to be explored for BCI applications. One such signal is the N2pc event-related potential (ERP). The N2pc is an ERP elicited 150ms to 350ms post-stimulus onset in response to target detection in visual search tasks. During this time window, target detection causes a negative deflection in the ERPs measured contralaterally to the target, allowing the lateralization of the target to be determined. Here we explore the feasibility of an N2pc-based BCI paradigm by analyzing the classification performance of participants based on data collected during an N2pc elicitation task. We quantify performance as a function of two variables; channel selection and the number of trials averaged together to obtain the ERP. Preliminary results indicate that with as few as three trials, the N2pc can be classified at nearly 90% accuracy in some individuals. These results could directly lead to the development of a new BCI paradigm, which we plan to realize in future work through the construction of a speller interface.

AB - Research over the last decade has shown that brain-computer interfaces (BCI) based on electroencephalography (EEG) can provide an alternative input paradigm for both clinical and healthy populations. Currently, the majority of BCI paradigms rely on a limited number of brain potentials; thus there remain many EEG signals to be explored for BCI applications. One such signal is the N2pc event-related potential (ERP). The N2pc is an ERP elicited 150ms to 350ms post-stimulus onset in response to target detection in visual search tasks. During this time window, target detection causes a negative deflection in the ERPs measured contralaterally to the target, allowing the lateralization of the target to be determined. Here we explore the feasibility of an N2pc-based BCI paradigm by analyzing the classification performance of participants based on data collected during an N2pc elicitation task. We quantify performance as a function of two variables; channel selection and the number of trials averaged together to obtain the ERP. Preliminary results indicate that with as few as three trials, the N2pc can be classified at nearly 90% accuracy in some individuals. These results could directly lead to the development of a new BCI paradigm, which we plan to realize in future work through the construction of a speller interface.

UR - http://www.scopus.com/inward/record.url?scp=84897679102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897679102&partnerID=8YFLogxK

U2 - 10.1109/NER.2013.6696110

DO - 10.1109/NER.2013.6696110

M3 - Conference contribution

AN - SCOPUS:84897679102

SN - 9781467319690

T3 - International IEEE/EMBS Conference on Neural Engineering, NER

SP - 1021

EP - 1024

BT - 2013 6th International IEEE EMBS Conference on Neural Engineering, NER 2013

ER -