Cargando…

Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment

Assessment of mental workload in real-world conditions is key to ensuring the performance of workers executing tasks that demand sustained attention. Previous literature has employed electroencephalography (EEG) to this end despite having observed that EEG correlates of mental workload vary across s...

Descripción completa

Detalles Bibliográficos
Autores principales: Albuquerque, Isabela, Monteiro, João, Rosanne, Olivier, Falk, Tiago H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576998/
https://www.ncbi.nlm.nih.gov/pubmed/36267659
http://dx.doi.org/10.3389/frai.2022.992732
_version_ 1784811656903131136
author Albuquerque, Isabela
Monteiro, João
Rosanne, Olivier
Falk, Tiago H.
author_facet Albuquerque, Isabela
Monteiro, João
Rosanne, Olivier
Falk, Tiago H.
author_sort Albuquerque, Isabela
collection PubMed
description Assessment of mental workload in real-world conditions is key to ensuring the performance of workers executing tasks that demand sustained attention. Previous literature has employed electroencephalography (EEG) to this end despite having observed that EEG correlates of mental workload vary across subjects and physical strain, thus making it difficult to devise models capable of simultaneously presenting reliable performance across users. Domain adaptation consists of a set of strategies that aim at allowing for improving machine learning systems performance on unseen data at training time. Such methods, however, might rely on assumptions over the considered data distributions, which typically do not hold for applications of EEG data. Motivated by this observation, in this work we propose a strategy to estimate two types of discrepancies between multiple data distributions, namely marginal and conditional shifts, observed on data collected from different subjects. Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies. In particular, we consider EEG data collected from individuals performing mental tasks while running on a treadmill and pedaling on a stationary bike and explore the effects of different normalization strategies commonly used to mitigate cross-subject variability. We show the effects that different normalization schemes have on statistical shifts and their relationship with the accuracy of mental workload prediction as assessed on unseen participants at training time.
format Online
Article
Text
id pubmed-9576998
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-95769982022-10-19 Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment Albuquerque, Isabela Monteiro, João Rosanne, Olivier Falk, Tiago H. Front Artif Intell Artificial Intelligence Assessment of mental workload in real-world conditions is key to ensuring the performance of workers executing tasks that demand sustained attention. Previous literature has employed electroencephalography (EEG) to this end despite having observed that EEG correlates of mental workload vary across subjects and physical strain, thus making it difficult to devise models capable of simultaneously presenting reliable performance across users. Domain adaptation consists of a set of strategies that aim at allowing for improving machine learning systems performance on unseen data at training time. Such methods, however, might rely on assumptions over the considered data distributions, which typically do not hold for applications of EEG data. Motivated by this observation, in this work we propose a strategy to estimate two types of discrepancies between multiple data distributions, namely marginal and conditional shifts, observed on data collected from different subjects. Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies. In particular, we consider EEG data collected from individuals performing mental tasks while running on a treadmill and pedaling on a stationary bike and explore the effects of different normalization strategies commonly used to mitigate cross-subject variability. We show the effects that different normalization schemes have on statistical shifts and their relationship with the accuracy of mental workload prediction as assessed on unseen participants at training time. Frontiers Media S.A. 2022-10-04 /pmc/articles/PMC9576998/ /pubmed/36267659 http://dx.doi.org/10.3389/frai.2022.992732 Text en Copyright © 2022 Albuquerque, Monteiro, Rosanne and Falk. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Artificial Intelligence
Albuquerque, Isabela
Monteiro, João
Rosanne, Olivier
Falk, Tiago H.
Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title_full Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title_fullStr Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title_full_unstemmed Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title_short Estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
title_sort estimating distribution shifts for predicting cross-subject generalization in electroencephalography-based mental workload assessment
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576998/
https://www.ncbi.nlm.nih.gov/pubmed/36267659
http://dx.doi.org/10.3389/frai.2022.992732
work_keys_str_mv AT albuquerqueisabela estimatingdistributionshiftsforpredictingcrosssubjectgeneralizationinelectroencephalographybasedmentalworkloadassessment
AT monteirojoao estimatingdistributionshiftsforpredictingcrosssubjectgeneralizationinelectroencephalographybasedmentalworkloadassessment
AT rosanneolivier estimatingdistributionshiftsforpredictingcrosssubjectgeneralizationinelectroencephalographybasedmentalworkloadassessment
AT falktiagoh estimatingdistributionshiftsforpredictingcrosssubjectgeneralizationinelectroencephalographybasedmentalworkloadassessment