An Adaptive Approach for Task-Driven BCI Calibration

Frida Heskebeck; Carolina Bergeling

Abstract

One of the most significant obstacles for the everyday use of systems based on BrainComputer Interfaces (BCIs) is the tediousness of calibration. Successful improvements on calibration, particularly the time needed and the userexperience, have been made with, e.g., transfer learning, gamification, and task estimation [1, 2, 3]. In
this work, we present an adaptive approach to BCI systems’ calibration with a model that evaluates if more calibration is needed. We inspect the model in its simplest form to showcase its versatility.

Original language	English
Publication status	Published - 2021 Jun
Event	BCI meeting 2021 - Virtual Duration: 2021 Jun 7 → 2021 Jun 9 https://bcisociety.org/bci-meeting/

Conference

Conference	BCI meeting 2021
Period	2021/06/07 → 2021/06/09
Internet address	https://bcisociety.org/bci-meeting/

Subject classification (UKÄ)

Control Engineering

Free keywords

BCI
Calibration
EEG
brain-computer interface

Access to Document

Abstract.Frida.HeskebeckFinal published version, 142 KB

https://bcisociety.org/wp-content/uploads/2021/05/vBCI-Abstract-Book-.pdf

1 Finished
1 Active

Optimizing the Next Generation Brain Computer Interfaces using Cloud Computing
Heskebeck, F., Bernhardsson, B., Bergeling, C. & Hägglund, T.
2019/08/05 → 2024/08/01
Project: Dissertation
Realtime Individualization of Brain Computer Interfaces
Bergeling, C., Bernhardsson, B., Sandsten, M., Heskebeck, F. & Anderson, R.
2019/06/01 → 2022/06/01
Project: Research

Cite this

@conference{de71d9e13dfb46d2b54f61abe48a8d2d,

title = "An Adaptive Approach for Task-Driven BCI Calibration",

abstract = "One of the most significant obstacles for the everyday use of systems based on BrainComputer Interfaces (BCIs) is the tediousness of calibration. Successful improvements on calibration, particularly the time needed and the userexperience, have been made with, e.g., transfer learning, gamification, and task estimation [1, 2, 3]. Inthis work, we present an adaptive approach to BCI systems{\textquoteright} calibration with a model that evaluates if more calibration is needed. We inspect the model in its simplest form to showcase its versatility.",

keywords = "BCI, Calibration, EEG, brain-computer interface",

author = "Frida Heskebeck and Carolina Bergeling",

year = "2021",

month = jun,

language = "English",

note = "BCI meeting 2021 ; Conference date: 07-06-2021 Through 09-06-2021",

url = "https://bcisociety.org/bci-meeting/",

}

TY - CONF

T1 - An Adaptive Approach for Task-Driven BCI Calibration

AU - Heskebeck, Frida

AU - Bergeling, Carolina

PY - 2021/6

Y1 - 2021/6

N2 - One of the most significant obstacles for the everyday use of systems based on BrainComputer Interfaces (BCIs) is the tediousness of calibration. Successful improvements on calibration, particularly the time needed and the userexperience, have been made with, e.g., transfer learning, gamification, and task estimation [1, 2, 3]. Inthis work, we present an adaptive approach to BCI systems’ calibration with a model that evaluates if more calibration is needed. We inspect the model in its simplest form to showcase its versatility.

AB - One of the most significant obstacles for the everyday use of systems based on BrainComputer Interfaces (BCIs) is the tediousness of calibration. Successful improvements on calibration, particularly the time needed and the userexperience, have been made with, e.g., transfer learning, gamification, and task estimation [1, 2, 3]. Inthis work, we present an adaptive approach to BCI systems’ calibration with a model that evaluates if more calibration is needed. We inspect the model in its simplest form to showcase its versatility.

KW - BCI

KW - Calibration

KW - EEG

KW - brain-computer interface

M3 - Abstract

T2 - BCI meeting 2021

Y2 - 7 June 2021 through 9 June 2021

ER -

An Adaptive Approach for Task-Driven BCI Calibration

Abstract

Conference

Subject classification (UKÄ)

Free keywords

Access to Document

Fingerprint

Projects

Optimizing the Next Generation Brain Computer Interfaces using Cloud Computing

Realtime Individualization of Brain Computer Interfaces

Cite this