EEG-based Workload Estimation Across Affective Contexts
Workload estimation from electroencephalographic signals (EEG) offers a highly sensitive tool to adapt the human-computer interaction to the user state. To create systems that reliably work in the complexity of the real world, a robustness against contextual changes (e.g., mood), has to be achieved....
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2014-06-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00114/full |
id |
doaj-605c92d9892c45b2a40ed2619e16696f |
---|---|
record_format |
Article |
spelling |
doaj-605c92d9892c45b2a40ed2619e16696f2020-11-25T00:55:24ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2014-06-01810.3389/fnins.2014.0011483439EEG-based Workload Estimation Across Affective ContextsChristian eMühl0Camille eJeunet1Camille eJeunet2Fabien eLotte3Fabien eLotte4INRIAINRIAUniversity of BordeauxINRIALaBRIWorkload estimation from electroencephalographic signals (EEG) offers a highly sensitive tool to adapt the human-computer interaction to the user state. To create systems that reliably work in the complexity of the real world, a robustness against contextual changes (e.g., mood), has to be achieved. To study the resilience of state-of-the-art EEG-based workload classification against stress we devise a novel experimental protocol, in which we manipulated the affective context (stressful/non-stressful) while the participant solved a task with 2 workload levels. We recorded self-ratings, behavior, and physiology from 24 participants to validate the protocol. We test the capability of different, subject-specific workload classifiers using either frequency-domain, time-domain, or both feature varieties to generalize across contexts. We show that the classifiers are able to transfer between affective contexts, though performance suffers independent of the used feature domain. However, cross-context training is a simple and powerful remedy allowing the extraction of features in all studied feature varieties that are more resilient to task-unrelated variations in signal characteristics. Especially for frequency-domain features, across-context training is leading to a performance comparable to within-context training and testing. We discuss the significance of the result for neurophysiology-based workload detection in particular and for the construction of reliable passive brain-computer interfaces in general.http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00114/fullClassificationElectroencephalographyWorkloadstressBrain-computer interfacePassive Brain Computer Interface |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Christian eMühl Camille eJeunet Camille eJeunet Fabien eLotte Fabien eLotte |
spellingShingle |
Christian eMühl Camille eJeunet Camille eJeunet Fabien eLotte Fabien eLotte EEG-based Workload Estimation Across Affective Contexts Frontiers in Neuroscience Classification Electroencephalography Workload stress Brain-computer interface Passive Brain Computer Interface |
author_facet |
Christian eMühl Camille eJeunet Camille eJeunet Fabien eLotte Fabien eLotte |
author_sort |
Christian eMühl |
title |
EEG-based Workload Estimation Across Affective Contexts |
title_short |
EEG-based Workload Estimation Across Affective Contexts |
title_full |
EEG-based Workload Estimation Across Affective Contexts |
title_fullStr |
EEG-based Workload Estimation Across Affective Contexts |
title_full_unstemmed |
EEG-based Workload Estimation Across Affective Contexts |
title_sort |
eeg-based workload estimation across affective contexts |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroscience |
issn |
1662-453X |
publishDate |
2014-06-01 |
description |
Workload estimation from electroencephalographic signals (EEG) offers a highly sensitive tool to adapt the human-computer interaction to the user state. To create systems that reliably work in the complexity of the real world, a robustness against contextual changes (e.g., mood), has to be achieved. To study the resilience of state-of-the-art EEG-based workload classification against stress we devise a novel experimental protocol, in which we manipulated the affective context (stressful/non-stressful) while the participant solved a task with 2 workload levels. We recorded self-ratings, behavior, and physiology from 24 participants to validate the protocol. We test the capability of different, subject-specific workload classifiers using either frequency-domain, time-domain, or both feature varieties to generalize across contexts. We show that the classifiers are able to transfer between affective contexts, though performance suffers independent of the used feature domain. However, cross-context training is a simple and powerful remedy allowing the extraction of features in all studied feature varieties that are more resilient to task-unrelated variations in signal characteristics. Especially for frequency-domain features, across-context training is leading to a performance comparable to within-context training and testing. We discuss the significance of the result for neurophysiology-based workload detection in particular and for the construction of reliable passive brain-computer interfaces in general. |
topic |
Classification Electroencephalography Workload stress Brain-computer interface Passive Brain Computer Interface |
url |
http://journal.frontiersin.org/Journal/10.3389/fnins.2014.00114/full |
work_keys_str_mv |
AT christianemuhl eegbasedworkloadestimationacrossaffectivecontexts AT camilleejeunet eegbasedworkloadestimationacrossaffectivecontexts AT camilleejeunet eegbasedworkloadestimationacrossaffectivecontexts AT fabienelotte eegbasedworkloadestimationacrossaffectivecontexts AT fabienelotte eegbasedworkloadestimationacrossaffectivecontexts |
_version_ |
1725230523635204096 |